TX-CNN: Detecting tuberculosis in chest X-ray images using convolutional neural network
The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Abstract
In Low and Middle-Income Countries (LMICs), efforts to eliminate the Tuberculosis (TB) epidemic are challenged by the persistent social inequalities in health, the limited number of local healthcare professionals, and the weak healthcare infrastructure found in resource-poor settings. The modern development of computer techniques has accelerated the TB diagnosis process. In this paper, we propose a novel method using Convolutional Neural Network(CNN) to deal with unbalanced, less-category X-ray images. Our method improves the accuracy for classifying multiple TB manifestations by a large margin. We explore the effectiveness and efficiency of shuffle sampling with cross-validation in training the network and find its outstanding effect in medical images classification. We achieve an 85.68% classification accuracy in a large TB image dataset, surpassing any state-of-art classification accuracy in this area. Our methods and results show a promising path for more accurate and faster TB diagnosis in LMICs healthcare facilities.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 4×
“When training AlexNet, we use the standard 7-layer network structure[6], which is consist of five convolutional layers and two fully-connected layers.”
BackgroundMethodInfluentialImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
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 · cited 11×
“On the top of AlexNet/GoogLeNet, we place a softmax layer to get the score for each category.”
InfluentialGoing 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
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
A survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332 · cited 1×
“In medical image analysis[13, 14], researchers try various models to learn powerful features for tumor detection[15, 16], cancer diagnosis[17, 18] and illness prevention.”
BackgroundGlobal tuberculosis report (2014)
Gabbasova, L. A., & Who, E. R. E. (2014) · Cited by 12,702
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 · cited 4×
“Since the chest X-ray images are still not abundant for training large complex model, we use the pretrained model from ImageNet that are public available in Model Zoo among the Caffe[22] community and then finetune on our chest Xray image database.”
MethodInfluentialShin, 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
Deep learning in medical image analysis
Shen, D., Wu, G., & Suk, H.-I. (2017) · Annual Review of Biomedical Engineering · doi:10.1146/annurev-bioeng-071516-044442 · Cited by 4,968
Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
Tajbakhsh, N., Shin, J. Y., Gurudu, S. R., Hurst, R. T., Kendall, C. B., Gotway, M. B., & Liang, J. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2535302 · Cited by 3,277 · cited 2×
“In medical image analysis[13, 14], researchers try various models to learn powerful features for tumor detection[15, 16], cancer diagnosis[17, 18] and illness prevention.”
BackgroundMethodMitosis Detection in Breast Cancer Histology Images with Deep Neural Networks
Cireşan, D. C., Giusti, A., Gambardella, L. M., & Schmidhuber, J. (2013) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-40763-5_51 · Cited by 1,536 · cited 2×
“Comparing with general image applications[6, 7], deep learning models for medical images tend to be smaller[17], as the region-of-interest(ROI) are usually small.”
BackgroundShiraishi, J., Katsuragawa, S., Ikezoe, J., Matsumoto, T., Kobayashi, T., Komatsu, K.-I., Matsui, M., Fujita, H., Kodera, Y., & Doi, K. (2000) · American Journal of Roentgenology · doi:10.2214/ajr.174.1.1740071 · Cited by 1,004 · cited 2×
“Even though some databases like ImageCLEF, JSRT Digital Image Database[2] and ANODE Grand Challenge Database contain TB images, they are mostly focused on one or two TB manifestations(e.g, pulmonary nodule); 2) lacking high-performance computing system for accurate diagnosis by analyzing the chest X-ray images.”
BackgroundDeep convolutional neural networks for multi-modality isointense infant brain image segmentation
Zhang, W., Li, R., Deng, H., Wang, L., Lin, W., Ji, S., & Shen, D. (2015) · NeuroImage · doi:10.1016/j.neuroimage.2014.12.061 · Cited by 817 · cited 1×
“In medical image analysis[13, 14], researchers try various models to learn powerful features for tumor detection[15, 16], cancer diagnosis[17, 18] and illness prevention.”
BackgroundRelay Backpropagation for Effective Learning of Deep Convolutional Neural Networks
Shen, L., Lin, Z., & Huang, Q. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46478-7_29 · Cited by 421 · cited 1×
“Inspired by the previous work from [23], we propose a shuffle sampling technique to augment data.”
MethodX-ray Categorization and Retrieval on the Organ and Pathology Level, Using Patch-Based Visual Words
Avni, U., Greenspan, H., Konen, E., Sharon, M., & Goldberger, J. (2011) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2010.2095026 · Cited by 195 · cited 1×
“Another aspect is to explore the organ and pathology level for X-ray image categorization[10].”
BackgroundDeep Learning in Medical Image Analysis
(2021) · MDPI eBooks · doi:10.3390/books978-3-0365-1470-3 · Cited by 111
Detecting tuberculosis in radiographs using combined lung masks
Jaeger, S., Karargyris, A., Antani, S., & Thoma, G. (2012) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2012.6347110 · Cited by 106 · cited 2×
“The use of computer-aided chest radiography for TB screening and diagnosis[3, 4, 5] has been limited due to the modest sensitivity and specificity, and high inter- and intra-observer differences in reporting shapes of tuberculosis on radiographic images.”
BackgroundMethodCao, Y., Liu, C., Liu, B., Brunette, M. J., Zhang, N., Sun, T., Zhang, P., Peinado, J., Garavito, E. S., Garcia, L. L., et al. (2016) · 2016 IEEE First International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE) · doi:10.1109/chase.2016.18 · Cited by 104 · cited 1×
“Recent studies[16, 18, 21] show that using a pretrained model from ImageNet dataset, then finetune with a more specific dataset yield outstanding classification and detection results.”
MethodSelf-citationde Alcantara, M. F., Cao, Y., Liu, C., Liu, B., Brunette, M., Zhang, N., Sun, T., Zhang, P., Chen, Q., Li, Y., et al. (2017) · Smart Health · doi:10.1016/j.smhl.2017.04.003 · Cited by 69
Self-citationNovel coarse-to-fine dual scale technique for tuberculosis cavity detection in chest radiographs
Xu, T., Cheng, I., Long, R., & Mandal, M. K. (2013) · EURASIP Journal on Image and Video Processing · doi:10.1186/1687-5281-2013-3 · Cited by 61 · cited 2×
“The use of computer-aided chest radiography for TB screening and diagnosis[3, 4, 5] has been limited due to the modest sensitivity and specificity, and high inter- and intra-observer differences in reporting shapes of tuberculosis on radiographic images.”
BackgroundMethodDetermining features for discriminating PTB and normal lungs using phase congruency model
Rijal, O. M., Ebrahimian, H., & Noor, N. M. (2012) · IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI ...) · doi:10.1109/bhi.2012.6211583 · Cited by 19 · cited 1×
“The first aspect is the computer-aided screening and scoring algorithms using chest radiographic features for the TB diagnosis[3, 4, 5, 8, 9].”
Method
Cited by
Deep learning approaches for COVID-19 detection based on chest X-ray images
Ismael, A. M., & Şengür, A. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.114054 · Cited by 746
Application of deep learning for fast detection of COVID-19 in X-Rays using nCOVnet
Panwar, H., Gupta, P. K., Siddiqui, M. K., Morales-Menendez, R., & Singh, V. (2020) · Chaos, Solitons & Fractals · doi:10.1016/j.chaos.2020.109944 · Cited by 646
CoroDet: A deep learning based classification for COVID-19 detection using chest X-ray images
Hussain, E., Hasan, M., Rahman, M. A., Lee, I., Tamanna, T., & Parvez, M. Z. (2021) · Chaos, Solitons & Fractals · doi:10.1016/j.chaos.2020.110495 · Cited by 461
Deep Learning for Smart Healthcare—A Survey on Brain Tumor Detection from Medical Imaging
Arabahmadi, M., Farahbakhsh, R., & Rezazadeh, J. (2022) · Sensors · doi:10.3390/s22051960 · Cited by 253
Laçi, H., Sevrani, K., & Iqbal, S. (2025) · BMC Medical Imaging · doi:10.1186/s12880-025-01701-5 · Cited by 24
“An effective approach is the use of a pre-trained model to have a strong feature foundation and then fine-tuning it on the given dataset [95].”
Metadata
- Authors
- Liu, C., Cao, Y., Alcantara, M., Liu, B., Brunette, M., Peinado, J., & Curioso, W.
- Venue
- 2017 IEEE International Conference on Image Processing (ICIP)
- Publisher
- IEEE
- Published
- 2017-09
- Pages
- 2314-2318
- ISSN
- 1522-4880 (ISSN-L)
- OpenAlex
- W2794167658
- Cited by
- 173
- References
- 22
- FWCI
- 17.33
- Type
- conference paper
- Language
- en
- Open access
- closed
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.