Automated Segmentation of Breast Cancer Focal Lesions on Ultrasound Images
Sensors · 2025
DOI: 10.3390/s25051593 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Dmitry Pasynkov und 7 weiteren Autor:innen. Beteiligte Einrichtung: Medical Institute, Department of Radiology and Oncology, Mari State University, Ministry of Education and Science of Russian Federation, 1 Lenin Squa…. Hauptthemen laut MEDLINE: Breast Neoplasms, Image Processing, Computer-Assisted, Ultrasonography, Mammary. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Russian Science Foundation, QU Health, Qatar University.
Abstract (Originalsprache)
Ultrasound (US) remains the main modality for the differential diagnosis of changes revealed by mammography. However, the US images themselves are subject to various types of noise and artifacts from reflections, which can worsen the quality of their analysis. Deep learning methods have a number of disadvantages, including the often insufficient substantiation of the model, and the complexity of collecting a representative training database. Therefore, it is necessary to develop effective algorithms for the segmentation, classification, and analysis of US images. The aim of the work is to develop a method for the automated detection of pathological lesions in breast US images and their segmentation. A method is proposed that includes two stages of video image processing: (1) searching for a region of interest using a random forest classifier, which classifies normal tissues, (2) selecting the contour of the lesion based on the difference in brightness of image pixels. The test set included 52 ultrasound videos which contained histologically proven suspicious lesions. The average frequency of lesion detection per frame was 91.89%, and the average accuracy of contour selection according to the IoU metric was 0.871. The proposed method can be used to segment a suspicious lesion.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Medical Institute, Department of Radiology and Oncology, Mari State University, Ministry of Education and Science of Russian Federation, 1 Lenin Square, Yoshkar-Ola 424000, Russia.
- Kazan State Medical Academy-Branch Campus of the Federal State Budgetary Educational Institution of Further Professional Education, Russian Medical Academy of Continuous Professional Education, Ministry of Healthcare of…
- Institute of Computational Mathematics and Information Technologies, Kazan Federal University, 18 Kremlevskaya St., Kazan 420008, Russia.
- Pediatric Faculty, Kazan Medical University, Ministry of Health of Russian Federation, 49 Butlerov St., Kazan 420012, Russia.
- Pharmaceutical Sciences Department, College of Pharmacy, QU Health, Qatar University, Doha 2713, Qatar.
ORCID-Profile: Dmitry Pasynkov, Ivan Egoshin, Alexey Kolchev, Ivan Kliouchkin, Olga Pasynkova, Zahraa Saad, Anis Daou, Esam Mohamed Abuzenar
Förderung
- Russian Science Foundation
- QU Health, Qatar University
Zitieren
APA
Pasynkov, D., Egoshin, I., Kolchev, A., Kliouchkin, I., Pasynkova, O., Saad, Z., Daou, A., & Abuzenar, E. M. (2025). Automated Segmentation of Breast Cancer Focal Lesions on Ultrasound Images. Sensors. https://doi.org/10.3390/s25051593
Vancouver
Pasynkov D, Egoshin I, Kolchev A, Kliouchkin I, Pasynkova O, Saad Z, et al. Automated Segmentation of Breast Cancer Focal Lesions on Ultrasound Images. Sensors. 2025. doi:10.3390/s25051593
BibTeX
@article{Pasynkov2025,
author = {Pasynkov, Dmitry and Egoshin, Ivan and Kolchev, Alexey and Kliouchkin, Ivan and Pasynkova, Olga and Saad, Zahraa and Daou, Anis and Abuzenar, Esam Mohamed},
title = {Automated Segmentation of Breast Cancer Focal Lesions on Ultrasound Images},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25051593}
}
EUVIMED