Automated Segmentation of Thyroid Nodule, Gland, and Cystic Components From Ultrasound Images Using Deep Learning

• Published in: IEEE access Vol. 8; pp. 63482 - 63496
• Main Authors: Kumar, Viksit, Webb, Jeremy, Gregory, Adriana, Meixner, Duane D., Knudsen, John M., Callstrom, Matthew, Fatemi, Mostafa, Alizad, Azra
• Format: Journal Article
• Language: English
• Published: United States IEEE 2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Automation; Cancer; Deep learning; Image segmentation; Inference algorithms; Nodules; segmentation; Thyroid gland; thyroid nodule; thyroid nodule volume; Training; Ultrasonic imaging; Ultrasound; Workflow; Deep learning; thyroid nodule; segmentation; thyroid nodule volume; ultrasound
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2020.2982390

Sonographic features associated with margins, shape, size, and volume of thyroid nodules are used to assess their risk of malignancy. Automatically segmenting nodules from normal thyroid gland would enable an automated estimation of these features. A novel multi-output convolutional neural network algorithm with dilated convolutional layers is presented to segment thyroid nodules, cystic components inside the nodules, and normal thyroid gland from clinical ultrasound B-mode scans. A prospective study was conducted, collecting data from 234 patients undergoing a thyroid ultrasound exam before biopsy. The training and validation sets encompassed 188 patients total; the testing set consisted of 48 patients. The algorithm effectively segmented thyroid anatomy into nodules, normal gland, and cystic components. The algorithm achieved a mean Dice coefficient of 0.76, a mean true positive fraction of 0.90, and a mean false positive fraction of 1.61 × 10 -6 . The values are on par with a conventional seeded algorithm. The proposed algorithm eliminates the need for a seed in the segmentation process, thus automatically detecting and segmenting the thyroid nodules and cystic components. The detection rate for thyroid nodules and cystic components was 82% and 44%, respectively. The inference time per image, per fold was 107ms. The mean error in volume estimation of thyroid nodules for five select cases was 7.47%. The algorithm can be used for detection, segmentation, size estimation, volume estimation, and generating thyroid maps for thyroid nodules. The algorithm has applications in point of care, mobile health monitoring, improving workflow, reducing localization time, and assisting sonographers with limited expertise.