AI-Assisted Tuberculosis Detection and Classification from Chest X-Rays Using a Deep Learning Normalization-Free Network Model

被引:39
作者
Acharya, Vasundhara [1 ]
Dhiman, Gaurav [2 ,3 ,4 ]
Prakasha, Krishna [5 ]
Bahadur, Pranshu [5 ]
Choraria, Ankit [5 ]
Sushobhitha, M. [6 ]
Sowjanya, J. [7 ]
Prabhu, Srikanth [1 ]
Chadaga, Krishnaraj [1 ]
Viriyasitavat, Wattana [8 ]
Kautish, Sandeep [9 ]
机构
[1] Manipal Acad Higher Educ, Manipal Inst Technol, Dept Comp Sci & Engn, Manipal 576104, India
[2] Lebanese Amer Univ, Dept Elect & Comp Engn, Byblos, Lebanon
[3] Graph Era Deemed Univ, Dept Comp Sci & Engn, Manipal 248002, India
[4] Univ Int Iberoamer, Dept Project Management, Campeche 24560, Mexico
[5] Manipal Acad Higher Educ, Manipal Inst Technol, Dept Informat Technol, Manipal, Karnataka, India
[6] Sri Dharmasthala Manjunatheshwara Inst Ayurveda &, Dept Shalakya Tantra, Bengaluru, India
[7] Sri Dharmasthala Manjunatheshwara Inst Ayurveda &, Dept Kayachikitsa, Bengaluru, India
[8] Chulalongkorn Univ, Fac Commerce & Accountancy, Dept Stat, Business Informat Technl Div, Bangkok, Thailand
[9] Janaki Coll Profess Studies, Janakpur, Nepal
关键词
RADIOGRAPHS;
D O I
10.1155/2022/2399428
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Tuberculosis (TB) is an airborne disease caused by Mycobacterium tuberculosis. It is imperative to detect cases of TB as early as possible because if left untreated, there is a 70% chance of a patient dying within 10 years. The necessity for supplementary tools has increased in mid to low-income countries due to the rise of automation in healthcare sectors. The already limited resources are being heavily allocated towards controlling other dangerous diseases. Modern digital radiography (DR) machines, used for screening chest X-rays of potential TB victims are very practical. Coupled with computer-aided detection (CAD) with the aid of artificial intelligence, radiologists working in this field can really help potential patients. In this study, progressive resizing is introduced for training models to perform automatic inference of TB using chest X-ray images. ImageNet fine-tuned Normalization-Free Networks (NFNets) are trained for classification and the Score-Cam algorithm is utilized to highlight the regions in the chest X-Rays for detailed inference on the diagnosis. The proposed method is engineered to provide accurate diagnostics for both binary and multiclass classification. The models trained with this method have achieved 96.91% accuracy, 99.38% AUC, 91.81% sensitivity, and 98.42% specificity on a multiclass classification dataset. Moreover, models have also achieved top-1 inference metrics of 96% accuracy and 98% AUC for binary classification. The results obtained demonstrate that the proposed method can be used as a secondary decision tool in a clinical setting for assisting radiologists.
引用
收藏
页数:19
相关论文
共 53 条
[1]  
Amato F., CHATBOTS MEET EHEALT
[2]  
Bharati S., 2021, INT J HYBRID INTELLI, V17, P71, DOI DOI 10.3233/HIS-210008
[3]  
Bharati S., ARTIF INTELL, V1, P1
[4]  
Bharati Subrato, 2020, Inform Med Unlocked, V20, P100391, DOI 10.1016/j.imu.2020.100391
[5]  
Brock A., 2021, arXiv
[6]  
Brock A, 2021, Arxiv, DOI [arXiv:2102.06171, 10.48550/arXiv.2102.06171]
[7]  
Chadaga Krishnaraj, 2022, Journal of Physics: Conference Series, V2161, DOI 10.1088/1742-6596/2161/1/012017
[8]  
Chan S., DERMATOL THER, V10
[9]   Role of Gist and PHOG Features in Computer-Aided Diagnosis of Tuberculosis without Segmentation [J].
Chauhan, Arun ;
Chauhan, Devesh ;
Rout, Chittaranjan .
PLOS ONE, 2014, 9 (11)
[10]  
Chen TL, 2021, Arxiv, DOI arXiv:2104.08215