Deep Learning in Breast Calcifications Classification: Analysis of Cross-Database Knowledge Transferability

Adam Mračko, Ivan Cimrák, Lucia Vanovčanová, Lucia Vanovčanová, Viera Lehotská, Viera Lehotská

2024

Abstract

Study delves into the application of deep learning models for the classification of breast calcifications in mammography images. Initial objective was to investigate various convolutional neural network (CNN) architectures and their influence on model accuracy. ResNet101 emerged as the most effective architecture, although other models exhibited comparable performances. The insights gained were subsequently applied to the main goal, which focused on examining the transferability of knowledge between models trained on digitalized films (Curated Breast Imaging Subset of Digital Database for Screening Mammograph) and those trained on digital mammography images (Optimam Database). Results confirmed the lack of seamless transferability, prompting the creation of a combined dataset for training, significantly improving overall model accuracy to 76.2%. The study also scrutinized instances of incorrect predictions across different models, particularly those posing challenges even for medical professionals. Visualizations using Grad-Cam aided in understanding the models’ decision-making process.

Paper Citation

in Harvard Style

Mračko A., Cimrák I., Vanovčanová L. and Lehotská V. (2024). Deep Learning in Breast Calcifications Classification: Analysis of Cross-Database Knowledge Transferability. In Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOINFORMATICS; ISBN 978-989-758-688-0, SciTePress, pages 527-535. DOI: 10.5220/0012535200003657

in Bibtex Style

@conference{bioinformatics24,
author={Adam Mračko and Ivan Cimrák and Lucia Vanovčanová and Viera Lehotská},
title={Deep Learning in Breast Calcifications Classification: Analysis of Cross-Database Knowledge Transferability},
booktitle={Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOINFORMATICS},
year={2024},
pages={527-535},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012535200003657},
isbn={978-989-758-688-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOINFORMATICS
TI - Deep Learning in Breast Calcifications Classification: Analysis of Cross-Database Knowledge Transferability
SN - 978-989-758-688-0
AU - Mračko A.
AU - Cimrák I.
AU - Vanovčanová L.
AU - Lehotská V.
PY - 2024
SP - 527
EP - 535
DO - 10.5220/0012535200003657
PB - SciTePress