Fusing enhanced Transformer and large kernel CNN for malignant thyroid nodule segmentation

Quick and accurate diagnosis for malignant thyroid nodules via ultrasonography is a valuable but challenging task even for experienced radiologists because of the complexity and variability of ultrasound images. Many computer-aided diagnosis (CAD) methods have been proposed to assist radiologists by providing objective suggestions. However, most existing segmentation approaches lack the ability to keep precise shape information and capture global long-range dependencies. To settle the above issues, we propose a deep learning-based CAD method called Transformer fusing CNN Network (TCNet) to segment malignant thyroid nodules automatically. Our proposed TCNet contains a large kernel CNN branch and an enhanced Transformer branch. In the former branch, we devise a Large Kernel Module (LKM) to extract the precise shape features of malignant thyroid nodules in ultrasound images. While in the latter branch, we design an Enhanced Transformer Module (ETM) to establish the remote connection between thyroid nodule pixels. To integrate multiscale feature maps produced from different phases of both branches, we develop a Multiscale Fusion Module (MFM) to connect the two branches. We compare the proposed model with several current commonly used segmentation methods on the MTNS dataset and other public datasets. The experimental results demonstrate the superiority and effectiveness of our method. •We propose Transformer fusing CNN Network (TCNet) for thyroid nodule segmentation.•We design the Large Kernel Module (LKM) to capture shape of thyroid nodule.•We propose the Enhanced Transformer Module (ETM) to model long-range relations.•We introduce the Multiscale Fusing Module (MFM) to connect the two branches.•We build a malignant thyroid nodule segmentation (MTNS) dataset.