AI – Brigham and Women's Hospital, Division of

Nature Medicine Publications detail Mahmood Lab’s Design of AI Foundation Models to Advance Pathology

Posted on March 25, 2024April 12, 2024 by Tarissa Arnold Mages

Two foundation models for pathology AI developed by the Mahmood Lab published in Nature Medicine: UNI and CONCH.

Foundation models, advanced artificial intelligence systems trained on large-scale datasets, hold the potential to provide unprecedented advancements for the medical field. In computational pathology (CPath), these models may excel in diagnostic accuracy, prognostic insights, and predicting therapeutic responses.

These foundation models were adapted to over 30 clinical, diagnostic needs, including disease detection, disease diagnosis, organ transplant assessment, and rare disease analysis. The new models overcame limitations posed by current models, performing well not only for the clinical tasks the researchers tested but also showing promise for identifying new, rare and challenging diseases.

Jakob Nikolas Kather MD, Msc – “Deep Learning-based biomarkers for precision oncology”

Precision oncology requires complex biomarkers which are often based on molecular and genetic tests of tumor tissue. For many of these tests, universal implementation in clinical practice is limited. However, for virtually every cancer patient, tissue slides stained with hematoxylin and eosin (H&E) are available. Deep Learning can extract biomarkers for better treatment decisions from these images. This talk will summarize the state of the art of Deep Learning in oncology for precision oncology biomarkers. It will cover the technical foundations, emerging use cases and established applications which are available for clinical use already.

Prof. Dr. Jakob Nikolas Kather, MD, MSc
Else Kröner Professor for Clinical Artificial Intelligence
Technical University, Dresden

Professor Jakob Kather holds dual appointments in medicine and computer science at the Technical University (TU) Dresden, Germany, serves as a senior physician in medical oncology at the University Hospital Dresden and holds an additional affiliation with the National Center for Tumor Diseases (NCT) in Heidelberg. His research is focused on applying artificial intelligence in precision oncology. Prof. Kather’s research team at TU Dresden is using deep learning techniques to analyze a spectrum of clinical data, including histopathology, radiology images, textual records, and multimodal datasets. Guided by the belief that medical and tech expertise needs to be combined, medical researchers in his team learn computer programming and data analysis, while computer scientists are immersed in cancer biology and oncology. Prof. Kather chairs the “Working group on Artificial Intelligence” at the German Society of Hematology and Oncology (DGHO) and is a member of the pathology task force of the American Association for Cancer Research (AACR). His work is supported by numerous European and national grants, which enable the team to develop new deep learning methods for medical data analysis techniques and to apply them in precision oncology.

Hybrid Talk
In person: TBD
On Zoom

Time: TBD

Hosted by: Mahmood Lab

Cincinnati Children’s Artificial Intelligence Imaging Research Center

Faisal Mahmood at CCAIIRC, Cincinnati, Ohio

Harris H. Wang, PhD Columbia University-“Spatial metagenomics, culturomics, and engineering of human and environmental microbiomes”

BWH Computational Pathology Special Seminar

Harris H. Wang, PhD
Associate Professor of Systems Biology
Interim Chair, Department of Systems Biology, Columbia University

Microbes that colonize the gastrointestinal tract play important roles in host metabolism, immunity, and homeostasis. Microbes that live in soil are responsible for a variety of key decomposition and remediation activities in the biosphere. Better tools to study and alter these microbiomes are essential for unlocking their vast potential to improve human health and combat climate change. This talk will describe our recent efforts to develop next-generation tools to study and modify microbial communities. Specifically, I will discuss new advances in spatial metagenomics, AI-enabled culturomics, and precision microbiome editing to program different microbiomes with new traits. These capabilities provide a foundation to accelerate the development of microbiome-based products and therapies.

Research Links: http://wanglab.c2b2.columbia.edu/

Harris Wang is an Associate Professor of Systems Biology and serves as the Interim Chair of the Department of Systems Biology at Columbia University, Vagelos College of Physicians and Surgeons. He is also jointly appointed the Department of Pathology and Cell Biology. Dr. Wang received his B.S. degrees in Mathematics and Physics from MIT and his Ph.D. in Biophysics from Harvard University. His research group mainly develops enabling genomic technologies to characterize the mammalian gut microbiome and to engineer these microbes with the capacity to monitor and improve human health. Dr. Wang is an Investigator of the Burroughs Wellcome Fund and the recipient of numerous awards, including the Vilcek Prize for Creative Promise in Biomedical Science, Blavatnik National Award Finalist, NSF CAREER, Sloan Research Fellowship, and the Presidential Early Career Award for Scientists and Engineers (PECASE).

Date: Friday October 27, 2023
Time: 2:00-3:00pm ET
In Person: Wolf Conference Center, Hale BTM 02006B, 60 Fenwood Rd Boston 02115
Online: https://partners.zoom.us/j/89199829402
Meeting ID: 891 9982 9402

Algorithmic fairness in artificial intelligence for medicine and healthcare: Nature Biomedical Engineering

Posted on July 1, 2023October 30, 2023 by Tarissa Arnold Mages

In healthcare, the development and deployment of insufficiently fair systems of artificial intelligence (AI) can undermine the delivery of equitable care. Assessments of AI models stratified across subpopulations have revealed inequalities in how patients are diagnosed, treated and billed. In this Perspective, we outline fairness in machine learning through the lens of healthcare, and discuss how algorithmic biases (in data acquisition, genetic variation and intra-observer labelling variability, in particular) arise in clinical workflows and the resulting healthcare disparities. We also review emerging technology for mitigating biases via disentanglement, federated learning and model explainability, and their role in the development of AI-based software as a medical device.

Chen RJ, Wang JJ, Williamson DFK, Chen TY, Lipkova J, Lu MY, Sahai S, Mahmood F. Algorithmic fairness in artificial intelligence for medicine and healthcare. Nat Biomed Eng. 2023 06; 7(6):719-742. PMID: 37380750.