Mahmood Lab
AI for Pathology Image Analysis

Mahmood Lab aims to utilize machine learning, data fusion, and medical image analysis to develop streamlined workflows for objective diagnosis, prognosis, and biomarker discovery. We are interested in developing automated and objective mechanisms for reducing interobserver and intraobserver variability in cancer diagnosis using artificial intelligence as an assistive tool for pathologists. The lab also focuses on the development of new algorithms and methods to identify clinically relevant morphologic phenotypes and biomarkers associated with response to specific therapeutic agents. We develop multimodal fusion algorithms for combining information from multiple imaging modalities, familial and patient histories and multi-omics data to make more precise diagnostic, prognostic and therapeutic determinations. We are affiliated with the Bioinformatics and Integrative Genomics (BIG) program at Harvard and the Cancer Data Science Program at the Dana-Farber Cancer Institute and the Broad Institute of Harvard and MIT.

Contact:
✉️faisalmahmood<at>bwh.harvard.edu
🏢8002-K, HBTM, 60 Fenwood Rd., Boston, MA 02115

Administrative Assistant
Martina Bragg, mbragg<at>bwh.harvard.edu, 617-525-8953

Recent Media Coverage

• Nvidia News: Under the Microscope: Top Pathology Lab Fuses Data Sources to Develop Cancer-Detecting AI
• Forbes: Transforming Federal Healthcare with AI
• Bioengineering Today: How to Train Your Radiology AI
• Auntminnie.com: Cinematic rendering bolsters AI for depth estimation on endoscopy
• JHU News: Johns Hopkins School of Medicine Excellence in Research Award

News

• Aug’20: Pathomic Fusion accepted to IEEE Transactions on Medical Imaging.
• Aug’20: Andrew Schaumberg and Muhammad Shaban joined the lab – welcome.
• June’20: New demo: TOAD, New code: TOAD.
• June’20: New preprint: Tumor Origin Prediction via Deep Learning. 
• April’20: New code release: CLAM.
• April’20: New preprint: CLAM, check our interactive demo here.
• April’20: Maha, Dehan, and John joined the lab – welcome.
• April’20: Upcoming invited talk at Virtual Pathology Grand Rounds (Hosted by UCSF).
• Feb’20: Upcoming invited talk at Nvidia GTC San Jose 2020.
• Feb’20: Jana, Sharifa, Matteo, Bowen, and MyeongSeo joined the lab – welcome.
• Feb’20: Mahmood lab presenting three oral talks at SPIE Medical Imaging.
• Feb’20: Upcoming nano-course on Deep Learning for Biomedical Image Analysis.
• Jan’20: Upcoming invited talk at the FDA on 01/15.
• Dec’19: New code release: Pathomic Fusion
• Dec’19: New pre-print: Pathomic Fusion (Deep Multimodal fusion for integrating histology and -omic data for diagnosis, prognosis).
• Dec’19: Article accepted IEEE Transactions on Medical Imaging.
• Nov’19: Mahmood Lab will be presenting four abstracts at USCAP 2020 in Los Angeles.
• Nov’19: Upcoming Invited Talk at CCDS Grand Rounds.
• Nov’19: Mahmood Lab featured in Nvidia News: Under the Microscope: Top Pathology Lab Fuses Data Sources to Develop Cancer-Detecting AI
• Nov’19: Mahmood lab will be presenting three posters at Discover Brigham 2019.
• Oct’19: New Pre-print GCNs for Prostate TMA classification (ISBI 2020 submission).
• Oct’19: New Pre-print MIL+CPC for semi-supervised histology classification (Accepted for presentation at NeurIPS ML4H 2019).
• Oct’19: Dr. Mahmood becomes an Associate Member of the Broad Institute of Harvard and MIT.
• Oct’19: Max Lu awarded the NeurIPS 2019 ML4H travel award – congratulations.
• Oct’19: Richard Chen awarded the NeurIPS 2019 ML4H travel award – congratulations.
• Oct’19: Mahmood Lab presenting three oral talks at SPIE Medical Imaging 2019 – Digital Pathology Conference in Houston.
• Oct’19: Two papers accepted at NeurIPS ML4H 2019. Pre-prints will be available soon. Visit us in Vancouver to learn more.
• Aug’19: Dr. Mahmood will be giving an invited talk at Nvidia GTC DC 2019.
• Aug’19: Mahmood Lab giving one oral and two poster presentations at Pathology Visions 2019 in Orlando.
• July’19: New pre-print: GANPOP: GAN-based Prediction of Optical Properties from Single Snapshot Wide-field Images (IEEE TMI Submission.)
• July’19: Dr. Mahmood becomes a full member of the cancer data sciences program at the Dana-Farber Cancer Institute / Harvard Cancer Center.
• July’19: Jingwen Wang, Research Intern joined the lab – welcome.
• July’19: Paper accepted at 2019 KDD Workshop on Applied Data Science for Healthcare.
• July’19: Dr. Mahmood becomes a member of the Harvard Bioinformatics and Integrative Genomics (BIG) faculty.
• June’19: Article accepted in IEEE Robotics and Automation Letters.
• June’19: Max Lu, Research Assistant joined the lab – welcome.
• June’19: Mahmood Lab welcomes its first member, Richard Chen, Harvard BIG PhD Student joined the lab.
• May’19: Article accepted in IEEE Transactions on Medical Imaging.
• April’19: Paper accepted in ICLR 2019 Workshop.
• April’19: Mahmood lab opens its doors, check out careers for postdoctoral fellowships.

———————————————————-

• Mar’19: Article accepted in Biomedical Optics Express.
• Dec’18: New Pre-Print: Diffuser Wavefront Sensor
• Nov’18: New Pre-Print: Multimodal DenseNet
• Oct’18: New Pre-Print: Deep LSR
• Oct’18: New Pre-Print: Nuclei Segmentation in Histopathology Data.
• Oct’18: 3 oral and 2 poster presentations accepted at SPIE Medical Imaging.
• Oct’18: 2 oral and 2 poster presentations accepted at SPIE Photonics West.
• Oct’18: Invited talk at Nvidia GTC DC 2018.
• Sept’18: Invited talk at SAS Deep Learning Symposium.
• Aug’18: Article accepted in Physics in Medicine and Biology.
• July’18: Article accepted in Medical Image Analysis.
• March’18: Article accepted in IEEE Transactions on Medical Imaging.
• March’18: Poster presented at Nvidia GTC 2018.
• March’18: Poster presented at SPIE Medical Imaging 2018.
• Feb’18: Article accepted in IEEE International Symposium in Biomedical Imaging (ISBI).
• Jan’18: Oral talk presented at SPIE Photonics West 2018.
• Jan’18: Article accepted in IEEE Signal Processing Letters.
• July’18: Article accepted in IEEE Access.
• June 2017: Article accepted in International Journal of Reconfigurable Computing.