Generalization of Deep Convolutional Neural Networks - A Case-study on Open-source Chest Radiographs

Deep Convolutional Neural Networks (DCNNs) have attracted extensive attention and been applied in many areas, including medical image analysis and clinical diagnosis. One major challenge is to conceive a DCNN model with remarkable performance on both internal and external data. We demonstrate that DCNNs may not generalize to new data, but increasing the quality and heterogeneity of the training data helps to improve the generalizibility factor. We use InceptionResNetV2 and DenseNet121 architectures to predict the risk of 5 common chest pathologies. The experiments were conducted on three publicly available databases: CheXpert, ChestX-ray14, and MIMIC Chest Xray JPG. The results show the internal performance of each of the 5 pathologies outperformed external performance on both of the models. Moreover, our strategy of exposing the models to a mix of different datasets during the training phase helps to improve model performance on the external dataset.

[1]  Andrew Y. Ng,et al.  CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning , 2017, ArXiv.

[2]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  John D. Austin,et al.  Adaptive histogram equalization and its variations , 1987 .

[4]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[5]  Michael Grass,et al.  Comparison of Deep Learning Approaches for Multi-Label Chest X-Ray Classification , 2018, Scientific Reports.

[6]  Hongtao Lu,et al.  Using deep convolutional neural networks for multi-classification of thyroid tumor by histopathology: a large-scale pilot study. , 2019, Annals of translational medicine.

[7]  Yifan Yu,et al.  CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison , 2019, AAAI.

[8]  Roger G. Mark,et al.  MIMIC-CXR: A large publicly available database of labeled chest radiographs , 2019, ArXiv.

[9]  Ronald M. Summers,et al.  ChestX-ray: Hospital-Scale Chest X-ray Database and Benchmarks on Weakly Supervised Classification and Localization of Common Thorax Diseases , 2019, Deep Learning and Convolutional Neural Networks for Medical Imaging and Clinical Informatics.

[10]  David F. Steiner,et al.  Chest Radiograph Interpretation with Deep Learning Models: Assessment with Radiologist-adjudicated Reference Standards and Population-adjusted Evaluation. , 2019, Radiology.

[11]  Paolo Napoletano,et al.  Benchmark Analysis of Representative Deep Neural Network Architectures , 2018, IEEE Access.

[12]  Marcus A. Badgeley,et al.  Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study , 2018, PLoS medicine.

[13]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[14]  Imon Banerjee,et al.  Beyond the Artificial Intelligence Hype: What Lies Behind the Algorithms and What We Can Achieve. , 2020, Journal of thoracic imaging.

[15]  Ahmed Hosny,et al.  Artificial intelligence in radiology , 2018, Nature Reviews Cancer.

[16]  S. Park,et al.  Design Characteristics of Studies Reporting the Performance of Artificial Intelligence Algorithms for Diagnostic Analysis of Medical Images: Results from Recently Published Papers , 2019, Korean journal of radiology.