Saved in:
Bibliographic Details
Main Authors: Isett, Brian, Dadey, Rebekah, Li, Aofei, Augustin, Ryan C., Smith, Kate, Singhi, Aatur D., Gu, Qiangqiang, Bao, Riyue
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.08844
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915848800698368
author Isett, Brian
Dadey, Rebekah
Li, Aofei
Augustin, Ryan C.
Smith, Kate
Singhi, Aatur D.
Gu, Qiangqiang
Bao, Riyue
author_facet Isett, Brian
Dadey, Rebekah
Li, Aofei
Augustin, Ryan C.
Smith, Kate
Singhi, Aatur D.
Gu, Qiangqiang
Bao, Riyue
contents Accurate localization of tumor regions from hematoxylin and eosin-stained whole-slide images is fundamental for translational research including spatial analysis, molecular profiling, and tissue architecture investigation. However, deep learning-based tumor detection trained within specific cancers may exhibit reduced robustness when applied across different tumor types. We investigated whether balanced training across cancers at modest scale can achieve high performance and generalize to unseen tumor types. A multi-cancer tumor localization model (MuCTaL) was trained on 79,984 non-overlapping tiles from four cancers (melanoma, hepatocellular carcinoma, colorectal cancer, and non-small cell lung cancer) using transfer learning with DenseNet169. The model achieved a tile-level ROC-AUC of 0.97 in validation data from the four training cancers, and 0.71 on an independent pancreatic ductal adenocarcinoma cohort. A scalable inference workflow was built to generate spatial tumor probability heatmaps compatible with existing digital pathology tools. Code and models are publicly available at https://github.com/AivaraX-AI/MuCTaL.
format Preprint
id arxiv_https___arxiv_org_abs_2603_08844
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Lightweight Multi-Cancer Tumor Localization Framework for Deployable Digital Pathology
Isett, Brian
Dadey, Rebekah
Li, Aofei
Augustin, Ryan C.
Smith, Kate
Singhi, Aatur D.
Gu, Qiangqiang
Bao, Riyue
Computer Vision and Pattern Recognition
Artificial Intelligence
Accurate localization of tumor regions from hematoxylin and eosin-stained whole-slide images is fundamental for translational research including spatial analysis, molecular profiling, and tissue architecture investigation. However, deep learning-based tumor detection trained within specific cancers may exhibit reduced robustness when applied across different tumor types. We investigated whether balanced training across cancers at modest scale can achieve high performance and generalize to unseen tumor types. A multi-cancer tumor localization model (MuCTaL) was trained on 79,984 non-overlapping tiles from four cancers (melanoma, hepatocellular carcinoma, colorectal cancer, and non-small cell lung cancer) using transfer learning with DenseNet169. The model achieved a tile-level ROC-AUC of 0.97 in validation data from the four training cancers, and 0.71 on an independent pancreatic ductal adenocarcinoma cohort. A scalable inference workflow was built to generate spatial tumor probability heatmaps compatible with existing digital pathology tools. Code and models are publicly available at https://github.com/AivaraX-AI/MuCTaL.
title A Lightweight Multi-Cancer Tumor Localization Framework for Deployable Digital Pathology
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.08844