Search

Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. In biomedical image analysis, chosen performance metrics often do not reflect the domain interest, and thus fail to adequately measure scientific progress and hinder translation of ML techniques into practice. To overcome this, we created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. Developed by a large international consortium in a multistage Delphi process, it is based on the novel concept of a problem fingerprint-a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), dataset and algorithm output. On the basis of the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as classification tasks at image, object or pixel level, namely image-level classification, object detection, semantic segmentation and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. Its applicability is demonstrated for various biomedical use cases., (© 2024. Springer Nature America, Inc.)

The availability of computational hardware and developments in (medical) machine learning (MML) increases medical mixed realities' (MMR) clinical usability. Medical instruments have played a vital role in surgery for ages. To further accelerate the implementation of MML and MMR, three-dimensional (3D) datasets of instruments should be publicly available. The proposed data collection consists of 103, 3D-scanned medical instruments from the clinical routine, scanned with structured light scanners. The collection consists, for example, of instruments, like retractors, forceps, and clamps. The collection can be augmented by generating likewise models using 3D software, resulting in an inflated dataset for analysis. The collection can be used for general instrument detection and tracking in operating room settings, or a freeform marker-less instrument registration for tool tracking in augmented reality. Furthermore, for medical simulation or training scenarios in virtual reality and medical diminishing reality in mixed reality. We hope to ease research in the field of MMR and MML, but also to motivate the release of a wider variety of needed surgical instrument datasets., (© 2023. The Author(s).)

Background: With the rise in importance of personalized medicine and deep learning, we combine the two to create personalized neural networks. The aim of the study is to show a proof of concept that data from just one patient can be used to train deep neural networks to detect tumor progression in longitudinal datasets., Methods: Two datasets with 64 scans from 32 patients with glioblastoma multiforme (GBM) were evaluated in this study. The contrast-enhanced T1w sequences of brain magnetic resonance imaging (MRI) images were used. We trained a neural network for each patient using just two scans from different timepoints to map the difference between the images. The change in tumor volume can be calculated with this map. The neural networks were a form of a Wasserstein-GAN (generative adversarial network), an unsupervised learning architecture. The combination of data augmentation and the network architecture allowed us to skip the co-registration of the images. Furthermore, no additional training data, pre-training of the networks or any (manual) annotations are necessary., Results: The model achieved an AUC-score of 0.87 for tumor change. We also introduced a modified RANO criteria, for which an accuracy of 66% can be achieved., Conclusions: We show a novel approach to deep learning in using data from just one patient to train deep neural networks to monitor tumor change. Using two different datasets to evaluate the results shows the potential to generalize the method., (© 2023. The Author(s).)

Cranial implants are commonly used for surgical repair of craniectomy-induced skull defects. These implants are usually generated offline and may require days to weeks to be available. An automated implant design process combined with onsite manufacturing facilities can guarantee immediate implant availability and avoid secondary intervention. To address this need, the AutoImplant II challenge was organized in conjunction with MICCAI 2021, catering for the unmet clinical and computational requirements of automatic cranial implant design. The first edition of AutoImplant (AutoImplant I, 2020) demonstrated the general capabilities and effectiveness of data-driven approaches, including deep learning, for a skull shape completion task on synthetic defects. The second AutoImplant challenge (i.e., AutoImplant II, 2021) built upon the first by adding real clinical craniectomy cases as well as additional synthetic imaging data. The AutoImplant II challenge consisted of three tracks. Tracks 1 and 3 used skull images with synthetic defects to evaluate the ability of submitted approaches to generate implants that recreate the original skull shape. Track 3 consisted of the data from the first challenge (i.e., 100 cases for training, and 110 for evaluation), and Track 1 provided 570 training and 100 validation cases aimed at evaluating skull shape completion algorithms at diverse defect patterns. Track 2 also made progress over the first challenge by providing 11 clinically defective skulls and evaluating the submitted implant designs on these clinical cases. The submitted designs were evaluated quantitatively against imaging data from post-craniectomy as well as by an experienced neurosurgeon. Submissions to these challenge tasks made substantial progress in addressing issues such as generalizability, computational efficiency, data augmentation, and implant refinement. This paper serves as a comprehensive summary and comparison of the submissions to the AutoImplant II challenge. Codes and models are available at https://github.com/Jianningli/Autoimplant_II., Competing Interests: Declaration of Competing Interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Michal Španěl is affiliated with TESCAN 3DIM that sponsored the challenge., (Copyright © 2023 Elsevier B.V. All rights reserved.)

Competing Interests: Die Autorinnen/Autoren geben an, dass kein Interessenkonflikt besteht.

Purpose: The aim of this study was to systematically evaluate the effect of thresholding algorithms used in computer vision for the quantification of prostate-specific membrane antigen positron emission tomography (PET) derived tumor volume (PSMA-TV) in patients with advanced prostate cancer. The results were validated with respect to the prognostication of overall survival in patients with advanced-stage prostate cancer., Materials and Methods: A total of 78 patients who underwent [ 177 Lu]Lu-PSMA-617 radionuclide therapy from January 2018 to December 2020 were retrospectively included in this study. [ 68 Ga]Ga-PSMA-11 PET images, acquired prior to radionuclide therapy, were used for the analysis of thresholding algorithms. All PET images were first analyzed semi-automatically using a pre-evaluated, proprietary software solution as the baseline method. Subsequently, five histogram-based thresholding methods and two local adaptive thresholding methods that are well established in computer vision were applied to quantify molecular tumor volume. The resulting whole-body molecular tumor volumes were validated with respect to the prognostication of overall patient survival as well as their statistical correlation to the baseline methods and their performance on standardized phantom scans., Results: The whole-body PSMA-TVs, quantified using different thresholding methods, demonstrate a high positive correlation with the baseline methods. We observed the highest correlation with generalized histogram thresholding (GHT) (Pearson r (r), p value (p): r = 0.977, p < 0.001) and Sauvola thresholding (r = 0.974, p < 0.001) and the lowest correlation with Multiotsu (r = 0.877, p < 0.001) and Yen thresholding methods (r = 0.878, p < 0.001). The median survival time of all patients was 9.87 months (95% CI [9.3 to 10.13]). Stratification by median whole-body PSMA-TV resulted in a median survival time from 11.8 to 13.5 months for the patient group with lower tumor burden and 6.5 to 6.6 months for the patient group with higher tumor burden. The patient group with lower tumor burden had significantly higher probability of survival (p < 0.00625) in eight out of nine thresholding methods (Fig. 2); those methods were SUVmax50 (p = 0.0038), SUV ≥3 (p = 0.0034), Multiotsu (p = 0.0015), Yen (p = 0.0015), Niblack (p = 0.001), Sauvola (p = 0.0001), Otsu (p = 0.0053), and Li thresholding (p = 0.0053)., Conclusion: Thresholding methods commonly used in computer vision are promising tools for the semiautomatic quantification of whole-body PSMA-TV in [ 68 Ga]Ga-PSMA-11-PET. The proposed algorithm-driven thresholding strategy is less arbitrary and less prone to biases than thresholding with predefined values, potentially improving the application of whole-body PSMA-TV as an imaging biomarker., (© 2023. The Author(s).)

Objectives: In the Cancer Core Europe Consortium (CCE), standardized biomarkers are required for therapy monitoring oncologic multicenter clinical trials. Multiparametric functional MRI and particularly diffusion-weighted MRI offer evident advantages for noninvasive characterization of tumor viability compared to CT and RECIST. A quantification of the inter- and intraindividual variation occurring in this setting using different hardware is missing. In this study, the MRI protocol including DWI was standardized and the residual variability of measurement parameters quantified., Methods: Phantom and volunteer measurements (single-shot T2w and DW-EPI) were performed at the seven CCE sites using the MR hardware produced by three different vendors. Repeated measurements were performed at the sites and across the sites including a traveling volunteer, comparing qualitative and quantitative ROI-based results including an explorative radiomics analysis., Results: For DWI/ADC phantom measurements using a central post-processing algorithm, the maximum deviation could be decreased to 2%. However, there is no significant difference compared to a decentralized ADC value calculation at the respective MRI devices. In volunteers, the measurement variation in 2 repeated scans did not exceed 11% for ADC and is below 20% for single-shot T2w in systematic liver ROIs. The measurement variation between sites amounted to 20% for ADC and < 25% for single-shot T2w. Explorative radiomics classification experiments yield better results for ADC than for single-shot T2w., Conclusion: Harmonization of MR acquisition and post-processing parameters results in acceptable standard deviations for MR/DW imaging. MRI could be the tool in oncologic multicenter trials to overcome the limitations of RECIST-based response evaluation., Key Points: • Harmonizing acquisition parameters and post-processing homogenization, standardized protocols result in acceptable standard deviations for multicenter MR-DWI studies. • Total measurement variation does not to exceed 11% for ADC in repeated measurements in repeated MR acquisitions, and below 20% for an identical volunteer travelling between sites. • Radiomic classification experiments were able to identify stable features allowing for reliable discrimination of different physiological tissue samples, even when using heterogeneous imaging data., (© 2022. The Author(s).)

Within the scope of the two NUM projects CODEX and RACOON we developed a preliminary technical concept for documenting clinical and radiological COVID-19 data in a collaborative approach and its preceding findings of a requirement analysis. At first, we provide an overview of NUM and its two projects CODEX and RACOON including the GECCO data set. Furthermore, we demonstrate the foundation for the increased collaboration of both projects, which was additionally supported by a survey conducted at University Hospital Frankfurt. Based on the survey results mint Lesion™, developed by Mint Medical and used at all project sites within RACOON, was selected as the "Electronic Data Capture" (EDC) system for CODEX. Moreover, to avoid duplicate entry of GECCO data into both EDC systems, an early effort was made to consider a collaborative and efficient technical approach to reduce the workload for the medical documentalists. As a first effort we present a preliminary technical concept representing the current and possible future data workflow of CODEX and RACOON. This concept includes a software component to synchronize GECCO data sets between the two EDC systems using the HL7 FHIR standard. Our first approach of a collaborative use of an EDC system and its medical documentalists could be beneficial in combination with the presented synchronization component for all participating project sites of CODEX and RACOON with regard to an overall reduced documentation workload.

Background: Artificial intelligence (AI) has the potential to fundamentally change medicine within the coming decades. Radiological imaging is one of the primary fields of its clinical application., Objectives: In this article, we summarize previous AI developments with a focus on oncological radiology. Based on selected examples, we derive scenarios for developments in the next 10 years., Materials and Methods: This work is based on a review of various literature and product databases, publications by regulatory authorities, reports, and press releases., Conclusions: The clinical use of AI applications is still in an early stage of development. The large number of research publications shows the potential of the field. Several certified products have already become available to users. However, for a widespread adoption of AI applications in clinical routine, several fundamental prerequisites are still awaited. These include the generation of evidence justifying the use of algorithms through representative clinical studies, adjustments to the framework for approval processes and dedicated education and teaching resources for its users. It is expected that use of AI methods will increase, thus, creating new opportunities for improved diagnostics, therapy, and more efficient workflows.

Prostate-specific membrane antigen (PSMA)-targeting PET imaging is becoming the reference standard for prostate cancer staging, especially in advanced disease. Yet, the implications of PSMA PET-derived whole-body tumor volume for overall survival are poorly elucidated to date. This might be because semiautomated quantification of whole-body tumor volume as a PSMA PET biomarker is an unmet clinical challenge. Therefore, in the present study we propose and evaluate a software that enables the semiautomated quantification of PSMA PET biomarkers such as whole-body tumor volume. Methods: The proposed quantification is implemented as a research prototype. PSMA-accumulating foci were automatically segmented by a percental threshold (50% of local SUV max ). Neural networks were trained to segment organs in PET/CT acquisitions (training CTs: 8,632, validation CTs: 53). Thereby, PSMA foci within organs of physiologic PSMA uptake were semiautomatically excluded from the analysis. Pretherapeutic PSMA PET/CTs of 40 consecutive patients treated with 177 Lu-PSMA-617 were evaluated in this analysis. The whole-body tumor volume (PSMA TV50 ), SUV max , SUV mean , and other whole-body imaging biomarkers were calculated for each patient. Semiautomatically derived results were compared with manual readings in a subcohort (by 1 nuclear medicine physician). Additionally, an interobserver evaluation of the semiautomated approach was performed in a subcohort (by 2 nuclear medicine physicians). Results: Manually and semiautomatically derived PSMA metrics were highly correlated (PSMA TV50 : R 2 = 1.000, P < 0.001; SUV max : R 2 = 0.988, P < 0.001). The interobserver agreement of the semiautomated workflow was also high (PSMA TV50 : R 2 = 1.000, P < 0.001, interclass correlation coefficient = 1.000; SUV max : R 2 = 0.988, P < 0.001, interclass correlation coefficient = 0.997). PSMA TV50 (ml) was a significant predictor of overall survival (hazard ratio: 1.004; 95% confidence interval: 1.001-1.006, P = 0.002) and remained so in a multivariate regression including other biomarkers (hazard ratio: 1.004; 95% confidence interval: 1.001-1.006 P = 0.004). Conclusion: PSMA TV50 is a promising PSMA PET biomarker that is reproducible and easily quantified by the proposed semiautomated software. Moreover, PSMA TV50 is a significant predictor of overall survival in patients with advanced prostate cancer who receive 177 Lu-PSMA-617 therapy., (© 2020 by the Society of Nuclear Medicine and Molecular Imaging.)

Machine learning (ML) is entering many areas of society, including medicine. This transformation has the potential to drastically change medicine and medical practice. These aspects become particularly clear when considering the different stages of oncologic patient care and the involved interdisciplinary and intermodality interactions. In recent publications, computers-in collaboration with humans or alone-have been outperforming humans regarding tumor identification, tumor classification, estimating prognoses, and evaluation of treatments. In addition, ML algorithms, e.g., artificial neural networks (ANNs), which constitute the drivers behind many of the latest achievements in ML, can deliver this level of performance in a reproducible, fast, and inexpensive manner. In the future, artificial intelligence applications will become an integral part of the medical profession and offer advantages for oncologic diagnostics and treatment.

Rationale: PSMA-PET-CT enables measuring molecular expression of prostate-specific membrane antigen (PSMA) in vivo , which is the target molecule of 177 Lu-PSMA-617 (Lu-PSMA) therapy. However, the correlation of PSMA expression and overall survival (OS) in patients treated with Lu-PSMA therapy is currently unclear; especially with regard to coexistence of high and low PSMA expressing metastases. To this end, this retrospective single arm study elucidates the correlation of PSMA expression and overall survival in patients treated with Lu-PSMA therapy. Additionally, PET based criteria to define low PSMA expression were explored. Methods: Eighty-five patients referred to Lu-PSMA therapy were included in the analysis. Pretherapeutic 68 Ga-PSMA-PET-CT scans were available for all patients. SUV max of the highest PSMA expressing metastasis (PSMA max ), SUV max of the lowest PSMA expressing metastasis (PSMA min ), and average SUV max of all metastases (PSMA average ) amongst other PET parameters were measured for each patient. A log-rank cutoff-finder was used to determine low (lowPSMA average ) and high (highPSMA average ) average PSMA expression as well as low (lowPSMA min ) and high (highPSMA min ) minimal PSMA expression. Results: PSMA average was a significant prognosticator of overall survival in contrast to PSMA max (HR: 0.959; p = 0.047 vs. HR: 0.992; p = 0.231). Optimal log rank cut-offs were: PSMA average = 14.3; PSMA min = 10.2. Patients with low average PSMA expression (lowPSMA average ) had significantly shorter survival compared to those with high average expression (highPSMA average ) (5.3 vs. 15.1 months; p < 0.001; HR: 3.738, 95%CI = 1.953-7.154; p < 0.001). Patients with low PSMA expressing metastases (lowPSMA min ) had shorter survival compared to those without a low PSMA expressing metastasis (highPSMA min ) (p = 0.003; 7.9 months vs. 21.3; HR: 4.303, 95%CI = 1.521-12.178; p = 0.006). Patients that were classified as highPSMA average but with lowPSMA min had an intermediate overall survival (11.4 months; longer compared to lowPSMA average , 5.3 months, p = 0.002; but shorter compared to highPSMA min , 21.3 months, p = 0.02). Conclusion: Low average PSMA expression is a negative prognosticator of overall survival. Absence of low PSMA expressing metastases is associated with best overall survival and the maximum PSMA expression seems not suited to prognosticate overall survival. Low PSMA expression might therefore be a negative prognosticator for the outcome of patients treated with Lu-PSMA therapy. Future studies are warranted to elucidate the degree of low PSMA expression tolerable for Lu-PSMA therapy., (© The author(s).)

Clinical Issue: Hybrid imaging enables the precise visualization of cellular metabolism by combining anatomical and metabolic information. Advances in artificial intelligence (AI) offer new methods for processing and evaluating this data., Methodological Innovations: This review summarizes current developments and applications of AI methods in hybrid imaging. Applications in image processing as well as methods for disease-related evaluation are presented and discussed., Materials and Methods: This article is based on a selective literature search with the search engines PubMed and arXiv., Assessment: Currently, there are only a few AI applications using hybrid imaging data and no applications are established in clinical routine yet. Although the first promising approaches are emerging, they still need to be evaluated prospectively. In the future, AI applications will support radiologists and nuclear medicine radiologists in diagnosis and therapy.

Background: The methods of machine learning and artificial intelligence are slowly but surely being introduced in everyday medical practice. In the future, they will support us in diagnosis and therapy and thus improve treatment for the benefit of the individual patient. It is therefore important to deal with this topic and to develop a basic understanding of it., Objectives: This article gives an overview of the exciting and dynamic field of machine learning and serves as an introduction to some methods primarily from the realm of supervised learning. In addition to definitions and simple examples, limitations are discussed., Conclusions: The basic principles behind the methods are simple. Nevertheless, due to their high dimensional nature, the factors influencing the results are often difficult or impossible to understand by humans. In order to build confidence in the new technologies and to guarantee their safe application, we need explainable algorithms and prospective effectiveness studies.

Clinical Issue: The reproducible and exhaustive extraction of information from radiological images is a central task in the practice of radiology. Dynamic developments in the fields of artificial intelligence (AI) and machine learning are introducing new methods for this task. Radiomics is one such method and offers new opportunities and challenges for the future of radiology., Methodological Innovations: Radiomics describes the quantitative evaluation, interpretation, and clinical assessment of imaging markers in radiological data. Components of a radiomics analysis are data acquisition, data preprocessing, data management, segmentation of regions of interest, computation and selection of imaging markers, as well as the development of a radiomics model used for diagnosis and prognosis. This article explains these components and aims at providing an introduction to the field of radiomics while highlighting existing limitations., Materials and Methods: This article is based on a selective literature search with the PubMed search engine., Assessment: Even though radiomics applications have yet to arrive in routine clinical practice, the quantification of radiological data in terms of radiomics is underway and will increase in the future. This holds the potential for lasting change in the discipline of radiology. Through the successful extraction and interpretation of all the information encoded in radiological images the next step in the direction of a more personalized, future-oriented form of medicine can be taken.