| dc.description |
I would like to express my sincere gratitude to my supervisor, Md. Asadur Rahman,
Ph.D., Assistant Professor, Department of Biomedical Engineering, MIST, for his
effective guidance and support throughout this research work whenever necessary.
My sincere gratitude goes to Colonel Syed Mahfuzur Rahman, the respected Head of
the Department, for his persistent guidance and financial allocation that made this
research work possible. I also extend my profound appreciation to the Department of
Biomedical Engineering, MIST, for their co-operations and for facilitating me with the
materials and laboratory resources to carry out my research work.
I am also indebted to all the individuals who directly or indirectly helped and supported
me with their technical and editorial feedback in carrying out my research work. I want to
acknowledge Capt Kumar Shrestha, my fellow companion, for his continuous support
and cooperation in the journey of completing my M.Sc. Engineering together.
Finally, I would like to acknowledge the continuous love and support from my loving
family and friends throughout the journey and am grateful to everyone who has made this
M.Sc. thesis a reality. |
en_US |
| dc.description.abstract |
Chest X-ray (CXR) image is a widely used diagnostic tool for various chest diseases.
Human interpretation of CXR images, however, has never been always effective. The
diagnostic level of the radiologists along with other factors like cognitive ability,
experience, fatigue, and other human-dependent factors may impair the diagnostic
procedure with missed information, misinterpretation, and requiring more time and cost.
Computer-aided analysis of CXR images has already demonstrated its potential over
manual or human screening to facilitate rapid, correct, and low-cost diagnosis of chest
diseases. Existing computer-aided systems are still not suitable for real-time applications
due to limited findings, limited generalizability across wide datasets, and not being
computationally and economically affordable as well. Therefore, an efficient Convolution
Neural Network (CNN) based computer-aided decision support system, the CXRNet, was
developed for the automatic detection of abnormalities from CXR images in a real-time
clinical scenario. The proposed CXRNet model is a 16-layered CNN architecture with 5
output classes: Cardiomegaly, COVID, Normal, Pneumonia, and Tuberculosis. This
architecture is trained with frontal CXR images obtained from various sources to improve
the generalization of the model across multiple datasets. Upon testing the model on three
different data distribution conditions (70% training and 30% testing, 80% training and 20%
testing, and 90% training and 10% testing), it achieved a state-of-the-art performance with
an average accuracy of 95.7%, a precision of 95.3%, a recall of 95.3%, and an f1-score
of 95.3% for the multiclass classification task. The proposed CXRNet also demonstrates
excellent performance on binary classification tasks with an average accuracy of
over 98% for each disease condition. The results obtained from this work outperform
several other custom-designed CNN architectures as well as pre-trained models-based
architectures like ResNet, VGG, DenseNet, Xception, Inception, etc. Furthermore, with
proper testing, validation, and debugging of the model in clinical practice, it can be
successfully deployed as a decision support system for radiologists. |
en_US |
