Deep learning for precise diagnosis and subtype triage of drug-resistant tuberculosis on chest computed tomography

Abstract

Deep learning, transforming input data into target prediction through intricate network structures, has inspired novel exploration in automated diagnosis based on medical images. The distinct morphological characteristics of chest abnormalities between drug-resistant tuberculosis (DR-TB) and drug-sensitive tuberculosis (DS-TB) on chest computed tomography (CT) are of potential value in differential diagnosis, which is challenging in the clinic. Hence, based on 1176 chest CT volumes from the equal number of patients with tuberculosis (TB), we presented a Deep learning-based system for TB drug resistance identification and subtype classification (DeepTB), which could automatically diagnose DR-TB and classify crucial subtypes, including rifampicin-resistant tuberculosis, multidrug-resistant tuberculosis, and extensively drug-resistant tuberculosis. Moreover, chest lesions were manually annotated to endow the model with robust power to assist radiologists in image interpretation and the Circos revealed the relationship between chest abnormalities and specific types of DR-TB. Finally, DeepTB achieved an area under the curve (AUC) up to 0.930 for thoracic abnormality detection and 0.943 for DR-TB diagnosis. Notably, the system demonstrated instructive value in DR-TB subtype classification with AUCs ranging from 0.880 to 0.928. Meanwhile, class activation maps were generated to express a human-understandable visual concept. Together, showing a prominent performance, DeepTB would be impactful in clinical decision-making for DR-TB.

Keywords

computed tomography / deep learning / drug-resistant tuberculosis / multidrug-resistant tuberculosis / rifampicin-resistant tuberculosis

References

1	Global Tuberculosis Report 2023. Geneva: World Health Organization; 2023.
2	C Lange, K Dheda, D Chesov, et al. Management of drug-resistant tuberculosis. Lancet. 2019;394(10202):953-966.
3	AS Dean, O Tosas Auguet, P Glaziou, et al. 25 years of surveillance of drug-resistant tuberculosis: achievements, challenges, and way forward. Lancet Infect Dis. 2022;22(7):e191-e196.
4	Global Tuberculosis Report 2021. World Health Organization; 2021.
5	OS Pedersen, FB Holmgaard, MKD Mikkelsen, et al. Global treatment outcomes of extensively drug-resistant tuberculosis in adults: a systematic review and meta-analysis. J Infect. 2023;87(3):177-189.
6	TY Akalu, ACA Clements, HF Wolde, KA Alene. Prevalence of long-term physical sequelae among patients treated with multi-drug and extensively drug-resistant tuberculosis: a systematic review and meta-analysis. EClinicalMedicine. 2023;57:101900.
7	WHO consolidated guidelines on tuberculosis. Module 3: diagnosis—rapid diagnostics for tuberculosis detection. Geneva: World Health Organization; 2021.
8	J Domínguez, MJ Boeree, E Cambau, et al. Clinical implications of molecular drug resistance testing for Mycobacterium tuberculosis: a 2023 TBnet/RESIST-TB consensus statement. Lancet Infect Dis. 2023;23(4):e122-e137.
9	CJ Meehan, GA Goig, TA Kohl, et al. Whole genome sequencing of Mycobacterium tuberculosis: current standards and open issues. Nat Rev Micro. 2019;17(9):533-545.
10	N Moodley, K Velen, A Saimen, et al. Digital chest radiography enhances screening efficiency for pulmonary tuberculosis in primary health clinics in South Africa. Clin Infect Dis. 2022;74(9):1650-1658.
11	MJ Chung, KS Lee, WJ Koh, et al. Drug-sensitive tuberculosis, multidrug-resistant tuberculosis, and nontuberculous mycobacterial pulmonary disease in nonAIDS adults: comparisons of thin-section CT findings. Eur Radiol. 2006;16(9):1934-1941.
12	QS Song, CJ Zheng, KP Wang, et al. Differences in pulmonary nodular consolidation and pulmonary cavity among drug-sensitive, rifampicin-resistant and multi-drug resistant tuberculosis patients: a computerized tomography study with history length matched cases. J Thorac Dis. 2022;14(7):2522-2531.
13	N Cheng, S Wu, X Luo, et al. A comparative study of chest computed tomography findings: 1030 cases of drug-sensitive tuberculosis versus 516 cases of drug-resistant tuberculosis. Infect Drug Resist. 2021;14:1115-1128.
14	W Yu, W Tan, P Lu. Classification and imaging manifestations of drug-resistant pulmonary tuberculosis. Electron J Emerg Infect Dis. 2019;4(1):42-47.
15	S Kazemzadeh, J Yu, S Jamshy, et al. Deep learning detection of active pulmonary tuberculosis at chest radiography matched the clinical performance of radiologists. Radiology. 2023;306(1):124-137.
16	S Lee, JJ Yim, N Kwak, et al. Deep learning to determine the activity of pulmonary tuberculosis on chest radiographs. Radiology. 2021;301(2):435-442.
17	P Lakhani, B Sundaram. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology. 2017;284(2):574-582.
18	EJ Hwang, S Park, KN Jin, et al. Development and validation of a deep learning-based automatic detection algorithm for active pulmonary tuberculosis on chest radiographs. Clin Infect Dis. 2019;69(5):739-747.
19	C Yan, L Wang, J Lin, et al. A fully automatic artificial intelligence-based CT image analysis system for accurate detection, diagnosis, and quantitative severity evaluation of pulmonary tuberculosis. Eur Radiol. 2022;32(4):2188-2199.
20	P Rajpurkar, C O'Connell, A Schechter, et al. CheXaid: deep learning assistance for physician diagnosis of tuberculosis using chest x-rays in patients with HIV. npj Digit Med. 2020;3:115.
21	RL Draelos, D Dov, MA Mazurowski, et al. Machine-learning-based multiple abnormality prediction with large-scale chest computed tomography volumes. Med Image Anal. 2021;67:101857.
22	XW Gao, Y Qian. Prediction of multidrug-resistant TB from CT pulmonary images based on deep learning techniques. Mol Pharm. 2018;15(10):4326-4335.
23	S Jaeger, OH Juarez-Espinosa, S Candemir, et al. Detecting drug-resistant tuberculosis in chest radiographs. Int J Comput Assist Radiol Surg. 2018;13(12):1915-1925.
24	A Fedorov, R Beichel, J Kalpathy-Cramer, et al. 3D Slicer as an image computing platform for the Quantitative Imaging Network. Magn Reson Imaging. 2012;30(9):1323-1341.
25	IS Pradipta, LD Forsman, J Bruchfeld, E Hak, JW Alffenaar. Risk factors of multidrug-resistant tuberculosis: a global systematic review and meta-analysis. J Infect. 2018;77(6):469-478.
26	Y Balabanova, B Radiulyte, E Davidaviciene, et al. Risk factors for drug-resistant tuberculosis patients in Lithuania, 2002–2008. Eur Respir J. 2012;39(5):1266-1269.
27	Global Tuberculosis Report 2020. World Health Organization; 2020.
28	M Salahuddin, S Karanth, D Ocazionez, YMRM Estrada, SV Cherian. Clinical characteristics and etiologies of miliary nodules in the US: a single-center study. Am J Med. 2019;132(6):767-769.
29	J Yosinski, J Clune, AM Nguyen, TJ Fuchs, H Lipson, Understanding neural networks through deep visualization. ArXiv. 2015;abs/1506.06579.
30	WHO consolidated guidelines on tuberculosis. Module 4: treatment—drug-resistant tuberculosis treatment, 2022 update. Geneva: World Health Organization; 2022.
31	Y Zhao, S Xu, L Wang, et al. National survey of drug-resistant tuberculosis in China. N Engl J Med. 2012;366(23):2161-2170.
32	K Kliiman, A Altraja. Predictors of extensively drug-resistant pulmonary tuberculosis. Ann Intern Med. 2009;150(11):766-775.
33	N Ahmad, SD Ahuja, OW Akkerman, et al. Treatment correlates of successful outcomes in pulmonary multidrug-resistant tuberculosis: an individual patient data meta-analysis. Lancet. 2018;392(10150):821-834.
34	SS Shin, S Keshavjee, IY Gelmanova, et al. Development of extensively drug-resistant tuberculosis during multidrug-resistant tuberculosis treatment. Am J Respir Crit Care Med. 2010;182(3):426-432.
35	Y Li, Z Xu, X Lv, et al. Radiomics analysis of lung CT for multidrug resistance prediction in active tuberculosis: a multicentre study. Eur Radiol. 2023;33(9):6308-6317.
36	Y LeCun, Y Bengio, G Hinton. Deep learning. Nature. 2015;521(7553):436-444.
37	K Bera, N Braman, A Gupta, V Velcheti, A Madabhushi. Predicting cancer outcomes with radiomics and artificial intelligence in radiology. Nat Rev Clin Oncol. 2022;19(2):132-146.
38	K Zhang, X Liu, J Shen, et al. Clinically applicable AI system for accurate diagnosis, quantitative measurements, and prognosis of COVID-19 pneumonia using computed tomography. Cell. 2020;181(6):1423-1433.e1411.
39	B Ehteshami Bejnordi, M Veta, P Johannes van Diest, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA. 2017;318(22):2199-2210.
40	OJ Skrede, S De Raedt, A Kleppe, et al. Deep learning for prediction of colorectal cancer outcome: a discovery and validation study. Lancet. 2020;395(10221):350-360.
41	S Wang, H Yu, Y Gan, et al. Mining whole-lung information by artificial intelligence for predicting EGFR genotype and targeted therapy response in lung cancer: a multicohort study. Lancet Digit Health. 2022;4(5):e309-e319.
42	HY Zhou, Y Yu, C Wang, et al. A transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics. Nat Biomed Eng. 2023;7(6):743-755.
43	G Wang, X Liu, J Shen, et al. A deep-learning pipeline for the diagnosis and discrimination of viral, non-viral and COVID-19 pneumonia from chest X-ray images. Nat Biomed Eng. 2021;5(6):509-521.
44	C Wang, J Ma, J Shao, et al. Non-invasive measurement using deep learning algorithm based on multi-source features fusion to predict PD-L1 expression and survival in NSCLC. Front Immunol. 2022;13:828560.
45	J Xue, J Li, D Sun, et al. Functional evaluation of intermediate coronary lesions with integrated computed tomography angiography and invasive angiography in patients with stable coronary artery disease. J Transl Int Med. 2022;10(3):255-263.
46	C Wang, J Ma, S Zhang, et al. Development and validation of an abnormality-derived deep-learning diagnostic system for major respiratory diseases. npj Digit Med. 2022;5(1):124.
47	Y Zhou, X Xu, L Song, et al. The application of artificial intelligence and radiomics in lung cancer. Precis Clin Med. 2020;3(3):214-227.
48	S Liang, J Ma, G Wang, et al. The application of artificial intelligence in the diagnosis and drug resistance prediction of pulmonary tuberculosis. Front Med (Lausanne). 2022;9:935080.
49	J Shao, J Feng, J Li, et al. Novel tools for early diagnosis and precision treatment based on artificial intelligence. Chin Med J Pulm Crit Care Med. 2023;1(3):148-160.
50	ZZ Qin, S Ahmed, MS Sarker, et al. Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms. Lancet Digit Health. 2021;3(9):e543-e554.
51	FA Khan, A Majidulla, G Tavaziva, et al. 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 Digit Health. 2020;2(11):e573-e581.
52	MR Farhat, R Sultana, O Iartchouk, et al. Genetic determinants of drug resistance in Mycobacterium tuberculosis and their diagnostic value. Am J Respir Crit Care Med. 2016;194(5):621-630.
53	ML Chen, A Doddi, J Royer, et al. Beyond multidrug resistance: leveraging rare variants with machine and statistical learning models in Mycobacterium tuberculosis resistance prediction. EBioMedicine. 2019;43:356-369.
54	Y Yang, TM Walker, S Kouchaki, et al. An end-to-end heterogeneous graph attention network for Mycobacterium tuberculosis drug-resistance prediction. Brief Bioinform. 2021;22(6):bbab299.
55	Y Yang, TM Walker, AS Walker, et al. DeepAMR for predicting co-occurrent resistance of Mycobacterium tuberculosis. Bioinformatics. 2019;35(18):3240-3249.
56	M Karki, K Kantipudi, H Yu, Identifying drug-resistant tuberculosis in chest radiographs: evaluation of CNN architectures and training strategies. 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC); 2021:2964-2967.
57	E Skoura, A Zumla, J Bomanji. Imaging in tuberculosis. Int J Infect Dis. 2015;32:87-93.
58	Q Du, S Liang, J Guo. Automatic diagnose of drug-resistance tuberculosis from CT images based on deep neural networks. In: Fang L, Povey D, Zhai G, Mei T, Wang R, eds. Artificial Intelligenc. Springer Nature Switzerland; 2022:256-267. Springer.
59	K Weiss, TM Khoshgoftaar, D Wang. A survey of transfer learning. J Big Data. 2016;3(1):9.
60	P Rajpurkar, E Chen, O Banerjee, EJ Topol. AI in health and medicine. Nat Med. 2022;28(1):31-38.
61	JE van Engelen, HH Hoos. A survey on semi-supervised learning. Mach Learn. 2020;109(2):373-440.
62	S Ruder, An overview of multi-task learning in deep neural networks. ArXiv. 2017;abs/1706.05098.
63	C Shorten, TM Khoshgoftaar. A survey on image data augmentation for deep learning. J Big Data. 2019;6:1-48.
64	F Liu, Y Tian, Y Chen, et al. ACPL: anti-curriculum pseudo-labelling for semi-supervised medical image classification. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2022:20665-20674.
65	E Arazo, D Ortego, P Albert, NE O'Connor, K McGuinness, Pseudo-labeling and confirmation bias in deep semi-supervised learning. 2020 International Joint Conference on Neural Networks (IJCNN); 2020:1-8.
66	S Ji, M Yang, K Yu. 3D convolutional neural networks for human action recognition. IEEE Trans Pattern Anal Mach Intell. 2013;35(1):221-231.
67	C Szegedy, V Vanhoucke, S Ioffe, J Shlens, Z Wojna, Rethinking the inception architecture for computer vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016:2818-2826.
68	G Huang, Z Liu, LVD Maaten, KQ Weinberger, Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2017:2261-2269.
69	K Simonyan, A Zisserman, Very deep convolutional networks for large-scale image recognition. CoRR. 2014, abs/1409.1556.
70	K He, X Zhang, S Ren, J Sun, Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016:770-778.
71	K Hara, H Kataoka, Y Satoh, Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and imageNet?2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition; 2018:6546-6555.
72	Y Xie, Y Xia, J Zhang, et al. Knowledge-based collaborative deep learning for benign-malignant lung nodule classification on chest CT. IEEE Trans Med Imaging. 2019;38(4):991-1004.
73	P Sedgwick. How to read a receiver operating characteristic curve. BMJ. 2015;350:h2464.
74	M Benary, XD Wang, M Schmidt, et al. Leveraging large language models for decision support in personalized oncology. JAMA Netw Open. 2023;6(11):e2343689.