papers

Publications (25)

cs.CV2018

Leveraging Unlabeled Whole-Slide-Images for Mitosis Detection

Saad Ullah Akram, Talha Qaiser, Simon Graham +3

Mitosis count is an important biomarker for prognosis of various cancers. At present, pathologists typically perform manual counting on a few selected regions of interest in breast…

eess.IV2022

TIAger: Tumor-Infiltrating Lymphocyte Scoring in Breast Cancer for the TiGER Challenge

Adam Shephard, Mostafa Jahanifar, Ruoyu Wang +6

The quantification of tumor-infiltrating lymphocytes (TILs) has been shown to be an independent predictor for prognosis of breast cancer patients. Typically, pathologists give an e…

cs.CV2021

Lizard: A Large-Scale Dataset for Colonic Nuclear Instance Segmentation and Classification

Simon Graham, Mostafa Jahanifar, Ayesha Azam +14

The development of deep segmentation models for computational pathology (CPath) can help foster the investigation of interpretable morphological biomarkers. Yet, there is a major b…

q-bio.QM2024

HoverFast: an accurate, high-throughput, clinically deployable nuclear segmentation tool for brightfield digital pathology images

Petros Liakopoulos, Julien Massonnet, Jonatan Bonjour +7

In computational digital pathology, accurate nuclear segmentation of Hematoxylin and Eosin (H&E) stained whole slide images (WSIs) is a critical step for many analyses and tissue c…

cs.CV2018

Methods for Segmentation and Classification of Digital Microscopy Tissue Images

Quoc Dang Vu, Simon Graham, Minh Nguyen Nhat To +11

High-resolution microscopy images of tissue specimens provide detailed information about the morphology of normal and diseased tissue. Image analysis of tissue morphology can help…

eess.IV2022

One Model is All You Need: Multi-Task Learning Enables Simultaneous Histology Image Segmentation and Classification

Simon Graham, Quoc Dang Vu, Mostafa Jahanifar +4

The recent surge in performance for image analysis of digitised pathology slides can largely be attributed to the advances in deep learning. Deep models can be used to initially lo…