Abstract
Aim
We propose a novel graph rank-based average pooling neural network (GRAPNN) to detect secondary pulmonary tuberculosis patients via chest CT imaging.
Methods
First, we propose a novel rank-based pooling neural network (RAPNN) to learn the individual image-level features from chest CT images. Second, we integrate the graph convolutional network (GCN), which learns relation-aware representation among the batch of chest CT images, to RAPNN. Third, we build a novel Graph RAPNN (GRAPNN) model based on the previous integration via k-means clustering and k-nearest neighbors’ algorithm. Besides, an improved data augmentation is utilized to handle overfitting problem. Grad-ACM is used to make this GRAPNN model explainable.
Results
This proposed GRAPNN method is compared with seven state-of-the-art algorithms. The results showed GRAPNN model yields the best performances with a sensitivity of 94.65%, a specificity of 95.12%, a precision of 95.17%, an accuracy of 94.88%, and an F1 score of 94.87%.
Conclusions
Our GRAPNN is superior to other seven state-of-the-art approaches. The explainable mechanism in our method can identify the lesions of important lung parts (tuberculosis cavities and surrounding small lesions) for transparent decision.
References
Akhtar N, Ragavendran U (2020) Interpretation of intelligence in CNN-pooling processes: a methodological survey. Neural Comput Appl 32(3):879–898
Bagci U, Kubler A, Luna B, Jain S, Bishai WR, Mollura DJ (2013) Computer-aided detection and quantification of cavitary tuberculosis from CT scans. Med Phys 40(11):14
Bhati S, Kumar V, Singh S, Singh J (2020) Synthesis, characterization, antimicrobial, anti-tubercular, antioxidant activities and docking simulations of derivatives of 2-(pyridin-3-yl)-1H-benzo d imidazole and 1,3,4-oxadiazole analogy. Lett Drug Des Discov 17(8):1047–1059
Giacomelli IL, Neto RS, Marchiori E, Pereira M, Hochhegger B (2018) Chest X-ray and chest CT findings in patients diagnosed with pulmonary tuberculosis following solid organ transplantation: a systematic review. J Bras Pneumol 44(2):161–166
Glasmachers T (2017) Limits of end-to-end learning. Proc Mach Learn Res 77:17–32
Han J, Hou S-M (2019) Multiple sclerosis detection via wavelet entropy and feedforward neural network trained by adaptive genetic algorithm. Lect Notes Comput Sci 11507:87–97
Iliyasu G, Mohammad AB, Yakasai AM, Dayyab FM, Oduh J, Habib AG (2018) Gram-negative bacilli are a major cause of secondary pneumonia in patients with pulmonary tuberculosis: evidence from a cross-sectional study in a tertiary hospital in Nigeria. Trans R Soc Trop Med Hyg 112(5):252–254
James-Reynolds C, Currie E, Gao XHW (2020) Analysis of tuberculosis severity levels from CT pulmonary images based on enhanced residual deep learning architecture. Neurocomputing 392:233–244
Jiang YY (2017) Cerebral micro-bleed detection based on the convolution neural network with rank based average pooling. IEEE Access 5:16576–16583
Jiang Y, Zhao K, Xia K, Xue J, Zhou L, Ding Y, Qian P (2019) A novel distributed multitask fuzzy clustering algorithm for automatic MR brain image segmentation. J Med Syst 43(5):118
Jiang Y, Gu X, Wu D, Hang W, Xue J, Qiu S, Chin-Teng L (2020a) A novel negative-transfer-resistant fuzzy clustering model with a shared cross-domain transfer latent space and its application to brain CT image segmentation. IEEE/ACM Trans Comput Biol Bioinf. https://doi.org/10.1109/TCBB.2019.2963873
Jiang Y, Zhang Y, Lin C, Wu D, Lin C (2020b) EEG-based driver drowsiness estimation using an online multi-view and transfer tsk fuzzy system. IEEE Trans Intell Transp Syst. https://doi.org/10.1109/TITS.2020.2973673
Kaplan M, Kneifel C, Orlikowski V, Dorff J, Newton M, Howard A, Shinn D, Bishawi M, Chidyagwai S, Balogh P, Randles A (2020) Cloud computing for COVID-19: lessons learned from massively parallel models of ventilator splitting. Comput Sci Eng 22(6):37–47
Khan FA, Majidulla A, Tavaziva G, Nazish A, Abidi SK, Benedetti A, Menzies D, Johnston JC, Khan AJ, Saeed S (2020) Chest x-ray analysis with deep learning-based software as a triage test for pulmonary tuberculosis: a prospective study of diagnostic accuracy for culture-confirmed disease. Lancet Digital Health 2(11):E573–E581
Kundu S, Marzan M, Gan SH, Islam MA (2020) Prevalence of antibiotic-resistant pulmonary tuberculosis in bangladesh: a systematic review and meta-analysis. Antibiotics-Basel 9(10):21
Lee SW, Kim HY (2020) Stock market forecasting with super-high dimensional time-series data using ConvLSTM, trend sampling, and specialized data augmentation. Expert Syst Appl 161:20
Li, L. J., H. Y. Huang and X. Y. Jin (2018). AE-CNN Classification of Pulmonary Tuberculosis Based on CT images. Ninth International Conference on Information Technology in Medicine and Education, Hangzhou, China, IEEE. 39–42.
Luies L, du Preez I (2020) The echo of pulmonary tuberculosis: mechanisms of clinical symptoms and other disease-induced systemic complications. Clin Microbiol Rev 33(4):19
Moreno-Barea FJ, Jerez JM, Franco L (2020) Improving classification accuracy using data augmentation on small data sets. Expert Syst Appl 161:14
Nayak DR (2020) Diagnosis of secondary pulmonary tuberculosis by an eight-layer improved convolutional neural network with stochastic pooling and hyperparameter optimization. J Ambient Intell Human Comput. https://doi.org/10.1007/s12652-020-02612-9
Park S, Jin KN, Kim JI, Choi SY, Lee JH, Goo JM, Aum J, Yim JJ, Park CM, Kim DH, Kim DH, Woo S, Choi W, Hwang IP, Song YS, Lim J, Kim H, Wi JY, Oh SS, Kang MJ, Woo C (2019) Development and validation of a deep learning-based automatic detection algorithm for active pulmonary tuberculosis on chest radiographs. Clin Infect Dis 69(5):739–747
Rai DK, Alok, (2019) Clinico-radiological difference between primary and secondary MDR pulmonary tuberculosis. J Clin Diagn Res 13(3):OC08–OC010
Rajpurkar P, O’Connell C, Schechter A, Asnani N, Li JS, Kiani A, Ball RL, Mendelson M, Maartens G, van Hoving DJ, Griesel R, Ng AY, Boyles TH, Lungren MP (2020) CheXaid: deep learning assistance for physician diagnosis of tuberculosis using chest x-rays in patients with HIV. NPJ Digital Medicine 3(1):8
Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2020) Grad-CAM: visual explanations from deep networks via gradient-based localization. Int J Comput Vision 128(2):336–359
Shi ZL, Ye YD, Wu YP (2016) Rank-based pooling for deep convolutional neural networks. Neural Netw 83:21–31
Shi, J., R. Wang, Y. Zheng, Z. Jiang and L. Yu (2019). Graph Convolutional Networks for Cervical Cell Classification. Second MICCAI Workshop on Computational Pathology (COMPAT), Shenzhen, China, MICCAI.
Simonyan, K. and A. Zisserman (2015). Very deep convolutional networks for large-scale image recognition. International Conference on Learning Representations (ICLR), San Diego, CA, USA, Computational and Biological Learning Society. 1–14.
Tang, C. and E. Lee (2018). Hearing loss identification via wavelet entropy and combination of Tabu search and particle swarm optimization. 23rd International Conference on Digital Signal Processing (DSP), Shanghai, China, IEEE. 1–5.
Tani N, Kunimatsu Y, Sato I, Ogura Y, Hirose K, Takeda T (2020) Drug-induced interstitial lung disease associated with dasatinib coinciding with active tuberculosis. Respirol Case Rep 8(7):3
Tekchandani H, Verma S, Londhe N (2020) Performance improvement of mediastinal lymph node severity detection using GAN and Inception network. Comput Methods Programs Biomed 194:14
Wang S-H (2021) Covid-19 classification by FGCNet with deep feature fusion from graph convolutional network and convolutional neural network. Inf Fus 67:208–229
Xie YL, Wu ZY, Han X, Wang HY, Wu YF, Cui L, Feng J, Zhu ZH, Chen ZYL (2020) Computer-aided system for the detection of multicategory pulmonary tuberculosis in radiographs. J Healthc Eng 2020:12
Zheng LF, Wang Y, Hemanth DJ, Sangiah AK, Shi FQ (2019) Data augmentation on mice liver cirrhosis microscopic images employing convolutional neural networks and support vector machine. J Ambient Intell Human Comput 10(10):4023–4032
Zhou, B., A. Khosla, A. Lapedriza, A. Oliva and A. Torralba (2016). Learning Deep Features for Discriminative Localization. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, IEEE. 2921–2929.
Acknowledgement
This paper is partially supported by Royal Society International Exchanges Cost Share Award, UK (RP202G0230); Medical Research Council Confidence in Concept Award, UK (MC_PC_17171); Hope Foundation for Cancer Research, UK (RM60G0680); MINECO/JUNTA/FEDER, Spain/regional/Europe (RTI2018-098913-B100, CV2045250, A-TIC-080-UGR18); British Heart Foundation Accelerator Award, UK
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wang, SH., Govindaraj, V., Gorriz, J.M. et al. Explainable diagnosis of secondary pulmonary tuberculosis by graph rank-based average pooling neural network. J Ambient Intell Human Comput (2021). https://doi.org/10.1007/s12652-021-02998-0
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12652-021-02998-0