Automated segmentation of knee bone and cartilage combining statistical shape knowledge and convolutional neural networks: Data from the Osteoarthritis Initiative

By F. Ambellan, A. Tack, M. Ehlke, S. Zachow. 2019

354 citations recorded by the source corpus.

HighlightsIntegration of SSM‐based anatomical knowledge in an CNN‐based segmentation of femoral and tibial bone via a voting scheme.SSM‐based postprocessing for segmentation of knee bones.3D CNNs for segmentation of femoral and tibial cartilage.A thorough assessment of segmentation quality on three different datasets and publication of 507 manual reference segmentations (femur/tibia, bone/cartilage). ABSTRACT We present a method for the automated segmentation of knee bones and cartilage from magnetic resonance imaging (MRI) that combines a priori knowledge of anatomical shape with Convolutional Neural Networks (CNNs). The proposed approach incorporates 3D Statistical Shape Models (SSMs) as well as 2D and 3D CNNs to achieve a robust and accurate segmentation of even highly pathological knee structures. The shape models and neural networks employed are trained using data from the Osteoarthritis Initiative (OAI) and the MICCAI grand challenge “Segmentation of Knee Images 2010” (SKI10), respectively. We evaluate our method on 40 validation and 50 submission datasets from the SKI10 challenge. For the first time, an accuracy equivalent to the inter‐observer variability of human readers is achieved in this challenge. Moreover, the quality of the proposed method is thoroughly assessed using various measures for data from the OAI, i.e. 507 manual segmentations of bone and cartilage, and 88 additional manual segmentations of cartilage. Our method yields sub‐voxel accuracy for both OAI datasets. We make the 507 manual segmentations as well as our experimental setup publicly available to further aid research in the field of medical image segmentation. In conclusion, combining localized classification via CNNs with statistical anatomical knowledge via SSMs results in a state‐of‐the‐art segmentation method for knee bones and cartilage from MRI data.

Subfields: Computer Vision and Pattern Recognition, Rheumatology, Medical Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Rheumatology

In Medical Imaging

Citations in the corpus

SimpleClick: Interactive Image Segmentation with Simple Vision Transformers (2022, methodology): “Out-of-domain evaluation on three medical image datasets: ssTEM [15], BraTS [4], and OAIZIB [2].”
3D Deep Learning on Medical Images: A Review (2020, methodology): “In [55], Ambellan et al. proposed a technique with 3D Statistical Shape Models along with 2D in addition to 3D CNN's to accomplish an effective and precise seg mentation of knee structures.”
iSegFormer: Interactive Segmentation via Transformers with Application to 3D Knee MR Images (2021, methodology): “Datasets The OAI-ZIB [32] dataset consists of 507 3D MR images with segmentations for femur, tibia, tibial cartilage, and femoral cartilage.”