Enhancing Breast Cancer Diagnosis: Automated Segmentation and Detection with YOLOv8

Farag Alhsnony, Lamia Sellami

2024

Abstract

Breast cancer is a pervasive global health concern, demanding precise and timely diagnosis for effective treatment. In this research, we present an innovative approach to breast cancer segmentation using YOLOv8x-seg, a specialized variant of the YOLO (You Only Look Once) model optimized for semantic segmentation. The methodology commences with comprehensive data collection from the Curated Breast Imaging Subset of DDSM (CBIS-DDSM) dataset, which encompasses various breast conditions, and meticulous data annotation facilitated by Roboflow. The YOLOv8x-seg model is trained to achieve an F1-score of 95.27% and an IoU (Intersection over Union) of 89.51%. These metrics are indicative of the model’s ability to accurately identify and segment breast cancer anomalies within mammography images. The anticipated outcome is a model poised to significantly improve the efficiency and accuracy of breast cancer diagnosis, offering a valuable contribution to the field of medical image analysis.

Download


Paper Citation


in Harvard Style

Alhsnony F. and Sellami L. (2024). Enhancing Breast Cancer Diagnosis: Automated Segmentation and Detection with YOLOv8. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 665-672. DOI: 10.5220/0012382500003636


in Bibtex Style

@conference{icaart24,
author={Farag Alhsnony and Lamia Sellami},
title={Enhancing Breast Cancer Diagnosis: Automated Segmentation and Detection with YOLOv8},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={665-672},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012382500003636},
isbn={978-989-758-680-4},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Enhancing Breast Cancer Diagnosis: Automated Segmentation and Detection with YOLOv8
SN - 978-989-758-680-4
AU - Alhsnony F.
AU - Sellami L.
PY - 2024
SP - 665
EP - 672
DO - 10.5220/0012382500003636
PB - SciTePress