A novel multiple-instance learning-based approach to computer-aided detection of tuberculosis on chest X-rays
- PMID: 25163057
- DOI: 10.1109/TMI.2014.2350539
A novel multiple-instance learning-based approach to computer-aided detection of tuberculosis on chest X-rays
Abstract
To reach performance levels comparable to human experts, computer-aided detection (CAD) systems are typically optimized following a supervised learning approach that relies on large training databases comprising manually annotated lesions. However, manually outlining those lesions constitutes a difficult and time-consuming process that renders detailedly annotated data difficult to obtain. In this paper, we investigate an alternative approach, namely multiple-instance learning (MIL), that does not require detailed information for optimization. We have applied MIL to a CAD system for tuberculosis detection. Only the case condition (normal or abnormal) was required during training. Based upon the well-known miSVM technique, we propose an improved algorithm that overcomes miSVM's drawbacks related to positive instance underestimation and costly iteration. To show the advantages of our MIL-based approach as compared with a traditional supervised one, experiments with three X-ray databases were conducted. The area under the receiver operating characteristic curve was utilized as a performance measure. With the first database, for which training lesion annotations were available, our MIL-based method was comparable to the supervised system ( 0.86 versus 0.88 ). When evaluating the remaining databases, given their large difference with the previous image set, the most appealing strategy was to retrain the CAD systems. However, since only the case condition was available, only the MIL-based system could be retrained. This scenario, which is common in real-world applications, demonstrates the better adaptation capabilities of the proposed approach. After retraining, our MIL-based system significantly outperformed the supervised one ( 0.86 versus 0.79 and 0.91 versus 0.85 , and p=0.0002 , respectively).
Similar articles
-
A comparative study of multiple instance learning methods for cancer detection using T-cell receptor sequences.Comput Struct Biotechnol J. 2021 May 24;19:3255-3268. doi: 10.1016/j.csbj.2021.05.038. eCollection 2021. Comput Struct Biotechnol J. 2021. PMID: 34141144 Free PMC article. Review.
-
Multiple-Instance Learning for Medical Image and Video Analysis.IEEE Rev Biomed Eng. 2017;10:213-234. doi: 10.1109/RBME.2017.2651164. Epub 2017 Jan 10. IEEE Rev Biomed Eng. 2017. PMID: 28092576 Review.
-
On Combining Multiple-Instance Learning and Active Learning for Computer-Aided Detection of Tuberculosis.IEEE Trans Med Imaging. 2016 Apr;35(4):1013-24. doi: 10.1109/TMI.2015.2505672. Epub 2015 Dec 4. IEEE Trans Med Imaging. 2016. PMID: 26660889
-
A novel multiple instance learning method based on extreme learning machine.Comput Intell Neurosci. 2015;2015:405890. doi: 10.1155/2015/405890. Epub 2015 Feb 3. Comput Intell Neurosci. 2015. PMID: 25705220 Free PMC article.
-
Multiple-instance learning algorithms for computer-aided detection.IEEE Trans Biomed Eng. 2008 Mar;55(3):1015-21. doi: 10.1109/TBME.2007.909544. IEEE Trans Biomed Eng. 2008. PMID: 18334393
Cited by
-
AI for Detection of Tuberculosis: Implications for Global Health.Radiol Artif Intell. 2024 Mar;6(2):e230327. doi: 10.1148/ryai.230327. Radiol Artif Intell. 2024. PMID: 38197795 Free PMC article.
-
Microwave bone fracture diagnosis using deep neural network.Sci Rep. 2023 Oct 7;13(1):16957. doi: 10.1038/s41598-023-44131-5. Sci Rep. 2023. PMID: 37805642 Free PMC article.
-
Quantitative Chest X-ray Radiomics for Therapy Response Monitoring in Patients with Pulmonary Tuberculosis.Diagnostics (Basel). 2023 Sep 1;13(17):2842. doi: 10.3390/diagnostics13172842. Diagnostics (Basel). 2023. PMID: 37685380 Free PMC article.
-
Deep joint learning of pathological region localization and Alzheimer's disease diagnosis.Sci Rep. 2023 Jul 19;13(1):11664. doi: 10.1038/s41598-023-38240-4. Sci Rep. 2023. PMID: 37468538 Free PMC article.
-
Machine and Deep Learning for Tuberculosis Detection on Chest X-Rays: Systematic Literature Review.J Med Internet Res. 2023 Jul 3;25:e43154. doi: 10.2196/43154. J Med Internet Res. 2023. PMID: 37399055 Free PMC article.
MeSH terms
LinkOut - more resources
Full Text Sources
Medical
Miscellaneous