A Comparative Analysis of Image Descriptors for Histopathological Classification of Gastric Cancer

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Usai, Marco, Loddo, Andrea, Perniciano, Alessandra, Atzori, Maurizio, Di Ruberto, Cecilia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909547439849472
author Usai, Marco
Loddo, Andrea
Perniciano, Alessandra
Atzori, Maurizio
Di Ruberto, Cecilia
author_facet Usai, Marco
Loddo, Andrea
Perniciano, Alessandra
Atzori, Maurizio
Di Ruberto, Cecilia
contents Gastric cancer ranks as the fifth most common and fourth most lethal cancer globally, with a dismal 5-year survival rate of approximately 20%. Despite extensive research on its pathobiology, the prognostic predictability remains inadequate, compounded by pathologists' high workload and potential diagnostic errors. Thus, automated, accurate histopathological diagnosis tools are crucial. This study employs Machine Learning and Deep Learning techniques to classify histopathological images into healthy and cancerous categories. Using handcrafted and deep features with shallow learning classifiers on the GasHisSDB dataset, we offer a comparative analysis and insights into the most robust and high-performing combinations of features and classifiers for distinguishing between normal and abnormal histopathological images without fine-tuning strategies. With the RF classifier, our approach can reach F1 of 93.4%, demonstrating its validity.
format Preprint
id arxiv_https___arxiv_org_abs_2503_17105
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Comparative Analysis of Image Descriptors for Histopathological Classification of Gastric Cancer
Usai, Marco
Loddo, Andrea
Perniciano, Alessandra
Atzori, Maurizio
Di Ruberto, Cecilia
Image and Video Processing
Computer Vision and Pattern Recognition
Gastric cancer ranks as the fifth most common and fourth most lethal cancer globally, with a dismal 5-year survival rate of approximately 20%. Despite extensive research on its pathobiology, the prognostic predictability remains inadequate, compounded by pathologists' high workload and potential diagnostic errors. Thus, automated, accurate histopathological diagnosis tools are crucial. This study employs Machine Learning and Deep Learning techniques to classify histopathological images into healthy and cancerous categories. Using handcrafted and deep features with shallow learning classifiers on the GasHisSDB dataset, we offer a comparative analysis and insights into the most robust and high-performing combinations of features and classifiers for distinguishing between normal and abnormal histopathological images without fine-tuning strategies. With the RF classifier, our approach can reach F1 of 93.4%, demonstrating its validity.
title A Comparative Analysis of Image Descriptors for Histopathological Classification of Gastric Cancer
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.17105