Computer‐aided diagnosis for classifying benign versus malignant thyroid nodules based on ultrasound images: A comparison with radiologist‐based assessments. Issue 1 (6th January 2016)

• Record Type: Journal Article
• Authors: Chang, Yongjun; Paul, Anjan Kumar; Kim, Namkug; Baek, Jung Hwan; Choi, Young Jun; Ha, Eun Ju; Lee, Kang Dae; Lee, Hyoung Shin; Shin, DaeSeock; Kim, Nakyoung
• Is Part Of: Medical physics. Volume 43:Issue 1(2016)
• Page Start: 554
• Page End: 567
• Publication Date: 2016-01-06
• Subjects: biomedical ultrasonics -- feature extraction -- feature selection -- image classification -- image segmentation -- medical image processing -- support vector machines; Medical diagnosis with acoustics; Diagnosis using ultrasonic, sonic or infrasonic waves -- Biological material, e.g. blood, urine; Haemocytometers -- In which a programme is changed according to experience gained by the computer itself during a complete run; Learning machines -- Digital computing or data processing equipment or methods, specially adapted for specific applications -- Image data processing or generation, in general -- Inference methods or devices; SVM classifier -- computer‐aided diagnosis -- image segmentation -- textural features -- thyroid cancer; Ultrasonography -- Radiologists -- Optical inspection -- Cancer -- Medical image segmentation -- Flow visualization -- Medical image noise -- Multivariate analysis -- Anisotropy; Medical physics -- Periodicals; Medical physics; Geneeskunde; Natuurkunde; Toepassingen; Biophysics; Periodicals; Periodicals; Electronic journals; 610.153
• DOI: 10.1118/1.4939060
• Languages: English
• ISSNs: 0094-2405

Abstract

Abstract : Purpose: To develop a semiautomated computer‐aided diagnosis (cad ) system for thyroid cancer using two‐dimensional ultrasound images that can be used to yield a second opinion in the clinic to differentiate malignant and benign lesions. Methods: A total of 118 ultrasound images that included axial and longitudinal images from patients with biopsy‐confirmed malignant ( n = 30) and benign ( n = 29) nodules were collected. Thyroidcad software was developed to extract quantitative features from these images based on thyroid nodule segmentation in which adaptive diffusion flow for active contours was used. Various features, including histogram, intensity differences, elliptical fit, gray‐level co‐occurrence matrixes, and gray‐level run‐length matrixes, were evaluated for each region imaged. Based on these imaging features, a support vector machine (SVM) classifier was used to differentiate benign and malignant nodules. Leave‐one‐out cross‐validation with sequential forward feature selection was performed to evaluate the overall accuracy of this method. Additionally, analyses with contingency tables and receiver operating characteristic (ROC) curves were performed to compare the performance ofcad with visual inspection by expert radiologists based on established gold standards. Results: Most univariate features for this proposedcad system attained accuracies that ranged from 78.0% to 83.1%. When optimal SVM parameters that were established using a grid search method with features that radiologists use for visual inspection were employed, the authors could attain rates of accuracy that ranged from 72.9% to 84.7%. Using leave‐one‐out cross‐validation results in a multivariate analysis of various features, the highest accuracy achieved using the proposedcad system was 98.3%, whereas visual inspection by radiologists reached 94.9% accuracy. To obtain the highest accuracies, "axial ratio" and "max probability" in axial images were most frequently included in the optimal feature sets for the authors' proposedcad system, while "shape" and "calcification" in longitudinal images were most frequently included in the optimal feature sets for visual inspection by radiologists. The computed areas under curves in the ROC analysis were 0.986 and 0.979 for the proposedcad system and visual inspection by radiologists, respectively; no significant difference was detected between these groups. Conclusions: The use of thyroidcad to differentiate malignant from benign lesions shows accuracy similar to that obtained via visual inspection by radiologists. Thyroidcad might be considered a viable way to generate a second opinion for radiologists in clinical practice.