잠시만 기다려 주세요. 로딩중입니다.

Application of machine learning to ultrasound images to differentiate follicular neoplasms of the thyroid gland

Ultrasonography 2020년 39권 3호 p.257 ~ 265
신일아, 김영재, 한경화, 이은정, 김혜정, 신정희, 문희정, 육지현, 김광기, 곽진영,
소속 상세정보
신일아 ( Shin Il-Ah ) - Yonsei University College of Medicine Severance Hospital Department of Radiology
김영재 ( Kim Young-Jae ) - Gachon University Department of Biomedical Engineering
한경화 ( Han Kyung-Hwa ) - Yonsei University College of Medicine Severance Hospital Department of Radiology
이은정 ( Lee Eun-Jung ) - Yonsei University Department of Computational Science and Engineering
김혜정 ( Kim Hye-Jung ) - Kyungpook National University School of Medicine Kyungpook National University Chilgok Hospital Department of Radiology
신정희 ( Shin Jung-Hee ) - Sungkyunkwan University School of Medicine Samsung Medical Center Department of Radiology
문희정 ( Moon Hee-Jung ) - Yonsei University College of Medicine Severance Hospital Department of Radiology
육지현 ( Youk Ji-Hyun ) - Yonsei University College of Medicine Gangnam Severance Hospital Department of Radiology
김광기 ( Kim Kwang-Gi ) - Gachon University Department of Biomedical Engineering
곽진영 ( Kwak Jin-Young ) - Yonsei University College of Medicine Severance Hospital Department of Radiology

Abstract


Purpose: This study was conducted to evaluate the diagnostic performance of machine learning in differentiating follicular adenoma from carcinoma using preoperative ultrasonography (US).

Methods: In this retrospective study, preoperative US images of 348 nodules from 340 patients were collected from two tertiary referral hospitals. Two experienced radiologists independently reviewed each image and categorized the nodules according to the 2015 American Thyroid Association guideline. Categorization of a nodule as highly suspicious was considered a positive diagnosis for malignancy. The nodules were manually segmented, and 96 radiomic features were extracted from each region of interest. Ten significant features were selected and used as final input variables in our in-house developed classifier models based on an artificial neural network (ANN) and support vector machine (SVM). The diagnostic performance of radiologists and both classifier models was calculated and compared.

Results: In total, 252 nodules from 245 patients were confirmed as follicular adenoma and 96 nodules from 95 patients were diagnosed as follicular carcinoma. As measures of diagnostic performance, the average sensitivity, specificity, and accuracy of the two experienced radiologists in discriminating follicular adenoma from carcinoma on preoperative US images were 24.0%, 84.0%, and 64.8%, respectively. The sensitivity, specificity, and accuracy of the ANN and SVM-based models were 32.3%, 90.1%, and 74.1% and 41.7%, 79.4%, and 69.0%, respectively. The kappa value of the two radiologists was 0.076, corresponding to slight agreement.

Conclusion: Machine learning-based classifier models may aid in discriminating follicular adenoma from carcinoma using preoperative US.

키워드

Follicular neoplasm; Ultrasonography; Machine learning; Artificial neural network; Support vector machine

원문 및 링크아웃 정보

 

등재저널 정보