Xiao Luo PhD1,2,3, Min Xu1,2,4, Guoxue Tang1,2,5, Yi Wang PhD6, Na Wang6, Dong Ni PhD6, Xi Lin PhD1,2, An-Hua Li1,2. 1. State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-sen University Cancer Center, Guangzhou, China. 2. Department of Ultrasound, Sun Yat-Sen University Cancer Center, Guangzhou, China. 3. Department of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, China. 4. Department of Ultrasound, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou, China. 5. Department of Ultrasound, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangzhou, China. 6. National Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, China, and also with the Medical UltraSound Image Computing (MUSIC) Lab, Shenzhen, China.
Abstract
OBJECTIVES: The aim of this study was to investigate the detection efficacy of deep learning (DL) for automatic breast ultrasound (ABUS) and factors affecting its efficacy. METHODS: Females who underwent ABUS and handheld ultrasound from May 2016 to June 2017 (N = 397) were enrolled and divided into training (n = 163 patients with breast cancer and 33 with benign lesions), test (n = 57) and control (n = 144) groups. A convolutional neural network was optimized to detect lesions in ABUS. The sensitivity and false positives (FPs) were evaluated and compared for different breast tissue compositions, lesion sizes, morphologies and echo patterns. RESULTS: In the training set, with 688 lesion regions (LRs), the network achieved sensitivities of 93.8%, 97.2% and 100%, based on volume, lesion and patient, respectively, with 1.9 FPs per volume. In the test group with 247 LRs, the sensitivities were 92.7%, 94.5% and 96.5%, respectively, with 2.4 FPs per volume. The control group, with 900 volumes, showed 0.24 FPs per volume. The sensitivity was 98% for lesions > 1 cm3, but 87% for those ≤1 cm3 (p < 0.05). Similar sensitivities and FPs were observed for different breast tissue compositions (homogeneous, 97.5%, 2.1; heterogeneous, 93.6%, 2.1), lesion morphologies (mass, 96.3%, 2.1; non-mass, 95.8%, 2.0) and echo patterns (homogeneous, 96.1%, 2.1; heterogeneous 96.8%, 2.1). CONCLUSIONS: DL had high detection sensitivity with a low FP but was affected by lesion size. ADVANCES IN KNOWLEDGE: DL is technically feasible for the automatic detection of lesions in ABUS.
OBJECTIVES: The aim of this study was to investigate the detection efficacy of deep learning (DL) for automatic breast ultrasound (ABUS) and factors affecting its efficacy. METHODS: Females who underwent ABUS and handheld ultrasound from May 2016 to June 2017 (N = 397) were enrolled and divided into training (n = 163 patients with breast cancer and 33 with benign lesions), test (n = 57) and control (n = 144) groups. A convolutional neural network was optimized to detect lesions in ABUS. The sensitivity and false positives (FPs) were evaluated and compared for different breast tissue compositions, lesion sizes, morphologies and echo patterns. RESULTS: In the training set, with 688 lesion regions (LRs), the network achieved sensitivities of 93.8%, 97.2% and 100%, based on volume, lesion and patient, respectively, with 1.9 FPs per volume. In the test group with 247 LRs, the sensitivities were 92.7%, 94.5% and 96.5%, respectively, with 2.4 FPs per volume. The control group, with 900 volumes, showed 0.24 FPs per volume. The sensitivity was 98% for lesions > 1 cm3, but 87% for those ≤1 cm3 (p < 0.05). Similar sensitivities and FPs were observed for different breast tissue compositions (homogeneous, 97.5%, 2.1; heterogeneous, 93.6%, 2.1), lesion morphologies (mass, 96.3%, 2.1; non-mass, 95.8%, 2.0) and echo patterns (homogeneous, 96.1%, 2.1; heterogeneous 96.8%, 2.1). CONCLUSIONS: DL had high detection sensitivity with a low FP but was affected by lesion size. ADVANCES IN KNOWLEDGE: DL is technically feasible for the automatic detection of lesions in ABUS.
Authors: Wendie A Berg; Jeffrey D Blume; Jean B Cormack; Ellen B Mendelson; Daniel Lehrer; Marcela Böhm-Vélez; Etta D Pisano; Roberta A Jong; W Phil Evans; Marilyn J Morton; Mary C Mahoney; Linda Hovanessian Larsen; Richard G Barr; Dione M Farria; Helga S Marques; Karan Boparai Journal: JAMA Date: 2008-05-14 Impact factor: 56.272
Authors: Youngjune Kim; Jiwon Rim; Sun Mi Kim; Bo La Yun; So Yeon Park; Hye Shin Ahn; Bohyoung Kim; Mijung Jang Journal: Ultrasonography Date: 2020-03-24
Authors: Jan C M van Zelst; Tao Tan; Paola Clauser; Angels Domingo; Monique D Dorrius; Daniel Drieling; Michael Golatta; Francisca Gras; Mathijn de Jong; Ruud Pijnappel; Matthieu J C M Rutten; Nico Karssemeijer; Ritse M Mann Journal: Eur Radiol Date: 2018-02-07 Impact factor: 5.315