NEC-Net: A hybrid transformer for necrotizing enterocolitis diagnosis by lesion segmentation on abdominal X-rays.
Authors
Affiliations (7)
Affiliations (7)
- School of Automation, Guangdong Province Key Laboratory of Intelligent Decision and Cooperative Control, Guangdong University of Technology, Guangzhou, China. Electronic address: [email protected].
- School of Automation, Guangdong Province Key Laboratory of Intelligent Decision and Cooperative Control, Guangdong University of Technology, Guangzhou, China. Electronic address: [email protected].
- Maternal and Children Health Care Hospital (Huzhong Hospital) of Huadu, Guangzhou, China. Electronic address: [email protected].
- School of Automation, Guangdong Province Key Laboratory of Intelligent Decision and Cooperative Control, Guangdong University of Technology, Guangzhou, China. Electronic address: [email protected].
- Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, China. Electronic address: [email protected].
- Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, China. Electronic address: [email protected].
- Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong, China. Electronic address: [email protected].
Abstract
Accurate lesion segmentation in medical imaging is essential for computer-aided diagnosis and clinical decision-making. In particular, necrotizing enterocolitis (NEC), a life-threatening gastrointestinal disease in neonates, requires precise localization of lesion areas from abdominal X-rays to support timely intervention. However, NEC lesion segmentation is highly challenging due to local feature similarity, indistinct boundaries, and overlapping tissues in radiographic images. To address these issues, we propose NEC-Net, a hybrid CNN-Transformer architecture specifically designed for fine-grained NEC lesion segmentation: a Series-Parallel Large Kernel Attention module to enhance the representation of elongated structures, a Multi-layer Edge-enhanced Perception Module for improved boundary sensitivity, and a Short-range Concatenation Decoding structure to better handle small lesions. Extensive experiments on a clinical dataset comprising 752 annotated NEC cases demonstrate the superiority of NEC-Net, achieving 77.92% mIoU, 86.14% mean Dice coefficient and 35.31 HD95. The model, along with associated tools, is available at https://github.com/priscillaLee0830/NEC-application, offering practical value for NEC radiological alert and clinical deployment.