A Multitask Approach for Automated Detection and Segmentation of Thyroid Nodules in Ultrasound Images
Preprint
Abstract
Objective Poor risk stratification of thyroid nodules by ultrasound has motivated the need for a deep learning-based approach for nodule segmentation. This paper demonstrates the effectiveness of a multitask approach to detect ultrasounds containing potential nodules and segment nodules on the suspected images. Methods Ultrasound studies were acquired from 280 patients at UCLA Health, totaling 9888 images. A novel anomaly detection (AD) module, to classify suspicious ultrasound images, was integrated with various state of the art segmentation architectures. The trained models were evaluated on a portion of the in-house dataset, as well as two external validation (EV) sets, to understand how the AD module affected segmentation performance. Results The addition of AD to the architectures improved image-level nodule detection, evidenced by the increase in F1 scores and image-wide Dice similarity coefficient. Of the models with AD, MSUNet-AD had the highest F1 score of 0.829; however, there was a decrease in DSC on just images with nodules (DSC+) from 0.726 to 0.627. This drop was observed across all models when AD was added; however, closer analysis of DSC+ by nodule size revealed that this difference was not significant in larger nodules, which are more likely to be clinically relevant. Finally, evaluation of MSUNet with and without AD on the EV datasets demonstrated comparable performance with the UCLA dataset. Conclusion The proposed architecture is an automated multitask method that can both detect and segment nodules in ultrasound. Performance on the EV datasets demonstrates generalizability of the model.Keywords
All Related Versions
- Published version: Computers in Biology and Medicine, 170, 107974.
This publication has 19 references indexed in Scilit:
- Lesion Attributes Segmentation for Melanoma Detection with Multi-Task U-Net2019
- UNet++: A Nested U-Net Architecture for Medical Image Segmentation2018
- Multitask Cascade Convolution Neural Networks for Automatic Thyroid Nodule Detection and RecognitionIEEE Journal of Biomedical and Health Informatics, 2018
- 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation2016
- 2015 American Thyroid Association 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 CancerThyroid®, 2016
- The Natural History of Benign Thyroid NodulesJAMA, 2015
- Interobserver and Intraobserver Variations in Ultrasound Assessment of Thyroid NodulesThyroid®, 2010
- Preoperative Staging of Papillary Thyroid Carcinoma: Comparison of Ultrasound Imaging and CTAmerican Journal of Roentgenology, 2009
- Predicting Thyroid MalignancyThe Journal of Clinical Endocrinology & Metabolism, 2006
- Thyroid Incidentalomas: Management Approaches to Nonpalpable Nodules Discovered Incidentally on Thyroid ImagingAnnals of Internal Medicine, 1997