Application of artificial neural networks for reduction of false-positive detections in digital chest radiographs
- PMID: 8130511
- PMCID: PMC2248546
Application of artificial neural networks for reduction of false-positive detections in digital chest radiographs
Abstract
A methodology based on the fuzzy set theory and the convolution neural network (CNN) architecture is proposed to tackle the problem of reducing false-positive rate in automatic lung nodule detection. The CNN which simulates human visual mechanism was trained by a supervised back-propagation algorithm based on fuzzy membership functions. The training and testing database consists of image blocks (each 32 x 32 pixels) of suspected lung nodule areas (nodule candidates) which were generated from our pre-scanning program [1]. A linguistic label was assigned to each nodule candidate of the training set, then the label was converted to a membership value through a pre-defined membership function and used as teaching signal (desired outputs) during the network learning. Before the nodule candidate was fed to the network input, it was pre-processed to reduce the complex background noise and the contrast discrepancy resulted from film development. During the network testing phase, a defuzzification process was applied to decipher the trained network's output triggered by the nodule candidate in the testing set. Finally, a Receiver Operating Characteristic (ROC) analysis was used to evaluate the CNN's performance based on the defuzzified output of the testing database. Preliminary results showed an average Az (the performance index) of 0.84 which is equivalent to 0.80 true-positive detection (sensitivity) with an average 2-3 false-positive detections per chest image.
Comment in
-
Computerized detection of pulmonary nodules in digital chest images: use of morphological filters in reducing false-positive detections.Med Phys. 1990 Sep-Oct;17(5):861-5. doi: 10.1118/1.596478. Med Phys. 1990. PMID: 2233573
-
Non-small-cell lung cancer: results of the New York screening program.Radiology. 1984 May;151(2):289-93. doi: 10.1148/radiology.151.2.6324279. Radiology. 1984. PMID: 6324279
-
Neural networks in radiology: an introduction and evaluation in a signal detection task.Med Phys. 1990 Mar-Apr;17(2):234-41. doi: 10.1118/1.596501. Med Phys. 1990. PMID: 2333049
-
Image feature analysis and computer-aided diagnosis in digital radiography. 3. Automated detection of nodules in peripheral lung fields.Med Phys. 1988 Mar-Apr;15(2):158-66. doi: 10.1118/1.596247. Med Phys. 1988. PMID: 3386584
Similar articles
-
A preliminary study on computerized lesion localization in MR mammography using 3D nMITR maps, multilayer cellular neural networks, and fuzzy c-partitioning.Med Phys. 2008 Jan;35(1):195-205. doi: 10.1118/1.2805477. Med Phys. 2008. PMID: 18293575
-
Automatic lung nodule detection using profile matching and back-propagation neural network techniques.J Digit Imaging. 1993 Feb;6(1):48-54. doi: 10.1007/BF03168418. J Digit Imaging. 1993. PMID: 8439583
-
The effects of physics-based data augmentation on the generalizability of deep neural networks: Demonstration on nodule false-positive reduction.Med Phys. 2019 Oct;46(10):4563-4574. doi: 10.1002/mp.13755. Epub 2019 Aug 27. Med Phys. 2019. PMID: 31396974
-
Detection of lung nodules in digital chest radiographs using artificial neural networks: a pilot study.J Digit Imaging. 1995 May;8(2):88-94. doi: 10.1007/BF03168131. J Digit Imaging. 1995. PMID: 7612706
-
Reduction of false positives in lung nodule detection using a two-level neural classification.IEEE Trans Med Imaging. 1996;15(2):206-17. doi: 10.1109/42.491422. IEEE Trans Med Imaging. 1996. PMID: 18215903
Cited by
-
Differentiation between nodules and end-on vessels using a convolution neural network architecture.J Digit Imaging. 1995 Aug;8(3):132-41. doi: 10.1007/BF03168087. J Digit Imaging. 1995. PMID: 7488656
-
Prediction of survival in surgical unresectable lung cancer by artificial neural networks including genetic polymorphisms and clinical parameters.J Clin Lab Anal. 2003;17(6):229-34. doi: 10.1002/jcla.10102. J Clin Lab Anal. 2003. PMID: 14614746 Free PMC article.
-
Deep learning in medical imaging and radiation therapy.Med Phys. 2019 Jan;46(1):e1-e36. doi: 10.1002/mp.13264. Epub 2018 Nov 20. Med Phys. 2019. PMID: 30367497 Free PMC article. Review.
-
Artificial neural networks: a prospective tool for the analysis of psychiatric disorders.J Psychiatry Neurosci. 1996 Jul;21(4):239-47. J Psychiatry Neurosci. 1996. PMID: 8754592 Free PMC article. Review.
-
Artificial Neural Networks in Lung Cancer Research: A Narrative Review.J Clin Med. 2023 Jan 22;12(3):880. doi: 10.3390/jcm12030880. J Clin Med. 2023. PMID: 36769528 Free PMC article. Review.
References
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical