Automated thyroid nodule detection from ultrasound imaging using deep convolutional neural networks. (July 2020)

• Record Type: Journal Article
• Authors: Abdolali, Fatemeh; Kapur, Jeevesh; Jaremko, Jacob L.; Noga, Michelle; Hareendranathan, Abhilash R.; Punithakumar, Kumaradevan
• Is Part Of: Computers in biology and medicine. Volume 122(2020)
• Publication Date: 2020-07
• Subjects: Computer aided diagnosis -- Convolutional neural network -- Deep learning -- Mask R-CNN -- Thyroid nodules -- Ultrasound; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2020.103871
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Thyroid cancer is the most common endocrine cancer and its incidence has continuously increased worldwide. In this paper, we focus on the challenging problem of nodule detection from ultrasound scans. In current clinical practice, this task is performed manually, which is tedious, subjective and highly depends on the clinical experience of radiologists. We propose a novel deep neural network architecture with carefully designed loss function regularization, and network hyperparameters to perform nodule detection without complex post-processing refinement steps. The local training and validation datasets consist of 2461 and 820 ultrasound frames acquired from 60 and 20 patients with a high degree of variability, respectively. The core of the proposed method is a deep learning framework based on multi-task model Mask R-CNN. We have developed a loss function with regularization that prioritizes detection over segmentation. Validation was conducted for 821 ultrasound frames from 20 patients. The proposed model can detect various types of thyroid nodules. The experimental results indicate that our proposed method is effective in thyroid nodule detection. Comparisons with the results by Faster R-CNN and conventional Mask R-CNN demonstrate that the proposed model outperforms the prior state-of-the-art detection methods. Highlights: Computer aided detection of thyroid nodules is an essential step for diagnosis. The proposed deep learning nodule detection framework is based on multi-task model named Mask R-CNN. A regularized loss function is applied to prioritize detection task over segmentation task. The proposed model is able to detect various types of thyroid nodules in noisy ultrasound scans. Proposed Mask R-CNN variant outperforms two previous state-of-the-art nodule detection methods.