A Lightweight Multi-Cancer Tumor Localization Framework for Deployable Digital Pathology

• URL: http://arxiv.org/abs/2603.08844v1
• Date: Mon, 09 Mar 2026 19:00:04 GMT
• Title: A Lightweight Multi-Cancer Tumor Localization Framework for Deployable Digital Pathology
• Abstract summary: Deep learning-based tumor detection trained within specific cancers may exhibit reduced robustness when applied across different tumor types.<n>A multi-cancer tumor localization model (MuCTaL) was trained on 79,984 non-overlapping tiles from four cancers.<n>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 ductal adenocarcinoma cohort.
• Score: 0.46843765915430247
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Dual-Modal Lung Cancer AI: Interpretable Radiology and Microscopy with Clinical Risk Integration [0.0]
  This study proposes a dual-modal artificial intelligence framework that integrates CT radiology with hematoxylin and eosin histopathology for lung cancer diagnosis and subtype classification.<n>The system employs convolutional neural networks to extract radiologic and histopathologic features and incorporates clinical metadata to improve robustness.<n> Experimental results show strong performance with accuracy up to 0.87, AUROC above 0.97, and macro F1-score of 0.88.
  arXiv  Detail & Related papers  (2026-04-17T14:37:54Z)
• Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks [59.37427210144734]
  We introduce R-Super, which trains AI to segment tumors that match descriptions in medical reports.<n>When trained on 101,654 reports, AI models achieved performance comparable to those trained on 723 masks.<n>R-Super enabled segmentation of tumors in the spleen, gallbladder, prostate, bladder, uterus, and esophagus.
  arXiv  Detail & Related papers  (2025-10-16T15:35:44Z)
• Generalisation of automatic tumour segmentation in histopathological whole-slide images across multiple cancer types [0.5986174494948199]
  The model was developed using over 20 000 whole-slide images from over 4 000 patients with colorectal, endometrial, lung, or prostate carcinoma.<n>No loss of performance was observed when comparing the universal model with models specialised on single cancer types.
  arXiv  Detail & Related papers  (2025-10-13T09:18:15Z)
• Boosting Pathology Foundation Models via Few-shot Prompt-tuning for Rare Cancer Subtyping [80.92960114162746]
  We propose PathPT, a novel framework that exploits the potential of vision-language pathology foundation models.<n>PathPT converts WSI-level supervision into fine-grained tile-level guidance by leveraging the zero-shot capabilities of VL models.<n>Results show that PathPT consistently delivers superior performance, achieving substantial gains in subtyping accuracy and cancerous region grounding ability.
  arXiv  Detail & Related papers  (2025-08-21T18:04:41Z)
• An ensemble deep learning approach to detect tumors on Mohs micrographic surgery slides [0.0]
  The objective of this study is to develop a deep learning model to detect basal cell carcinoma (BCC) and artifacts on Mohs slides.<n>We present an AI system that can detect tumors and non-tumors in Mohs slides with high success.
  arXiv  Detail & Related papers  (2025-04-07T16:05:42Z)
• Towards Generalizable Tumor Synthesis [48.45704270448412]
  Tumor synthesis enables the creation of artificial tumors in medical images, facilitating the training of AI models for tumor detection and segmentation. This paper made a progressive stride toward generalizable tumor synthesis by leveraging a critical observation. We have ascertained that generative AI models, e.g., Diffusion Models, can create realistic tumors generalized to a range of organs even when trained on a limited number of tumor examples from only one organ.
  arXiv  Detail & Related papers  (2024-02-29T18:57:39Z)
• CancerUniT: Towards a Single Unified Model for Effective Detection, Segmentation, and Diagnosis of Eight Major Cancers Using a Large Collection of CT Scans [45.83431075462771]
  Human readers or radiologists routinely perform full-body multi-organ multi-disease detection and diagnosis in clinical practice. Most medical AI systems are built to focus on single organs with a narrow list of a few diseases. CancerUniT is a query-based Mask Transformer model with the output of multi-tumor prediction.
  arXiv  Detail & Related papers  (2023-01-28T20:09:34Z)
• Deep learning-based approach to reveal tumor mutational burden status from whole slide images across multiple cancer types [41.61294299606317]
  Tumor mutational burden (TMB) is a potential genomic biomarker of immunotherapy. TMB detected through whole exome sequencing lacks clinical penetration in low-resource settings. In this study, we proposed a multi-scale deep learning framework to address the detection of TMB status from routinely used whole slide images.
  arXiv  Detail & Related papers  (2022-04-07T07:02:32Z)
• Pan-Tumor CAnine cuTaneous Cancer Histology (CATCH) Dataset [6.547056001246874]
  We present a publicly available dataset consisting of 350 whole slide images of seven different canine cutaneous tumors complemented by 12,424 polygon annotations for 13 histologic classes. Regarding sample size and annotation extent, this exceeds most publicly available datasets which are oftentimes limited to the tumor area or merely provide patch-level annotations.
  arXiv  Detail & Related papers  (2022-01-27T11:16:26Z)
• EMT-NET: Efficient multitask network for computer-aided diagnosis of breast cancer [58.720142291102135]
  We propose an efficient and light-weighted learning architecture to classify and segment breast tumors simultaneously. We incorporate a segmentation task into a tumor classification network, which makes the backbone network learn representations focused on tumor regions. The accuracy, sensitivity, and specificity of tumor classification is 88.6%, 94.1%, and 85.3%, respectively.
  arXiv  Detail & Related papers  (2022-01-13T05:24:40Z)
• Segmentation for Classification of Screening Pancreatic Neuroendocrine Tumors [72.65802386845002]
  This work presents comprehensive results to detect in the early stage the pancreatic neuroendocrine tumors (PNETs) in abdominal CT scans. To the best of our knowledge, this task has not been studied before as a computational task. Our approach outperforms state-of-the-art segmentation networks and achieves a sensitivity of $89.47%$ at a specificity of $81.08%$.
  arXiv  Detail & Related papers  (2020-04-04T21:21:44Z)
• Stan: Small tumor-aware network for breast ultrasound image segmentation [68.8204255655161]
  We propose a novel deep learning architecture called Small Tumor-Aware Network (STAN) to improve the performance of segmenting tumors with different size. The proposed approach outperformed the state-of-the-art approaches in segmenting small breast tumors.
  arXiv  Detail & Related papers  (2020-02-03T22:25:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.