ImageCHD: A 3D Computed Tomography Image Dataset for Classification of Congenital Heart Disease

Congenital heart disease (CHD) is the most common type of birth defects, which occurs 1 in every 110 births in the United States. CHD usually comes with severe variations in heart structure and great artery connections that can be classified into many types. Thus highly specialized domain knowledge and time-consuming human process is needed to analyze the associated medical images. On the other hand, due to the complexity of CHD and the lack of dataset, little has been explored on the automatic diagnosis (classification) of CHDs. In this paper, we present ImageCHD, the first medical image dataset for CHD classification. ImageCHD contains 110 3D Computed Tomography (CT) images covering most types of CHD, which is of decent size compared with existing medical imaging datasets. Classification of CHDs requires the identification of large structural changes without any local tissue changes, with limited data. It is an example of a larger class of problems that are quite difficult for current machine-learning based vision methods to solve. To demonstrate this, we further present a baseline framework for automatic classification of CHD, based on a state-of-the-art CHD segmentation method. Experimental results show that the baseline framework can only achieve a classification accuracy of 82.0% under selective prediction scheme with 88.4% coverage, leaving big room for further improvement. We hope that ImageCHD can stimulate further research and lead to innovative and generic solutions that would have an impact in multiple domains. Our dataset is released to the public [1].

[1]  Xiaobo Sharon Hu,et al.  Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[2]  Xin Yang,et al.  Class-Balanced Deep Neural Network for Automatic Ventricular Structure Segmentation , 2017, STACOM@MICCAI.

[3]  Horst Bischof,et al.  Multi-label Whole Heart Segmentation Using CNNs and Anatomical Label Configurations , 2017, STACOM@MICCAI.

[4]  Xiahai Zhuang,et al.  Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI , 2016, Medical Image Anal..

[5]  Jinjun Xiong,et al.  MSU-Net: Multiscale Statistical U-Net for Real-time 3D Cardiac MRI Video Segmentation , 2019, MICCAI.

[6]  Irena Galić,et al.  Whole Heart Segmentation from CT images Using 3D U-Net architecture , 2019, 2019 International Conference on Systems, Signals and Image Processing (IWSSIP).

[7]  Yun Tian,et al.  Automatic Whole Heart Segmentation Using a Two-Stage U-Net Framework and an Adaptive Threshold Window , 2019, IEEE Access.

[8]  Jianjiang Feng,et al.  CFUN: Combining Faster R-CNN and U-net Network for Efficient Whole Heart Segmentation , 2018, ArXiv.

[9]  Jürgen Weese,et al.  Iterative Segmentation from Limited Training Data: Applications to Congenital Heart Disease , 2018, DLMIA/ML-CDS@MICCAI.

[10]  Ran El-Yaniv,et al.  Selective Prediction of Financial Trends with Hidden Markov Models , 2011, NIPS.

[11]  Leonidas J. Guibas,et al.  The Earth Mover's Distance as a Metric for Image Retrieval , 2000, International Journal of Computer Vision.

[12]  Guang Yang,et al.  A two-stage 3D Unet framework for multi-class segmentation on full resolution image , 2018, ArXiv.

[13]  Kuanquan Wang,et al.  Multi-Depth Fusion Network for Whole-Heart CT Image Segmentation , 2019, IEEE Access.

[14]  Danny Z. Chen,et al.  HFA-Net: 3D Cardiovascular Image Segmentation with Asymmetrical Pooling and Content-Aware Fusion , 2019, MICCAI.

[15]  Xin Yang,et al.  3D FractalNet: Dense Volumetric Segmentation for Cardiovascular MRI Volumes , 2016, RAMBO+HVSMR@MICCAI.

[16]  Cheng Chen,et al.  PnP-AdaNet: Plug-and-Play Adversarial Domain Adaptation Network at Unpaired Cross-Modality Cardiac Segmentation , 2019, IEEE Access.

[17]  S. Nielles-Vallespin,et al.  Respiratory self‐navigation for whole‐heart bright‐blood coronary MRI: Methods for robust isolation and automatic segmentation of the blood pool , 2012, Magnetic resonance in medicine.

[18]  Jinjun Xiong,et al.  SCNN: A General Distribution based Statistical Convolutional Neural Network with Application to Video Object Detection , 2019, AAAI.

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

[20]  Jian Zhuang,et al.  Whole Heart and Great Vessel Segmentation in Congenital Heart Disease Using Deep Neural Networks and Graph Matching , 2019, MICCAI.

[21]  Xin Yang,et al.  Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved? , 2018, IEEE Transactions on Medical Imaging.

[22]  Guang Yang,et al.  A Two-Stage U-Net Model for 3D Multi-class Segmentation on Full-Resolution Cardiac Data , 2018, STACOM@MICCAI.

[23]  Rongzhao Zhang,et al.  A Fine-Grain Error Map Prediction and Segmentation Quality Assessment Framework for Whole-Heart Segmentation , 2019, MICCAI.

[24]  Xin Yang,et al.  Hybrid Loss Guided Convolutional Networks for Whole Heart Parsing , 2017, STACOM@MICCAI.

[25]  Yinghuan Shi,et al.  Cross-Modal Attention-Guided Convolutional Network for Multi-modal Cardiac Segmentation , 2019, MLMI@MICCAI.

[26]  Venkatraman Bhat,et al.  Illustrated Imaging Essay on Congenital Heart Diseases: Multimodality Approach Part I: Clinical Perspective, Anatomy and Imaging Techniques. , 2016, Journal of clinical and diagnostic research : JCDR.

[27]  Tim Leiner,et al.  Dilated Convolutional Neural Networks for Cardiovascular MR Segmentation in Congenital Heart Disease , 2016, RAMBO+HVSMR@MICCAI.