Data Management And Sharing System of China National Clinical Research Center for Neurological Diseases

《国家中心数据管理与共享系统操作说明书 —— 研究者部分》

An Energy Matching Vessel Segmentation Framework in 3D Medical Image

First author：Pan Liu,Gao Huang,Jing Jing

Corresponding author：Yongjun Wang,Kunlun He

Angiography deep learning medical image segmentation real order derivative total variation

essential_information

2023-12-06

Published articles

Journal：IEEE Transactions on Medical Imaging

Publication type: Original Contributions

IF(IF): 10.6

PMID: 38048240 Link To Pubmed Full text Download

Background And Purpose

Accurate vascular segmentation from High Resolution 3-Dimensional (HR3D) medical scans is crucial for clinicians to visualize complex vasculature and diagnose related vascular diseases. However, a reliable and scalable vessel segmentation framework for HR3D scans remains a challenge.

Method

In this work, we propose a Highresolution Energy-matching Segmentation (HrEmS) framework that utilizes deep learning to directly process the entire HR3D scan and segment the vasculature to the finest level. The HrEmS framework introduces two novel components. Firstly, it uses the real-order total variation operator to construct a new loss function that guides the segmentation network to obtain the correct topology structure by matching the energy of the predicted segment to the energy of the manual label. This is different from traditional loss functions such as dice loss, which matches the pixels between predicted segment and manual label. Secondly, a curvature-based weight-correction module is developed, which directs the network to focus on crucial and complex structural parts of the vasculature instead of the easy parts. The proposed HrEmS framework was tested on three in-house multi-center datasets and three public datasets, and demonstrated improved results in comparison with the state-of-the-art methods using both topology-relevant and volumetric-relevant metrics.

Conclusion

Furthermore, a doubleblind assessment by three experienced radiologists on the critical points of the clinical diagnostic processes provided additional evidence of the superiority of the HrEmS frame-work

Main results

In this work, we propose a Highresolution Energy-matching Segmentation (HrEmS) framework that utilizes deep learning to directly process the entire HR3D scan and segment the vasculature to the finest level. The HrEmS framework introduces two novel components. Firstly, it uses the real-order total variation operator to construct a new loss function that guides the segmentation network to obtain the correct topology structure by matching the energy of the predicted segment to the energy of the manual label. This is different from traditional loss functions such as dice loss, which matches the pixels between predicted segment and manual label. Secondly, a curvature-based weight-correction module is developed, which directs the network to focus on crucial and complex structural parts of the vasculature instead of the easy parts. The proposed HrEmS framework was tested on three in-house multi-center datasets and three public datasets, and demonstrated improved results in comparison with the state-of-the-art methods using both topology-relevant and volumetric-relevant metrics.