Comparative analysis of deep learning methods for breast ultrasound lesion detection and classification

Breast ultrasound (BUS) computer-aided diagnosis (CAD) systems aims to perform two major steps: detecting lesions and classifying them as benign or malignant. However, the impact of combining both steps has not been previously addressed. Moreover, the specific method employed can influence the final...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Physica medica Jg. 134; S. 104993
Hauptverfasser: Vallez, Noelia, Mateos-Aparicio-Ruiz, Israel, Rienda, Miguel Angel, Deniz, Oscar, Bueno, Gloria
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Italy Elsevier Ltd 01.06.2025
Schlagworte:
Breast cancer
Breast Neoplasms - diagnostic imaging
CAD pipeline
Classification
Deep Learning
Detection
Diagnosis, Computer-Assisted - methods
Female
Humans
Image Processing, Computer-Assisted - methods
Segmentation
Ultrasonography, Mammary
Ultrasound
Breast cancer
Segmentation
Detection
Ultrasound
CAD pipeline
Classification
ISSN:1120-1797, 1724-191X, 1724-191X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Breast ultrasound (BUS) computer-aided diagnosis (CAD) systems aims to perform two major steps: detecting lesions and classifying them as benign or malignant. However, the impact of combining both steps has not been previously addressed. Moreover, the specific method employed can influence the final outcome of the system. In this work, a comparison of the effects of using object detection, semantic segmentation and instance segmentation to detect lesions in BUS images was conducted. To this end, four approaches were examined: a) multi-class object detection, b) one-class object detection followed by localized region classification, c) multi-class segmentation, and d) one-class segmentation followed by segmented region classification. Additionally, a novel dataset for BUS segmentation, called BUS-UCLM, has been gathered, annotated and shared publicly. The evaluation of the methods proposed was carried out with this new dataset and four publicly available datasets: BUSI, OASBUD, RODTOOK and UDIAT. Among the four approaches compared, multi-class detection and multi-class segmentation achieved the best results when instance segmentation CNNs are used. The best results in detection were obtained with a multi-class Mask R-CNN with a COCO AP50 metric of 72.9%. In the multi-class segmentation scenario, Poolformer achieved the best results with a Dice score of 77.7%. The analysis of detection and segmentation models in BUS highlights several key challenges, emphasizing the complexity of accurately identifying and segmenting lesions. Among the methods evaluated, instance segmentation has proven to be the most effective for BUS images, offering superior performance in delineating individual lesions. •The analysis of detection and segmentation models reveals key challenges in BUS.•Instance segmentation outperforms other methods in BUS images.•Normal tissue surrounding BUS lesions provides valuable information for diagnosis.•The introduction of the novel BUS-UCLM dataset will advance BUS research.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1120-1797
1724-191X
1724-191X
DOI:10.1016/j.ejmp.2025.104993