Determination of COPD severity from chest CT images using deep transfer learning network

POLAT Ö., ŞALK İ., DOĞAN Ö. T.

MULTIMEDIA TOOLS AND APPLICATIONS, cilt.81, sa.15, ss.21903-21917, 2022 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 81 Sayı: 15
  • Basım Tarihi: 2022
  • Doi Numarası: 10.1007/s11042-022-12801-7
  • Dergi Adı: MULTIMEDIA TOOLS AND APPLICATIONS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, FRANCIS, ABI/INFORM, Applied Science & Technology Source, Compendex, Computer & Applied Sciences, INSPEC, zbMATH
  • Sayfa Sayıları: ss.21903-21917
  • Anahtar Kelimeler: COPD severity classification, Convolutional neural networks, Transfer learning, Inception-V3, STATEMENT, DISEASE
  • Sivas Cumhuriyet Üniversitesi Adresli: Evet

Özet

The purpose of this study is to present a solution to the problem of detecting the severity of Chronic Obstructive Pulmonary Disease (COPD) from chest CT images using deep transfer learning network. The study has a novelty in terms of classifying the severity of COPD with machine learning methods for the first time in the literature. Transfer learning has been preferred because of its proven performance in image analysis and classification. In this study, a dataset containing a total of 1815 CT images from 121 patients with moderate, severe and very severe COPD was used. Lung parenchyma was first segmented from CT images using HSV color space thresholding. Then Inception-V3 model was trained and tested on the segmented image dataset for COPD severity classification. The tests were repeated 10 times. The proposed model was able to detect the severity level of COPD with an average accuracy of 96.79% and a maximum of 97.98%. The classification result proved that the severity of COPD can be classified with very high performance. Thus, the applied transfer learning is promising in medical sciences and can assist to radiologists in making quick and accurate decisions.