Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group.

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.

Artificial Intelligence-based Tumor Segmentation in Mouse Models of Lung Adenocarcinoma.

BACKGROUND: Mouse models are highly effective for studying the pathophysiology of lung adenocarcinoma and evaluating new treatment strategies. Treatment efficacy is primarily determined by the total tumor burden measured on excised tumor specimens. The measurement process is time-consuming and prone to human errors. To address this issue, we developed a novel deep learning model to segment lung tumor foci on digitally scanned hematoxylin and eosin (H&E) histology slides. METHODS: Digital slides of 239 mice from 9 experimental cohorts were split into training (n=137), validation (n=37), and testing cohorts (n=65). Image patches of 500×500 pixels were extracted from 5× and 10× magnifications, along with binary masks of expert annotations representing ground-truth tumor regions. Deep learning models utilizing DeepLabV3+ and UNet architectures were trained for binary segmentation of tumor foci under varying stain normalization conditions. The performance of algorithm segmentation was assessed by Dice Coefficient, and detection was evaluated by sensitivity and positive-predictive value (PPV). RESULTS: The best model on patch-based validation was DeepLabV3+ using a Resnet-50 backbone, which achieved Dice 0.890 and 0.873 on validation and testing cohort, respectively. This result corresponded to 91.3 Sensitivity and 51.0 PPV in the validation cohort and 93.7 Sensitivity and 51.4 PPV in the testing cohort. False positives could be reduced 10-fold with thresholding artificial intelligence (AI) predicted output by area, without negative impact on Dice Coefficient. Evaluation at various stain normalization strategies did not demonstrate improvement from the baseline model. CONCLUSIONS: A robust AI-based algorithm for detecting and segmenting lung tumor foci in the pre-clinical mouse models was developed. The output of this algorithm is compatible with open-source software that researchers commonly use.

PhyloPen: Phylogenetic Tree Browsing Using a Pen and Touch Interface.

Phylogenetic trees are used by researchers across multiple fields of study to display historical relationships between organisms or genes. Trees are used to examine the speciation process in evolutionary biology, to classify families of viruses in epidemiology, to demonstrate co-speciation in host and pathogen studies, and to explore genetic changes occurring during the disease process in cancer, among other applications. Due to their complexity and the amount of data they present in visual form, phylogenetic trees have generally been difficult to render for publication and challenging to directly interact with in digital form. To address these limitations, we developed PhyloPen, an experimental novel multi-touch and pen application that renders a phylogenetic tree and allows users to interactively navigate within the tree, examining nodes, branches, and auxiliary information, and annotate the tree for note-taking and collaboration. We present a discussion of the interactions implemented in PhyloPen and the results of a formative study that examines how the application was received after use by practicing biologists -- faculty members and graduate students in the discipline. These results are to be later used for a fully supported implementation of the software where the community will be welcomed to participate in its development.

Best practices for data sharing in phylogenetic research.

As phylogenetic data becomes increasingly available, along with associated data on species' genomes, traits, and geographic distributions, the need to ensure data availability and reuse become more and more acute. In this paper, we provide ten "simple rules" that we view as best practices for data sharing in phylogenetic research. These rules will help lead towards a future phylogenetics where data can easily be archived, shared, reused, and repurposed across a wide variety of projects.

Arbor: comparative analysis workflows for the tree of life.

We describe our efforts to develop a software package, Arbor, that will enable scientific research in all aspects of comparative biology. This software will enable developmental biologists, geneticists, ecologists, geographers, paleobiologists, educators, and students to analyze diverse types of comparative data at multiple phylogenetic and spatiotemporal scales using an intuitive visual interface. Arbor's user-defined workflows will be exported and shared so that entire analyses can be quickly replicated with new or updated data. Arbor will also be designed to easily and seamlessly expand to include novel analytical tools as they are developed. Here we describe the core components of Arbor, as well as provide details of one proposed test case to illustrate the software's key functionality.

IA-FEMesh: an open-source, interactive, multiblock approach to anatomic finite element model development.

Finite element (FE) analysis is a valuable tool in musculoskeletal research. The demands associated with mesh development, however, often prove daunting. In an effort to facilitate anatomic FE model development we have developed an open-source software toolkit (IA-FEMesh). IA-FEMesh employs a multiblock meshing scheme aimed at hexahedral mesh generation. An emphasis has been placed on making the tools interactive, in an effort to create a user friendly environment. The goal is to provide an efficient and reliable method for model development, visualization, and mesh quality evaluation. While these tools have been developed, initially, in the context of skeletal structures they can be applied to countless applications.