A computer-aided diagnosis system using artificial intelligence for the diagnosis and characterization of thyroid nodules on ultrasound: initial clinical assessment.

Related Articles

A computer-aided diagnosis system using artificial intelligence for the diagnosis and characterization of thyroid nodules on ultrasound: initial clinical assessment.

Thyroid. 2017 Jan 10;:

Authors: Choi YJ, Baek JH, Park HS, Shim WH, Kim TY, Shong Y, Lee JH

Abstract
Background We describe an initial clinical assessment of a new, commercially available, computer-aided diagnosis (CAD) system using artificial intelligence (AI) for thyroid ultrasound, and evaluate its performance in the diagnosis of malignant thyroid nodules and categorization of nodule characteristics. Methods This prospective study protocol was reviewed and approved by the institutional review board. Patients with thyroid nodules with decisive diagnosis, whether benign or malignant on the basis of cytopathologic or US results, were consecutively enrolled from November 2015 to February 2016. An experienced radiologist reviewed the ultrasound image characteristics of the thyroid nodules, while another radiologist assessed the same thyroid nodules using the CAD system, providing ultrasound characteristics and a diagnosis of whether nodules were benign or malignant. We compared the diagnostic performance and agreement of US characteristics between experienced radiologist and the CAD system. Results In total, 102 thyroid nodules from 89 patients were included; 59 (57.8%) were benign and 43 (42.2%) were malignant. The CAD system showed a similar sensitivity as the experienced radiologist (sensitivity: 90.7% versus 88.4%, P>0.99), but a lower specificity, and a lower area under the receiver operating characteristic (AUROC) curve (specificity: 74.6% versus 94.9%, P=0.002; AUROC: 0.83 versus 0.92, P=0.021). Classifications of the ultrasound characteristics (composition, orientation, echogenicity, and spongiform) between radiologist and CAD system were in substantial agreement (kappa=0.659, 0.740, 0.733, and 0.658, respectively), while margin definition showed a fair agreement (kappa=0.239). Conclusion The sensitivity of the CAD system using AI for malignant thyroid nodules was as good as that of the experienced radiologist, while specificity and accuracy were lower than those of the experienced radiologist. The CAD system showed an acceptable agreement with the experienced radiologist for characterization of thyroid nodules.

PMID: 28071987 [PubMed - as supplied by publisher]

http://ift.tt/2iGCGFw