Augmented Fusion Method for the Diagnosis of ILD and the Promotion of Better Clinical Results

The Interstitial Lung Diseases (ILDs) are characterized by lung fibrosis (scarring). Nodule, Idiopathic Pulmonary Fibrosis (IPF) and Honeycomb are the main categories of ILDs. The goal of medical image fusion is to create a unified representation of clinical information from multiple sources that can be used for more accurate diagnosis. Using image enhancing approaches along with fusion techniques that are based on wavelet transform and IHS transform-based techniques may help with early detection of these ILDs. A mathematical technique called wavelet transformations can record changes in edges and textures at various sizes in images. A frequent sharpening approach is the IHS method, which includes transforming a color picture from the RGB space to the IHS space using a variety of operations. More precise abnormality extraction can be achieved by using image fusion and enhancement techniques and assessing those using metrics like Structural Similarity Index Method (SSIM), Mean Square Error (MSE), and Global Consistency Error (GCE) across various pulmonary image modalities. The SVM classifier uses characteristics that were retrieved from upgraded pictures to categorize the illness, improving prognosis, preventing severe diseases and diagnosing ILDs at the earliest.