AMS-U-Net: automatic mass segmentation in digital breast tomosynthesis via U-Net
Journal of Medical Imaging · 23.03.2024 · 11 (02) · 1-18
DOI: 10.1117/1.jmi.11.2.024005 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Medical Imaging, erschienen am 23.03.2024. Verfasst von Ahmad Qasem und 2 weiteren Autor:innen. Beteiligte Einrichtung: University of Kansas Medical Center, The Reliable Intelligence and Medical Innovation Laboratory (RIMI Lab), Department of Biostatistics & Data Scien…. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIGMS NIH HHS.
Abstract (Originalsprache)
PurposeThe objective of this study was to develop a fully automatic mass segmentation method called AMS-U-Net for digital breast tomosynthesis (DBT), a popular breast cancer screening imaging modality. The aim was to address the challenges posed by the increasing number of slices in DBT, which leads to higher mass contouring workload and decreased treatment efficiency.ApproachThe study used 50 slices from different DBT volumes for evaluation. The AMS-U-Net approach consisted of four stages: image pre-processing, AMS-U-Net training, image segmentation, and post-processing. The model performance was evaluated by calculating the true positive ratio (TPR), false positive ratio (FPR), F-score, intersection over union (IoU), and 95% Hausdorff distance (pixels) as they are appropriate for datasets with class imbalance.ResultsThe model achieved 0.911, 0.003, 0.911, 0.900, 5.82 for TPR, FPR, F-score, IoU, and 95% Hausdorff distance, respectively.ConclusionsThe AMS-U-Net model demonstrated impressive visual and quantitative results, achieving high accuracy in mass segmentation without the need for human interaction. This capability has the potential to significantly increase clinical efficiency and workflow in DBT for breast cancer screening.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- University of Kansas Medical Center, The Reliable Intelligence and Medical Innovation Laboratory (RIMI Lab), Department of Biostatistics & Data Science, Kansas City, Kansas, United States.
- Nanfang Hospital, Southern Medical University, Department of Radiology, Guangzhou, China.
- University of Kansas Cancer Center, Kansas City, Kansas, United States.
ORCID-Profile: Zhiguo Zhou
Förderung
- NIGMS NIH HHS
Zitieren
APA
Qasem, A., Qin, G., & Zhou, Z. (2024). AMS-U-Net: automatic mass segmentation in digital breast tomosynthesis via U-Net. Journal of Medical Imaging, 11(02), 1-18. https://doi.org/10.1117/1.jmi.11.2.024005
Vancouver
Qasem A, Qin G, Zhou Z. AMS-U-Net: automatic mass segmentation in digital breast tomosynthesis via U-Net. Journal of Medical Imaging. 2024;11(02):1-18. doi:10.1117/1.jmi.11.2.024005
BibTeX
@article{Qasem2024,
author = {Qasem, Ahmad and Qin, Genggeng and Zhou, Zhiguo},
title = {AMS-U-Net: automatic mass segmentation in digital breast tomosynthesis via U-Net},
journal = {Journal of Medical Imaging},
year = {2024},
volume = {11},
number = {02},
pages = {1--18},
doi = {10.1117/1.jmi.11.2.024005}
}
EUVIMED