Publications

Our research integrates computer vision, deep learning, optimization, and natural language processing, with a primary application focus on digital and computational pathology. Contributions such as 2DMamba, Tissue2Vec, Vim4Path, ADPv2, and AdaFisher collectively drive forward transparent, efficient, and clinically relevant machine learning for pathology and medical imaging.

(See also the personal webpage of our group members)

 

List of Publications

Published

2025

  1. Illustration for PathTTT: Test-Time Training with Meta-auxiliary Learning for Pathology Image Classification
    PathTTT: Test-Time Training with Meta-auxiliary Learning for Pathology Image Classification
    Haoyu He, Mahdi S. Hosseini, Yang Wang
    Information Processing in Medical Imaging (IPMI 2025) – LNCS 15829 ·
    Link DOI
  2. Illustration for LBMamba: Locally Bi-directional Mamba
    LBMamba: Locally Bi-directional Mamba
    Jingwei Zhang, Xi Han, Hong Qin, Mahdi S. Hosseini, Dimitris Samaras
    Transactions on Machine Learning Research ·
    Link arXiv GitHub
  3. Illustration for Investigating Zero-Shot Diagnostic Pathology in Vision-Language Models with Efficient Prompt Design
    Investigating Zero-Shot Diagnostic Pathology in Vision-Language Models with Efficient Prompt Design
    Vineet Sharma, Ahmed Alagha, Hamza Khellaf, Vincent Quoc-Huy Trinh, Mahdi S. Hosseini
    6th International Conference on Deep Learning Theory and Applications (DeLTA 2025) ·
    Link arXiv DOI
  4. Illustration for Ultrasound Image Generation using Latent Diffusion Models
    Ultrasound Image Generation using Latent Diffusion Models
    Baptiste Freiche, Asma El-Khoury, Ali Nasiri-Sarvi, Mahdi S. Hosseini, Daniel Garcia, Adrian Basarab
    Medical Imaging 2025: Ultrasonic Imaging, Tomography (SPIE Vol. 13412) ·
    Link arXiv GitHub DOI
  5. Illustration for 2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification
    2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification
    Jingwei Zhang, Anh Tien Nguyen, Xi Han, Vincent Quoc-Huy Trinh, Hong Qin, Dimitris Samaras, Mahdi S. Hosseini
    Proceedings of the IEEE/CVF Conference on Computer Vision, Pattern Recognition (CVPR) 2025 ·
    Link arXiv GitHub DOI
  6. Illustration for Efficient Self-Supervised Barlow Twins from Limited Tissue Slide Cohorts for Colonic Pathology Diagnostics
    Efficient Self-Supervised Barlow Twins from Limited Tissue Slide Cohorts for Colonic Pathology Diagnostics
    Charles Notton, Varun Sharma, Vincent Quoc-Huy Trinh, Liang Chen, Ming Xu, Sonal Varma, Mahdi S. Hosseini
    Medical Image Analysis ·
    Link arXiv GitHub
  7. Illustration for Vision Mamba for Classification of Breast Ultrasound Images
    Vision Mamba for Classification of Breast Ultrasound Images
    Ali Nasiri-Sarvi, Mahdi S. Hosseini, Hassan Rivaz
    Deep Breast Workshop on AI, Imaging for Diagnostic, Treatment Challenges in Breast Care (LNCS 15451) ·
    Link arXiv GitHub DOI
  8. Illustration for AdaFisher: Adaptive Second Order Optimization via Fisher Information
    AdaFisher: Adaptive Second Order Optimization via Fisher Information
    Daniel Martins Gomes, Yiming Zhang, Evgenii Beliakov, Guillaume Wolf, Mahdi S. Hosseini
    International Conference on Learning Representations (ICLR) 2025 ·
    Link arXiv GitHub Poster

2024

  1. Illustration for Computational Pathology: A Survey Review, the Way Forward
    Computational Pathology: A Survey Review, the Way Forward
    Mahdi S. Hosseini, Babak Ehteshami Bejnordi, Vincent Quoc-Huy Trinh, Lyndon Chan, Danial Hasan, Xiang Li, Shuo Yang, others
    ["Journal of Pathology Informatics", "Vol. 15", "pp. "]100357
    Link arXiv GitHub DOI
  2. Illustration for Vim4Path: Self-Supervised Vision Mamba for Histopathology Images
    Vim4Path: Self-Supervised Vision Mamba for Histopathology Images
    Ali Nasiri-Sarvi, Vincent Quoc-Huy Trinh, Hassan Rivaz, Mahdi S. Hosseini
    Proceedings of the IEEE/CVF Conference on Computer Vision, Pattern Recognition (CVPR) 2024 ·
    Link arXiv GitHub DOI

Under Review / Under Revision

  1. Illustration for SPARC: Concept-Aligned Sparse Autoencoders for Cross-Model, Cross-Modal Interpretability
    SPARC: Concept-Aligned Sparse Autoencoders for Cross-Model, Cross-Modal Interpretability
    Ali Nasiri-Sarvi, Hassan Rivaz, Mahdi S. Hosseini
    arXiv:2507.06265 · · 2025
    arXiv GitHub
  2. Illustration for ADPv2: A Hierarchical Histological Tissue Type-Annotated Dataset for Potential Biomarker Discovery of Colorectal Disease
    ADPv2: A Hierarchical Histological Tissue Type-Annotated Dataset for Potential Biomarker Discovery of Colorectal Disease
    Zhiyuan Yang, Kai Li, Sophia Ghamoshi Ramandi, Patricia Brassard, Hakim Khellaf, Vincent Quoc-Huy Trinh, Jennifer Zhang, Lina Chen, Corwyn Rowsell, Sonal Varma, Konstantinos N. Plataniotis, Mahdi S. Hosseini
    arxiv:2507.05656 · · 2025
    Link arXiv
  3. Illustration for Comparative Analysis of Diffusion Generative Models in Computational Pathology
    Comparative Analysis of Diffusion Generative Models in Computational Pathology
    Denisha Thakkar, Vincent Quoc-Huy Trinh, Sonal Varma, Samira Ebrahimi Kahou, Hassan Rivaz, Mahdi S. Hosseini
    arXiv:2411.15719 · · 2024
    arXiv GitHub