Magnetic Resonance Image based Lung Disorder Detection Models in Deep Learning-A Comprehensive Survey

Lung disorders, including pneumonia, cardiomegaly, tuberculosis and lung cancer can cause serious sickness, hospitalization, or even death, especially in the elderly and other medically fragile people all over the globe. Nearly 8.32 million individuals have died from COVID-19, one of several new lung-related diseases that have emerged in the recent several decades. In the present post COVID-19 scenario, it is vital to fight against lung diseases by ensuring that patients are diagnosed promptly and given the necessary therapy. It is possible to reverse the progression of some diseases, including lung disease, if caught early enough. To accurately categorize lung diseases, numerous deep learning architectures are proposed. Even though there are numerous models suggested, every model has their limitation in performance. Numerous detection methods have been developed by researchers, which has helped in the prevention of lung ailments. Imaging tests like Magnetic Resonance Imaging (MRI), Computed Tomography (CT) scans and chest X-rays can help doctors determine how far the infection has gone in the lungs and provide a clearer picture of the patient’s health. Utilizing computer-aided detection technologies can improve multimodal imaging approaches, allowing doctors to diagnose more efficiently and with higher quality. This research presents a brief survey on various deep learning and machine learning models in image denoising and segmentation models, feature extraction and selection models, classification models for lung disorders detection. This research is useful for academicians, researchers, medical experts to design efficient models for accurate and quick detection of lung disorders.