Mai Shibusawa1, Ryohei Nakayama2, Yuko Okanami3, Yumi Kashikura4, Nao Imai3, Takashi Nakamura5, Hiroko Kimura3, Masako Yamashita3, Noriko Hanamura3, Tomoko Ogawa3. 1. Department of Breast Surgery, Mie University Hospital, 2-174 Edobashi, Tsu City, Mie, 514-8507, Japan. shibu-m@clin.medic.mie-u.ac.jp. 2. Department of Electronic and Computer Engineering, Ritsumeikan University, 1-1-1 Noji-Higashi, Kusatsu City, Shiga, 525-8577, Japan. 3. Department of Breast Surgery, Mie University Hospital, 2-174 Edobashi, Tsu City, Mie, 514-8507, Japan. 4. Department of Senology, Tsukuba Medical Center Hospital, 1-3-1 Amakubo, Tsukuba City, Ibaraki, 305-8558, Japan. 5. Department of Breast Surgery, Nabari City Hospital, 1-178 Yurigaokanishi, Nabari City, Mie, 518-0481, Japan.
Abstract
PURPOSE: The purpose of this study was to evaluate the usefulness of a computer-aided diagnosis (CAD) scheme for improving the performance of clinicians to diagnose non-mass lesions appearing as hypoechoic areas on breast ultrasonographic images. METHODS: The database included 97 ultrasonographic images with hypoechoic areas: 48 benign cases [benign lesion with benign mammary tissue or fibrocystic disease (n = 20), fibroadenoma (n = 11), and intraductal papilloma (n = 17)] and 49 malignant cases [ductal carcinoma in situ (n = 17) and invasive ductal carcinoma (n = 32)]. Seven clinicians, three expert breast surgeons, and four general surgeons participated in the observer study. They were asked their confidence level concerning the possibility of malignancy in all 97 cases with and without the use of the CAD scheme. Receiver operating characteristic (ROC) analysis was performed to evaluate the usefulness of the CAD scheme. RESULTS: The areas under the ROC curve (AUC) improved for all observers when they used the CAD scheme and increased from 0.649 to 0.783 (P = 0.0167). Notably, the AUC for the general surgeon group increased from 0.625 to 0.793 (P = 0.045). CONCLUSIONS: This study showed that the performance of clinicians to diagnose non-mass lesions appearing as hypoechoic areas on breast ultrasonographic images was improved by the use of a CAD scheme.
PURPOSE: The purpose of this study was to evaluate the usefulness of a computer-aided diagnosis (CAD) scheme for improving the performance of clinicians to diagnose non-mass lesions appearing as hypoechoic areas on breast ultrasonographic images. METHODS: The database included 97 ultrasonographic images with hypoechoic areas: 48 benign cases [benign lesion with benign mammary tissue or fibrocystic disease (n = 20), fibroadenoma (n = 11), and intraductal papilloma (n = 17)] and 49 malignant cases [ductal carcinoma in situ (n = 17) and invasive ductal carcinoma (n = 32)]. Seven clinicians, three expert breast surgeons, and four general surgeons participated in the observer study. They were asked their confidence level concerning the possibility of malignancy in all 97 cases with and without the use of the CAD scheme. Receiver operating characteristic (ROC) analysis was performed to evaluate the usefulness of the CAD scheme. RESULTS: The areas under the ROC curve (AUC) improved for all observers when they used the CAD scheme and increased from 0.649 to 0.783 (P = 0.0167). Notably, the AUC for the general surgeon group increased from 0.625 to 0.793 (P = 0.045). CONCLUSIONS: This study showed that the performance of clinicians to diagnose non-mass lesions appearing as hypoechoic areas on breast ultrasonographic images was improved by the use of a CAD scheme.
Entities:
Keywords:
Breast non-mass lesions; Breast ultrasonography; Computer-aided diagnosis