Advertisement
Published in:
08-12-2021 | Original Article
Transfer learning for automatic joint segmentation of thyroid and breast lesions from ultrasound images
Published in: International Journal of Computer Assisted Radiology and Surgery | Issue 2/2022
Log inActivate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
Purpose
It plays a significant role to accurately and automatically segment lesions from ultrasound (US) images in clinical application. Nevertheless, it is extremely challenging because distinct components of heterogeneous lesions are similar to background in US images. In our study, a transfer learning-based method is developed for full-automatic joint segmentation of nodular lesions.
Methods
Transfer learning is a widely used method to build high performing computer vision models. Our transfer learning model is a novel type of densely connected convolutional network (SDenseNet). Specifically, we pre-train SDenseNet based on ImageNet dataset. Then our SDenseNet is designed as a multi-channel model (denoted Mul-DenseNet) for automatically jointly segmenting lesions. As comparison, our SDenseNet using different transfer learning is applied to segmenting nodules, respectively. In our study, we find that more datasets for pre-training and multiple pre-training do not always work in segmentation of nodules, and the performance of transfer learning depends on a judicious choice of dataset and characteristics of targets.
Results
Experimental results illustrate a significant performance of the Mul-DenseNet compared to that of other methods in the study. Specially, for thyroid nodule segmentation, overlap metric (OM), dice ratio (DR), true-positive rate (TPR), false-positive rate (FPR) and modified Hausdorff distance (MHD) are \(0.9257\pm 0.0027\), \(0.9596\pm 0.0009\), \(0.9869\pm 0.0008\), \(0.0183\pm 0.0066\) and \(0.3897\pm 0.3488\) mm, respectively; for breast nodule segmentation, OM, DR, TPR, FPR and MHD are \(0.8912\pm 0.0072\), \(0.9513\pm 0.0038\), \(0.9835\pm 0.0015\), \(0.2381\pm 0.1301\) and \(0.2017\pm 0.0302\) mm, respectively.
Conclusions
The experimental results illustrate our transfer learning models are very effective in segmentation of lesions, which also demonstrate that it is potential of our proposed Mul-DenseNet model in clinical applications. This model can reduce heavy workload of the physicians so that it can avoid misdiagnosis cases due to excessive fatigue. Moreover, it is easy and reproducible to detect lesions without medical expertise.