The diagnostic value of artificial intelligence B-ultrasound image computer-aided diagnosis system in adult goiter
10.3760/cma.j.cn231583-20231215-00134
- VernacularTitle:人工智能B超影像计算机辅助诊断系统对成人甲状腺肿诊断价值的研究
- Author:
Zexu ZHANG
1
;
Zongyu YUE
;
Honglei XIE
;
Yue SU
;
Haowen PAN
;
Jia LI
;
Wenjing CHE
;
Xin HOU
;
Meng ZHAO
;
Lanchun LIU
;
Dandan LI
;
Xian XU
;
Weidong LI
;
Fangang MENG
;
Lijun FAN
;
Lixiang LIU
;
Ming LI
;
Peng LIU
Author Information
1. 哈尔滨医科大学中国疾病预防控制中心地方病控制中心碘缺乏病防治研究所 国家卫生健康委病因流行病学重点实验室 黑龙江省微量元素与人类健康重点实验室 黑龙江省普通高校病因流行病学重点实验室，哈尔滨 150081
- Keywords:
Goiter;
Ultrasonography;
Artificial intelligence;
Diagnostic efficacy
- From:
Chinese Journal of Endemiology
2024;43(11):922-927
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To study the diagnostic value of artificial intelligence B-ultrasound image computer-aided diagnosis system (hereinafter referred to as intelligent ultrasound system) in adult goiter.Methods:In June 2022 and March 2023, two phases of thyroid disease survey were carried out in 4 cities in Anhui Province. One village was selected in each city, and 250 adults were selected as survey subjects in each village. Adult bilateral thyroid area was scanned by both intelligent ultrasound system and conventional ultrasound scanning equipment, and the effectiveness of intelligent ultrasound system in the diagnosis of goiter was analyzed based on the results of conventional ultrasound examination. Receiver operating characteristic (ROC) curve was drawn, and Kappa test was used to analyze the consistency between intelligent ultrasound system and conventional ultrasound examination in the diagnosis of goiter. At the same time, Spearman correlation analysis and Bland-Altman method were used to evaluate the consistency of the two methods in measuring thyroid volume.Results:After screening and removing outliers and missing values, a total of 910 adults were included, including 253 males (27.80%) and 657 females (72.20%). The age was (45.92 ± 10.20) years old, ranging from 18 to 60 years old. The sensitivity, specificity, and accuracy of the intelligent ultrasound system for diagnosing adult goiter were 80.00%, 99.67%, and 99.56%, respectively. The area under the ROC curve (AUC) was 0.996, which was consistent with the results of conventional ultrasound examination for diagnosing goiter ( κ = 0.67, P < 0.001). After controlling for variables such as gender, thyroid function, and thyroid nodules, the intelligent ultrasound system showed good consistency with conventional ultrasound examination in the diagnosis of goiter in females, adults with thyroid dysfunction, and adults without thyroid nodules ( κ = 0.66, 0.80, 0.80, P < 0.001). The consistency in the diagnosis of goiter in adults with thyroid nodules was moderate ( κ = 0.56, P < 0.001). Spearman correlation analysis showed a highly positive correlation between the measurement results of adult thyroid volume by intelligent ultrasound system and conventional ultrasound examination ( r = 0.88, P < 0.001). The Bland-Altman method results showed that only 4.62% (42/910) of points in adults were outside the 95% consistency limit, indicating good consistency between intelligent ultrasound system and conventional ultrasound examination in measuring thyroid volume (< 5%). The proportion of points outside the 95% consistency limit in males, adults with thyroid dysfunction, and adults with thyroid nodules was 6.72% (17/253), 5.83% (12/206), and 6.45% (12/186), respectively. Conclusions:The intelligent ultrasound system has certain diagnostic value for adult goiter and has good consistency with conventional ultrasound examination for thyroid volume measurement. However, the accuracy of diagnosis for males and adults with thyroid nodules still needs to be improved.
