Search

Computational methods have made substantial progress in improving the accuracy and throughput of pathology workflows for diagnostic, prognostic, and genomic prediction. Still, lack of interpretability remains a significant barrier to clinical integration. We present an approach for predicting clinically-relevant molecular phenotypes from whole-slide histopathology images using human-interpretable image features (HIFs). Our method leverages >1.6 million annotations from board-certified pathologists across >5700 samples to train deep learning models for cell and tissue classification that can exhaustively map whole-slide images at two and four micron-resolution. Cell- and tissue-type model outputs are combined into 607 HIFs that quantify specific and biologically-relevant characteristics across five cancer types. We demonstrate that these HIFs correlate with well-known markers of the tumor microenvironment and can predict diverse molecular signatures (AUROC 0.601–0.864), including expression of four immune checkpoint proteins and homologous recombination deficiency, with performance comparable to ‘black-box’ methods. Our HIF-based approach provides a comprehensive, quantitative, and interpretable window into the composition and spatial architecture of the tumor microenvironment., Computational methods have made progress in improving classification accuracy and throughput of pathology workflows, but lack of interpretability remains a barrier to clinical integration. Here, the authors present an approach for predicting clinically-relevant molecular phenotypes from whole-slide histopathology images using human-interpretable image features.

While computational methods have made substantial progress in improving the accuracy and throughput of pathology workflows for diagnostic, prognostic, and genomic prediction, lack of interpretability remains a significant barrier to clinical integration. In this study, we present a novel approach for predicting clinically-relevant molecular phenotypes from histopathology whole-slide images (WSIs) using human-interpretable image features (HIFs). Our method leverages >1.6 million annotations from board-certified pathologists across >5,700 WSIs to train deep learning models for high-resolution tissue classification and cell detection across entire WSIs in five cancer types. Combining cell- and tissue-type models enables computation of 607 HIFs that comprehensively capture specific and biologically-relevant characteristics of multiple tumors. We demonstrate that these HIFs correlate with well-known markers of the tumor microenvironment (TME) and can predict diverse molecular signatures, including immune checkpoint protein expression and homologous recombination deficiency (HRD). Our HIF-based approach provides a novel, quantitative, and interpretable window into the composition and spatial architecture of the TME.

Assessment of tumor-infiltrating lymphocytes (TILs) is increasingly recognized as an integral part of the prognostic workflow in triple-negative (TNBC) and HER2-positive breast cancer, as well as many other solid tumors. This recognition has come about thanks to standardized visual reporting guidelines, which helped to reduce inter-reader variability. Now, there are ripe opportunities to employ computational methods that extract spatio-morphologic predictive features, enabling computer-aided diagnostics. We detail the benefits of computational TILs assessment, the readiness of TILs scoring for computational assessment, and outline considerations for overcoming key barriers to clinical translation in this arena. Specifically, we discuss: 1. ensuring computational workflows closely capture visual guidelines and standards; 2. challenges and thoughts standards for assessment of algorithms including training, preanalytical, analytical, and clinical validation; 3. perspectives on how to realize the potential of machine learning models and to overcome the perceptual and practical limits of visual scoring., info:eu-repo/semantics/published

3130 Background: IMpower150 is a phase 3 study measuring the effect of carboplatin and paclitaxel (CP) combined with atezolizumab (A) and/or bevacizumab (B) in patients with advanced nonsquamous NSCLC, testing the hypothesis that anti-PD-L1 therapy may be enhanced by the blockade of VEGF. Here, we apply a machine-learning based approach to quantify the tumor micro-environment (TME) and vasculature and identify associations with clinical outcome in IMpower150. Methods: Digitized H&E images were registered onto the PathAI research platform (n=1027). Over 200K annotations from 90 pathologists were used to train convolutional neural networks (CNNs) that classify human-interpretable features (HIFs) of cells and tissue structures from images. Blood vessel compression (BVC) indices were calculated using the long versus short axes for each predicted blood vessel. HIFs were clustered to reduce redundancy, and selected features were associated with progression free survival (PFS) within each arm (ABCP, ACP, and BCP) using Cox proportional hazard models. Results: We used the trained CNNs to generate 4,534 features summarizing each patient’s histopathology and TME. After association with survival and correction for multiple comparisons we identified clusters that were significantly associated with survival in at least one arm. Among patients receiving treatments that target PD-L1 (ABCP and ACP), high lymphocyte to fibroblast ratio (LFR) was associated with improved PFS (HR=0.64 (0.51, 0.81), p < 0.001) and showed no significant association with PFS among patients treated with BCP alone (HR=1.13 (0.85, 1.51), p=0.4). Among BCP treated patients, a higher average BVC within the tumor tissue was associated with improved PFS (HR=0.67 (0.50,0.90), p=0.01) and worse PFS among patients treated with ACP (HR=1.50 (1.10,2.06), p=0.009). Conclusions: We developed a deep learning-based assay for quantifying pathology features of the TME and vasculature from H&E images. Application of this system to Impower150 identified an association between high LFR and improved PFS among patients receiving PD-L1 targeting therapy, and between low BVC and improved PFS among patients receiving BCP. These findings support the importance of the TME and vasculature in determining response to PD-L1 and VEGF-targeting therapies.

Background: Approximately 15-25% of patients with atypical ductal hyperplasia (ADH) diagnosed on breast core needle biopsy (CNB) are upgraded to ductal carcinoma in situ (DCIS) or invasive carcinoma (IC) on surgical excision. The reproducible identification of patients with ADH on CNB who are more likely to have upgrades at excision remains elusive. We hypothesized that a machine learning approach could be utilized to train models to recognize ADH on digitized pathology images and to identify cases of ADH more likely to be upgraded to DCIS or IC at excision. The purpose of this study was to determine the accuracy of the machine learning approach to identify ADH. Methods: 726 digitized images of CNB slides derived from 306 cases with a diagnosis of ADH between 11/2004-3/2018 were included in this study. Independent histologic review by two breast pathologists identified slides with and without ADH from each case. 39 board certified pathologists with experience in evaluation of breast biopsies were employed for tissue region annotation on the PathAI research platform (not intended for diagnostic purposes), yielding 14,118 tissue region annotations. Region annotations included ADH, ADH stroma, flat epithelial atypia (FEA), lobular neoplasia (LN), calcifications (Ca), columnar cell change/hyperplasia, sclerosing adenosis, papilloma, normal terminal duct lobular units and other non-atypical breast tissue regions. These annotations were used to train a convolutional neural network (CNN) with 35 layers and approximately 9 million parameters to identify ADH. The data were split into training and testing sets, representing 61.1% and 38.9% of the data respectively. The distribution of cases, images with ADH and cases with upgrade were balanced between the training and testing sets. Results: CNB specimens were assigned labels of “ADH” or “No ADH” based on histologic assessment. AI models were able to predict the diagnosis of ADH with 85% sensitivity (144 of 168 images within the test set) and 69% specificity (78 of 113 images within the test set). The slide-level area under the receiver operator curve (ROC) for this model was 0.84. Conclusions: A deep learning-based classifier showed strong performance for the identification of ADH from whole slide images of H&E stained breast CNBs. With further development, this approach may improve the reproducibility and standardization of the diagnosis of ADH. Future analyses will focus on determining if morphologic features of ADH extracted by the deep learning system can be used to predict upgrade to DCIS and IC. This approach may help stratify patients with ADH on CNB into those who require surgical excision and those who can be followed with active surveillance. Citation Format: Jennifer K. Kerner, Allison Cleary, Suyog Jain, Harsha Pokkalla, Benjamin Glass, Sam Grossmith, Maya Harary, Elizabeth Mittendorf, Andrew H. Beck, Aditya Khosla, Stuart J. Schnitt, Ilan Wapinski, Tari King. Artificial intelligence powered predictive analysis of atypical ductal hyperplasia from digitized pathology images [abstract]. In: Proceedings of the 2019 San Antonio Breast Cancer Symposium; 2019 Dec 10-14; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2020;80(4 Suppl):Abstract nr P5-02-02.

A number of lesions have been documented to arise within congenital melanocytic nevi (CMNs). Although the most frequent malignancy arising within a CMN is melanoma, the association between rhabdomyosarcoma and CMN has rarely been documented. We present a case arising in a 4-month-old girl with a giant CMN. She presented for evaluation of a pedunculated lesion at the superior gluteal crease that had been present since birth and exhibited rapid growth. Biopsy of the lesion revealed two distinct components: an expansile proliferation of pleomorphic cells with varying degrees of cellularity and a proliferation of banal-appearing melanocytic nevic cells. The cells of the expansile proliferation displayed a wide range of morphologic features, including nests of round cells, spindle-shaped cells, and more differentiated rhabdomyoblasts within a myxoid, highly vascularized stroma. Cross-striations, a marker of skeletal muscle differentiation, were present. These tumor cells were strongly immunoreactive with desmin, myo-D1, and myogenin. Fluorescence in situ hybridization analysis with PAX3/7-FKHR probes was negative. A diagnosis of embryonal rhabdomyosarcoma in association with CMN was made. Initial excision revealed tumor at the margins, and the patient underwent reexcision with subsequent chemotherapy with vincristine, actinomycin D, and cyclophosphamide. She was disease-free at the 6-year follow-up. It has been postulated that the combination of melanocytic and rhabdomyoblastic cells within the same lesion may imply derivation from a common pluripotent stem cell or neural crest cell. Clinicians following patients with giant CMN should consider rhabdomyosarcoma in the differential diagnosis of lesions arising within the nevus.

2594 Background: Distribution patterns of CD8+ T cells within the tumor microenvironment (TME) can be assessed by IA, which may reflect underlying tumor biology and serve as a potential biomarker to assess the utility of I-O therapy. These patterns are variable and may be classified as immune desert (minimal infiltrate), excluded (T cells confined to tumor stroma or to the invasive margin), or inflamed (T cells diffusely infiltrating tumor parenchyma and stroma). We hypothesized that association of a GEP signature with abundance of parenchymal and stromal T-cell infiltrates may identify biomarkers of response or resistance to I-O therapy. To test this, we applied an AI-powered IA platform to quantify CD8+ T cells by geographical location and used GEP to define both CD8 abundance and associated geographic localization to tumor parenchyma and stroma. Methods: We performed an analysis using a tumor inflammatory GEP assay and CD8 immunohistochemistry on procured specimens (335 melanoma, 391 SCCHN). Digitized slides were used to train a convolutional neural network to quantify the number of CD8+ T cells in stroma, tumor parenchyma, parenchyma-stromal interface, and invasive margin. Generalized constrained regression models were used to predict GEP signatures specifically for stromal and parenchymal CD8+ T cells. Results: Parenchymal and stromal GEP scores were highly concordant with CD8+ infiltrate geography (adj- r2: 0.67, 0.65, respectively; P ≤ 0.01). Little overlap existed between gene sets associated with parenchymal and stromal CD8 T-cell geographies. CSF1R and NECTIN2 gene expression was observed to correlate inversely with parenchymal localization and directly with stromal CD8+ T-cell abundance. Conclusions: GEP signatures can be identified that are concordant with various CD8+ T-cell localization patterns in melanoma and SCCHN, demonstrating that GEP-IA can be developed to identify the immune status of interest in the TME. The specific genes identified have potential to elucidate mechanisms of resistance and/or inform I-O targets that can be further evaluated in relation to clinical significance in future studies.