Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Neural network–based computer-aided lung cancer detection

Neural network–based computer-aided lung cancer detection Recent advancements in the field of computing and the availability of medical databases have led to an immense enthusiasm among biomedical engineering researchers to explore the area of predictive analytics further. The main aim of our study is to develop a computer-aided diagnosis model for automatic detection of pulmonary nodules. Thresholding (multi-threshold) is applied to the computed tomography images to segment the suspicious nodules from other parts of the lungs. Six features extracted from the segmented image are later fed to the artificial neural network. Feedforward neural network–based classifier is trained and tested to predict cancer risk. Our model obtained 76% accuracy, 75% sensitivity, and 78% specificity. All these experiments have been carried out using Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (LIDC-IDRI). Moreover, the precision obtained is 85.71%, and F1 score is 79.9%. The results indicate that our model achieved 76% accuracy, 85.71% precision, 75% recall, and 79.9% F1 score. The proposed computer-aided diagnosis system obtained a 2.22% false positive rate, and it can assist clinicians in classifying the cancerous nodules. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Research on Biomedical Engineering Springer Journals

Neural network–based computer-aided lung cancer detection

Download PDF
15 pages

Loading next page...
 
/lp/springer-journals/neural-network-based-computer-aided-lung-cancer-detection-b5hnRg0ABA
Publisher
Springer Journals
Copyright
Copyright © Sociedade Brasileira de Engenharia Biomedica 2021
ISSN
2446-4732
eISSN
2446-4740
DOI
10.1007/s42600-021-00173-0
Publisher site
See Article on Publisher Site

Abstract

Recent advancements in the field of computing and the availability of medical databases have led to an immense enthusiasm among biomedical engineering researchers to explore the area of predictive analytics further. The main aim of our study is to develop a computer-aided diagnosis model for automatic detection of pulmonary nodules. Thresholding (multi-threshold) is applied to the computed tomography images to segment the suspicious nodules from other parts of the lungs. Six features extracted from the segmented image are later fed to the artificial neural network. Feedforward neural network–based classifier is trained and tested to predict cancer risk. Our model obtained 76% accuracy, 75% sensitivity, and 78% specificity. All these experiments have been carried out using Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (LIDC-IDRI). Moreover, the precision obtained is 85.71%, and F1 score is 79.9%. The results indicate that our model achieved 76% accuracy, 85.71% precision, 75% recall, and 79.9% F1 score. The proposed computer-aided diagnosis system obtained a 2.22% false positive rate, and it can assist clinicians in classifying the cancerous nodules.

Journal

Research on Biomedical Engineering – Springer Journals

Published: Dec 1, 2021

Keywords: Computer-aided diagnosis; Artificial intelligence; Lung cancer; LIDC-IDRI; Feature extraction; Segmentation

References

  • A comprehensive review of computer-aided diagnosis of pulmonary nodules based on computed tomography scans
    Cao, W; Wu, R; Cao, G; He, Z
  • Upper-bound on dose reduction in CT reconstruction for nodule detection
    De Man, R; Wang, G; Kalra, MK; Otrakji, A; Hsieh, S; Pelc, N
  • Fusion of quantitative image and genomic biomarkers to improve prognosis assessment of early stage lung cancer patients
    Emaminejad, N
  • Computer-assisted decision support system in pulmonary cancer detection and stage classification on CT images
    Masood, A
  • Lung cancer detection using nearest neighbour classifier
    Mohana, RM; Devi, RDH; Bai, A
  • A fast and efficient CAD system for improving the performance of malignancy level classification on lung nodules
    Wang, BIN; Si, S; Cui, E; Dou, S; Zhu, J
  • Texture feature extraction to improve accuracy of malignant and benign cancer detection on Ct-scan images
    Widodo, S; Rosyid, I; Faizuddin Bin Noor, M; Bin Ismail, R