Search bioRxiv⌕ Search

Biology subjects

DeLair, D.

Publications and source records attributed to DeLair, D..

2 recordsLinked to original sources
bioRxiv2020

MiMSI - a deep multiple instance learning framework improves microsatellite instability detection from tumor next-generation sequencing

Microsatellite instability (MSI) is a critical phenotype of cancer genomes and an FDA-recognized biomarker that can guide treatment with immune checkpoint inhibitors. Recent work has demonstrated that next-generation sequencing data can be used to identify samples with MSI-high phenotype. However, low tumor purity, as frequently observed in routine clinical samples, poses a challenge to the sensitivity of existing algorithms. To overcome this critical issue, we developed MiMSI, an MSI classifier based on deep neural networks and trained using a dataset that included low tumor purity MSI cases in a multiple instance learning framework. On a challenging yet representative set of cases, MiMSI showed higher sensitivity (0.940) and auROC (0.988) than MSISensor(sensitivity: 0.57; auROC: 0.911), an open-source software previously validated for clinical use at our institution using MSK-IMPACT large panel targeted NGS data.

bioinformatics↗
bioRxiv2020

Predicting Endometrial Cancer Subtypes and Molecular Features from Histopathology Images Using Multi-resolution Deep Learning Models

The determination of endometrial carcinoma histological subtypes, molecular subtypes, and mutation status is a critical diagnostic process that directly affects patients prognosis and treatment options. Compared to the histopathological approach, however, the availability of molecular subtyping is limited as it can only be accurately obtained by genomic sequencing, which may be cost prohibitive. Here, we implemented a customized multi-resolution deep convolutional neural network, Panoptes, that predicts not only the histological subtypes, but also molecular subtypes and 18 common gene mutations based on digitized H&E stained pathological images. The model achieved high accuracy and generalized well on independent datasets. Our results suggest that Panoptes has potential clinical application of helping pathologists determine molecular subtypes and mutations of endometrial carcinoma without sequencing. SignificanceRecently, molecular subtyping and mutation status are increasingly utilized in clinical practice as they offer better-informed prognosis and the possibility of individualized therapies for endometrial carcinoma patients. Taking advantage of the multi-resolution nature of the whole slide digital histopathology images, our Panoptes models integrate features of different magnification and make accurate predictions of histological subtypes, molecular subtypes, and key mutations in much faster workflows compared to conventional sequencing-based analyses. Feature extraction and visualization revealed that the model relied on human-interpretable patterns. Overall, our multi-resolution deep learning model is capable of assisting pathologists determine molecular subtypes of endometrial carcinoma, which can potentially accelerate diagnosis process.

bioinformatics↗