Better Rough Than Scarce: Proximal Femur Fracture Segmentation With Rough Annotations
- 23 April 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 43 (9) , 3240-3252
Abstract
Proximal femoral fracture segmentation in computed tomography (CT) is essential in the preoperative planning of orthopedic surgeons. Recently, numerous deep learning-based approaches have been proposed for segmenting various structures within CT scans. Nevertheless, distinguishing various attributes between fracture fragments and soft tissue regions in CT scans frequently poses challenges, which have received comparatively limited research attention. Besides, the cornerstone of contemporary deep learning methodologies is the availability of annotated data, while detailed CT annotations remain scarce. To address the challenge, we propose a novel weakly-supervised framework, namely Rough Turbo Net (RT-Net), for the segmentation of proximal femoral fractures. We emphasize the utilization of human resources to produce rough annotations on a substantial scale, as opposed to relying on limited fine-grained annotations that demand a substantial time to create. In RT-Net, rough annotations pose fractured-region constraints, which have demonstrated significant efficacy in enhancing the accuracy of the network. Conversely, the fine annotations can provide more details for recognizing edges and soft tissues. Besides, we design a spatial adaptive attention module (SAAM) that adapts to the spatial distribution of the fracture regions and align feature in each decoder. Moreover, we propose a fine-edge loss which is applied through an edge discrimination network to penalize the absence or imprecision edge features. Extensive quantitative and qualitative experiments demonstrate the superiority of RT-Net to state-of-the-art approaches. Furthermore, additional experiments show that RT-Net has the capability to produce pseudo labels for raw CT images that can further improve fracture segmentation performance and has the potential to improve segmentation performance on public datasets. The code is available at: https://github.com/zyairelu/RT-Net.Keywords
Funding Information
- National Natural Science Foundation of China (U22A2051, 82027807)
- National Key Research and Development Program of China (2022YFC2405200)
- Natural Science Foundation of Beijing Municipality (7212202)
- Institute for Intelligent Healthcare, Tsinghua University (2022ZLB001)
- Tsinghua-Foshan Innovation Special Fund (2021THFS0104)
- Capital Health Development Research Project (SF2022-2-4096)
This publication has 53 references indexed in Scilit:
- MDC-net: A new convolutional neural network for nucleus segmentation in histopathology images with distance maps and contour informationComputers in Biology and Medicine, 2021
- Teach Me to Segment with Mixed Supervision: Confident Students Become Masters2021
- Deep-learning-assisted detection and segmentation of rib fractures from CT scans: Development and validation of FracNetEBioMedicine, 2020
- Deep learning with noisy labels: Exploring techniques and remedies in medical image analysisMedical Image Analysis, 2020
- Latent3DU-net: Multi-level Latent Shape Space Constrained 3D U-net for Automatic Segmentation of the Proximal Femur from Radial MRI of the Hip2018
- Risk factors for implant failure after fixation of proximal femoral fractures with fracture of the lateral femoral wallInjury, 2018
- Computer assisted preoperative planning of bone fracture reduction: Simulation techniques and new trendsMedical Image Analysis, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Weakly supervised histopathology cancer image segmentation and classificationMedical Image Analysis, 2014
- Capturing the multiscale anatomical shape variability with polyaffine transformation treesMedical Image Analysis, 2012