Detection of Cancer-Associated Nuclei in Histopathology Images Using Deep Convolutional Neural Networks

Read full text Summarise with VIRAT
Authors: Afya Shaikh
Cited by: 0
References: 5

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This paper presents a deep-learning pipeline for detecting nuclei-positive regions in hematoxylin and eosin (H&E) histopathology images. The study uses the public CryoNuSeg segmentation dataset, distributed through Kaggle, which contains 30 frozen tissue sections from ten human organs together with more than 8,000 manually annotated nuclei. Images were normalized, divided into smaller patches, and paired with binary masks so that the model learned a pixel-wise segmentation task rather than a slide-level diagnosis task. On the held-out evaluation set, the final model reached 0.91 pixel accuracy, with class-wise precision and recall of 0.96 and 0.92 for background pixels and 0.73 and 0.86 for nuclei pixels. The corresponding macro F1-score was 0.87, the weighted F1-score was 0.91, and the ROC–AUC score was 0.95. Qualitative comparisons showed that predicted masks tracked the overall location and shape of many nuclei-rich regions, although false positives remained in crowded or weak-contrast tissue. The results suggest that a compact convolutional neural network can provide a useful nuclei-segmentation baseline on public histopathology data and can serve as a starting point for more rigorous computational pathology work.

Fields of Study & Subjects

AI in cancer detection Cell Image Analysis Techniques Digital Imaging for Blood Diseases

Publication details

Journal / source
SSRN Electronic Journal
Publication date
1 January 2026
Language
EN
Document type
Preprint