An efficient end-to-end deep neural network for interstitial lung diseaserecognition and classification


Junayed M. S., Jeny A. A., Islam M. B., Ahmed I., Shah A. S.

TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, cilt.30, ss.1235-1250, 2022 (SCI-Expanded) identifier identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 30
  • Basım Tarihi: 2022
  • Doi Numarası: 10.55730/1300-0632.3846
  • Dergi Adı: TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Applied Science & Technology Source, Compendex, Computer & Applied Sciences, INSPEC, TR DİZİN (ULAKBİM)
  • Sayfa Sayıları: ss.1235-1250
  • Anahtar Kelimeler: Interstitial Lung Diseases, Pattern Classification, Pattern Recognition, CNN, CT Scan Image Analysis, COMPUTED-TOMOGRAPHY SCANS, ALGORITHMS
  • Yıldız Teknik Üniversitesi Adresli: Evet

Özet

The automated Interstitial Lung Diseases (ILDs) classification technique is essential for assisting clinicians during the diagnosis process. Detecting and classifying ILDs patterns is a challenging problem. This paper introduces an end-to-end deep convolution neural network (CNN) for classifying ILDs patterns. The proposed model comprises four convolutional layers with different kernel sizes and Rectified Linear Unit (ReLU) activation function, followed by batch normalization and max-pooling with a size equal to the final feature map size well as four dense layers. We used the ADAM optimizer to minimize categorical cross-entropy. A dataset consisting of 21328 image patches of 128 CT scans with five classes is taken to train and assess the proposed model. A comparison study showed that the presented model outperformed pre-trained CNNs and five-fold cross-validation on the same dataset. For ILDs pattern classification, the proposed approach achieved the accuracy scores of 99.09% and the average F score of 97.9% that outperforms three pre-trained CNNs. These outcomes show that the proposed model is relatively state-of-the-art in precision, recall, f score, and accuracy.