ABSTRACT
Objective To investigate the efficacy of AI-SONICTM Thyroid system, a version 2.0 artificial intelligence (AI) automatic detection system, in the preoperative ultrasound diagnosis of thyroid nodules, and to evaluate the application value of AI automatic detection system version 2.0 in the differential diagnosis of benign and malignant thyroid nodules by comparing with the subjective diagnosis conclusions of sonographers with different seniorities. Methods A total of 247 patients (325 thyroid nodules) admitted to the Department of General Surgery in our hospital from Aug. 2019 to Jan. 2020 were selected for this study. All patients underwent routine ultrasound examinations by a senior sonographer with 13 years of experience in thyroid ultrasound diagnosis and a junior sonographer with 4 years of work experience. At the same time, the patients were also examined by another sonographer with 20 years of work experience using AI automatic detection system version 2.0, without knowing the diagnosis conclusions of the above two sonographers. Kappa test was used to evaluate the consistency of the results of routine ultrasound examination of sonographers with different seniorities and AI automatic detection system version 2.0 and the postoperative pathological results. Results The postoperative pathology confirmed 229 malignant nodules and 96 benign nodules. The sensitivity, specificity and accuracy in the diagnosis of benign and malignant thyroid nodules were 85.15% (195/229), 66.67% (64/96) and 79.69% (259/325), 93.45% (214/229), 79.17% (76/96) and 89.23% (290/325), and 92.58% (212/229), 71.88% (69/96) and 86.46% (281/325) for junior sonographer, senior sonographer and AI automatic detection system version 2.0, respectively. The Kappa consistency test results showed that the diagnosis result of senior sonographer was highly consistent with the pathological diagnosis result (Kappa value 0.78, P＜0.01), while the diagnosis results of junior sonographer and AI automatic detection system version 2.0 were generally consistent with the pathological diagnosis result (Kappa values 0.55 and 0.74, both P＜0.01). Conclusion The sensitivity, accuracy and specificity of the AI automatic detection system version 2.0 AI-SONICTM Thyroid in diagnosing benign and malignant thyroid nodules are similar to those of routine ultrasound examination by senior sonographers, and the system might be a reliable auxiliary means for preoperative evaluation of benign and malignant thyroid nodules.
ABSTRACT
Objective: To explore the application value of artificial intelligence (AI) automatic detection system in preoperative ultrasonic diagnosis of thyroid nodules. Methods: Totally 98 patients with 137 thyroid nodules admitted to the General Surgery Department of Changzheng Hospital of Naval Medical University (Second Military Medical University) from April 2019 to July 2019 were enrolled in this study. Pathological data and ultrasonic diagnosis results were retrospectively analyzed. All patients underwent conventional ultrasonography and AI automatic detection before surgery. The diagnoses for benign and malignant thyroid nodules were compared between conventional ultrasonography and AI automatic detection system, which were based on the postoperative pathology. The sensitivity, specificity and accuracy of the two examination methods were calculated, and Kappa coefficient was performed to measure the consistency between the two methods and postoperative pathological diagnosis. Results: The sensitivity, specificity and accuracy of conventional ultrasonography in diagnosis of benign and malignant thyroid nodules were respectively 93.75% (90/96), 80.49% (33/41) and 89.78% (123/137), and those of AI automatic detection were 89.58% (86/96), 68.29% (28/41) and 83.21% (114/137). There was substantial coefficience between conventional ultrasonography and pathological diagnosis results (Kappa=0.75, P<0.001), and that was fair coefficience between AI automatic detection system and pathological diagnosis results (Kappa=0.59, P<0.001). Conclusion: The sensitivity and accuracy of AI automatic detection system are slightly lower than but close to those of conventional ultrasonography in differentiating benign from malignant thyroid nodules. AI automatic detection system can be used as an effective supplement to assist conventional ultrasonography for preoperative assessment of thyroid nodules.