Lab profile
About CPHAI
CPHAI is an interdisciplinary research center dedicated to advancing precision health by personalizing healthcare strategies to optimize patient care. The center leverages artificial intelligence and machine learning to analyze complex biomedical data for individual risk assessment, treatment determination, and real-time clinical decision-making while ensuring ethical and equitable use of these technologies.
Machine LearningBiomedical InformaticsDigital PathologyMedical ImagingRadiology InformaticsMultiomics InformaticsNatural Language ProcessingBiomedical Engineering
01 · Research focus
Research areas and highlights
Topics and recent work as stated on the lab’s own site.
- OncoDHNet: A Multi-Model AI for Breast Cancer Recurrence Risk PredictionA multi-model AI approach integrating whole-slide imaging with clinicopathologic data to classify breast cancer patients into high- and low-risk groups as a cost-effective alternative to genomic assays.
- IvRA FrameworkA framework for training language models with enhanced interpretability by regularizing attention distributions to produce explanations that meet critical interpretability criteria.
- MENTALMANIP DatasetA dataset with 4,000 annotated dialogues aimed at studying mental manipulation in conversations to improve mental health interventions.
- MaskHIT: A Foundational Model for Pathology Image AnalysisA foundational model trained on over 7,000 whole-slide images that excels in identifying critical histological patterns for survival predictions and cancer classification.
- EndoNet ModelAn AI model that enables endometrial cancer grading without labor-intensive manual annotation by pathologists using convolutional neural networks and vision transformers.
- Proto-LMA tool that improves the understandability of large language models without compromising performance by enhancing how these models are fine-tuned.
02 · People
Leadership and researchers
People listed on the lab’s team pages, by role.
Saeed HassanpourDirector · PhD (Biomedical Data Science, Machine Learning & Biomedical Informatics)LinkedIn ↗
Margaret AckermanCo-Director · PhD (Thayer, Bio. & Chem. Engineering)
Ryan HalterCo-Director · PhD (Thayer, Biomedical Engineering)
Sarah Masud PreumCo-Director · PhD (CS, Machine Learning & Informatics)LinkedIn ↗
Parth ShahCo-Director · MD (Pathology, Multiomics Informatics)
Jessica SinCo-Director · MD, PhD (Radiology, Radiology Informatics)
Louis VaickusCo-Director · MD, PhD (Pathology, Digital Pathology)
Soroush VosoughiCo-Director · PhD (CS, Machine Learning)
Indrani BhattacharyaPhD (Biomedical Data Science, Assistant Professor)
03 · Research intelligence
Research Intelligence evidence
Publications, grants and clinical trials linked to the lab’s researchers in Health AI Central’s research data.
Publications & preprints
- Multimodal AI Methods for Predicting Pathologic Complete Response in Breast Cancer.Journal of imaging informatics in medicine · 2026
- An Explanatory Deep Learning Pipeline for the Prediction and Visualization of Spatially Resolved Biomarker Expression in Triple-Negative Breast Cancer.The American journal of pathology · 2026
- Contrastive multimodal deep learning for survival prediction in grade 2/3 gliomas.JNCI cancer spectrum · 2026
Active NIH grants
- Center for Quantitative Biology: A focus on "omics", from organisms to single cellsMichael Whitfield · NIGMS · FY 2026
- Advancing Digital Pathology through Novel Machine Learning MethodologiesSaeed Hassanpour · NLM · FY 2026
- Intraoperative stereo imaging for oral specimen orientation and margin visualizationRyan Halter · NIDCR · FY 2025
04 · Updates
Updates and lab news
News and events from the lab’s own site.
- OncoDHNet: A Multi-Model AI for Breast Cancer Recurrence Risk PredictionPublicationDec 13, 2024 · nature.com
- Enhancing Language Model Explanations with Interpretability: The IvRA FrameworkPublicationNov 18, 2024 · aclanthology.org
- Dr. Indrani Bhattacharya: A New Addition to CPHAI to Spearhead AI Innovations in HealthcareAnnouncementNov 1, 2024 · sites.dartmouth.edu
- The Cure Podcast: The Future of AI in HealthcareNewsOct 31, 2024
- Challenges for AI: Detecting Manipulative Language in ConversationsPublicationOct 13, 2024 · web.cs.dartmouth.edu
- AI Advancement in Endometrial Cancer: The EndoNet ModelPublicationSep 22, 2024
- Introducing MENTALMANIP: A Dataset for Understanding Conversational ManipulationPublicationSep 12, 2024 · aclanthology.org
- Introducing MaskHIT: A Foundational Model for Pathology Image AnalysisPublicationSep 2, 2024
05 · Official presence
Lab sources and channels
The lab’s own pages and accounts.
06 · Related
Related labs and centers
Labs at the same institution and labs working on similar topics.