论文信息 - A Coarse-to-Fine Deep Heatmap Regression Method for Adolescent Idiopathic Scoliosis Assessment

A Coarse-to-Fine Deep Heatmap Regression Method for Adolescent Idiopathic Scoliosis Assessment

Spinal anterior-posterior x-ray CT imaging is an appealing tool to aid diagnosis and elucidate Adolescent Idiopathic Scoliosis (AIS) Assessment. In this paper, we propose an automatic detection method for AIS assessment from X-ray CT images. Our deep learning based coarse-to-fine heatmaps regression method achieves symmetric mean absolute percentage error (SMAPE) of 24.7987 in the grand challenge AASCE 2019.

[1] Thomas Brox,et al. U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[2] Liansheng Wang,et al. An Automated and Accurate Spine Curve Analysis System , 2019, IEEE Access.

[3] Shuo Li,et al. Automated comprehensive Adolescent Idiopathic Scoliosis assessment using MVC‐Net , 2018, Medical Image Anal..

[4] Kaiming He,et al. Mask R-CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[5] Liansheng Wang,et al. Accurate automated Cobb angles estimation using multi-view extrapolation net , 2019, Medical Image Anal..

[6] Michael Brady,et al. A Representation for Mammographic Image Processing , 1995, CVRMed.

[7] Shuo Li,et al. Automatic Landmark Estimation for Adolescent Idiopathic Scoliosis Assessment Using BoostNet , 2017, MICCAI.

[8] Jie Li,et al. An Attention-Guided Deep Regression Model for Landmark Detection in Cephalograms , 2019, MICCAI.