Diagnostic efficiency of existing guidelines and the AI-SONIC™ artificial intelligence for ultrasound-based risk assessment of thyroid nodules

Abstract

IntroductionThe thyroid ultrasound guidelines include the American College of Radiology Thyroid Imaging Reporting and Data System, Chinese-Thyroid Imaging Reporting and Data System, Korean Society of Thyroid Radiology, European-Thyroid Imaging Reporting and Data System, American Thyroid Association, and American Association of Clinical Endocrinologists/American College of Endocrinology/Associazione Medici Endocrinologi guidelines. This study aimed to compare the efficiency of the six ultrasound guidelines vs. an artificial intelligence system (AI-SONICTM) in differentiating thyroid nodules, especially medullary thyroid carcinoma.MethodsThis retrospective study included patients with medullary thyroid carcinoma, papillary thyroid carcinoma, or benign nodules who underwent nodule resection between May 2010 and April 2020 at one hospital. The diagnostic efficacy of the seven diagnostic tools was evaluated using the receiver operator characteristic curves.ResultsFinally, 432 patients with 450 nodules were included for analysis. The American Association of Clinical Endocrinologists/American College of Endocrinology/Associazione Medici Endocrinologi guidelines had the best sensitivity (88.1%) and negative predictive value (78.6%) for differentiating papillary thyroid carcinoma or medullary thyroid carcinoma vs. benign nodules, while the Korean Society of Thyroid Radiology guidelines had the best specificity (85.6%) and positive predictive value (89.6%), and the American Thyroid Association guidelines had the best accuracy (83.7%). When assessing medullary thyroid carcinoma, the American Thyroid Association guidelines had the highest area under the curve (0.78), the American College of Radiology Thyroid Imaging Reporting and Data System guidelines had the best sensitivity (90.2%), and negative predictive value (91.8%), and AI-SONICTM had the best specificity (85.6%) and positive predictive value (67.5%). The Chinese-Thyroid Imaging Reporting and Data System guidelines had the best under the curve (0.86) in diagnosing malignant tumors vs. benign tumors, followed by the American Thyroid Association and Korean Society of Thyroid Radiology guidelines. The best positive likelihood ratios were achieved by the Korean Society of Thyroid Radiology guidelines and AI-SONICTM (both 5.37). The best negative likelihood ratio was achieved by the American Association of Clinical Endocrinologists/American College of Endocrinology/Associazione Medici Endocrinologi guidelines (0.17). The highest diagnostic odds ratio was achieved by the American Thyroid Association guidelines (24.78).DiscussionAll six guidelines and the AI-SONICTM system had satisfactory value in differentiating benign vs. malignant thyroid nodules.

Diagnostic performance of the gallbladder reporting and data system combined with color doppler flow imaging for gallbladder cancer in the Asian population

“…Combining CDFI with the GB-RADS enhances the diagnostic AC in differentiating between benign and malignant gallbladder wall thickening disease in Asian populations. This approach evaluates ultrasound characteristics using two-dimensional ultrasound alongside CDFI, significantly improving diagnostic performance ( 28 ).…”

Advanced multimodal imaging of solid thyroid lesions with artificial intelligence-optimized B-mode, elastography, and contrast-enhanced ultrasonography parametric and with perfusion imaging: Initial results

“…Using artificial intelligence (AI) approaches, suspicious lesions are first detected, then outlined and longitudinal diameter and transverse diameter measured. Then the characterization can be entered into a predefined scheme, adapted to the criteria of TI-RADS [8][9][10]. Then, finally, an evaluation is made and color-coded a localization in the scheme.…”

“…If the results of the elastography measurements are also taken into account with regard to the possible tissue compaction of the tumors, additional criteria for malignancy can be obtained at high values. CEUS is helpful if wash out kinetics is to reveal the possible malignancy of individual foci in struma multinodosa [4][5][6][7][8][9][10][11][12][13][14][15][16]. Adenomas may show a central wash out in parts with persistent marginal vascularization.…”

“…Due to increasingly improving ultrasound technology with high-resolution multifrequency probes, cystic as well as complicated cystic lesions and tumor foci can be assessed with modern ultrasound even at small sizes of less than 1 cm in diameter [1][2][3][4][5][6]. Initial artificial intelligence (AI) approaches are being used to attempt to detect suspicious thyroid foci, size them, and digitally document criteria for classification according to TI-RADS in a standardized manner [7][8][9][10].…”