Next Article in Journal
Happy Cow or Thinking Pig? WUR Wolf—Facial Coding Platform for Measuring Emotions in Farm Animals
Previous Article in Journal
SLASSY—An Assistance System for Performing Design for Manufacturing in Sheet-Bulk Metal Forming: Architecture and Self-Learning Aspects
Article

COVID-19 Diagnosis from Chest CT Scans: A Weakly Supervised CNN-LSTM Approach

1
Artificial Intelligence and Data Analytics, KoçDigital with BCG, Istanbul 34700, Turkey
2
Department of Radiology, VKF American Hospital, Istanbul 34365, Turkey
*
Author to whom correspondence should be addressed.
Academic Editors: Tianhua Chen, Pan Su and Yinghua Shen
AI 2021, 2(3), 330-341; https://doi.org/10.3390/ai2030020
Received: 21 May 2021 / Revised: 28 June 2021 / Accepted: 3 July 2021 / Published: 12 July 2021
(This article belongs to the Special Issue AI for Intelligent Healthcare)
Advancements in deep learning and availability of medical imaging data have led to the use of CNN-based architectures in disease diagnostic assisted systems. In spite of the abundant use of reverse transcription-polymerase chain reaction-based tests in COVID-19 diagnosis, CT images offer an applicable supplement with their high sensitivity rates. Here, we study the classification of COVID-19 pneumonia and non-COVID-19 pneumonia in chest CT scans using efficient deep learning methods to be readily implemented by any hospital. We report our deep network framework design that encompasses Convolutional Neural Networks and bidirectional Long Short Term Memory architectures. Our study achieved high specificity (COVID-19 pneumonia: 98.3%, non-COVID-19 pneumonia: 96.2% Healthy: 89.3%) and high sensitivity (COVID-19 pneumonia: 84.0%, non-COVID-19 pneumonia: 93.9% Healthy: 94.9%) in classifying COVID-19 pneumonia, non-COVID-19 pneumonia and healthy patients. Next, we provide visual explanations for the Convolutional Neural Network predictions with gradient-weighted class activation mapping (Grad-CAM). The results provided a model explainability by showing that Ground Glass Opacities, indicators of COVID-19 pneumonia disease, were captured by our convolutional neural network. Finally, we have implemented our approach in three hospitals proving its compatibility and efficiency. View Full-Text
Keywords: deep learning; computed tomography; image classification; COVID-19; medical image analysis; pneumonia; CNN; LSTM; medical diagnosis deep learning; computed tomography; image classification; COVID-19; medical image analysis; pneumonia; CNN; LSTM; medical diagnosis
Show Figures

Figure 1

MDPI and ACS Style

Kara, M.; Öztürk, Z.; Akpek, S.; Turupcu, A. COVID-19 Diagnosis from Chest CT Scans: A Weakly Supervised CNN-LSTM Approach. AI 2021, 2, 330-341. https://doi.org/10.3390/ai2030020

AMA Style

Kara M, Öztürk Z, Akpek S, Turupcu A. COVID-19 Diagnosis from Chest CT Scans: A Weakly Supervised CNN-LSTM Approach. AI. 2021; 2(3):330-341. https://doi.org/10.3390/ai2030020

Chicago/Turabian Style

Kara, Mustafa, Zeynep Öztürk, Sergin Akpek, and Ayşegül Turupcu. 2021. "COVID-19 Diagnosis from Chest CT Scans: A Weakly Supervised CNN-LSTM Approach" AI 2, no. 3: 330-341. https://doi.org/10.3390/ai2030020

Find Other Styles

Article Access Map by Country/Region

1
Back to TopTop