Detection of Lung Cancer on Computed Tomography Using Artificial In-telligence Applications Developed by Deep Learning Methods and the Con-tribution of Deep Learning to the Classification of Lung Carcinoma


Aydın N., Çelik Ö., Aslan A. F. , Odabaş A., Dündar E., Şahin M. C.

CURRENT MEDICAL IMAGING, vol.17, no.9, pp.1137-1141, 2021 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 17 Issue: 9
  • Publication Date: 2021
  • Doi Number: 10.2174/1573405617666210204210500
  • Journal Name: CURRENT MEDICAL IMAGING
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Biotechnology Research Abstracts, EMBASE, MEDLINE
  • Page Numbers: pp.1137-1141
  • Keywords: Lung cancer, adenocarcinoma, deep learning, convolutional neural network, algorithm, computed tomography, TARGETED THERAPY
  • Eskisehir Osmangazi University Affiliated: Yes

Abstract

Background: Every year, lung cancer contributes to a high percentage deaths in the world. Early detection of lung cancer is important for its effective treatment, and non-invasive rapid methods are usually used for diagnosis. Introduction: In this study, we aimed to detect lung cancer using deep learning methods and deter-mine the contribution of deep learning to the classification of lung carcinoma using a convolutional neural network (CNN). Methods: A total of 301 patients diagnosed with lung carcinoma pathologies in our hospital were included in the study. In the thorax, Computed Tomography (CT) was performed for diagnostic pur-poses prior to the treatment. After tagging the section images, tumor detection, small and non-s-mall cell lung carcinoma differentiation, adenocarcinoma-squamous cell lung carcinoma differentia-tion, and adenocarcinoma-squamous cell-small cell lung carcinoma differentiation were sequential-ly performed using deep CNN methods. Results: In total, 301 lung carcinoma images were used to detect tumors, and the model obtained with the deep CNN system exhibited 0.93 sensitivity, 0.82 precision, and 0.87 F1 score in detect-ing lung carcinoma. In the differentiation of small cell-non-small cell lung carcinoma, the sensitivi-ty, precision and F1 score of the CNN model at the test stage were 0.92, 0.65, and 0.76, respective-ly. In the adenocarcinoma-squamous cancer differentiation, the sensitivity, precision, and F1 score were 0.95, 0.80, and 0.86, respectively. The patients were finally grouped as small cell lung carci-noma, adenocarcinoma, and squamous cell lung carcinoma, and the CNN model was used to deter-mine whether it could differentiate these groups. The sensitivity, specificity, and F1 score of this model were 0.90, 0.44, and 0.59, respectively, in this differentiation. Conclusion: In this study, we successfully detected tumors and differentiated between adenocarci-noma-squamous cell carcinoma groups with the deep learning method using the CNN model. Due to their non-invasive nature and the success of the deep learning methods, they should be integrat-ed into radiology to diagnose lung carcinoma.