Skip to main content Skip to secondary navigation
View of the front of Stanford Campus

The Langlotz Lab

The Langlotz laboratory is focused on the development and application of machine learning and other innovative computational and analytical methods to accelerate disease detection and eliminate diagnostic errors.

Main content start
6 CXRs showing synthetic images depicting various pathology
Generative Models

Adapting Stable Diffusion to Create Realistic Clinical Images with Specific Pathologic Conditions

Knowledge graph extracted from a radiology report
Knowledge Graph Extraction

Extracting Clinical Entities and Relations to Form Knowledge Graphs from Radiology Reports

Image encoder and text encoder contrastive learning framework
Contrastive Pre-Training

Contrastive Learning of Medical Visual Representations from Paired Images and Text

Class activation maps
Computer Vision

Deep Learning to Assess Skeletal Maturity on Pediatric Hand Radiographs

Factual correctness reinforcement learning schematic
Clinical Text Summarization

Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports

Plot of synonym density vs synonym log rank
Terminology and Ontology

Expanding a radiology lexicon using contextual patterns in radiology reports

Foundational research flows
Research Policy

A Roadmap for Foundational Research on Artificial Intelligence in Medical Imaging: From the 2018 NIH/RSNA/ACR/The Academy Workshop

Table of ethics questions and responses
Data Sharing Ethics

Ethics of Using and Sharing Clinical Imaging Data for AI

The Radiology Report (Cover)
Radiology Reporting

The Radiology Report: A Guide to Thoughtful Communication for Radiologists and Other Medical Professionals