Search

Introduction: The advent of immune checkpoint blockade (ICB) has led to significantly improved disease outcome in lung adenocarcinoma (ADC), but response of ALK/EGFR-positive tumors to immune therapy is limited. The underlying immune biology is incompletely understood., Methods: We performed comparative mRNA expression profiling of 31 ALK-positive, 40 EGFR-positive and 43 ALK/EGFR-negative lung ADC focused on immune gene expression. The presence and levels of tumor infiltration lymphocytes (TILs) as well as fourteen specific immune cell populations were estimated from the gene expression profiles., Results: While total TILs were not lower in ALK-positive and EGFR-positive tumors compared to ALK/EGFR-negative tumors, specific immunosuppressive characteristics were detected in both subgroups: In ALK-positive tumors, regulatory T cells were significantly higher compared to EGFR-positive (fold change: FC = 1.9, p = 0.0013) and ALK/EGFR-negative tumors (FC = 2.1, p = 0.00047). In EGFR-positive tumors, cytotoxic cells were significantly lower compared to ALK-positive (FC =  - 1.7, p = 0.016) and to ALK/EGFR-negative tumors (FC =  - 2.1, p = 2.0E-05). A total number of 289 genes, 40 part of cytokine-cytokine receptor signaling, were differentially expressed between the three subgroups. Among the latter, five genes were differently expressed in both ALK-positive and EGFR-positive tumors, while twelve genes showed differential expression solely in ALK-positive tumors and eleven genes solely in EGFR-positive tumors., Conclusion: Targeted gene expression profiling is a promising tool to read out tumor microenvironment characteristics from routine diagnostic lung cancer biopsies. Significant immune reactivity including specific immunosuppressive characteristics in ALK- and EGFR-positive lung ADC, but not a total absence of immune infiltration supports further clinical evaluation of immune-modulators as partners of ICB in such tumors., (© 2021. The Author(s).)

There is a growing need for systems that efficiently support the work of medical teams at the precision-oncology point of care. Here, we present the implementation of the Molecular Tumor Board Portal (MTBP), an academic clinical decision support system developed under the umbrella of Cancer Core Europe that creates a unified legal, scientific and technological platform to share and harness next-generation sequencing data. Automating the interpretation and reporting of sequencing results decrease the need for time-consuming manual procedures that are prone to errors. The adoption of an expert-agreed process to systematically link tumor molecular profiles with clinical actions promotes consistent decision-making and structured data capture across the connected centers. The use of information-rich patient reports with interactive content facilitates collaborative discussion of complex cases during virtual molecular tumor board meetings. Overall, streamlined digital systems like the MTBP are crucial to better address the challenges brought by precision oncology and accelerate the use of emerging biomarkers., (© 2022. The Author(s).)

Background: Over the past decade, the development of molecular high-throughput methods (omics) increased rapidly and provided new insights for cancer research. In parallel, deep learning approaches revealed the enormous potential for medical image analysis, especially in digital pathology. Combining image and omics data with deep learning tools may enable the discovery of new cancer biomarkers and a more precise prediction of patient prognosis. This systematic review addresses different multimodal fusion methods of convolutional neural network-based image analyses with omics data, focussing on the impact of data combination on the classification performance., Methods: PubMed was screened for peer-reviewed articles published in English between January 2015 and June 2021 by two independent researchers. Search terms related to deep learning, digital pathology, omics, and multimodal fusion were combined., Results: We identified a total of 11 studies meeting the inclusion criteria, namely studies that used convolutional neural networks for haematoxylin and eosin image analysis of patients with cancer in combination with integrated omics data. Publications were categorised according to their endpoints: 7 studies focused on survival analysis and 4 studies on prediction of cancer subtypes, malignancy or microsatellite instability with spatial analysis., Conclusions: Image-based classifiers already show high performances in prognostic and predictive cancer diagnostics. The integration of omics data led to improved performance in all studies described here. However, these are very early studies that still require external validation to demonstrate their generalisability and robustness. Further and more comprehensive studies with larger sample sizes are needed to evaluate performance and determine clinical benefits., Competing Interests: Conflict of interest statement The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: T.J.B. would like to disclose that he is the owner of Smart Health Heidelberg GmbH (Handschuhsheimer Landstr. 9/1, 69120 Heidelberg, Germany; https://smarthealth.de) which developed the online teledermatology apps AppDoc (https://online-hautarzt.net) and Intimarzt (https://intimarzt.de) and the online doctor service doc2go (https://doc2go.de), outside of the submitted work. JNK declares consulting services for Owkin, France and Panakeia, UK. No other potential conflicts of interest are reported by any of the authors., (Copyright © 2021 The Authors. Published by Elsevier Ltd.. All rights reserved.)

Undifferentiated mesenchymal tumors arising from the inner lining (intima) of large arteries are classified as intimal sarcomas (ISA) with MDM2 amplification as their molecular hallmark. Interestingly, undifferentiated pleomorphic sarcomas (UPS) of the heart have recently been suggested to represent the cardiac analog of ISA due to morphological overlap and high prevalence of MDM2 amplifications in both neoplasms. However, little is known about ISAs and cardiac UPS without MDM2 amplifications and molecular data supporting their common classification is sparse. Here, we report a series of 35 cases comprising 25 ISAs of the pulmonary artery, one ISA of the renal artery and 9 UPS of the left atrium. Tumors were analyzed utilizing the Illumina Infinium MethylationEPIC BeadChip array, enabling copy number profile generation and unsupervised DNA methylation analysis. DNA methylation patterns were investigated using t-distributed stochastic neighbor embedding (t-SNE) analysis. Histologically, all ISAs and UPS of the left atrium resembled extra-cardiac UPS. All cases exhibited highly complex karyotypes with overlapping patterns between ISA and UPS. 29/35 cases showed mutually exclusive amplifications in the cell-cycle associated oncogenes MDM2 (25/35), MDM4 (2/35), and CDK6 (2/35). We further observed recurrent co-amplifications in PDGFRA (21/35), CDK4 (15/35), TERT (11/35), HDAC9 (9/35), and CCND1 (4/35). Sporadic co-amplifications occurred in MYC, MYCN, and MET (each 1/35). The tumor suppressor CDKN2A/B was frequently deleted (10/35). Interestingly, DNA methylation profiling (t-SNE) revealed an overlap of ISA and cardiac UPS. This "ISA" methylation signature was distinct from potential histologic and molecular mimics. In conclusion, our data reveal MDM4 and CDK6 amplifications in ISAs and UPS of the left atrium, lacking MDM2 amplification. We further report novel co-amplifications of various oncogenes, which may have therapeutic implications. Finally, the genetic and epigenetic concordance of ISAs and UPS of the left atrium further supports a shared pathogenesis and common classification., (© 2021. The Author(s).)

For most rare cancers, precision oncology approaches are not established because these entities are poorly understood and their investigation requires the collaboration of many centers. The MASTER precision oncology network demonstrates that clinical whole-genome/exome and RNA sequencing yield molecular mechanism-aware treatments that benefit a substantial proportion of patients with advanced rare cancers and will prepare the ground for future clinical trials., Competing Interests: Consulting or advisory board membership: Bayer, Illumina, Roche; honoraria: Amgen, Eli Lilly, PharmaMar, Roche; research funding: AstraZeneca, Pfizer, PharmaMar, Roche; travel or accommodation expenses: Amgen, Eli Lilly, Illumina, PharmaMar, Roche. The other authors declare no competing interests., (© 2021 Taylor & Francis Group, LLC.)

The clinical relevance of comprehensive molecular analysis in rare cancers is not established. We analyzed the molecular profiles and clinical outcomes of 1,310 patients (rare cancers, 75.5%) enrolled in a prospective observational study by the German Cancer Consortium that applies whole-genome/exome and RNA sequencing to inform the care of adults with incurable cancers. On the basis of 472 single and six composite biomarkers, a cross-institutional molecular tumor board provided evidence-based management recommendations, including diagnostic reevaluation, genetic counseling, and experimental treatment, in 88% of cases. Recommended therapies were administered in 362 of 1,138 patients (31.8%) and resulted in significantly improved overall response and disease control rates (23.9% and 55.3%) compared with previous therapies, translating into a progression-free survival ratio >1.3 in 35.7% of patients. These data demonstrate the benefit of molecular stratification in rare cancers and represent a resource that may promote clinical trial access and drug approvals in this underserved patient population. SIGNIFICANCE: Rare cancers are difficult to treat; in particular, molecular pathogenesis-oriented medical therapies are often lacking. This study shows that whole-genome/exome and RNA sequencing enables molecularly informed treatments that lead to clinical benefit in a substantial proportion of patients with advanced rare cancers and paves the way for future clinical trials. See related commentary by Eggermont et al., p. 2677 . This article is highlighted in the In This Issue feature, p. 2659 ., (©2021 American Association for Cancer Research.)

Background: Lymph node status is a prognostic marker and strongly influences therapeutic decisions in colorectal cancer (CRC)., Objectives: The objective of the study is to investigate whether image features extracted by a deep learning model from routine histological slides and/or clinical data can be used to predict CRC lymph node metastasis (LNM)., Methods: Using histological whole slide images (WSIs) of primary tumours of 2431 patients in the DACHS cohort, we trained a convolutional neural network to predict LNM. In parallel, we used clinical data derived from the same cases in logistic regression analyses. Subsequently, the slide-based artificial intelligence predictor (SBAIP) score was included in the regression. WSIs and data from 582 patients of the TCGA cohort were used as the external test set., Results: On the internal test set, the SBAIP achieved an area under receiver operating characteristic (AUROC) of 71.0%, the clinical classifier achieved an AUROC of 67.0% and a combination of the two classifiers yielded an improvement to 74.1%. Whereas the clinical classifier's performance remained stable on the TCGA set, performance of the SBAIP dropped to an AUROC of 61.2%. Performance of the clinical classifier depended strongly on the T stage., Conclusion: Deep learning-based image analysis may help predict LNM of patients with CRC using routine histological slides. Combination with clinical data such as T stage might be useful. Strategies to increase performance of the SBAIP on external images should be investigated., Competing Interests: Conflict of interest statement The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: T.J.B. would like to disclose that he is the owner of Smart Health Heidelberg GmbH (Handschuhsheimer Landstr. 9/1, 69120 Heidelberg, Germany; https://smarthealth.de) which developed the online dermatokoteledermatology apps AppDoc (https://online-hautarzt.net) and Intimarzt (https://intimarzt.de) and the online doctor service doc2go (https://doc2go.de), outside of the submitted work. J.N.K. has a consulting role at Owkin, France. All other authors have not declared any conflicts of interest., (Copyright © 2021 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

Key stakeholders from the cancer research continuum met in May 2021 at the European Cancer Research Summit in Porto to discuss priorities and specific action points required for the successful implementation of the European Cancer Mission and Europe's Beating Cancer Plan (EBCP). Speakers presented a unified view about the need to establish high-quality, networked infrastructures to decrease cancer incidence, increase the cure rate, improve patient's survival and quality of life, and deal with research and care inequalities across the European Union (EU). These infrastructures, featuring Comprehensive Cancer Centres (CCCs) as key components, will integrate care, prevention and research across the entire cancer continuum to support the development of personalized/precision cancer medicine in Europe. The three pillars of the recommended European infrastructures - namely translational research, clinical/prevention trials and outcomes research - were pondered at length. Speakers addressing the future needs of translational research focused on the prospects of multiomics assisted preclinical research, progress in Molecular and Digital Pathology, immunotherapy, liquid biopsy and science data. The clinical/prevention trial session presented the requirements for next-generation, multicentric trials entailing unified strategies for patient stratification, imaging, and biospecimen acquisition and storage. The third session highlighted the need for establishing outcomes research infrastructures to cover primary prevention, early detection, clinical effectiveness of innovations, health-related quality-of-life assessment, survivorship research and health economics. An important outcome of the Summit was the presentation of the Porto Declaration, which called for a collective and committed action throughout Europe to develop the cancer research infrastructures indispensable for fostering innovation and decreasing inequalities within and between member states. Moreover, the Summit guidelines will assist decision making in the context of a unique EU-wide cancer initiative that, if expertly implemented, will decrease the cancer death toll and improve the quality of life of those confronted with cancer, and this is carried out at an affordable cost., (© 2021 The Authors. Molecular Oncology published by John Wiley & Sons Ltd on behalf of Federation of European Biochemical Societies.)

Background: Multiple studies have compared the performance of artificial intelligence (AI)-based models for automated skin cancer classification to human experts, thus setting the cornerstone for a successful translation of AI-based tools into clinicopathological practice., Objective: The objective of the study was to systematically analyse the current state of research on reader studies involving melanoma and to assess their potential clinical relevance by evaluating three main aspects: test set characteristics (holdout/out-of-distribution data set, composition), test setting (experimental/clinical, inclusion of metadata) and representativeness of participating clinicians., Methods: PubMed, Medline and ScienceDirect were screened for peer-reviewed studies published between 2017 and 2021 and dealing with AI-based skin cancer classification involving melanoma. The search terms skin cancer classification, deep learning, convolutional neural network (CNN), melanoma (detection), digital biomarkers, histopathology and whole slide imaging were combined. Based on the search results, only studies that considered direct comparison of AI results with clinicians and had a diagnostic classification as their main objective were included., Results: A total of 19 reader studies fulfilled the inclusion criteria. Of these, 11 CNN-based approaches addressed the classification of dermoscopic images; 6 concentrated on the classification of clinical images, whereas 2 dermatopathological studies utilised digitised histopathological whole slide images., Conclusions: All 19 included studies demonstrated superior or at least equivalent performance of CNN-based classifiers compared with clinicians. However, almost all studies were conducted in highly artificial settings based exclusively on single images of the suspicious lesions. Moreover, test sets mainly consisted of holdout images and did not represent the full range of patient populations and melanoma subtypes encountered in clinical practice., Competing Interests: Conflict of interest statement The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: J.S.U. is on the advisory board or has received honoraria and travel support from Amgen, Bristol Myers Squibb, GSK, LEO Pharma, Merck Sharp and Dohme, Novartis, Pierre Fabre and Roche, outside the submitted work. M.G. has received speaker's honoraria and/or has served as a consultant and/or member of advisory boards for Almirall, Argenx, Biotest, Eli Lilly, Janssen Cilag, LEO Pharma, Novartis and UCB, outside the submitted work. H.A.H. worked as a consultant or received honoraria and travel support from Heine Optotechnik GmbH, JenLab GmbH, FotoFinder Systems GmbH, Magnosco GmbH, SciBase AB, Beiersdorf AG, Almirall Hermal GmbH and Galderma Laboratorium GmbH. V.M.R. is on the advisory board or has received honoraria or ownership in Inhabit Brands, Inc. unrelated to this work. Sondermann W. reports grants from medi GmbH Bayreuth, personal fees from Janssen, grants and personal fees from Novartis, personal fees from Lilly, personal fees from UCB, personal fees from Almirall, personal fees from LEO Pharma and personal fees from Sanofi Genzyme, outside the submitted work. H.P.S. is a shareholder of MoleMap NZ Limited and e-derm consult GmbH and undertakes regular tele-dermatological reporting for both companies. H.P.S. is a medical consultant for Canfield Scientific, Inc., MoleMap Australia Pty Ltd and Revenio Research Oy and a medical advisor for First Derm. M.L-V. has received speaker's honoraria and/or received grants and/or participated in clinical trials of AbbVie, Almirall, Amgen, Celgene, Eli Lilly, Janssen Cilag, LEO Pharma, Novartis and UCB, outside the submitted work. A.Z. has been an advisor and/or received speaker's honoraria and/or received grants and/or participated in clinical trials of AbbVie, Almirall, Amgen, Beiersdorf Dermo Medical, Bencard Allergy, Celgene, Eli Lilly, Janssen Cilag, LEO Pharma, Novartis, Sanofi-Aventis and UCB Pharma, outside the submitted work. Kittler H. received speaker's honoraria from FotoFinder Systems GmbH and received non-financial support from Heine Optotechnik GmbH, Derma Medical and 3Gen. T.J.B. reports owning a company that develops mobile apps, including the teledermatology services AppDoc (https://online-hautarzt.de) and Intimarzt (https://Intimarzt.de); Smart Health Heidelberg GmbH, Handschuhsheimer Landstr. 9/1, 69120 Heidelberg, https://smarthealth.de. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

Objective: To develop a new digital biomarker based on the analysis of primary tumour tissue by a convolutional neural network (CNN) to predict lymph node metastasis (LNM) in a cohort matched for already established risk factors., Patients and Methods: Haematoxylin and eosin (H&E) stained primary tumour slides from 218 patients (102 N+; 116 N0), matched for Gleason score, tumour size, venous invasion, perineural invasion and age, who underwent radical prostatectomy were selected to train a CNN and evaluate its ability to predict LN status., Results: With 10 models trained with the same data, a mean area under the receiver operating characteristic curve (AUROC) of 0.68 (95% confidence interval [CI] 0.678-0.682) and a mean balanced accuracy of 61.37% (95% CI 60.05-62.69%) was achieved. The mean sensitivity and specificity was 53.09% (95% CI 49.77-56.41%) and 69.65% (95% CI 68.21-71.1%), respectively. These results were confirmed via cross-validation. The probability score for LNM prediction was significantly higher on image sections from N+ samples (mean [SD] N+ probability score 0.58 [0.17] vs 0.47 [0.15] N0 probability score, P = 0.002). In multivariable analysis, the probability score of the CNN (odds ratio [OR] 1.04 per percentage probability, 95% CI 1.02-1.08; P = 0.04) and lymphovascular invasion (OR 11.73, 95% CI 3.96-35.7; P < 0.001) proved to be independent predictors for LNM., Conclusion: In our present study, CNN-based image analyses showed promising results as a potential novel low-cost method to extract relevant prognostic information directly from H&E histology to predict the LN status of patients with prostate cancer. Our ubiquitously available technique might contribute to an improved LN status prediction., (© 2021 The Authors BJU International published by John Wiley & Sons Ltd on behalf of BJU International.)

Background: Gastrointestinal cancers account for approximately 20% of all cancer diagnoses and are responsible for 22.5% of cancer deaths worldwide. Artificial intelligence-based diagnostic support systems, in particular convolutional neural network (CNN)-based image analysis tools, have shown great potential in medical computer vision. In this systematic review, we summarise recent studies reporting CNN-based approaches for digital biomarkers for characterization and prognostication of gastrointestinal cancer pathology., Methods: Pubmed and Medline were screened for peer-reviewed papers dealing with CNN-based gastrointestinal cancer analyses from histological slides, published between 2015 and 2020.Seven hundred and ninety titles and abstracts were screened, and 58 full-text articles were assessed for eligibility., Results: Sixteen publications fulfilled our inclusion criteria dealing with tumor or precursor lesion characterization or prognostic and predictive biomarkers: 14 studies on colorectal or rectal cancer, three studies on gastric cancer and none on esophageal cancer. These studies were categorised according to their end-points: polyp characterization, tumor characterization and patient outcome. Regarding the translation into clinical practice, we identified several studies demonstrating generalization of the classifier with external tests and comparisons with pathologists, but none presenting clinical implementation., Conclusions: Results of recent studies on CNN-based image analysis in gastrointestinal cancer pathology are promising, but studies were conducted in observational and retrospective settings. Large-scale trials are needed to assess performance and predict clinical usefulness. Furthermore, large-scale trials are required for approval of CNN-based prediction models as medical devices., Competing Interests: Conflict of interest statement The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: TJB would like to disclose that he is the owner of Smart Health Heidelberg GmbH (Handschuhsheimer Landstr. 9/1, 69,120 Heidelberg, Germany, https://smarthealth.de) which developed the teledermatology services AppDoc (https://online-hautarzt.net) and Intimarzt (https://Intimarzt.de), outside the scope of the submitted work. JNK reports a consulting role at Owkin, France. All remaining authors have declared no conflicts of interest., (Copyright © 2021 The Authors. Published by Elsevier Ltd.. All rights reserved.)

Background: One prominent application for deep learning-based classifiers is skin cancer classification on dermoscopic images. However, classifier evaluation is often limited to holdout data which can mask common shortcomings such as susceptibility to confounding factors. To increase clinical applicability, it is necessary to thoroughly evaluate such classifiers on out-of-distribution (OOD) data., Objective: The objective of the study was to establish a dermoscopic skin cancer benchmark in which classifier robustness to OOD data can be measured., Methods: Using a proprietary dermoscopic image database and a set of image transformations, we create an OOD robustness benchmark and evaluate the robustness of four different convolutional neural network (CNN) architectures on it., Results: The benchmark contains three data sets-Skin Archive Munich (SAM), SAM-corrupted (SAM-C) and SAM-perturbed (SAM-P)-and is publicly available for download. To maintain the benchmark's OOD status, ground truth labels are not provided and test results should be sent to us for assessment. The SAM data set contains 319 unmodified and biopsy-verified dermoscopic melanoma (n = 194) and nevus (n = 125) images. SAM-C and SAM-P contain images from SAM which were artificially modified to test a classifier against low-quality inputs and to measure its prediction stability over small image changes, respectively. All four CNNs showed susceptibility to corruptions and perturbations., Conclusions: This benchmark provides three data sets which allow for OOD testing of binary skin cancer classifiers. Our classifier performance confirms the shortcomings of CNNs and provides a frame of reference. Altogether, this benchmark should facilitate a more thorough evaluation process and thereby enable the development of more robust skin cancer classifiers., Competing Interests: Conflict of interest statement The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: J.S.U. is on the advisory board or has received honoraria and travel support from Amgen, Bristol Myers Squibb, GSK, Leo Pharma, Merck Sharp and Dohme, Novartis, Pierre Fabre and Roche, outside the submitted work. F.M. has received travel support or/and speaker's fees or/and advisor's honoraria from Novartis, Roche, BMS, MSD and Pierre Fabre and research funding from Novartis and Roche. S.H. reports advisory roles for or has received honoraria from Pierre Fabre Pharmaceuticals, Novartis, Roche, BMS, Amgen and MSD outside the submitted work. A.H. reports clinical trial support, speaker's honoraria or consultancy fees from the following companies: Amgen, BMS, Merck Serono, MSD, Novartis, OncoSec, Philogen, Pierre Fabre, Provectus, Regeneron, Roche, OncoSec, Sanofi Genzyme and Sun Pharma, outside the submitted work. W.S. reports grants from medi GmbH Bayreuth, personal fees from Janssen, grants and personal fees from Novartis, personal fees from Lilly, personal fees from UCB, personal fees from Almirall, personal fees from Leo Pharma and personal fees from Sanofi Genzyme, outside the submitted work. B.S. reports advisory roles for or has received honoraria from Pierre Fabre Pharmaceuticals, Incyte, Novartis, Roche, BMS and MSD, research funding from BMS, Pierre Fabre Pharmaceuticals and MSD and travel support from Novartis, Roche, BMS, Pierre Fabre Pharmaceuticals and Amgen, outside the submitted work. M.G. has received speaker's honoraria and/or has served as a consultant and/or member of advisory boards for Almirall, argenx, Biotest, Eli Lilly, Janssen Cilag, Leo Pharma, Novartis and UCB, outside the submitted work. T.J.B. reports owning a company that develops mobile apps including the teledermatology services AppDoc (https://online-hautarzt.net) and Intimarzt (https://intimarzt.de): Smart Health Heidelberg GmbH, Handschuhsheimer Landstr. 9/1, 69120 Heidelberg, https://smarthealth.de. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

Aim: Sentinel lymph node status is a central prognostic factor for melanomas. However, the surgical excision involves some risks for affected patients. In this study, we therefore aimed to develop a digital biomarker that can predict lymph node metastasis non-invasively from digitised H&E slides of primary melanoma tumours., Methods: A total of 415 H&E slides from primary melanoma tumours with known sentinel node (SN) status from three German university hospitals and one private pathological practice were digitised (150 SN positive/265 SN negative). Two hundred ninety-one slides were used to train artificial neural networks (ANNs). The remaining 124 slides were used to test the ability of the ANNs to predict sentinel status. ANNs were trained and/or tested on data sets that were matched or not matched between SN-positive and SN-negative cases for patient age, ulceration, and tumour thickness, factors that are known to correlate with lymph node status., Results: The best accuracy was achieved by an ANN that was trained and tested on unmatched cases (61.8% ± 0.2%) area under the receiver operating characteristic (AUROC). In contrast, ANNs that were trained and/or tested on matched cases achieved (55.0% ± 3.5%) AUROC or less., Conclusion: Our results indicate that the image classifier can predict lymph node status to some, albeit so far not clinically relevant, extent. It may do so by mostly detecting equivalents of factors on histological slides that are already known to correlate with lymph node status. Our results provide a basis for future research with larger data cohorts., Competing Interests: Conflict of interest statement The authors declare the following financial interests/personal relationships which may be considered as potential competing interests:T.J.B. would like to disclose that he owns a health technology company (Smart Health Heidelberg GmbH, Handschuhsheimer Landstr. 9/1, 69120 Heidelberg, Germany, https://smarthealth.de), which develops mobile apps, outside the submitted work. All remaining authors have declared no conflicts of interest., (Copyright © 2021 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

Introduction: Local recurrences (LR) and distant metastases (DM) are common in retroperitoneal soft tissue sarcoma (RPS). Longer time to recurrence and resection of the recurrent lesion have been identified as beneficial prognostic factors for overall survival (OS) upon first tumor relapse. However, prognostic factors concerning OS upon subsequent recurrences are scarcely defined. In this study, we aimed to identify prognostic factors for post-relapse outcome in multiple recurrent RPS., Methods: Patients undergoing resection of primary and recurrent RPS at the University Hospital Heidelberg were retrospectively analyzed. Multivariable Cox regression analyses were performed to identify predictors of overall, LR- and DM-free survival. Subgroup analyses were performed for liposarcoma and leiomyosarcoma patients., Results: 201 patients with primary disease, 101 patients with first, 66 patients with second and 43 patients with third LR as well as 75 patients with DM were analyzed. More than 12 months to recurrence and resection of recurrence were associated with improved OS after resection of first and second LR (5-year OS for first/second LR; resection: 64%/62%, no resection: 20%/46%). Gross macroscopic incomplete resection of first (p < 0.001), second (p = 0.001), and third recurrences (p < 0.001) was an independent prognostic factor for poor OS., Conclusion: Development of LR and DM is frequent in RPS. Once a tumor relapsed, patients benefit from tumor resection not only in case of first, but also in case of subsequent recurrences., Competing Interests: Declaration of competing interest None., (Copyright © 2021 Elsevier Ltd, BASO ~ The Association for Cancer Surgery, and the European Society of Surgical Oncology. All rights reserved.)

Utilizing digital pathology algorithms for the objective quantification of immunohistochemical staining, this study aimed to identify robust prognostic biomarkers for oral cancer. Tissue microarrays with specimens of a large cohort of oral squamous cell carcinoma (n=222) were immunohistochemically stained to determine the expression of PD-L1, EGFR, and COX-2 and the amount of infiltrating NK cells and CD8-positive T cells. Immunoreactivity scores were assessed using both a classical manual scoring procedure and a digital semi-automatic approach using QuPath. Digital scoring was successful in quantifying the expression levels of different prognostic biomarkers (CD8: p<0.001; NK cells: p=0.002, PD-L1: p=0.026) and high levels of concordance with manual scoring results were observed. A combined score integrating EGFR expression, neck node status and immune cell signatures with a significant impact on overall and progression-free survival was identified (p<0.001). These data may contribute to the ongoing research on the identification of reliable and clinically relevant biomarkers for the individualization of primary and adjuvant treatment in oral cancer., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Moratin, Mock, Obradovic, Metzger, Flechtenmacher, Zaoui, Fröhling, Jäger, Krauss, Hoffmann, Freier, Horn, Hess and Freudlsperger.)

Background: The development of secondary resistance (SR) in metastatic colorectal cancer (mCRC) treated with anti-epidermal growth factor receptor (anti-EGFR) antibodies is not fully understood at the molecular level. Here we tested in vivo selection of anti-EGFR SR tumors in CRC patient-derived xenograft (PDX) models as a strategy for a molecular dissection of SR mechanisms., Methods: We analyzed 21 KRAS, NRAS, BRAF, and PI3K wildtype CRC patient-derived xenograft (PDX) models for their anti-EGFR sensitivity. Furthermore, 31 anti-EGFR SR tumors were generated via chronic in vivo treatment with cetuximab. A multi-omics approach was employed to address molecular primary and secondary resistance mechanisms. Gene set enrichment analyses were used to uncover SR pathways. Targeted therapy of SR PDX models was applied to validate selected SR pathways., Results: In vivo anti-EGFR SR could be established with high efficiency. Chronic anti-EGFR treatment of CRC PDX tumors induced parallel evolution of multiple resistant lesions with independent molecular SR mechanisms. Mutations in driver genes explained SR development in a subgroup of CRC PDX models, only. Transcriptional reprogramming inducing anti-EGFR SR was discovered as a common mechanism in CRC PDX models frequently leading to RAS signaling pathway activation. We identified cAMP and STAT3 signaling activation, as well as paracrine and autocrine signaling via growth factors as novel anti-EGFR secondary resistance mechanisms. Secondary resistant xenograft tumors could successfully be treated by addressing identified transcriptional changes by tailored targeted therapies., Conclusions: Our study demonstrates that SR PDX tumors provide a unique platform to study molecular SR mechanisms and allow testing of multiple treatments for efficient targeting of SR mechanisms, not possible in the patient. Importantly, it suggests that the development of anti-EGFR tolerant cells via transcriptional reprogramming as a cause of anti-EGFR SR in CRC is likely more prevalent than previously anticipated. It emphasizes the need for analyses of SR tumor tissues at a multi-omics level for a comprehensive molecular understanding of anti-EGFR SR in CRC., (© 2021. The Author(s).)

Background: Recent years have been witnessing a substantial improvement in the accuracy of skin cancer classification using convolutional neural networks (CNNs). CNNs perform on par with or better than dermatologists with respect to the classification tasks of single images. However, in clinical practice, dermatologists also use other patient data beyond the visual aspects present in a digitized image, further increasing their diagnostic accuracy. Several pilot studies have recently investigated the effects of integrating different subtypes of patient data into CNN-based skin cancer classifiers., Objective: This systematic review focuses on the current research investigating the impact of merging information from image features and patient data on the performance of CNN-based skin cancer image classification. This study aims to explore the potential in this field of research by evaluating the types of patient data used, the ways in which the nonimage data are encoded and merged with the image features, and the impact of the integration on the classifier performance., Methods: Google Scholar, PubMed, MEDLINE, and ScienceDirect were screened for peer-reviewed studies published in English that dealt with the integration of patient data within a CNN-based skin cancer classification. The search terms skin cancer classification, convolutional neural network(s), deep learning, lesions, melanoma, metadata, clinical information, and patient data were combined., Results: A total of 11 publications fulfilled the inclusion criteria. All of them reported an overall improvement in different skin lesion classification tasks with patient data integration. The most commonly used patient data were age, sex, and lesion location. The patient data were mostly one-hot encoded. There were differences in the complexity that the encoded patient data were processed with regarding deep learning methods before and after fusing them with the image features for a combined classifier., Conclusions: This study indicates the potential benefits of integrating patient data into CNN-based diagnostic algorithms. However, how exactly the individual patient data enhance classification performance, especially in the case of multiclass classification problems, is still unclear. Moreover, a substantial fraction of patient data used by dermatologists remains to be analyzed in the context of CNN-based skin cancer classification. Further exploratory analyses in this promising field may optimize patient data integration into CNN-based skin cancer diagnostics for patients' benefits., (©Julia Höhn, Achim Hekler, Eva Krieghoff-Henning, Jakob Nikolas Kather, Jochen Sven Utikal, Friedegund Meier, Frank Friedrich Gellrich, Axel Hauschild, Lars French, Justin Gabriel Schlager, Kamran Ghoreschi, Tabea Wilhelm, Heinz Kutzner, Markus Heppt, Sebastian Haferkamp, Wiebke Sondermann, Dirk Schadendorf, Bastian Schilling, Roman C Maron, Max Schmitt, Tanja Jutzi, Stefan Fröhling, Daniel B Lipka, Titus Josef Brinker. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 02.07.2021.)

The diagnosis of malignant pleural mesothelioma (MPM) is challenging because of its potential overlap with other neoplasms or even with reactive conditions. DNA methylation analysis is effective in diagnosing tumors. In the present study, this approach was tested for use in MPM diagnosis. The DNA methylation patterns of a discovery cohort and an independent-validation cohort of MPMs were compared to those of 202 cases representing malignant and benign diagnostic mimics (angiosarcoma, desmoid-type fibromatosis, epithelioid sarcoma, leiomyosarcoma, lung adenocarcinoma, lung squamous cell carcinoma, melanoma, nodular fasciitis, reactive mesothelial hyperplasia, sclerosing fibrous pleuritis, solitary fibrous tumor, and synovial sarcoma). By both unsupervised hierarchical clustering and t-distributed stochastic neighbor embedding analysis, MPM samples in the discovery cohort exhibited a DNA methylation profile different from those of other neoplastic and reactive mimics. These results were confirmed in the independent validation cohort and by in silico analysis of the MPM-The Cancer Genome Atlas data set. Copy number variation profiles were also inferred to identify molecular hallmarks of MPM, including CDKN2A and NF2 deletions. Methylation profiling was effective in the diagnosis of MPM, although caution is advised in samples with low tumor cell content., (Copyright © 2021 Association for Molecular Pathology and American Society for Investigative Pathology. Published by Elsevier Inc. All rights reserved.)

Increasingly extensive genomic diagnostics in cancer precision medicine require uniform evaluation criteria for the classification of variants with regard to their functional and therapeutic implications. In this review we present the most important guidelines and classification systems currently used in daily clinical practice, explain their advantages and disadvantages as well as differences and similarities, and present the step-by-step, systematic process that enables successful variant interpretation.

While genetic alterations in Epidermal growth factor receptor (EGFR) and PI3K are common in head and neck squamous cell carcinomas (HNSCC), their impact on oncogenic signaling and cancer drug sensitivities remains elusive. To determine their consequences on the transcriptional network, pathway activities of EGFR, PI3K, and 12 additional oncogenic pathways were inferred in 498 HNSCC samples of The Cancer Genome Atlas using PROGENy. More than half of HPV-negative HNSCC showed a pathway activation in EGFR or PI3K. An amplification in EGFR and a mutation in PI3KCA resulted in a significantly higher activity of the respective pathway (p = 0.017 and p = 0.007). Interestingly, both pathway activations could only be explained by genetic alterations in less than 25% of cases indicating additional molecular events involved in the downstream signaling. Suitable in vitro pathway models could be identified in a published drug screen of 45 HPV-negative HNSCC cell lines. An active EGFR pathway was predictive for the response to the PI3K inhibitor buparlisib (p = 6.36E-03) and an inactive EGFR and PI3K pathway was associated with efficacy of the B-cell lymphoma (BCL) inhibitor navitoclax (p = 9.26E-03). In addition, an inactive PI3K pathway correlated with a response to multiple Histone deacetylase inhibitor (HDAC) inhibitors. These findings require validation in preclinical models and clinical studies., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Mock, Plath, Moratin, Tapken, Jäger, Krauss, Fröhling, Hess and Zaoui.)

Background: Soft-tissue sarcomas (STS) are a heterogeneous group of mesenchymal tumors for which response to immunotherapies is not well established. Therefore, it is important to risk-stratify and identify STS patients who will most likely benefit from these treatments., Results: To reveal shared and distinct methylation signatures present in STS, we performed unsupervised deconvolution of DNA methylation data from the TCGA sarcoma and an independent validation cohort. We showed that leiomyosarcoma can be subclassified into three distinct methylation groups. More importantly, we identified a component associated with tumor-infiltrating leukocytes, which suggests varying degrees of immune cell infiltration in STS subtypes and an association with prognosis. We further investigated the genomic alterations that may influence tumor infiltration by leukocytes including RB1 loss in undifferentiated pleomorphic sarcomas and ELK3 amplification in dedifferentiated liposarcomas., Conclusions: In summary, we have leveraged unsupervised methylation-based deconvolution to characterize the immune compartment and molecularly stratify subtypes in STS, which may benefit precision medicine in the future.

Background: Modern anesthesia strives to offer personalized concepts to meet the patient's individual needs in sight of clinical outcome. Still, little is known about the impact of anesthesia on the plasma metabolome, although many metabolites have been shown to modulate the function of various immune cells, making it particularly interesting in the context of oncological surgery. In this study longitudinal dynamics in the plasma metabolome during general anesthesia in patients undergoing pancreatic surgery were analyzed., Materials and Methods: Prospective, observational study with 10 patients diagnosed with pancreatic (pre-) malignancy and subjected to elective resection surgery under general anesthesia. Plasma metabolites ( n = 630) were quantified at eight consecutive perioperative timepoints using mass spectrometry-based targeted metabolomics., Results: 39 metabolites significantly changed during the perioperative period. Tryptophan concentrations decreased by 45% with the maximum decrease after anesthesia induction ( p = 6.24E-07), while taurine synthesis increased ( p = 1.46E-04). Triacylglycerides and lysophosphatidylcholines were significantly reduced with increased liberation of free monounsaturated fatty acids ( p = 0.03). Carnitine levels decreased significantly ( p = 9.30E-04)., Conclusions: The major finding of this study was perioperative tryptophan depletion and increased taurine synthesis. Both are essential for immune cell function and are therefore of significant interest for perioperative management. Further studies are needed to identify influencing anesthetic factors., Competing Interests: CONFLICTS OF INTEREST Authors have no conflicts of interest to declare., (Copyright: © 2021 Mock-Ohnesorge et al.)

Background: Clinicians and pathologists traditionally use patient data in addition to clinical examination to support their diagnoses., Objectives: We investigated whether a combination of histologic whole slides image (WSI) analysis based on convolutional neural networks (CNNs) and commonly available patient data (age, sex and anatomical site of the lesion) in a binary melanoma/nevus classification task could increase the performance compared with CNNs alone., Methods: We used 431 WSIs from two different laboratories and analysed the performance of classifiers that used the image or patient data individually or three common fusion techniques. Furthermore, we tested a naive combination of patient data and an image classifier: for cases interpreted as 'uncertain' (CNN output score <0.7), the decision of the CNN was replaced by the decision of the patient data classifier., Results: The CNN on its own achieved the best performance (mean ± standard deviation of five individual runs) with AUROC of 92.30% ± 0.23% and balanced accuracy of 83.17% ± 0.38%. While the classification performance was not significantly improved in general by any of the tested fusions, naive strategy of replacing the image classifier with the patient data classifier on slides with low output scores improved balanced accuracy to 86.72% ± 0.36%., Conclusion: In most cases, the CNN on its own was so accurate that patient data integration did not provide any benefit. However, incorporating patient data for lesions that were classified by the CNN with low 'confidence' improved balanced accuracy., Competing Interests: Conflict of interest statement The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Haferkamp S. reports advisory roles for or has received honoraria from Pierre Fabre Pharmaceuticals, Novartis, Roche, BMS, Amgen and MSD outside the submitted work. Hauschild A. reports clinical trial support, speaker's honoraria or consultancy fees from the following companies: Amgen, BMS, Merck Serono, MSD, Novartis, Oncosec, Philogen, Pierre Fabre, Provectus, Regeneron, Roche, OncoSec, Sanofi-Genzyme and Sun Pharma, outside the submitted work. BS reports advisory roles for or has received honoraria from Pierre Fabre Pharmaceuticals, Incyte, Novartis, Roche, BMS and MSD, research funding from BMS, Pierre Fabre Pharmaceuticals and MSD, and travel support from Novartis, Roche, BMS, Pierre Fabre Pharmaceuticals and Amgen, outside the submitted work. JSU is on the advisory board or has received honoraria and travel support from Amgen, Bristol Myers Squibb, GSK, LeoPharma, Merck Sharp and Dohme, Novartis, Pierre Fabre, Roche, outside the submitted work. WS received travel expenses for attending meetings and/or (speaker) honoraria from Abbvie, Almirall, Bristol-Myers Squibb, Celgene, Janssen, LEO Pharma, Lilly, MSD, Novartis, Pfizer, Roche, Sanofi Genzyme and UCB outside the submitted work. FM has received travel support or/and speaker's fees or/and advisor's honoraria by Novartis, Roche, BMS, MSD and Pierre Fabre and research funding from Novartis and Roche. TJB reports owning a company that develops mobile applications (Smart Health Heidelberg GmbH, Handschuhsheimer Landstr. 9/1, 69120 Heidelberg, https://smarthealth.de). The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

Different mutational processes leave characteristic patterns of somatic mutations in the genome that can be identified as mutational signatures. Determining the contributions of mutational signatures to cancer genomes allows not only to reconstruct the etiology of somatic mutations, but can also be used for improved tumor classification and support therapeutic decisions. We here present the R package yet another package for signature analysis (YAPSA) to deconvolute the contributions of mutational signatures to tumor genomes. YAPSA provides in-built collections from the COSMIC and PCAWG SNV signature sets as well as the PCAWG Indel signatures and employs signature-specific cutoffs to increase sensitivity and specificity. Furthermore, YAPSA allows to determine 95% confidence intervals for signature exposures, to perform constrained stratified signature analyses to obtain enrichment and depletion patterns of the identified signatures and, when applied to whole exome sequencing data, to correct for the triplet content of individual target capture kits. With this functionality, YAPSA has proved to be a valuable tool for analysis of mutational signatures in molecular tumor boards in a precision oncology context. YAPSA is available at R/Bioconductor (http://bioconductor.org/packages/3.12/bioc/html/YAPSA.html)., (© 2020 The Authors. Genes, Chromosomes & Cancer published by Wiley Periodicals LLC.)

Purpose: CATCH (Comprehensive Assessment of clinical feaTures and biomarkers to identify patients with advanced or metastatic breast Cancer for marker driven trials in Humans) is a prospective precision oncology program that uses genomics and transcriptomics to guide therapeutic decisions in the clinical management of metastatic breast cancer. Herein, we report our single-center experience and results on the basis of the first 200 enrolled patients of an ongoing trial., Methods: From June 2017 to March 2019, 200 patients who had either primary metastatic or progressive disease, with any number of previous treatment lines and at least one metastatic site accessible to biopsy, were enrolled. DNA and RNA from tumor tissue and corresponding blood-derived nontumor DNA were profiled using whole-genome and transcriptome sequencing. Identified actionable alterations were brought into clinical context in a multidisciplinary molecular tumor board (MTB) with the aim of prioritizing personalized treatment recommendations., Results: Among the first 200 enrolled patients, 128 (64%) were discussed in the MTB, of which 64 (50%) were subsequently treated according to MTB recommendation. Of 53 evaluable patients, 21 (40%) achieved either stable disease (n = 13, 25%) or partial response (n = 8, 15%). Furthermore, 16 (30%) of those patients showed improvement in progression-free survival of at least 30% while on MTB-recommended treatment compared with the progression-free survival of the previous treatment line., Conclusion: The initial phase of this study demonstrates that precision oncology on the basis of whole-genome and RNA sequencing is feasible when applied in the clinical management of patients with metastatic breast cancer and provides clinical benefit to a substantial proportion of patients., Competing Interests: The following represents disclosure information provided by authors of this manuscript. All relationships are considered compensated unless otherwise noted. Relationships are self-held unless noted. I = Immediate Family Member, Inst = My Institution. Relationships may not relate to the subject matter of this manuscript. For more information about ASCO’s conflict of interest policy, please refer to www.asco.org/rwc or ascopubs.org/po/author-center. Open Payments is a public database containing information reported by companies about payments made to US-licensed physicians (Open Payments). Carlo FremdHonoraria: Roche, Pfizer, Celgene, AstraZeneca, Amgen Consulting or Advisory Role: Roche, Pfizer Travel, Accommodations, Expenses: Celgene, RocheLaura MichelHonoraria: AstraZeneca, Roche, Eisai, LillyDaniela RichterTravel, Accommodations, Expenses: IlluminaPeter HorakHonoraria: IpsenAlbrecht StenzingerConsulting or Advisory Role: AstraZeneca, Novartis, Bristol Myers Squibb, Bayer, Illumina, Thermo Fisher Scientific, Janssen, Lilly, Seattle Genetics, Takeda, AGCT Speakers' Bureau: Bristol Myers Squibb, AstraZeneca, MSD, Roche, Bayer, Illumina, Thermo Fisher Scientific, Novartis Research Funding: Chugai Pharma, Bristol Myers Squibb, BayerChristoph SpringfeldConsulting or Advisory Role: Celgene, Servier, Eisai, Roche, MSD, Bayer Travel, Accommodations, Expenses: Celgene, ServierKatharina SmetanayHonoraria: Celgene, Roche, Pfizer Travel, Accommodations, Expenses: CelgeneAthanasios MavratzasHonoraria: Roche, Eisai Europe, Pfizer Travel, Accommodations, Expenses: Roche, Eisai, PfizerFlorian SchuetzHonoraria: Roche, Pfizer, MSD Oncology, Amgen, AstraZeneca Consulting or Advisory Role: MSD OncologyStefan FröhlingHonoraria: PharmaMar, Roche, Lilly, Amgen Consulting or Advisory Role: Bayer, Illumina, Roche Research Funding: AstraZeneca, PharmaMar, Pfizer, Roche Travel, Accommodations, Expenses: PharmaMar, Roche, Lilly, AmgenHans-Peter SinnHonoraria: NanoString Technologies, Roche Pharma AG Research Funding: Roche Pharma AG Travel, Accommodations, Expenses: NanoString TechnologiesDirk JägerConsulting or Advisory Role: Roche/Genentech, Bristol Myers Squibb, BioNTech AG, AmgenAndreas SchneeweissHonoraria: Roche Pharma AG, Celgene, AstraZeneca, Pfizer, Novartis, MSD Oncology, Lilly, Tesaro Research Funding: Roche Pharma AG, Celgene, Abbvie, Molecular Partners Expert Testimony: Roche, AstraZeneca Travel, Accommodations, Expenses: Roche, Celgene No other potential conflicts of interest were reported., (© 2021 by American Society of Clinical Oncology.)

Objectives: Implementation of tyrosine kinase inhibitors (TKI) and other targeted therapies was a main advance in thoracic oncology with survival gains ranging from several months to years for non-small-cell lung cancer (NSCLC) patients. High-throughput comprehensive molecular profiling is of key importance to identify patients that can potentially benefit from these novel treatments., Material and Methods: Next-generation sequencing (NGS) was performed on 4500 consecutive formalin-fixed, paraffin-embedded specimens of advanced NSCLC (n = 4172 patients) after automated extraction of DNA and RNA for parallel detection of mutations and gene fusions, respectively., Results and Conclusion: Besides the 24.9 % (n = 1040) of cases eligible for approved targeted therapies based on the presence of canonical alterations in EGFR exons 18-21, BRAF, ROS1, ALK, NTRK, and RET, an additional n = 1260 patients (30.2 %) displayed rare or non-canonical mutations in EGFR (n = 748), BRAF (n = 135), ERBB2 (n = 30), KIT (n = 32), PIK3CA (n = 221), and CTNNB1 (n = 94), for which targeted therapies could also be potentially effective. A systematic literature search in conjunction with in silico evaluation identified n = 232 (5.5 %) patients, for which a trial of targeted treatment would be warranted according to available evidence (NCT level 1, i.e. published data showing efficacy in the same tumor entity). In conclusion, a sizeable fraction of NSCLC patients harbors rare or non-canonical alterations that may be associated with clinical benefit from currently available targeted drugs. Systematic identification and individualized management of these cases can expand applicability of precision oncology in NSCLC and extend clinical gain from established molecular targets. These results can also inform clinical trials., (Copyright © 2021 Elsevier B.V. All rights reserved.)

DNA sequencing and RNA sequencing are increasingly applied in precision oncology, where molecular tumor boards evaluate the actionability of genetic events in individual tumors to guide targeted treatment. To work toward an additional level of patient characterization, we assessed the abundance and activity of 27 proteins in 134 patients whose tumors had previously undergone whole-exome and RNA sequencing within the Molecularly Aided Stratification for Tumor Eradication Research (MASTER) program of National Center for Tumor Diseases, Heidelberg. Proteomic and phosphoproteomic targets were selected to reflect the most relevant therapeutic baskets in MASTER. Among six different therapeutic baskets, the proteomic data supported treatment recommendations that were based on DNA and RNA analyses in 10% to 57% and frequently suggested alternative treatment options. In several cases, protein activities explained the patients' clinical course and provided potential explanations for treatment failure. Our study indicates that the integrative analysis of DNA, RNA and protein data may refine therapeutic stratification of individual patients and, thus, holds potential to increase the success rate of precision cancer therapy. Prospective validation studies are needed to advance the integration of proteomic analysis into precision oncology., (© 2020 The Authors. International Journal of Cancer published by John Wiley & Sons Ltd on behalf of Union for International Cancer Control.)

Background: A basic requirement for artificial intelligence (AI)-based image analysis systems, which are to be integrated into clinical practice, is a high robustness. Minor changes in how those images are acquired, for example, during routine skin cancer screening, should not change the diagnosis of such assistance systems., Objective: To quantify to what extent minor image perturbations affect the convolutional neural network (CNN)-mediated skin lesion classification and to evaluate three possible solutions for this problem (additional data augmentation, test-time augmentation, anti-aliasing)., Methods: We trained three commonly used CNN architectures to differentiate between dermoscopic melanoma and nevus images. Subsequently, their performance and susceptibility to minor changes ('brittleness') was tested on two distinct test sets with multiple images per lesion. For the first set, image changes, such as rotations or zooms, were generated artificially. The second set contained natural changes that stemmed from multiple photographs taken of the same lesions., Results: All architectures exhibited brittleness on the artificial and natural test set. The three reviewed methods were able to decrease brittleness to varying degrees while still maintaining performance. The observed improvement was greater for the artificial than for the natural test set, where enhancements were minor., Conclusions: Minor image changes, relatively inconspicuous for humans, can have an effect on the robustness of CNNs differentiating skin lesions. By the methods tested here, this effect can be reduced, but not fully eliminated. Thus, further research to sustain the performance of AI classifiers is needed to facilitate the translation of such systems into the clinic., Competing Interests: Conflict of interest statement Sebastian H. reports advisory roles for or has received honoraria from Pierre Fabre Pharmaceuticals, Novartis, Roche, BMS, Amgen and MSD outside the submitted work. Axel H. reports clinical trial support, speaker's honoraria, or consultancy fees from the following companies: Amgen, BMS, Merck Serono, MSD, Novartis, Oncosec, Philogen, Pierre Fabre, Provectus, Regeneron, Roche, OncoSec, Sanofi-Genzyme, and Sun Pharma, outside, the submitted work. BS reports advisory roles for or has received honoraria from Pierre Fabre Pharmaceuticals, Incyte, Novartis, Roche, BMS and MSD, research funding from BMS, Pierre Fabre Pharmaceuticals and MSD, and travel support from Novartis, Roche, BMS, Pierre Fabre Pharmaceuticals and Amgen; outside the submitted work. JSU is on the advisory board or has received honoraria and travel support from Amgen, Bristol Myers Squibb, GSK, LeoPharma, Merck Sharp and Dohme, Novartis, Pierre Fabre, Roche, outside the submitted work. WS received travel expenses for attending meetings and/or (speaker) honoraria from Abbvie, Almirall, Bristol-Myers Squibb, Celgene, Janssen, LEO Pharma, Lilly, MSD, Novartis, Pfizer, Roche, Sanofi Genzyme and UCB outside the submitted work. FM has received travel support or/and speaker's fees or/and advisor's honoraria by Novartis, Roche, BMS, MSD and Pierre Fabre and research funding from Novartis and Roche. TJB reports owning a company that develops mobile apps (Smart Health Heidelberg GmbH, Handschuhsheimer Landstr. 9/1, 69120 Heidelberg; https://smarthealth.de). The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2020 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

The identification of gene fusions from RNA sequencing data is a routine task in cancer research and precision oncology. However, despite the availability of many computational tools, fusion detection remains challenging. Existing methods suffer from poor prediction accuracy and are computationally demanding. We developed Arriba, a novel fusion detection algorithm with high sensitivity and short runtime. When applied to a large collection of published pancreatic cancer samples ( n = 803), Arriba identified a variety of driver fusions, many of which affected druggable proteins, including ALK, BRAF, FGFR2, NRG1, NTRK1, NTRK3, RET, and ROS1. The fusions were significantly associated with KRAS wild-type tumors and involved proteins stimulating the MAPK signaling pathway, suggesting that they substitute for activating mutations in KRAS In addition, we confirmed the transforming potential of two novel fusions, RRBP1 - RAF1 and RASGRP1 - ATP1A1 , in cellular assays. These results show Arriba's utility in both basic cancer research and clinical translation., (© 2021 Uhrig et al.; Published by Cold Spring Harbor Laboratory Press.)

Background: Following surgery for soft tissue sarcoma of the retroperitoneum, the predominant pattern of failure is local recurrence, which remains the main cause of death. Radiotherapy is utilized to reduce recurrence rates but the efficacy of this strategy has not been definitely established. As treatment tolerability is more favorable with preoperative radiotherapy, normofractionated neoadjuvant treatment is the current approach. The final results of the prospective, randomized STRASS (EORTC 62092) trial, which compared the efficacy of this combined treatment to that of surgery alone, are still awaited; preliminary results presented at the 2019 ASCO Annual Meeting indicated that combined treatment is associated with better local control in patients with liposarcoma (74.5% of the cohort, 11% benefit in abdominal progression free survival after 3 years, p = 0.049). Particles allow better sparing of surrounding tissues at risk, e.g., bowel epithelium, and carbon ions additionally offer biologic advantages and are preferred in slow growing tumors. Furthermore, hypofractionation allows for a significantly shorter treatment interval with a lower risk of progression during radiotherapy., Methods and Design: We present a prospective, randomized, monocentric phase II trial. Patients with resectable or marginally resectable, histologically confirmed soft tissue sarcoma of the retroperitoneum will be randomized between neoadjuvant proton or neoadjuvant carbon ion radiotherapy in active scanning beam application technique (39 Gy [relative biological effectiveness, RBE] in 13 fractions [5-6 fractions per week] in each arm). The primary objective is the safety and feasibility based on the proportion of grade 3-5 toxicity (CTCAE, version 5.0) in the first 12 months after surgery or discontinuation of treatment for any reason related to the treatment. Local control, local progression-free survival, disease-free survival, overall survival, and quality of life are the secondary endpoints of the study., Discussion: The aim of this study is to confirm that hypofractionated, accelerated preoperative radiotherapy is safe and feasible. The rationale for the use of particle therapy is the potential for reduced toxicity. The data will lay the groundwork for a randomized phase III trial comparing hypofractionated proton and carbon ion irradiation with regard to local control., Trial Registration: ClinicalTrials.gov NCT04219202 . Retrospectively registered on January 6, 2020.

Background: An increasing number of studies within digital pathology show the potential of artificial intelligence (AI) to diagnose cancer using histological whole slide images, which requires large and diverse data sets. While diversification may result in more generalizable AI-based systems, it can also introduce hidden variables. If neural networks are able to distinguish/learn hidden variables, these variables can introduce batch effects that compromise the accuracy of classification systems., Objective: The objective of the study was to analyze the learnability of an exemplary selection of hidden variables (patient age, slide preparation date, slide origin, and scanner type) that are commonly found in whole slide image data sets in digital pathology and could create batch effects., Methods: We trained four separate convolutional neural networks (CNNs) to learn four variables using a data set of digitized whole slide melanoma images from five different institutes. For robustness, each CNN training and evaluation run was repeated multiple times, and a variable was only considered learnable if the lower bound of the 95% confidence interval of its mean balanced accuracy was above 50.0%., Results: A mean balanced accuracy above 50.0% was achieved for all four tasks, even when considering the lower bound of the 95% confidence interval. Performance between tasks showed wide variation, ranging from 56.1% (slide preparation date) to 100% (slide origin)., Conclusions: Because all of the analyzed hidden variables are learnable, they have the potential to create batch effects in dermatopathology data sets, which negatively affect AI-based classification systems. Practitioners should be aware of these and similar pitfalls when developing and evaluating such systems and address these and potentially other batch effect variables in their data sets through sufficient data set stratification., (©Max Schmitt, Roman Christoph Maron, Achim Hekler, Albrecht Stenzinger, Axel Hauschild, Michael Weichenthal, Markus Tiemann, Dieter Krahl, Heinz Kutzner, Jochen Sven Utikal, Sebastian Haferkamp, Jakob Nikolas Kather, Frederick Klauschen, Eva Krieghoff-Henning, Stefan Fröhling, Christof von Kalle, Titus Josef Brinker. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 02.02.2021.)

Sarcomas are malignant soft tissue and bone tumours affecting adults, adolescents and children. They represent a morphologically heterogeneous class of tumours and some entities lack defining histopathological features. Therefore, the diagnosis of sarcomas is burdened with a high inter-observer variability and misclassification rate. Here, we demonstrate classification of soft tissue and bone tumours using a machine learning classifier algorithm based on array-generated DNA methylation data. This sarcoma classifier is trained using a dataset of 1077 methylation profiles from comprehensively pre-characterized cases comprising 62 tumour methylation classes constituting a broad range of soft tissue and bone sarcoma subtypes across the entire age spectrum. The performance is validated in a cohort of 428 sarcomatous tumours, of which 322 cases were classified by the sarcoma classifier. Our results demonstrate the potential of the DNA methylation-based sarcoma classification for research and future diagnostic applications.

Immune checkpoint blockade (ICB) expands the therapeutic options for metastatic lung cancer nowadays representing a standard frontline strategy as monotherapy or combination therapy, as well as an option in oncogene-addicted NSCLC after exhaustion of targeted therapies. Predictive markers are urgently needed, since only a minority of patients benefits from ICB, while serious adverse effects of immunotoxicity may occur. The study cohort included 43 ICB-treated metastatic lung adenocarcinoma showing long-term response (n = 16), rapid progression (n = 21) or intermediate patterns of response (n = 6). Lung biopsies acquired before initiation of ICB were analyzed by targeted mRNA expression profiling of 770 genes. Level and proportions of 14 immune cell types were estimated using characteristic gene expression signatures. Abundance of B cells (HR = 0.66, p = .00074), CD45+ cells (HR = 0.61, p = .01) and total TILs (HR = 0.62, p = .025) was associated with prolonged progression-free survival after ICB treatment. In a ROC analysis, B cells (AUC = 0.77, p = .0055) and CD45+ cells (AUC = 0.73, p = .019) predicted benefit of ICB, which was not the case for PD-L1 mRNA (AUC = 0.54, p = .72) and PD-L1 protein expression (AUC = 0.68, p = .082). Clustering of 79 candidate predictive markers identified among 770 investigated genes revealed two distinct predictive clusters which included cytotoxic cell or macrophage markers, respectively. In summary, targeted gene expression profiling was feasible using routine diagnostics biopsies. This study proposes B cells and total TILs as complementary predictors of ICB benefit in NSCLC. While further preferably prospective validation is required, gene expression profiling could be integrated in the routine diagnostic work-up complementing existing NGS protocols., (© 2020 The Author(s). Published with license by Taylor & Francis Group, LLC.)

T-cell acute lymphoblastic leukemia (T-ALL) is a rare, aggressive T-cell malignancy. Chemotherapy alone cures only 25-45% of the cases, thus, novel treatment agents and strategies are urgently needed. We assessed the efficacy of ruxolitinib in a patient with a cutaneous relapse after allogeneic blood cell transplantation of a refractory T-ALL with a Janus kinase 3 ( JAK3 ) mutation. In this case report, we were able to show the potential benefit of the JAK inhibitor ruxolitinib in JAK3 -mutated refractory T-ALL and emphasize the importance of integrating molecular markers in current treatment decision making for patients with T-ALL., Competing Interests: The authors declare that there is no conflict of interest., (© 2020 The Authors. eJHaem published by British Society for Haematology and John Wiley & Sons Ltd.)

Circulating tumour DNA (ctDNA) analysis using next generation sequencing (NGS) is being implemented in clinical practice for treatment stratification and disease monitoring. However, using ctDNA to detect structural variants, a common occurrence in sarcoma, can be challenging. Here, we use a sarcoma-specific targeted NGS panel to identify translocations and copy number variants in a cohort of 12 tissue specimens and matched circulating cell-free DNA (cfDNA) from soft tissue sarcoma patients, including alveolar rhabdomyosarcoma ( n = 2), Ewing's Sarcoma ( n = 2), synovial sarcoma ( n = 2), extraskeletal myxoid chondrosarcoma ( n = 1), clear cell sarcoma ( n = 1), undifferentiated round cell sarcoma ( n = 1), myxoid liposarcoma ( n = 1), alveolar soft part cell sarcoma ( n = 1) and dedifferentiated liposarcoma ( n = 1). Structural variants were detected in 11/12 (91.6%) and 6/12 (50%) of tissue and plasma samples, respectively. Structural variants were detected in cfDNA at variant allele frequencies >0.2% with an average sequencing depth of 1026×. The results from this cohort show clinical potential for using NGS in ctDNA to aid in the diagnosis and clinical monitoring of sarcomas and warrant additional studies in larger cohorts.

Acute myeloid leukemia (AML) is an aggressive disease for which only few targeted therapies are available. Using high-throughput RNA interference (RNAi) screening in AML cell lines, we identified LIM kinase 1 (LIMK1) as a potential novel target for AML treatment. High LIMK1 expression was significantly correlated with shorter survival of AML patients and coincided with FLT3 mutations, KMT2A rearrangements, and elevated HOX gene expression. RNAi- and CRISPR-Cas9-mediated suppression as well as pharmacologic inhibition of LIMK1 and its close homolog LIMK2 reduced colony formation and decreased proliferation due to slowed cell-cycle progression of KMT2A-rearranged AML cell lines and patient-derived xenograft (PDX) samples. This was accompanied by morphologic changes indicative of myeloid differentiation. Transcriptome analysis showed upregulation of several tumor suppressor genes as well as downregulation of HOXA9 targets and mitosis-associated genes in response to LIMK1 suppression, providing a potential mechanistic basis for the anti-leukemic phenotype. Finally, we observed a reciprocal regulation between LIM kinases (LIMK) and CDK6, a kinase known to be involved in the differentiation block of KMT2A-rearranged AML, and addition of the CDK6 inhibitor palbociclib further enhanced the anti-proliferative effect of LIMK inhibition. Together, these data suggest that LIMK are promising targets for AML therapy.

Effective and sustained inhibition of non-enzymatic oncogenic driver proteins is a major pharmacological challenge. The clinical success of thalidomide analogues demonstrates the therapeutic efficacy of drug-induced degradation of transcription factors and other cancer targets 1-3 , but a substantial subset of proteins are resistant to targeted degradation using existing approaches 4,5 . Here we report an alternative mechanism of targeted protein degradation, in which a small molecule induces the highly specific, reversible polymerization of a target protein, followed by its sequestration into cellular foci and subsequent degradation. BI-3802 is a small molecule that binds to the Broad-complex, Tramtrack and Bric-à-brac (BTB) domain of the oncogenic transcription factor B cell lymphoma 6 (BCL6) and leads to the proteasomal degradation of BCL6 6 . We use cryo-electron microscopy to reveal how the solvent-exposed moiety of a BCL6-binding molecule contributes to a composite ligand-protein surface that engages BCL6 homodimers to form a supramolecular structure. Drug-induced formation of BCL6 filaments facilitates ubiquitination by the SIAH1 E3 ubiquitin ligase. Our findings demonstrate that a small molecule such as BI-3802 can induce polymerization coupled to highly specific protein degradation, which in the case of BCL6 leads to increased pharmacological activity compared to the effects induced by other BCL6 inhibitors. These findings open new avenues for the development of therapeutic agents and synthetic biology.

Malignant melanoma is the skin tumor that causes most deaths in Germany. At an early stage, melanoma is well treatable, so early detection is essential. However, the skin cancer screening program in Germany has been criticized because although melanomas have been diagnosed more frequently since introduction of the program, the mortality from malignant melanoma has not decreased. This indicates that the observed increase in melanoma diagnoses be due to overdiagnosis, i.e. to the detection of lesions that would never have created serious health problems for the patients. One of the reasons is the challenging distinction between some benign and malignant lesions. In addition, there may be lesions that are biologically equivocal, and other lesions that are classified as malignant according to current criteria, but that grow so slowly that they would never have posed a threat to patient's life. So far, these "indolent" melanomas cannot be identified reliably due to a lack of biomarkers. Moreover, the likelihood that an in-situ melanoma will progress to an invasive tumor still cannot be determined with any certainty. When benign lesions are diagnosed as melanoma, the consequences are unnecessary psychological and physical stress for the affected patients and incurred therapy costs. Vice versa, underdiagnoses in the sense of overlooked melanomas can adversely affect patients' prognoses and may necessitate more intense therapies. Novel diagnostic options could reduce the number of over- and underdiagnoses and contribute to more objective diagnoses in borderline cases. One strategy that has yielded promising results in pilot studies is the use of artificial intelligence-based diagnostic tools. However, these applications still await translation into clinical and pathological routine., (© 2020 Deutsche Dermatologische Gesellschaft (DDG). Published by John Wiley & Sons Ltd.)

Background: Oncological therapies show a number of undesired adverse effects on the cardiovascular system. In particular, the side effects of recently established oncological therapies are incompletely understood and clinical data are lacking in the interpretation of novel cardiac complications., Objective: This article provides a short overview of the mechanisms of cardiac side effects of certain oncological therapies., Material and Methods: The review is mainly based on data from preclinical studies., Results: Numerous toxic side effects have already been described and investigated in preclinical models. For certain groups of drugs (e.g. anthracyclines, tyrosine kinase inhibitors and immune checkpoint inhibitors) the underlying molecular mechanisms are still not fully understood., Conclusion: An improved understanding of the molecular mechanism involved in cardiotoxicity might help improve the quality of clinical decisions. Additionally, it will provide new insights into the pathophysiology of cardiac diseases. The aim is to use the results of translational research and to clinically implement them in suitable cardio-oncology units.