Lesion Segmentation in Automated 3D Breast Ultrasound: Volumetric Analysis. (March 2018)

• Record Type: Journal Article
• Authors: Agarwal, Richa; Diaz, Oliver; Lladó, Xavier; Gubern-Mérida, Albert; Vilanova, Joan C.; Martí, Robert
• Is Part Of: Ultrasonic imaging. Volume 40:Number 2(2018)
• Page Start: 97
• Page End: 112
• Publication Date: 2018-03
• Subjects: breast cancer -- lesion segmentation -- ABUS (Automated Breast Ultrasound) -- watershed -- temporal -- volumetric analysis; Diagnostic ultrasonic imaging -- Methodology -- Periodicals; Ultrasonic testing -- Periodicals; Ultrasonic imaging -- Periodicals; Ultrasonography -- Periodicals; Échographie -- Méthodologie -- Périodiques; Essais par ultrasons -- Périodiques; Imagerie ultrasonore -- Périodiques; 616.07543
• DOI: 10.1177/0161734617737733
• Languages: English
• ISSNs: 0161-7346

Abstract

Mammography is the gold standard screening technique in breast cancer, but it has some limitations for women with dense breasts. In such cases, sonography is usually recommended as an additional imaging technique. A traditional sonogram produces a two-dimensional (2D) visualization of the breast and is highly operator dependent. Automated breast ultrasound (ABUS) has also been proposed to produce a full 3D scan of the breast automatically with reduced operator dependency, facilitating double reading and comparison with past exams. When using ABUS, lesion segmentation and tracking changes over time are challenging tasks, as the three-dimensional (3D) nature of the images makes the analysis difficult and tedious for radiologists. The goal of this work is to develop a semi-automatic framework for breast lesion segmentation in ABUS volumes which is based on the Watershed algorithm. The effect of different de-noising methods on segmentation is studied showing a significant impact (p < 0 . 05 ) on the performance using a dataset of 28 temporal pairs resulting in a total of 56 ABUS volumes. The volumetric analysis is also used to evaluate the performance of the developed framework. A mean Dice Similarity Coefficient of0 . 69 ± 0 . 11 with a mean False Positive ratio0 . 35 ± 0 . 14 has been obtained. The Pearson correlation coefficient between the segmented volumes and the corresponding ground truth volumes isr 2 = 0 . 960 (p = 0 . 05 ). Similar analysis, performed on 28 temporal (prior and current) pairs, resulted in a good correlation coefficientr 2 = 0 . 967 (p < 0 . 05 ) for prior andr 2 = 0 . 956 (p < 0 . 05 ) for current cases. The developed framework showed prospects to help radiologists to perform an assessment of ABUS lesion volumes, as well as to quantify volumetric changes during lesions diagnosis and follow-up.