Supplemental Figure S4. Sample partitioning for training a MYOD1 mutation predictive model using K-fold cross-validation.

Supplemental Table S1. Whole slide image tissue segmentation statistics by an expert pathologist and probability prediction using a trained convolutional neural network. Supplemental Table S2. Clinical and molecular characteristics of FN-RMS samples used for training models for mutation prediction. Yellow boxes indicate genes included in defining the RAS pathway. Supplemental Table S3. Clinical information with COG risk stratification of FN-RMS samples used for training a prognostication predictive CNN.

Abstract Purpose: Rhabdomyosarcoma (RMS) is an aggressive soft-tissue sarcoma, which primarily occurs in children and young adults. We previously reported specific genomic alterations in RMS, which strongly correlated with survival; however, predicting these mutations or high-risk disease at diagnosis remains a significant challenge. In this study, we utilized convolutional neural networks (CNN) to learn histologic features associated with driver mutations and outcome using hematoxylin and eosin (H&E) images of RMS. Experimental Design: Digital whole slide H&E images were collected from clinically annotated diagnostic tumor samples from 321 patients with RMS enrolled in Children's Oncology Group (COG) trials (1998–2017). Patches were extracted and fed into deep learning CNNs to learn features associated with mutations and relative event-free survival risk. The performance of the trained models was evaluated against independent test sample data (n = 136) or holdout test data. Results: The trained CNN could accurately classify alveolar RMS, a high-risk subtype associated with PAX3/7-FOXO1 fusion genes, with an ROC of 0.85 on an independent test dataset. CNN models trained on mutationally-annotated samples identified tumors with RAS pathway with a ROC of 0.67, and high-risk mutations in MYOD1 or TP53 with a ROC of 0.97 and 0.63, respectively. Remarkably, CNN models were superior in predicting event-free and overall survival compared with current molecular-clinical risk stratification. Conclusions: This study demonstrates that high-risk features, including those associated with certain mutations, can be readily identified at diagnosis using deep learning. CNNs are a powerful tool for diagnostic and prognostic prediction of rhabdomyosarcoma, which will be tested in prospective COG clinical trials.

In this paper, we propose a multimodal brain tumor segmentation using a 3D ResUNet deep neural network architecture. Deep neural network has been applying in many domains, including computer vision, natural language processing, etc. It has also been used for semantic segmentation in medical imaging segmentation, including brain tumor segmentation. In this work, we utilize a 3D ResUNet to segment tumors in brain magnetic resonance image (MRI). Multimodal MRI is prevailing in brain tumor analysis due to providing rich tumor information. We apply the proposed method to theMultimodal Brain Tumor Segmentation Challenge (BraTS) 2021 validation dataset for tumor segmentation. The online evaluation of brain tumor segmentation using the proposed method offers the dice score coefficient (DSC) of 0.8196, 0.9195, and 0.8503 for enhancing tumor (ET), whole tumor (WT), and tumor core (TC), respectively.

Deep Neural Networks (DNNs) have successfully demonstrated superior overall performance in many image classification and recognition tasks on Hematoxylin and Eosin stain (H&E) histology images. Reported studies typically utilize high quality (20x or 40x) Whole Slide Images (WSIs) to deliver optimal performance. However, it remains uncertain how well DNNs can perform on lower quality Region of Interest (ROI) histology images in real-life scenarios. The NCI Patient Derived Models Repository (PDMR) database hosts a catalog of low magnification (4x) ROIs of tissue histology images across a total of 60 cancer models, providing an ideal test case for evaluating DNNs performance in real-life scenarios. Using five pre-trained models, we have benchmarked the NCI PDMR database ROIs on a selected set of popular DNN classifiers. Overall, on the binary carcinoma vs. sarcoma classification test, we have reached 89.57% accuracy on 4x ROIs using our downsizing models and 84.18% accuracy on 4x ROIs using our patch-based models. On the multi-class carcinoma classification test, we have reached 72.06% top-2 accuracy on 4x ROIs using our downsizing models and 78.07% top-2 accuracy on 4x ROIs using our patch-based models. Given that pathologist accuracies hover around 85% [26] [27], our models were comparable in performance. With such accuracies, we can utilize our DNNs to perform crucial tele-pathological tasks in underdeveloped countries and rural areas, enabling scientists to take a cell phone picture and feed that image into a battery powered small computer for rapid screenings on the field.

Abstract Background Tumor classification and feature quantification from H&E histology images are critical tasks for cancer diagnosis, cancer research, and treatment. However, both tasks involve tedious and time-consuming manual examination of histology images. We explored the usage of deep learning methods in segmentation and classification of histology images of cancer tissue for their potential in computer-aided tumor diagnosis and other clinical and research applications. Specifically, we evaluated performance of selected deep learning methods in stroma and glandular objects segmentation in tumor image data and tumor images classification. We automated these tasks to help facilitate downstream tumor image analysis, reduce the labor load of pathologists, and provide them with a second opinion on their analysis. Methods We modified a patch-based U-Net model and trained it to perform stroma detection and segmentation in cancer tissue. Then the semantic segmentation capabilities of the U-Net model were compared with that of a DeepLabV3+ model. We explored the possible use of transfer learning to train a patch-based model to classify cancer tissue images as carcinoma and sarcoma and to further classify them as carcinoma subtypes. Results In spite of the limited dataset available for the pilot study, we found that the DeepLabV3+ model performed biomedical image segmentation more effectively than U-Net when k-fold cross-validation was utilized, but U-Net still showed promise as an effective and efficient model when we used a customized validation approach. We believe that the DeepLabV3+ model can perform segmentation with even more accuracy if computation resource constraints are removed or if more data is used to augment the result. In terms of tumor classification, our selected models also consistently achieve test accuracies above 80%, with a model trained using transfer learning with VGG-16 network as the feature extractors, or convolutional base performing best. For multi-class tumor subtype classification, we also observed promising test accuracies from our models, and a customized post-processing method provided even higher prediction accuracy on test set images and this method can be further investigated. Conclusions This pilot exploratory study provided strong evidence for the powerful potentials of deep learning models for segmentation and classification of tumor image data.

The authors have withdrawn their manuscript while recent data-sharing permission questions are addressed. Therefore, the authors do not wish this work to be cited as a reference for the project. If you have any questions, please contact the corresponding author. ### Competing Interest Statement The authors have declared no competing interest.