Fibro-CoSANet: pulmonary fibrosis prognosis prediction using a convolutional self attention network

Idiopathic pulmonary fibrosis (IPF) is a restrictive interstitial lung disease that causes lung function decline by lung tissue scarring. Although lung function decline is assessed by the forced vital capacity (FVC), determining the accurate progression of IPF remains a challenge. To address this challenge, we proposed Fibro-CoSANet, a novel end-to-end multi-modal learning based approach, to predict the FVC decline. Fibro-CoSANet utilized computed tomography images and demographic information in convolutional neural network frameworks with a stacked attention layer. Extensive experiments on the OSIC Pulmonary Fibrosis Progression Dataset demonstrated the superiority of our proposed Fibro-CoSANet by achieving new state-of-the-art modified Laplace log-likelihood score of −6.68. This network may benefit research areas concerned with designing networks to improve the prognostic accuracy of IPF. The source-code for Fibro-CoSANet is available at: https://github.com/zabir-nabil/Fibro-CoSANet.

[1]  Alexander Wong,et al.  Fibrosis-Net: A Tailored Deep Convolutional Neural Network Design for Prediction of Pulmonary Fibrosis Progression From Chest CT Images , 2021, Frontiers in Artificial Intelligence.

[2]  Zhuowen Tu,et al.  Aggregated Residual Transformations for Deep Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Han Zhang,et al.  Self-Attention Generative Adversarial Networks , 2018, ICML.

[4]  Joyce S Lee,et al.  A Multidimensional Index and Staging System for Idiopathic Pulmonary Fibrosis , 2012, Annals of Internal Medicine.

[5]  Bingbing Ni,et al.  Reinventing 2D Convolutions for 3D Images , 2019, IEEE Journal of Biomedical and Health Informatics.

[6]  A. Nicholson,et al.  Marginal decline in forced vital capacity is associated with a poor outcome in idiopathic pulmonary fibrosis , 2009, European Respiratory Journal.

[7]  Shudong Wang,et al.  Classification of Pathological Types of Lung Cancer from CT Images by Deep Residual Neural Networks with Transfer Learning Strategy , 2020, Open medicine.

[8]  Hemanth Kalluri,et al.  Lung Cancer Detection Based on CT Scan Images by Using Deep Transfer Learning , 2019, Traitement du Signal.

[9]  G. Rossi,et al.  Idiopathic pulmonary fibrosis: An update , 2015, Annals of medicine.

[10]  D. Lynch,et al.  Idiopathic Pulmonary Fibrosis: The Association between the Adaptive Multiple Features Method and Fibrosis Outcomes , 2017, American journal of respiratory and critical care medicine.

[11]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[12]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[13]  J. Gruden.  CT in Idiopathic Pulmonary Fibrosis: Diagnosis and Beyond. , 2016, AJR. American journal of roentgenology.

[14]  Ankush Ghosh,et al.  Prediction Analysis of Idiopathic Pulmonary Fibrosis Progression from OSIC Dataset , 2020, 2020 IEEE International Conference on Computing, Power and Communication Technologies (GUCON).

[15]  Ashish Vaswani,et al.  Stand-Alone Self-Attention in Vision Models , 2019, NeurIPS.

[16]  S. Beucher.  Use of watersheds in contour detection , 1979 .

[17]  Takeshi Johkoh,et al.  Diagnosis of Idiopathic Pulmonary Fibrosis. An Official ATS/ERS/JRS/ALAT Clinical Practice Guideline , 2018, American journal of respiratory and critical care medicine.

[18]  Jonathan G. Goldin,et al.  Prediction of progression in idiopathic pulmonary fibrosis using CT scans at baseline: A quantum particle swarm optimization - Random forest approach , 2019, Artif. Intell. Medicine.

[19]  A. Yuille,et al.  Annotated normal CT data of the abdomen for deep learning: Challenges and strategies for implementation. , 2019, Diagnostic and interventional imaging.

[20]  R. Kulkarni,et al.  Convolutional neural networks in medical image understanding: a survey , 2021, Evolutionary Intelligence.

[21]  Gene H. Golub,et al.  Singular value decomposition and least squares solutions , 1970, Milestones in Matrix Computation.

[22]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  M. Selman,et al.  Familial pulmonary fibrosis is the strongest risk factor for idiopathic pulmonary fibrosis. , 2011, Respiratory medicine.