Prediction models for hormone receptor status in female breast cancer do not extend to males: further evidence of sex-based disparity in breast cancer.

Breast cancer prognosis and management for both men and women are reliant upon estrogen receptor alpha (ERα) and progesterone receptor (PR) expression to inform therapy. Previous studies have shown that there are sex-specific binding characteristics of ERα and PR in breast cancer and, counterintuitively, ERα expression is more common in male than female breast cancer. We hypothesized that these differences could have morphological manifestations that are undetectable to human observers but could be elucidated computationally. To investigate this, we trained attention-based multiple instance learning prediction models for ERα and PR using H&E-stained images of female breast cancer from the Cancer Genome Atlas (TCGA) (n = 1085) and deployed them on external female (n = 192) and male breast cancer images (n = 245). Both targets were predicted in the internal (AUROC for ERα prediction: 0.86 ± 0.02, p < 0.001; AUROC for PR prediction = 0.76 ± 0.03, p < 0.001) and external female cohorts (AUROC for ERα prediction: 0.78 ± 0.03, p < 0.001; AUROC for PR prediction = 0.80 ± 0.04, p < 0.001) but not the male cohort (AUROC for ERα prediction: 0.66 ± 0.14, p = 0.43; AUROC for PR prediction = 0.63 ± 0.04, p = 0.05). This suggests that subtle morphological differences invisible upon visual inspection may exist between the sexes, supporting previous immunohistochemical, genomic, and transcriptomic analyses.

Direct prediction of Homologous Recombination Deficiency from routine histology in ten different tumor types with attention-based Multiple Instance Learning: a development and validation study.

Background: Homologous Recombination Deficiency (HRD) is a pan-cancer predictive biomarker that identifies patients who benefit from therapy with PARP inhibitors (PARPi). However, testing for HRD is highly complex. Here, we investigated whether Deep Learning can predict HRD status solely based on routine Hematoxylin & Eosin (H&E) histology images in ten cancer types. Methods: We developed a fully automated deep learning pipeline with attention-weighted multiple instance learning (attMIL) to predict HRD status from histology images. A combined genomic scar HRD score, which integrated loss of heterozygosity (LOH), telomeric allelic imbalance (TAI) and large-scale state transitions (LST) was calculated from whole genome sequencing data for n=4,565 patients from two independent cohorts. The primary statistical endpoint was the Area Under the Receiver Operating Characteristic curve (AUROC) for the prediction of genomic scar HRD with a clinically used cutoff value. Results: We found that HRD status is predictable in tumors of the endometrium, pancreas and lung, reaching cross-validated AUROCs of 0.79, 0.58 and 0.66. Predictions generalized well to an external cohort with AUROCs of 0.93, 0.81 and 0.73 respectively. Additionally, an HRD classifier trained on breast cancer yielded an AUROC of 0.78 in internal validation and was able to predict HRD in endometrial, prostate and pancreatic cancer with AUROCs of 0.87, 0.84 and 0.67 indicating a shared HRD-like phenotype is across tumor entities. Conclusion: In this study, we show that HRD is directly predictable from H&E slides using attMIL within and across ten different tumor types.

Benchmarking weakly-supervised deep learning pipelines for whole slide classification in computational pathology.

Artificial intelligence (AI) can extract visual information from histopathological slides and yield biological insight and clinical biomarkers. Whole slide images are cut into thousands of tiles and classification problems are often weakly-supervised: the ground truth is only known for the slide, not for every single tile. In classical weakly-supervised analysis pipelines, all tiles inherit the slide label while in multiple-instance learning (MIL), only bags of tiles inherit the label. However, it is still unclear how these widely used but markedly different approaches perform relative to each other. We implemented and systematically compared six methods in six clinically relevant end-to-end prediction tasks using data from N=2980 patients for training with rigorous external validation. We tested three classical weakly-supervised approaches with convolutional neural networks and vision transformers (ViT) and three MIL-based approaches with and without an additional attention module. Our results empirically demonstrate that histological tumor subtyping of renal cell carcinoma is an easy task in which all approaches achieve an area under the receiver operating curve (AUROC) of above 0.9. In contrast, we report significant performance differences for clinically relevant tasks of mutation prediction in colorectal, gastric, and bladder cancer. In these mutation prediction tasks, classical weakly-supervised workflows outperformed MIL-based weakly-supervised methods for mutation prediction, which is surprising given their simplicity. This shows that new end-to-end image analysis pipelines in computational pathology should be compared to classical weakly-supervised methods. Also, these findings motivate the development of new methods which combine the elegant assumptions of MIL with the empirically observed higher performance of classical weakly-supervised approaches. We make all source codes publicly available at https://github.com/KatherLab/HIA, allowing easy application of all methods to any similar task.

Classical mathematical models for prediction of response to chemotherapy and immunotherapy.

Classical mathematical models of tumor growth have shaped our understanding of cancer and have broad practical implications for treatment scheduling and dosage. However, even the simplest textbook models have been barely validated in real world-data of human patients. In this study, we fitted a range of differential equation models to tumor volume measurements of patients undergoing chemotherapy or cancer immunotherapy for solid tumors. We used a large dataset of 1472 patients with three or more measurements per target lesion, of which 652 patients had six or more data points. We show that the early treatment response shows only moderate correlation with the final treatment response, demonstrating the need for nuanced models. We then perform a head-to-head comparison of six classical models which are widely used in the field: the Exponential, Logistic, Classic Bertalanffy, General Bertalanffy, Classic Gompertz and General Gompertz model. Several models provide a good fit to tumor volume measurements, with the Gompertz model providing the best balance between goodness of fit and number of parameters. Similarly, when fitting to early treatment data, the general Bertalanffy and Gompertz models yield the lowest mean absolute error to forecasted data, indicating that these models could potentially be effective at predicting treatment outcome. In summary, we provide a quantitative benchmark for classical textbook models and state-of-the art models of human tumor growth. We publicly release an anonymized version of our original data, providing the first benchmark set of human tumor growth data for evaluation of mathematical models.

Artificial Intelligence-based Detection of FGFR3 Mutational Status Directly from Routine Histology in Bladder Cancer: A Possible Preselection for Molecular Testing?

BACKGROUND: Fibroblast growth factor receptor (FGFR) inhibitor treatment has become the first clinically approved targeted therapy in bladder cancer. However, it requires previous molecular testing of each patient, which is costly and not ubiquitously available. OBJECTIVE: To determine whether an artificial intelligence system is able to predict mutations of the FGFR3 gene directly from routine histology slides of bladder cancer. DESIGN, SETTING, AND PARTICIPANTS: We trained a deep learning network to detect FGFR3 mutations on digitized slides of muscle-invasive bladder cancers stained with hematoxylin and eosin from the Cancer Genome Atlas (TCGA) cohort (n = 327) and validated the algorithm on the "Aachen" cohort (n = 182; n = 121 pT2-4, n = 34 stroma-invasive pT1, and n = 27 noninvasive pTa tumors). OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: The primary endpoint was the area under the receiver operating curve (AUROC) for mutation detection. Performance of the deep learning system was compared with visual scoring by an uropathologist. RESULTS AND LIMITATIONS: In the TCGA cohort, FGFR3 mutations were detected with an AUROC of 0.701 (p < 0.0001). In the Aachen cohort, FGFR3 mutants were found with an AUROC of 0.725 (p < 0.0001). When trained on TCGA, the network generalized to the Aachen cohort, and detected FGFR3 mutants with an AUROC of 0.625 (p = 0.0112). A subgroup analysis and histological evaluation found highest accuracy in papillary growth, luminal gene expression subtypes, females, and American Joint Committee on Cancer (AJCC) stage II tumors. In a head-to-head comparison, the deep learning system outperformed the uropathologist in detecting FGFR3 mutants. CONCLUSIONS: Our computer-based artificial intelligence system was able to detect genetic alterations of the FGFR3 gene of bladder cancer patients directly from histological slides. In the future, this system could be used to preselect patients for further molecular testing. However, analyses of larger, multicenter, muscle-invasive bladder cancer cohorts are now needed in order to validate and extend our findings. PATIENT SUMMARY: In this report, a computer-based artificial intelligence (AI) system was applied to histological slides to predict genetic alterations of the FGFR3 gene in bladder cancer. We found that the AI system was able to find the alteration with high accuracy. In the future, this system could be used to preselect patients for further molecular testing.

Predicting Mutational Status of Driver and Suppressor Genes Directly from Histopathology With Deep Learning: A Systematic Study Across 23 Solid Tumor Types.

In the last four years, advances in Deep Learning technology have enabled the inference of selected mutational alterations directly from routine histopathology slides. In particular, recent studies have shown that genetic changes in clinically relevant driver genes are reflected in the histological phenotype of solid tumors and can be inferred by analysing routine Haematoxylin and Eosin (H&E) stained tissue sections with Deep Learning. However, these studies mostly focused on selected individual genes in selected tumor types. In addition, genetic changes in solid tumors primarily act by changing signaling pathways that regulate cell behaviour. In this study, we hypothesized that Deep Learning networks can be trained to directly predict alterations of genes and pathways across a spectrum of solid tumors. We manually outlined tumor tissue in H&E-stained tissue sections from 7,829 patients with 23 different tumor types from The Cancer Genome Atlas. We then trained convolutional neural networks in an end-to-end way to detect alterations in the most clinically relevant pathways or genes, directly from histology images. Using this automatic approach, we found that alterations in 12 out of 14 clinically relevant pathways and numerous single gene alterations appear to be detectable in tissue sections, many of which have not been reported before. Interestingly, we show that the prediction performance for single gene alterations is better than that for pathway alterations. Collectively, these data demonstrate the predictability of genetic alterations directly from routine cancer histology images and show that individual genes leave a stronger morphological signature than genetic pathways.