Computer-aided diagnostic system for assessment of thyroid nodules on ultrasound: diagnostic performance compared with radiologist-based clinical assessments

doi:10.3877/cma.j.issn.1672-6448.2018.12.011

Abstract

Abstract:

Objective

To evaluate the difference in assessment of the American College Radiology thyroid imaging-reporting and data system score between a computer-aided diagnostic system (Am CAD-UT Dection) and radiologists and to discuss its value in the differential diagnosis of benign and malignant thyroid nodules on ultrasound.

Methods

This retrospective study analyzed 194 patients with thyroid nodules at Sun Yat-sen University Cancer Center between May 2015 and October 2016. Only one nodule was chosen in a patient and was proven by fine needle aspiration (FNA) cytology or thyroidectomy. A senior radiologist with 16 years of working experience and a junior radiologist with 4 years of working experience assessed the five major ultrasound characteristics of thyroid nodules including composition, echogenicity, shape, margin and echogenic foci separately, while the CAD system analyzed the same thyroid nodules automatically based on the ACR standard.

Results

The CAD system showed a similar performance to the senior radiologist (P=0.335) but performed better than the junior radiologist (P<0.001). Using TR5 as the diagnostic standard for malignancy, the CAD system was significantly consistent with the senior doctor in sensitivity (84.62% vs 86.54%, P=0.815) but was better than the junior doctor without a significant difference (84.62% vs 73.08%, P=0.052). The specificity of the CAD system was lower than those of the above two radiologists (65.56% vs 87.78%, 82.22%, P<0.01).

Conclusion

The CAD system exhibits a higher sensitivity but lower specificity and diagnostic performance than radiologist-based clinical assessments in the differential diagnosis of benign and malignant thyroid nodules.

Key words: Computer-aided diagnosis, Ultrasound, Thyroid nodule

Longzhong Liu, Qing Li, Xingzhang Long, Ying Liu, Miao Yun, Anhua Li. Computer-aided diagnostic system for assessment of thyroid nodules on ultrasound: diagnostic performance compared with radiologist-based clinical assessments[J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2018, 15(12): 942-947.

/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: https://chaosheng.cma-cmc.com.cn/EN/10.3877/cma.j.issn.1672-6448.2018.12.011

https://chaosheng.cma-cmc.com.cn/EN/Y2018/V15/I12/942

Figures/Tables 4

References 11

1	Haugen BR, Alexander EK, Bible KC, et al. 2015 American ThyroidAssociation Management Guidelines for Adult Patients with Thyroid Nodules and Differentiated Thyroid Cancer: The American Thyroid Association Guidelines Task Force on Thyroid Nodules and Differentiated Thyroid Cancer [J]. Thyroid, 2016, 26(1): 1-133.
2	Choi SH, Kim EK, Kwak JY, et al. Interobserver and intraobservervariations in ultrasound assessment of thyroid nodules [J]. Thyroid, 2010, 20(2): 167-172.
3	Tessler FN, Middleton WD, Grant EG, et al. ACR Thyroid Imaging, Reporting and Data System (TI-RADS): White Paper of the ACR TI-RADS Committee [J]. J Am Coll Radiol, 2017, 14(5): 587-595.
4	Chang KJ, Chen WH, Chen A, et al. Method for retrieving a tumor contour of an image processing system [P]: US, 8374892. 2013-02-12. DOI:US20110182489.
5	Chang KJ, Chen WH, Chen A, et al. Method for retrieving a tumor contour of an image processing system [P]: China, CN 102156874 B. 2015-07-29.
6	Chen KY, Chen CN, Wu MH, et al. Computerized detection and quantification of microcalcifications in thyroid nodules [J]. Ultrasound Med Biol, 2011, 37(6): 870-878.
7	Chen KY, Chen CN, Wu MH, et al. Computerized quantification of ultrasonic heterogeneity in thyroid nodules [J]. Ultrasound Med Biol, 2014, 40(11): 2581-2589.
8	Chabi ML, Borget I, Ardiles R, et al. Evaluation of the accuracy of a computer-CADded diagnosis (CAD) system in breast ultrasound according to the radiologist′s experience [J]. Acad Radiol, 2012, 19(3): 311-319.
9	Acharya UR, Faust O, Sree SV, et al. ThyroScreen system: highresolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform [J]. Comput Methods Programs Biomed, 2012,107(2): 233-241
10	Chang Y, Paul AK, Kim N, et al.Computer-CADded diagnosis for classifying benign versus malignant thyroid nodules based on ultrasound images: A comparison with radiologist-based assessments [J]. Med Phys, 2016, 43(1): 554-567.
11	Acharya UR, Swapna G, Sree SV, et al. A review on ultrasound-based thyroid cancer tissue characterization and automated classification [J]. Technol Cancer Res Treat, 2014, 13(4): 289-301.

病理结果证实	低年资医师					合计	高年资医师
病理结果证实	TR1	TR2	TR3	TR4	TR5	合计	TR1	TR2	TR3
良性	3	36	24	16	11	90	2	15	32
恶性	0	0	1	27	76	104	0	0	2
合计	3	36	25	43	87	194	2	15	34
病理结果证实	高年资医师		合计	安克侦CAD软件					合计
病理结果证实	TR4	TR5	合计	TR1	TR2	TR3	TR4	TR5	合计
良性	25	16	90	1	4	20	34	31	90
恶性	12	90	104	0	0	3	13	88	104
合计	37	106	194	1	4	23	47	119	194

病理结果证实	低年资医师					合计	高年资医师
病理结果证实	TR1	TR2	TR3	TR4	TR5	合计	TR1	TR2	TR3
良性	3	36	24	16	11	90	2	15	32
恶性	0	0	1	27	76	104	0	0	2
合计	3	36	25	43	87	194	2	15	34
病理结果证实	高年资医师		合计	安克侦CAD软件					合计
病理结果证实	TR4	TR5	合计	TR1	TR2	TR3	TR4	TR5	合计
良性	25	16	90	1	4	20	34	31	90
恶性	12	90	104	0	0	3	13	88	104
合计	37	106	194	1	4	23	47	119	194

分析方法	敏感度	特异度	阳性预测值	阴性预测值	诊断准确性
低年资医师	73.08^a	87.78^b	87.36	73.83	79.90
高年资医师	86.54	82.22^c	84.91	84.09	84.54
安克侦CAD软件	84.62	65.56	73.95	78.67	75.77

分析方法	敏感度	特异度	阳性预测值	阴性预测值	诊断准确性
低年资医师	73.08^a	87.78^b	87.36	73.83	79.90
高年资医师	86.54	82.22^c	84.91	84.09	84.54
安克侦CAD软件	84.62	65.56	73.95	78.67	75.77

[1]	Qi Lyu, Pinjing Hui, Yafang Ding, Yanhong Yan. Carotid contrast-enhanced ultrasound assessment of plaque vulnerability and its correlation with ischemic stroke [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(10): 1040-1045.
[2]	Lei Ding, Wen Luo, Xiao Yang, Lina Pang, Peidi Zhang, Haijing Liu, Jiani Yuan, Jin Liu. Application of high-frame-rate contrast-enhanced ultrasound in evaluation of imaging features of C-TIRADS 4-5 thyroid nodules [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(09): 887-894.
[3]	Qian Zhang, Jiahui Chen, Xuemeng Gao, Aoxue Zhao, Ying Huang. Value of radiomics features based on high-frame-rate contrast-enhanced ultrasound in differential diagnosis of benign and malignant thyroid nodules [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(09): 895-903.
[4]	Lianhua Zhu, Xiang Fei, Peng Han, Bo Jiang, Nan Li, Yukun Luo. Value of high frame rate contrast-enhanced ultrasound in differential diagnosis of gallbladder polyp lesions [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(09): 904-910.
[5]	Miao Li, Lianhua Zhu, Peng Han, Bo Jiang, Xiang Fei. Evaluation of relationsip between vascular morphology and risk factors for hepatocellular carcinoma by high-frame-rate contrast-enhanced ultrasound [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(09): 911-915.
[6]	Weiping Zhang, Jingling Wang, Zhixing Liu, Li Chen, Fangqun Chen. Characteristics of time-intensity curve of high-frame-rate contrast-enhanced ultrasound in clear cell renal cell carcinoma [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(09): 916-922.
[7]	Jianmin Ding, Zhengyi Qin, Xiang Zhang, Yan Zhou, Hongyu Zhou, Yandong Wang, Xiang Jing. Contrast-enhanced ultrasound versus gadoxetic acid-enhanced magnetic resonance imaging for LI-RADS classification of focal liver lesions ≤3 cm in patients at high risk of hepatocellular carcinoma: a prospective study [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(09): 930-938.
[8]	Dan Han, Ting Wang, Huan Xiao, Lirong Zhu, Jingyu Chen, Yi Tang. Diagnostic value of contrast enhanced ultrasound versus contrast enhanced computed tomography in benign and malignant liver lesions in children [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(09): 939-944.
[9]	Tingting Liu, Yanbing Lin, Shan Wang, Murong Chen, Zijian Tang, Dongling Dai, Bei Xia. Evaluation of metabolic dysfunction-associated fatty liver disease in children by ultrasound-guided attenuation parameter [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(08): 787-794.
[10]	Yanbo Ma, Yang Hua, Guimei Liu, Xiufeng Meng, Liping Cui. Risk factors for carotid atherosclerotic lesions in middle adults [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(08): 822-826.
[11]	Hua Shao, Ziyue Na, Hui Jing, Bo Li, Qiucheng Wang, Wen Cheng. Value of preoperative percutaneous contrast-enhanced ultrasound in diagnosis of axillary sentinel lymph node metastasis and burden in breast cancer [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(08): 849-853.
[12]	Xu Zhang, Jianping Xu, Dongming Su, Caifen Wang, Dali Wang, Wenzhi Zhang. Contrast-enhanced ultrasound features of male breast masses [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(08): 854-859.
[13]	Xining Wu, Peipei Zhang, Zhenhong Qi, Jing Zhang, Ruina Zhao, Hua Meng, Jianchu Li. Quality of ultrasonic diagnosis of retroperitoneal schwannomas and its influencing factors [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(07): 701-704.
[14]	bing Feng, Qiuguo Zou, Zhenbo Liang, Yanming Lu, Yi Zeng, Shumiao Wu. Clinical study of ultrasonic signs and molecular biological indicators of senile non-specific invasive breast cancer [J]. Chinese Journal of Operative Procedures of General Surgery(Electronic Edition), 2024, 18(01): 48-51.
[15]	Wenyi Zhao, Bingzi Zou, Guanhui Cai, Yongzhi Liu, Hong Wen. Application of ultrasound strain elastography combined with MRI-DWI guided targeted puncture in diagnosis of prostate lesions [J]. Chinese Journal of Clinicians(Electronic Edition), 2023, 17(9): 988-994.

Please choose a citation manager

Content to export