Multimodal feature distinguishing and deep learning approach to detect lung disease from MRI images.
Authors
Affiliations (1)
Affiliations (1)
- Department of Electrical Engineering, College of Engineering, University of Hafr Al Batin, Hafr Al Batin, 39524, Saudi Arabia. [email protected].
Abstract
Precise and early detection and diagnosis of lung diseases reduce the severity of life risk and further spread of infections in patients. Computer-based image processing techniques utilize magnetic resonance imaging (MRI) as input for computing, detecting, segmenting, etc., processes for improving the processing efficacy. This article introduces a Multimodal Feature Distinguishing Method (MFDM) for augmenting lung disease detection precision. The method distinguishes the extractable features of an MRI lung input using a homogeneity measure. Depending on the possible differentiations for heterogeneity feature detection, the training using a transformer network is pursued. This network performs differentiation verification and training classification independently and integrates the same for identifying heterogeneous features. The integration classifications are used for detecting the infected region based on feature precision. If the differentiation fails, then the transformer process reinitiates its process from the last known homogeneity feature between successive segments. Therefore, the distinguishing multimodal features between successive segments are validated for different differentiation levels, augmenting the accuracy. Thus, the introduced system ensures 8.78% of sensitivity, 8.81% of precision 9.75% of differentiation time while analyzing various lung features. Then, the effective results indicate that the MFDM model was successfully utilized in medical applications to improve the disease recognition rate.