Deep Learning at Chest Radiography: Automated Classification of Pulmonary Tuberculosis by Using Convolutional Neural Networks
The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
Purpose To evaluate the efficacy of deep convolutional neural networks (DCNNs) for detecting tuberculosis (TB) on chest radiographs. Materials and Methods Four deidentified HIPAA-compliant datasets were used in this study that were exempted from review by the institutional review board, which consisted of 1007 posteroanterior chest radiographs. The datasets were split into training (68.0%), validation (17.1%), and test (14.9%). Two different DCNNs, AlexNet and GoogLeNet, were used to classify the images as having manifestations of pulmonary TB or as healthy. Both untrained and pretrained networks on ImageNet were used, and augmentation with multiple preprocessing techniques. Ensembles were performed on the best-performing algorithms. For cases where the classifiers were in disagreement, an independent board-certified cardiothoracic radiologist blindly interpreted the images to evaluate a potential radiologist-augmented workflow. Receiver operating characteristic curves and areas under the curve (AUCs) were used to assess model performance by using the DeLong method for statistical comparison of receiver operating characteristic curves. Results The best-performing classifier had an AUC of 0.99, which was an ensemble of the AlexNet and GoogLeNet DCNNs. The AUCs of the pretrained models were greater than that of the untrained models (P < .001). Augmenting the dataset further increased accuracy (P values for AlexNet and GoogLeNet were .03 and .02, respectively). The DCNNs had disagreement in 13 of the 150 test cases, which were blindly reviewed by a cardiothoracic radiologist, who correctly interpreted all 13 cases (100%). This radiologist-augmented approach resulted in a sensitivity of 97.3% and specificity 100%. Conclusion Deep learning with DCNNs can accurately classify TB at chest radiography with an AUC of 0.99. A radiologist-augmented approach for cases where there was disagreement among the classifiers further improved accuracy. © RSNA, 2017
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Because AI-enabled diagnostic technology has made significant advances in radiology23,24, we recruited physicians with different levels of task expertise to perform a radiological task.”
From Do as AI say: susceptibility in deployment of clinical decision-aids (2021) · cites this paper as [24]
In the citing paper
“several studies have already been published in areas such as lesion detection [7], classification [8], segmentation [9], image reconstruction [10, 11], and natural language processing [12].”
From Convolutional neural networks: an overview and application in radiology (2018) · cites this paper as [7]
In the citing paper
“According to the results, the best area under the curve of receiver operating characteristic curves for detecting pulmonary tuberculosis from healthy cases was 0.99, which was obtained by ensemble of the AlexNet and GoogLeNet 2D-CNNs.”
From Convolutional neural networks: an overview and application in radiology (2018) · cites this paper as [7]
In the citing paper
“Four patient cohorts from one study90 provided contingency tables with raw diagnostic accuracy.”
From Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis (2021) · cites this paper as [90]
In the citing paper
“Reverse Transcription Polymerase chain reaction (RT-PCR) is the most used clinical screening method for the COVID-19 patients, which uses respiratory specimens for testing [5].”
From Can AI help in screening viral and COVID-19 pneumonia? (2020) · cites this paper as [5]
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
(2014) · Cited by 33,419
DeLong, E. R., DeLong, D. M., & Clarke-Pearson, D. L. (1988) · Biometrics · doi:10.2307/2531595 · Cited by 22,649
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077
Ensemble methods in machine learning
Dietterich, T. G. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-45014-9_1 · Cited by 8,408
The use of the area under the ROC curve in the evaluation of machine learning algorithms
Bradley, A. P. (1997) · Pattern Recognition · doi:10.1016/s0031-3203(96)00142-2 · Cited by 7,217
Shin, H.-C., Roth, H. R., Gao, M., Lu, L., Xu, Z., Nogues, I., Yao, J., Mollura, D., & Summers, R. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2528162 · Cited by 5,759
Research works printed but not linked: 9
- Jaeger S, 2013, Quant Imaging Med Surg, 3, 89
- Bar Y, 2015, Proceedings of SPIE: medical imaging 2015—computer-aided diagnosis, 9414
- Hua KL, 2015, Onco Targets Ther, 8, 2015
- Roth HR, 2015, Proceedings of SPIE: medical imaging 2015—image processing, 9413
- Hwang S, 2016, Proceedings of SPIE: medical imaging 2016—title, 9785
- Jaeger S, 2014, Quant Imaging Med Surg, 4, 475
- Fawcett T, 2004, Mach Learn, 31, 1
- Agresti A, 1998, Am Stat, 52, 119
- Srivastava N, 2014, J Mach Learn Res, 15, 1929
Cited by
Items 701–800 of 1,003
Deep learning prediction of sex on chest radiographs: a potential contributor to biased algorithms
Li, D., Lin, C. T., Sulam, J., & Yi, P. H. (2022) · Emergency Radiology · doi:10.1007/s10140-022-02019-3 · Cited by 27
“Transfer learning improves model performance, accelerates training, and reduces the demand for data [12], which is often a limiting factor in medical imaging research.”
BackgroundA nationwide survey on the perceptions of general surgeons on artificial intelligence
Voskens, F. J., Abbing, J. R., Ruys, A. T., Ruurda, J. P. H., & Broeders, I. A. M. J. (2022) · Artificial Intelligence Surgery · doi:10.20517/ais.2021.10 · Cited by 28
U-NetCTS: U-Net deep neural network for fully automatic segmentation of 3D CT DICOM volume
Dorgham, O. M., Naser, M. A., Ryalat, M. H., Hyari, A., Al-Najdawi, N. A., & Mirjalili, S. (2022) · Smart Health · doi:10.1016/j.smhl.2022.100304 · Cited by 23
A survey on artificial intelligence in pulmonary imaging
Saha, P. K., Nadeem, S. A., & Comellas, A. P. (2023) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1510 · Cited by 26
“Chest x-rays are used as the long-standing clinical standard for screening and diagnosis of various lung diseases (Gonz (cid:1) alez, Ash, et al., 2018; Hu et al., 2018; Lakhani & Sundaram, 2017; Ozturk et al., 2020; Panwar et al., 2020; Rajpurkar et al., 2017).”
MethodChoudhry, I. A., Iqbal, S., Alhussein, M. A., Qureshi, A. N., Aurangzeb, K., & Naqvi, R. A. (2024) · Expert Systems · doi:10.1111/exsy.13750 · Cited by 24
“In order to acquire an area under the curve (AUC) in the region of 0.94– 0.95, the authors (Lakhani and Sundaram 2017) utilised AlexNet and GoogLeNet neural networks, both with and without data augmentation, pre-training.”
InfluentialOhta, Y., Yunaga, H., Kitao, S., Fukuda, T., & Ogawa, T. (2019) · Radiology Artificial Intelligence · doi:10.1148/ryai.2019180061 · Cited by 20
Nobashi, T. W., Zacharias, C., Ellis, J. K., Ferri, V., Koran, M. E. I., Franc, B. L., Iagaru, A. H., & Davidzon, G. (2019) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-019-00289-x · Cited by 21
Kim, Y.-G., Cho, Y., Wu, C., Park, S., Jung, K.-H., Seo, J. B., Lee, H. J., Hwang, H. J., Lee, S. M., & Kim, N. (2019) · Scientific Reports · doi:10.1038/s41598-019-55373-7 · Cited by 26
Comparison of different machine learning approaches to detect femoral neck fractures in x-ray images
Açıcı, K., Sümer, E., & Beyaz, S. (2021) · Health and Technology · doi:10.1007/s12553-021-00543-9 · Cited by 20
McQuade, C., Kavanagh, D. O., O'Brien, C., Hunter, K., Nally, D., Hickie, C., Ward, E. V. M., & Torreggiani, W. C. (2021) · Clinical Imaging · doi:10.1016/j.clinimag.2021.05.015 · Cited by 21
Artificial intelligence and omics in malignant gliomas
Tambi, R., Zehra, B., Vijayakumar, A., Satsangi, D., Uddin, M. J., & Berdiev, B. K. (2024) · Physiological Genomics · doi:10.1152/physiolgenomics.00011.2024 · Cited by 25
A comprehensive review of AI methods in upper extremity/limb bone fracture detection
Pour, Z. M., & Berretti, S. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11296-6 · Cited by 18
Kawauchi, K., Hirata, K., Katoh, C., Ichikawa, S., Manabe, O., Kobayashi, K., Watanabe, S., Furuya, S., & Shiga, T. (2019) · Scientific Reports · doi:10.1038/s41598-019-43656-y · Cited by 21
The application of artificial intelligence to chest medical image analysis
Liu, F., Tang, J., Ma, J., Wang, C., Ha, Q., Yu, Y., & Zhou, Z. (2021) · Intelligent Medicine · doi:10.1016/j.imed.2021.06.004 · Cited by 22
Toward Drug-Target Interaction Prediction via Ensemble Modeling and Transfer Learning
Kao, P.-Y., Kao, S.-M., Huang, N.-L., & Lin, Y. (2021) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm52615.2021.9669729 · Cited by 28
“Ensembles have been proven to have better performance than any single model [20] in different applications including image classification [21], pulmonary tuberculosis diagnosis [22], [23], brain tumor segmentation [24]–[26], solar radiation”
BackgroundHan, D., He, T., Yu, Y., Guo, Y., Chen, Y., Duan, H., & Yu, N. (2022) · Academic Radiology · doi:10.1016/j.acra.2021.12.025 · Cited by 20
Detecting obstructive sleep apnea by craniofacial image–based deep learning
He, S., Su, H., Li, Y., Xu, W., Wang, X., & Han, D. (2022) · Sleep And Breathing · doi:10.1007/s11325-022-02571-9 · Cited by 21
“[14–16] Scaling up the dimension of ConvNets (width, depth, and resolution) is widely used to achieve better accuracy, but due to arbitrary scales, these factors often yield suboptimal accuracy and efficiency.”
BackgroundChest X-Ray Anomalous Object Detection and Classification Framework for Medical Diagnosis
Janjua, J. I., Khan, T. A., & Nadeem, M. (2022) · International Conference on Information Networking · doi:10.1109/icoin53446.2022.9687110 · Cited by 27
Automated evaluation of Tuberculosis using Deep Neural Networks
Le, T.-M., Nguyen, T.-B.-T., & Ngo, V. M. (2022) · EAI Endorsed Transactions on Industrial Networks and Intelligent Systems · doi:10.4108/eetinis.v8i30.478 · Cited by 21
“Paras Lakhani and Baskaran Sundaram [13] applied Deep Learning to an evaluation of the contemporary algorithms’ efficiency on four deidentified HIPAA-compliant datasets, including AlexNet [12] and”
MethodApplications of machine learning approaches to combat COVID-19: A survey
Tiwari, S. M., Doğan, O., Jabbar, M. A., Shandilya, S. K., Ortiz, F., Bajpai, S., & Banerjee, S. (2022) · Elsevier eBooks · doi:10.1016/b978-0-323-99878-9.00014-5 · Cited by 21
“These techniques are based on DL (Oh et al., 2020; To (cid:1) gac ¸ ar et al., 2020; Ucar and Korkmaz, 2020), while the applications of DL model are a challenging topic in the AI field in medical image processing and analysis (Kermany et al., 2018; Lakhani and Sundaram, 2017).”
Rudolph, J., Schachtner, B. M., Fink, N., Koliogiannis, V., Schwarze, V., Goller, S. S., Trappmann, L., Hoppe, B. F., Mansour, N., Fischer, M., et al. (2022) · Scientific Reports · doi:10.1038/s41598-022-16514-7 · Cited by 19
“During the past years, clinical applications of artificial intelligence (AI) algorithms have been increasingly brought into scientific focus since several AI systems have already successfully mimicked healthcare specialists’ diagnostic performance levels 10–18 .”
BackgroundAI and IoT Enabled Smart Hospital Management Systems
Gourisaria, M. K., Agrawal, R., Singh, V., Rautaray, S. S., & Pandey, M. (2022) · Studies in big data · doi:10.1007/978-981-19-5154-1_6 · Cited by 29
Kaothanthong, N., Limwattanayingyong, J., Silpa‐archa, S., Tadarati, M., Amphornphruet, A., Singhanetr, P., Lalitwongsa, P., Chantangphol, P., Amornpetchsathaporn, A., Chainakul, M., et al. (2023) · Diagnostics · doi:10.3390/diagnostics13020189 · Cited by 22
“Composed of multiple layers of artificial neural networks, DL led to a breakthrough in processing various important tasks in medicine, such as automated classification of tuberculosis on chest radiographs [7] or automated interpretation of echocardiography [8], with accuracies on par with medical experts in the field.”
BackgroundChou, Y.-B., Kale, A. U., Lanzetta, P., Aslam, T. M., Barratt, J., Danese, C., Eldem, B. M., Eter, N., Gale, R. P., Korobelnik, J., et al. (2023) · Current Opinion in Ophthalmology · doi:10.1097/icu.0000000000000979 · Cited by 24
“Uniting clinicians with AI systems has been proven to be synergistic, achieving better performance than either alone [27].”
BackgroundKaur, A., Kaur, L., & Singh, A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16292-y · Cited by 25
“The potential of DL for skin lesion classification and diabetic retinopathy screening, lymph node metastasis detection was demonstrated by Gulshan et al. (2016), Esteva et al. (2017), and Ehteshami Bejnordi et al. (2017) [10, 24, 32, 47].”
Xie, Y., Li, X., Chen, F., Wen, R., Jing, Y., Liu, C., & Wang, J. (2024) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims-23-878 · Cited by 26
“DCNNs have demonstrated their proficiency in accurately classifying skeletal structures and pinpointing site-specific fractures with expert-level precision (18-20).”
BackgroundDai, F., Liu, Q., Guo, Y., Xie, R., Wu, J., Deng, T., Zhu, H., Deng, L., & Li, S. (2024) · Oral Radiology · doi:10.1007/s11282-024-00739-5 · Cited by 23
“Therefore, we believed that the X-ray image features extracted were related to age and smoking. brought new vitality to image recognition [31].”
Multi-task Learning for Fine-Grained Eye Disease Prediction
Chelaramani, S., Gupta, M., Agarwal, V., Gupta, P. K., & Habash, R. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-41299-9_57 · Cited by 24
The Role and Promise of Artificial Intelligence in Medical Toxicology
Chary, M. A., Manini, A. F., Boyer, E. W., & Burns, M. M. (2020) · Journal of Medical Toxicology · doi:10.1007/s13181-020-00769-5 · Cited by 20
Rajpurkar, P., Joshi, A., Pareek, A., Ng, A. Y., & Lungren, M. P. (2021) · ACM Conference on Health, Inference, and Learning (CHIL) · doi:10.1145/3450439.3451876 · Cited by 23
“Chest X-ray models are developed and validated using digital X-rays with many deployment solutions relying on heavily integrated yet often disparate infrastructures [1, 12, 13, 17, 21, 25, 26].”
BackgroundPrimary clinical study of radiomics for diagnosing simple bone cyst of the jaw
Jiang, Z.-Y., Lan, T., Cai, W., & Tao, Q. (2021) · Dentomaxillofacial Radiology · doi:10.1259/dmfr.20200384 · Cited by 28
Cui, P., Zhao, S., & Chen, W. (2021) · Journal of Healthcare Engineering · doi:10.1155/2021/5578089 · Cited by 18
Liao, Q., Feng, H., Li, Y., Lai, X., Pan, J., Zhou, F., Zhou, L., & Chen, L. (2021) · Journal of X-Ray Science and Technology · doi:10.3233/xst-211019 · Cited by 27
Ahmed, S., Le, D., Son, T., Adejumo, T., Ma, G., & Yao, X. (2022) · Frontiers in Medicine · doi:10.3389/fmed.2022.864879 · Cited by 18
Development of a Deep Learning System to Detect Esophageal Cancer by Barium Esophagram
Zhang, P., She, Y., Gao, J., Feng, Z., Tan, Q., Min, X., & Xu, S. (2022) · Frontiers in Oncology · doi:10.3389/fonc.2022.766243 · Cited by 21
Wu, Y., Qi, S., Feng, J., Chang, R., Pang, H., Hou, J., Li, M., Wang, Y., Xia, S., & Qian, W. (2023) · Journal of Applied Biomedicine · doi:10.1016/j.bbe.2023.06.004 · Cited by 19
Chen, L., Li, X., Qin, Y., Li, M., Ma, Y., Wang, R., Xu, X., Yu, J., Lv, S., & Luo, H. (2023) · BMC Medical Imaging · doi:10.1186/s12880-023-01091-6 · Cited by 24
“Over time, deep learning has made significant progress in the diagnosis of lung diseases [6, 7], breast cancer [8], thyroid tumors [9], skin lesions [10], sarcopenia [11], meniscus tears [12], and other diseases.”
BackgroundEarly diagnosis and meta-agnostic model visualization of tuberculosis based on radiography images
Natarajan, S., Pradeepa, S., Arunachalam, R., Shanmuganathan, V., Dhiman, G., Chakrabarti, P., Chakrabarti, T., & Margala, M. (2023) · Scientific Reports · doi:10.1038/s41598-023-49195-x · Cited by 19
Gefter, W. B., Prokop, M., Seo, J. B., Raoof, S., Langlotz, C. P., & Hatabu, H. (2024) · Radiology · doi:10.1148/radiol.232778 · Cited by 24
Rudolph, J., Huemmer, C., Preuhs, A., Buizza, G., Hoppe, B. F., Dinkel, J., Koliogiannis, V., Fink, N., Goller, S. S., Schwarze, V., et al. (2024) · CHEST Journal · doi:10.1016/j.chest.2024.01.039 · Cited by 27
New Horizons of Artificial Intelligence in Medicine and Surgery
Luțenco, V., Țocu, G., Guliciuc, M., Moraru, M., Candussi, I.-L., Dănilă, D. M., Luțenco, V., Dimofte, F., Mihailov, O. M., & Mihailov, R. (2024) · Journal of Clinical Medicine · doi:10.3390/jcm13092532 · Cited by 22
“…tuberculosis, software analyzes lung In areas with high prevalence of pulmonary tuberculosis, software analyzes lung radiological images and gives results with very high sensitivity and specificity [10]. radiological images and gives results with very high sensitivity and speci fi city [10].”
BackgroundKim, J. S., Cho, Y., & Lim, T. H. (2019) · IEEE Access · doi:10.1109/access.2019.2923002 · Cited by 20
Efficient Pneumonia Detection for Chest Radiography Using ResNet-Based SVM
Eid, M. M., & Elawady, Y. H. (2021) · European Journal of Electrical Engineering and Computer Science · doi:10.24018/ejece.2021.5.1.268 · Cited by 21
“Despite the huge improvements in treatment and therapy, over two million children under 5 years of age die from pneumonia each year worldwide, rating nearly one in five under 5 deaths [1].”
BackgroundAuxiliary Diagnosis for COVID-19 with Deep Transfer Learning
Chen, H., Guo, S., Hao, Y., Fang, Y., Fang, Z., Wu, W., Liu, Z., & Li, S. (2021) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-021-00431-8 · Cited by 18
Pennig, L., Hoyer, U. C. I., Krauskopf, A., Shahzad, R., Jünger, S. T., Thiele, F. O., Laukamp, K. R., Grunz, J., Perkuhn, M., Schlamann, M., et al. (2021) · Neuroradiology · doi:10.1007/s00234-021-02697-9 · Cited by 21
“Given the increasing workload of radiology departments, DLMs and computer-aided detection algorithms represent a valuable assistance to clinicians to deal with the growing amount of data that need to be analyzed [16, 33, 34].”
BackgroundTsai, A. (2021) · Pediatric Radiology · doi:10.1007/s00247-021-05004-z · Cited by 20
“In the medical imaging arena, CNN has been developed for classification (pulmonary nodules [18] and liver masses [19]), segmentation (uterus [20], prostate [21] and liver [22]) and detection (pulmonary tuberculosis on chest radiographs [23] and breast cancer on mammograms [24]).”
MethodInception-based Deep Learning Architecture for Tuberculosis Screening using Chest X-rays
Das, D., Santosh, K., & Pal, U. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412748 · Cited by 18
“Similarly in [18], an ensemble of pre-trained AlexNet and GoogLeNet have been used, but on 4 combined datasets.”
MethodA Strong Baseline for Domain Adaptation and Generalization in Medical ImagingPreprint
Yao, L., Prosky, J., Covington, B., & Lyman, K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.01638 · Cited by 49
Classification of type of brain magnetic resonance images with deep learning technique
Sugimori, H., Hamaguchi, H., Fujiwara, T., & Ishizaka, K. (2021) · Magnetic Resonance Imaging · doi:10.1016/j.mri.2020.12.017 · Cited by 18
Tajima, S., Okamoto, Y., Kobayashi, T., Kiwaki, M., Sonoda, C., Kaori, T., Saito, H., Ishikawa, Y., & Takayoshi, S. (2022) · Journal of Oral and Maxillofacial Surgery Medicine and Pathology · doi:10.1016/j.ajoms.2022.02.004 · Cited by 23
Leng, H., Chen, C., Si, R., Chen, C., Qu, H., & Lv, X. (2022) · Journal of Raman Spectroscopy · doi:10.1002/jrs.6365 · Cited by 20
Transfer learning with NASNet-Mobile for Pneumonia X-ray classification
Naskinova, I. (2022) · Asian-European Journal of Mathematics · doi:10.1142/s1793557122502400 · Cited by 22
Dhruthi, R., Sreevalli, B. M., Kulkarni, S., Gudla, S., & Sandesh, B. J. (2024) · IEEE International Conference for Convergence in Technology (I2CT) · doi:10.1109/i2ct61223.2024.10543961 · Cited by 17
“Paras Lakhani and Baskaran Sundaram's study [2] assesses if deep convolutional neural networks (DCNNs) are useful for using chest radiographs to detect tuberculosis (TB).”
BackgroundImaging biomarkers and staging in IPF
Walsh, S. L. F. (2018) · Current Opinion in Pulmonary Medicine · doi:10.1097/mcp.0000000000000507 · Cited by 19
Feature Selection for Contour-based Tuberculosis Detection from Chest X-Ray Images
Afzali, A., Mofrad, F. B., & Pouladian, M. (2019) · National and International Iranian Conference on Biomedical Engineering (ICBME) · doi:10.1109/icbme49163.2019.9030395 · Cited by 16
Deep Learning in the Healthcare Industry: Theory and Applications
Shirazi, Z. A., de Souza, C. P. E., Kashef, R. F., & Rodrigues, F. F. (2020) · Advances in healthcare information systems and administration book series · doi:10.4018/978-1-7998-2581-4.ch010 · Cited by 21
Semi-supervised labelling of the femur in a whole-body post-mortem CT database using deep learning
Peña‐Solórzano, C. A., Albrecht, D. W., Bassed, R., Gillam, J., Harris, P. C., & Dimmock, M. (2020) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.103797 · Cited by 20
Xu, Y., Wu, P., Zhang, H., & Li, J. (2020) · Letters in Applied Microbiology · doi:10.1111/lam.13364 · Cited by 18
DeepCAT: Deep Computer-Aided Triage of Screening Mammography
Yi, P. H., Singh, D., Harvey, S. C., Hager, G. D., & Mullen, L. A. (2021) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-020-00407-0 · Cited by 19
Lung Opacity Pneumonia Detection with Improved Residual Networks
Latif, G., Anezi, F. Y. A., Sibai, F. N., & Alghazo, J. M. (2021) · Journal of Medical and Biological Engineering · doi:10.1007/s40846-021-00656-6 · Cited by 18
“With regards to the evaluation of deep convolutional neural networks (DCNN) for the detection of illnesses on chest radiographs for automated classification [15], a total of four datasets that contain 1007 chest radiograph images were used.”
BackgroundDataset shift assessment measures in monitoring predictive models
Becker, A., & Becker, J. (2021) · Procedia Computer Science · doi:10.1016/j.procs.2021.09.112 · Cited by 22
Zuo, T., Zheng, Y., He, L., Chen, T., Zheng, B., Zheng, S., You, J., Li, X., Liu, R., Bai, J., et al. (2021) · Frontiers in Oncology · doi:10.3389/fonc.2021.746750 · Cited by 19
Screening for Tuberculosis in Migrants: A Survey by the Global Tuberculosis Network
D'Ambrosio, L., Centis, R., Dobler, C., Tiberi, S., Matteelli, A., Denholm, J., Zenner, D., Al-Abri, S., Alyaquobi, F., Arbex, M., et al. (2021) · Antibiotics · doi:10.3390/antibiotics10111355 · Cited by 16
“The use of computeraided programs based on reading chest radiographs could overcome this limitation [42], with the technology becoming increasingly reliable [17].”
BackgroundLiu, L.-R., Hung-Wen, C., Huang, M., Huang, S.-T., Tsai, M., Chang, C., & Chang, K.-S. (2022) · Frontiers in Medicine · doi:10.3389/fmed.2022.893208 · Cited by 19
VGG-based BAPL Score Classification of 18F-Florbetaben Amyloid Brain PET
Kang, H. G., Kim, W.-G., Yang, G.-S., Kim, H., Jeong, J., Yoon, H.-J., Cho, K., Jeong, Y.-J., & Kang, D. (2018) · Journal of Experimental & Biomedical Sciences/Biomedical Science Letters · doi:10.15616/bsl.2018.24.4.418 · Cited by 17
Computer-Aided Detection of Lung Nodules in Chest X-Rays using Deep Convolutional Neural Networks
Uçar, M., & Uçar, E. (2019) · Sakarya University Journal of Computer and Information Sciences · doi:10.35377/saucis.02.01.538249 · Cited by 18
Artificial Intelligence: Knowledge and Attitude Among Lebanese Medical Students
Daher, O. A., Dabbousi, A. A., Chamroukh, R., Saab, A. Y., Al Ayoubi, A. R., & Salameh, P. (2024) · Cureus · doi:10.7759/cureus.51466 · Cited by 16
“Major news outlets have also discussed these issues, with some articles suggesting that algorithms might eventually surpass human radiologists in detecting pneumonia [22].”
Patra, R. C., Saritha, G., Raghuwanshi, G., Parthiban, P., & Ashok, V. (2023) · International Conference on Technological Advancements in Computational Sciences (ICTACS) · doi:10.1109/ictacs59847.2023.10390124 · Cited by 18
“The field of medical diagnosis has experienced a renaissance with the integration of DL. Lakhani and Sundaram (2017) introduced Convolutional Neural Networks (CNNs) as potent tools for diagnosing diabetic retinopathy.”
BackgroundHaixian, L., Shu, P., Zhao, L., Chunfeng, L., & Lun, L. (2025) · Frontiers in Oncology · doi:10.3389/fonc.2025.1576461 · Cited by 21
Li, H., He, L., Dudley, J. A., Maloney, T., Somasundaram, E., Brady, S. L., Parikh, N. A., & Dillman, J. R. (2020) · Pediatric Radiology · doi:10.1007/s00247-020-04854-3 · Cited by 17
“Indeed, a similar trend has been reported previously [25].”
BackgroundResultImage‐based deep learning in diagnosing the etiology of pneumonia on pediatric chest X‐rays
Longjiang, E., Zhao, B., Liu, H., Zheng, C., Song, X., Cai, Y., & Liang, H. (2020) · Pediatric Pulmonology · doi:10.1002/ppul.25229 · Cited by 19
Convolutional Neural Networks Model for Screening Tuberculosis Disease
Alawi, A. E. B., Al-basser, A., Sallam, A. A., Al-sabaeei, A., & Al-khateeb, H. (2021) · International Conference of Technology, Science and Administration (ICTSA) · doi:10.1109/ictsa52017.2021.9406520 · Cited by 17
“Paras Lakhani and Baskaran Sundaram [8] used two different types of Deep Convolution Neural Networks (DCNNs) for detecting TB in chest radiographs.”
MethodUnderstanding the Research Landscape of Deep Learning in Biomedical Science: Scientometric Analysis
Nam, S., Kim, D., Jung, W., & Zhu, Y. (2022) · Journal of Medical Internet Research · doi:10.2196/28114 · Cited by 24
“In these studies, excluding the study by Hochreiter and Schmidhuber [135], whose research topic pertained to computer science, deep learning was used for diagnostic image analysis of various areas [12-14 ,136] and for”
MethodLee, S., Lee, H. W., Kim, H., Kim, D. K., Yim, J., Yoon, S. H., & Kwak, N. (2022) · CHEST Journal · doi:10.1016/j.chest.2022.06.018 · Cited by 16
Diagnosing Drowning in Postmortem CT Images Using Artificial Intelligence
Ogawara, T., Usui, A., Homma, N., & Funayama, M. (2022) · The Tohoku Journal of Experimental Medicine · doi:10.1620/tjem.2022.j097 · Cited by 19
Computer-Assisted Clinical Diagnosis and Treatment
Hamid, N., Portnoy, J. M., & Pandya, A. (2023) · Current Allergy and Asthma Reports · doi:10.1007/s11882-023-01097-8 · Cited by 18
“The first area of medicine to embrace AI has been the field of imaging where quick, accurate identification of entities such as strokes [12], brain tumors [13], and pulmonary disease [14] can have major implications on outcomes for patients.”
BackgroundA hybrid deep convolutional neural network model for improved diagnosis of pneumonia
Mann, P. S., Panchal, S., Singh, S., Saggu, G. S., & Gupta, K. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-09147-y · Cited by 20
AI-Driven Medical Imaging Platform: Advancements in Image Analysis and Healthcare Diagnosis
Eldin, W. S., & Kaboudan, A. (2023) · Journal of ACS Advances in Computer Science · doi:10.21608/asc.2023.328064 · Cited by 26
Image-based deep learning in diagnosing mycoplasma pneumonia on pediatric chest X-rays
Lan, X., Zhang, Y.-X., Yuan, W.-H., Shi, F., & Guo, W. (2024) · BMC Pediatrics · doi:10.1186/s12887-024-05204-0 · Cited by 18
Artificial intelligence in respiratory care
Karthika, M., Sreedharan, J. K., Shevade, M., Mathew, C. S., & Ray, S. (2024) · Frontiers in Digital Health · doi:10.3389/fdgth.2024.1502434 · Cited by 24
Artificial Intelligence and Chest Imaging. Will Deep Learning Make Us Smarter?
Labaki, W. W., & Han, M. K. (2017) · American Journal of Respiratory and Critical Care Medicine · doi:10.1164/rccm.201709-1879ed · Cited by 18
Liew, C. J. Y., Krishnaswamy, P., Cheng, L. T., Tan, C. H., Poh, A. C. C., & Lim, C. C. T. (2019) · Annals of the Academy of Medicine Singapore · doi:10.47102/annals-acadmedsg.v48n1p16 · Cited by 20
Predict or draw blood: An integrated method to reduce lab tests
Yu, L., Zhang, Q., Bernstam, E. V., & Jiang, X. (2020) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2020.103394 · Cited by 16
Chest X-Ray Abnormality Detection Based on SqueezeNet
Akpınar, K. N., Genc, S., & Karagöl, S. (2020) · International Conference on Electrical, Communication, and Computer Engineering (ICECCE) · doi:10.1109/icecce49384.2020.9179404 · Cited by 16
Early pleural effusion detection from respiratory diseases including COVID-19 via deep learning
Serte, S., & Serener, A. (2020) · Medical Technologies Congress (TIPTEKNO) · doi:10.1109/tiptekno50054.2020.9299300 · Cited by 17
“Lakhani [9] investigated the use of deep learning methods to detect tuberculosis on chest radiographs containing pleural effusion, miliary and cavitation.”
BackgroundArtificial neural networks as clinical decision support systems
Shafi, I., Ansari, S., Din, S., Jeon, G., & Paul, A. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6342 · Cited by 21
Automated recognition of objects and types of forceps in surgical images using deep learning
Bamba, Y., Ogawa, S., Itabashi, M., Kameoka, S., Okamoto, T., & Yamamoto, M. (2021) · Scientific Reports · doi:10.1038/s41598-021-01911-1 · Cited by 19
Jeong, T. S., Yee, G. T., Kim, K. G., Kim, Y. J., Lee, S. G., & Kim, W. K. (2022) · Journal of Korean Neurosurgical Society · doi:10.3340/jkns.2022.0062 · Cited by 16
Transfer learning on T1-weighted images for brain age estimation
Jiang, H., Guo, J., Du, H., Xu, J., & Qiu, B. (2019) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2019218 · Cited by 20
Kim, H., Park, C. M., & Goo, J. M. (2020) · European Radiology · doi:10.1007/s00330-019-06589-8 · Cited by 19
Deivayanai, V. C., Swaminaathan, P., Vickram, A. S., Saravanan, A., Bibi, S., Aggarwal, N., Kumar, V., Alhadrami, A. H., Mohammedsaleh, Z. M., Altalhi, R., et al. (2025) · International Journal of Surgery · doi:10.1097/js9.0000000000002481 · Cited by 23
DDA: A deep neural network-based cognitive system for IoT-aided dermatosis discrimination
Guo, K., Li, T., Huang, R., Kang, J., & Chi, T. (2018) · Ad Hoc Networks · doi:10.1016/j.adhoc.2018.07.014 · Cited by 15
Comprehensive Claims of AI for Healthcare Applications-Coherence Towards COVID-19
Satpathy, S., Mohanty, S. N., Chatterjee, J. M., & Swain, A. (2021) · Medical virology · doi:10.1007/978-981-15-7317-0_1 · Cited by 17
Simplify the Difficult: Artificial Intelligence and Cloud Computing in Healthcare
Yadav, S., Kaushik, A., & Sharma, S. (2021) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-030-73885-3_7 · Cited by 20
A deep learning-based framework for automatic detection of drug resistance in tuberculosis patients
Duwairi, R., & Melhem, A. (2023) · Egyptian Informatics Journal · doi:10.1016/j.eij.2023.01.002 · Cited by 22
A Lightweight, Rapid and Efficient Deep Convolutional Network for Chest X-Ray Tuberculosis Detection
Capellán-Martín, D., Gómez-Valverde, J. J., Bermejo-Peláez, D., & Ledesma‐Carbayo, M. J. (2023) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi53787.2023.10230500 · Cited by 18
“For the development of this study, we considered a total of 800 frontal CXR images from two public datasets [14]: • Montgomery County X-ray Set (MC): 138 frontal CXRs. 80 CXRs are non-TB and 58 are abnormal with manifestations of TB, including effussions and milary patterns.”
BackgroundMethodInfluentialChehade, A. H., Abdallah, N., Marion, J.-M., Hatt, M., Oueidat, M., & Chauvet, P. E. (2024) · SN Computer Science · doi:10.1007/s42979-024-02751-2 · Cited by 23
“Ensemble techniques have been applied to a variety of deep learning architectures, including AlexNet [60, 63, 64], VGGNet [63–70], GoogleNet [37, 60, 63, 64, 71], MobileNet [71–74], ResNet [4, 11, 14, 41, 50, 64, 74–78], and DenseNet [5, 6, 12, 15, 38, 78–86], with promising results in the task of…”
Shanmuga Priya, K., Mani, A. P., Geethalakshmi, S., & Yadav, S. (2024) · Cureus · doi:10.7759/cureus.60280 · Cited by 15
Bai, X., Duan, J., Li, B., Fu, S., Yin, W., Yang, Z., & Qu, Z. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124398 · Cited by 21
Evaluating artificial intelligence for medical imaging: a primer for clinicians
Keni, S. (2024) · British Journal of Hospital Medicine · doi:10.12968/hmed.2024.0312 · Cited by 20
Metadata
- Authors
- Lakhani, P., & Sundaram, B.
- Affiliations
- Thomas Jefferson University (US)
- Venue
- Radiology
- Published
- 2017-08
- Volume
- 284
- Issue
- 2
- Pages
- 574-582
- ISSN
- 0033-8419 (ISSN-L)
- 1527-1315
- OpenAlex
- W2608231518
- Cited by
- 1,775
- References
- 26
- Citations by year
- 2026: 108 · 2025: 147 · 2024: 180 · 2023: 199 · 2022: 246 · 2021: 272 · 2020: 284 · 2019: 188 · 2018: 127 · 2017: 22
- FWCI
- 130.34
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Radiology (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › COVID-19 diagnosis using AI
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Health Sciences › Medicine › Infectious Diseases › Tuberculosis Research and Epidemiology
- Keywords
- pulmonary tuberculosis, chest radiography, automatic classification, convolutional neural networks, tuberculosis detection
- MeSH terms
- Algorithms, Humans, Retrospective Studies, ROC Curve, Sensitivity and Specificity, Radiography, Thoracic, Tuberculosis, Pulmonary, Neural Networks, Computer
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.