Classification of mammograms: Comparing a graphical to a geometrical approach

Breast carcinoma is the second most common cause of cancer-related deaths. Radiologists often use mammography, a noninvasive and inexpensive imaging tool, for the detection and classification of breast cancer (BC) lesions. However, manual analysis is labor-intensive and prone to diagnostic errors. I...

Full description

Saved in:
Bibliographic Details
Main Authors: Anirban Ghosh, Priya Ranjan, Kumar Dron Shrivastav, Rajiv Janardhanan
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:EngMedicine
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2950489925000181
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849321352184463360
author Anirban Ghosh
Priya Ranjan
Kumar Dron Shrivastav
Rajiv Janardhanan
author_facet Anirban Ghosh
Priya Ranjan
Kumar Dron Shrivastav
Rajiv Janardhanan
author_sort Anirban Ghosh
collection DOAJ
description Breast carcinoma is the second most common cause of cancer-related deaths. Radiologists often use mammography, a noninvasive and inexpensive imaging tool, for the detection and classification of breast cancer (BC) lesions. However, manual analysis is labor-intensive and prone to diagnostic errors. In this scenario, the large-scale deployment of computer-aided diagnosis using well-trained algorithms could significantly reduce the morbidity and mortality associated with this carcinoma. In this study, we used a similarity metric-based classification of mammograms using graphical (with two different image sizes) and geometrical approaches (with a single image size) for comparison to improve the specificity, sensitivity, and accuracy of BC prediction and triage of patients in the order of disease severity. Both classification techniques use two novel algorithms, hereafter referred to as the normal and hybrid methods, to select representative images from the training sets of healthy and unhealthy groups of mammograms. The normal method identifies a representative image by comparing images within a cohort, whereas the hybrid method adopts a comprehensive approach by comparing images from both cohorts. This study explored the effects of image size and cardinality of the training set. Finally, we explored the uncharted territory of mapping accuracy versus computational expense for the different approaches adopted in the current study.
format Article
id doaj-art-9f6ecf502ee1494694045727e37b6049
institution Kabale University
issn 2950-4899
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series EngMedicine
spelling doaj-art-9f6ecf502ee1494694045727e37b60492025-08-20T03:49:46ZengElsevierEngMedicine2950-48992025-06-012210007210.1016/j.engmed.2025.100072Classification of mammograms: Comparing a graphical to a geometrical approachAnirban Ghosh0Priya Ranjan1Kumar Dron Shrivastav2Rajiv Janardhanan3Department of ECE, SRM University AP, Guntur, 522240, Andhra Pradesh, India; Corresponding author.Kabir Vishwavidyalaya, Dasiya, Basti, 272150, UP, India; Vidya Vihar Institute of Technology, BIADA Industrial Growth Centre, Maranga, Purnea, 854301, Bihar, IndiaPATH India, Barakhamba Road, 110001, New Delhi, IndiaDepartment of Medical Research, SRM Institute of Science and Technology, Kattankulathur, 603203, Tamil Nadu, IndiaBreast carcinoma is the second most common cause of cancer-related deaths. Radiologists often use mammography, a noninvasive and inexpensive imaging tool, for the detection and classification of breast cancer (BC) lesions. However, manual analysis is labor-intensive and prone to diagnostic errors. In this scenario, the large-scale deployment of computer-aided diagnosis using well-trained algorithms could significantly reduce the morbidity and mortality associated with this carcinoma. In this study, we used a similarity metric-based classification of mammograms using graphical (with two different image sizes) and geometrical approaches (with a single image size) for comparison to improve the specificity, sensitivity, and accuracy of BC prediction and triage of patients in the order of disease severity. Both classification techniques use two novel algorithms, hereafter referred to as the normal and hybrid methods, to select representative images from the training sets of healthy and unhealthy groups of mammograms. The normal method identifies a representative image by comparing images within a cohort, whereas the hybrid method adopts a comprehensive approach by comparing images from both cohorts. This study explored the effects of image size and cardinality of the training set. Finally, we explored the uncharted territory of mapping accuracy versus computational expense for the different approaches adopted in the current study.http://www.sciencedirect.com/science/article/pii/S2950489925000181MammogramEarth Mover's distanceHorizontal visibility graphHamming-Ipsen-Mikhailov
spellingShingle Anirban Ghosh
Priya Ranjan
Kumar Dron Shrivastav
Rajiv Janardhanan
Classification of mammograms: Comparing a graphical to a geometrical approach
EngMedicine
Mammogram
Earth Mover's distance
Horizontal visibility graph
Hamming-Ipsen-Mikhailov
title Classification of mammograms: Comparing a graphical to a geometrical approach
title_full Classification of mammograms: Comparing a graphical to a geometrical approach
title_fullStr Classification of mammograms: Comparing a graphical to a geometrical approach
title_full_unstemmed Classification of mammograms: Comparing a graphical to a geometrical approach
title_short Classification of mammograms: Comparing a graphical to a geometrical approach
title_sort classification of mammograms comparing a graphical to a geometrical approach
topic Mammogram
Earth Mover's distance
Horizontal visibility graph
Hamming-Ipsen-Mikhailov
url http://www.sciencedirect.com/science/article/pii/S2950489925000181
work_keys_str_mv AT anirbanghosh classificationofmammogramscomparingagraphicaltoageometricalapproach
AT priyaranjan classificationofmammogramscomparingagraphicaltoageometricalapproach
AT kumardronshrivastav classificationofmammogramscomparingagraphicaltoageometricalapproach
AT rajivjanardhanan classificationofmammogramscomparingagraphicaltoageometricalapproach