J. Levy

Wearable facemask-attached disposable printed sensor arrays for point-of-need monitoring of ammonia in breath

This paper introduces a wearable sensor for measuring exhaled ammonia to detect kidney dysfunction, validated in lab and human trials.

DeltaAI: Semi-Autonomous Tissue Grossing Measurements and Recommendations using Neural Radiance Fields for Rapid, Complete Intraoperative Histological Assessment of Tumor Margins

DeltaAI uses Neural Radiance Fields to create 3D tissue models for faster and more accurate intraoperative tumor margin assessment in Mohs Micrographic Surgery.

Potential to Enhance Large Scale Molecular Assessments of Skin Photoaging through Virtual Inference of Spatial Transcriptomics from Routine Staining

This paper develops machine learning models to infer spatial transcriptomics data from H&E-stained skin slides, improving the assessment of photoaging and its therapeutic implications.

Spatial Omics Driven Crossmodal Pretraining Applied to Graph-based Deep Learning for Cancer Pathology Analysis

This paper applies spatial transcriptomics data with contrastive crossmodal pretraining to improve graph-based deep learning models for cancer histopathology analysis.

Inferring Spatially Resolved Transcriptomics Data from Whole Slide Images for the Assessment of Colorectal Tumor Metastasis: A Feasibility Study

This study investigates using deep learning to predict spatial transcriptomics data from whole slide images to assess colorectal tumor metastasis, finding that convolutional networks outperform transformer and graph-based models.

Assessment of Emerging Pretraining Strategies in Interpretable Multimodal Deep Learning for Cancer Prognostication

This study evaluates pretraining strategies in an interpretable multimodal deep learning framework for cancer prognosis, showing that pretraining improves performance over standard methods.

Graph neural networks ameliorate potential impacts of imprecise large-scale autonomous immunofluorescence labeling of immune cells on whole slide images

This study uses graph neural networks to improve TIL classification on whole slide images by leveraging contextual features from immunofluorescence labeling.

Mapping the landscape of genetic dependencies in chordoma

This study identifies essential genes in chordoma using CRISPR screens, revealing new therapeutic targets like PTPN11 and confirming known dependencies such as TBXT.

Uncovering Additional Predictors of Urothelial Carcinoma from Voided Urothelial Cell Clusters Through a Deep Learning Based Image Preprocessing Technique

This paper develops a deep learning-based preprocessing tool to analyze urothelial cell clusters in urine cytology, identifying key markers of atypia that could improve machine learning applications in bladder cancer detection.

Development of Biologically Interpretable Multimodal Deep Learning Model for Cancer Prognosis Prediction

This paper develops a multimodal deep learning model for cancer prognosis that integrates gene expression, DNA methylation, histopathological imaging, and clinical data, showing improved performance over unimodal approaches.

Improving the Virtual Trichrome Assessment through Bridge Category Models

This paper assesses Virtual Trichrome technologies using Bridge Category Models to account for bridge ratings in Fibrosis staging of NASH tissue.

Estimating the Inter- and Intra-Rater Reliability for NASH Fibrosis Staging in the Presence of Bridge Ordinal Ratings with Hierarchical Bridge Category Models

This paper develops hierarchical Bayesian models to assess inter- and intra-rater reliability for NASH fibrosis staging, showing improved precision over ad hoc methods.

Bridge Category Models: Development of Bayesian Modelling Procedures to Account for Bridge Ordinal Ratings for Disease Staging

The paper develops Bayesian models to handle bridge ordinal ratings in disease staging and shows they reduce bias and precision loss in models.

Mixed Effects Machine Learning Models for Colon Cancer Metastasis Prediction using Spatially Localized Immuno-Oncology Markers

This study uses mixed-effects machine learning to predict colon cancer metastasis by analyzing spatially localized immuno-oncology markers in tumor tissue.

Topological Feature Extraction and Visualization of Whole Slide Images using Graph Neural Networks

The paper introduces a framework combining graph neural networks and topological data analysis to extract and visualize features from whole-slide images, demonstrating its application in colon cancer staging.

A Large-Scale Internal Validation Study of Unsupervised Virtual Trichrome Staining Technologies on Non-alcoholic Steatohepatitis Liver Biopsies

This study validates the use of GANs for virtual trichrome staining of NASH liver biopsies, showing high correlation with real stains and clinical outcomes.

A pilot study of the effects of Mycoplasma ovipneumoniae exposure on domestic lamb growth and performance

This study examines the impact of Mycoplasma ovipneumoniae exposure on lamb growth and performance, finding reduced daily gains and carcass quality in exposed lambs.