Comparative analysis of deep learning methods for breast ultrasound lesion detection and classification.
Authors
Affiliations (3)
Affiliations (3)
- VISILAB, University of Castilla-La Mancha, E.T.S. Ingenieria Industrial, Avda. Camilo Jose Cela s/n, 13071 Ciudad Real, Spain. Electronic address: [email protected].
- VISILAB, University of Castilla-La Mancha, E.T.S. Ingenieria Industrial, Avda. Camilo Jose Cela s/n, 13071 Ciudad Real, Spain.
- Hospital General Universitario de Ciudad Real, C/ Obispo Rafael Torija s/n, 13005 Ciudad Real, Spain.
Abstract
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.