LM-DNN: pre-trained DNN with LSTM and cross Fold validation for detecting viral pneumonia from chest CT

ABSTRACT

Some of the viruses may cause lung parenchyma and airway involvement. Usually, viral pneumonia causes ground-glass opacities, bilateral peripheral distribution, consolidation, vascular thickening, and reticular opacity. These features are common in COVID-19 rather than Non-Covid-19 viral pneumonia. However, in advanced cases, COVID-19 viral pneumonia may cause organising pneumonia and fibrosis of the lung. Atypical findings of Non-Covid-19 pneumonia have included central peripheral distribution, pleural effusion, lymphadenopathy, nodules, tree-in-bud opacities, and pneumothorax. Therefore, differentiating Non-Covid-19 pneumonia from COVID-19 pneumonia at chest computed tomography (CT) is necessary. In that case, CT scans of the thorax are one of the essential tools for early identification and future prognosis of viral pneumonia. We have proposed a Computer-Aided Diagnostic (CAD) system that can detect features of chest CT using a Deep Neural Network (DNN) with Long Short-Term Memory (LSTM). Transfer learning using pre-trained DNN models (ResNet50, VGG19, InceptionV3, Xception, DenseNet121, and VGG16) is applied to retain both high-level and low-level features effectively. The deep features are passed to the LSTM layer. The LSTM is utilised as a classifier and detects long short-term dependencies. The proposed method employs a hybrid DNN-LSTM network for automatic detection to take advantage of the uniqueness of the two models. The proposed models are trained with common and different features present in the chest CT of COVID-19 and Non-Covid-19 viral pneumonia. The 5-fold cross-validation (CV) method validated and tested the proposed model. The proposed DNN model’s performance is quite improved with LSTM and CV. As a result, the proposed LM-DNN (VGG16+LSTM+CV) model has achieved the classification test accuracy of 91.58% and specificity of 93.86%, which offers superior performance with state-of-the-art. Also, the DenseNet121+LSTM+CV model has reached the classification test accuracy of 90.1% and sensitivity of 92%.

KEYWORDS:

• Deep Neural Network
• LSTM
• Chest CT
• Viral Pneumonia
• COVID-19

Acknowledgement

The authors are grateful to Dr. Biswarup Goswami (Respiratory Medicine, Health and Family Welfare Department, Government of West Bengal, India) for his valuable suggestions, medical assessment, and feasibility checking.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Sanjib Saha

Sanjib Saha is pursuing PhD in the Department of Computer Science and Engineering at National Institute of Technology, Durgapur, India. He is an Assistant Professor in the Department of Computer Science and Engineering at Dr. B. C. Roy Engineering College, Durgapur, India. His main research work focuses on Machine Learning, Deep Learning, and Medical Image Classification, Segmentation & Registration.

Debashis Nandi

Debashis Nandi is a Professor in the Department of Computer Science and Engineering at National Institute of Technology, Durgapur, India. He received PhD from Indian Institute of Technology, Kharagpur, India. He has more than 35 research publications. He has supervised more than 12 doctoral students. His main research work focuses on Image and Signal Processing, Medical Image Analysis, and Chaos & Information Security.