Analysis of tuberculosis severity levels from CT pulmonary images based on enhanced residual deep learning architecture

Abstract This research investigates the application of CT pulmonary images to the detection and characterisation of TB at five levels of severity, in order to monitor the efficacy of treatment. To contend with smaller datasets (i.e. in hundreds) and the characteristics of CT TB images in which abnormalities occupy only limited regions, a 3D block-based residual deep learning network (ResNet) coupled with injection of depth information (depth-ResNet) at each layer was implemented. Progress in evaluation has been accomplished in two ways. One is to assess the proposed depth-ResNet in prediction of severity scores and another is to analyse the probability of high severity of TB. For the former, delivered results are of 92.70 ± 5.97% and 67.15 ± 1.69% for proposed depth-ResNet and ResNet-50 respectively. For the latter, two additional measures are put forward, which are calculated using (1) the overall severity (1 to 5) probability, and (2) separate probabilities of both high severity (scores of 1 to 3) and low severity (scores of 4 and 5) respectively, when scores of 1 to 5 are mapped into initial probabilities of (0.9, 0.7, 0.5, 0.3, 0.2) respectively. As a result, these measures achieve the averaged accuracies of 75.88% and 85.29% for both methods respectively.

[1]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

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

[3]  Andrei Gabrielian,et al.  ImageCLEF 2018: Lesion-based TB-descriptor for CT Image Analysis , 2018, CLEF.

[4]  K. S. Lee,et al.  CT in adults with tuberculosis of the chest: characteristic findings and role in management. , 1995, AJR. American journal of roentgenology.

[5]  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.

[6]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Kyung Soo Lee,et al.  Pulmonary tuberculosis: up-to-date imaging and management. , 2008, AJR. American journal of roentgenology.

[8]  K. Doi,et al.  Development of a digital image database for chest radiographs with and without a lung nodule: receiver operating characteristic analysis of radiologists' detection of pulmonary nodules. , 2000, AJR. American journal of roentgenology.

[9]  Yu Qian,et al.  Application of Deep Learning Neural Network for Classification of TB lung CT Images based on Patches , 2017, CLEF.

[10]  Teresa Gonçalves,et al.  Texture Analysis from 3D Model and Individual Slice Extraction for Tuberculosis MDR Detection, Type Classification and Severity Scoring , 2018, CLEF.

[11]  Philipp Schaer,et al.  Experimental IR Meets Multilinguality, Multimodality, and Interaction , 2017, Lecture Notes in Computer Science.

[12]  Michael Riegler,et al.  Overview of ImageCLEF 2018: Challenges, Datasets and Evaluation , 2018, CLEF.

[13]  Xiaohong W. Gao,et al.  Prediction of multi-drug resistant TB from CT pulmonary Images based on deep learning techniques , 2018 .

[14]  D. McCauley,et al.  High resolution CT findings in miliary lung disease. , 1992, Journal of computer assisted tomography.

[15]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Andrew Zisserman,et al.  Two-Stream Convolutional Networks for Action Recognition in Videos , 2014, NIPS.

[17]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[18]  Xiaohong W. Gao,et al.  Classification of CT brain images based on deep learning networks , 2017, Comput. Methods Programs Biomed..

[19]  Victor Alves,et al.  Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images , 2016, IEEE Transactions on Medical Imaging.

[20]  Richard P. Wildes,et al.  Spatiotemporal Residual Networks for Video Action Recognition , 2016, NIPS.

[21]  Xiaohong W. Gao,et al.  Prediction of Multidrug-Resistant TB from CT Pulmonary Images Based on Deep Learning Techniques. , 2017, Molecular pharmaceutics.

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

[23]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

[24]  Stefan Conrad,et al.  Feature-Based Approach for Severity Scoring of Lung Tuberculosis from CT Images , 2018, CLEF.

[25]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[26]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[27]  Henning Müller,et al.  Texture-based Graph Model of the Lungs for Drug Resistance Detection, Tuberculosis Type Classification, and Severity Scoring: Participation in ImageCLEF 2018 Tuberculosis Task , 2018, CLEF.

[28]  Richard P. Wildes,et al.  Temporal Residual Networks for Dynamic Scene Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[30]  Ilaria Gori,et al.  Comparing and combining algorithms for computer-aided detection of pulmonary nodules in computed tomography scans: The ANODE09 study , 2010, Medical Image Anal..

[31]  N. Müller,et al.  Radiologic features of pulmonary tuberculosis: an assessment of 188 cases. , 1994, Canadian Association of Radiologists journal = Journal l'Association canadienne des radiologistes.

[32]  C. Lange,et al.  INVITED REVIEW SERIES: TUBERCULOSIS , 2010 .

[33]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.

[34]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[35]  Wei Li,et al.  A fused deep learning architecture for viewpoint classification of echocardiography , 2017, Inf. Fusion.