Performance Analysis of Brain MRI Classification with Hybrid Swin Transformer Models
Implementation plan:
——————————-
Step 1: Initially, we collect and load the Brain MRI – Multiple Sclerosis Dataset dataset.
Step 2: Next, we preprocess the MRI data. This includes the following steps.
2.1: First, the Augmentation process is done using the Generative Adversarial Network (GANs) Model.
2.2: Second, we implement Convolutional Neural Network to lower the class imbalance.
Step 3: Then, we perform a segmentation process based on 3D U-Net – Swin transformer – Linear population size reduction (3D-UN-ST-LPSR).
Step 4: Next, we implement the Feature extraction process using the Redundant Discrete Wavelet Transform – GrayScale Concurrence Matrixes – Index-Based Colorization Method (RDWT-GLCM-IBCM).
Step 5: Then, we implement the Recurrent Convolutional Neural Network – Improved Hunger Games Search Algorithm (RCNN-IHGS) for Classification of Multiple sclerosis.
Step 6: Finally, we plot performance for the following metrics:
6.1: Number of epochs vs. Accuracy (%)
6.2: Number of epochs vs. Precision (%)
6.3: Number of epochs vs. F1-Score (%)
6.4: Number of epochs vs. Recall (%)
6.5: Number of epochs vs. Loss (%)
6.6: Number of epochs vs. Dice Score (%)
6.7: Number of epochs vs. Sensitivity (%)
6.8: Confusion Matrix
Dataset Link:
——————-
Brain MRI – Multiple Sclerosis Dataset (kaggle.com)
Software Requirement:
1. Development Tool: Python – 3.11.4 or above
2. Operating System: Windows 10 (64-bit)
Note:
——–
1) If the above plan does not satisfy your requirement, please provide the processing details, like the above step-by-step.
2) Please note that this implementation plan does not include any further steps after it is put into implementation.
3) If the above plan satisfies your requirement please confirm with us.
4) We develop simulation based projects only, not in real time.
We implement an existing project:
Reference 1 Title: – Multiple Sclerosis Lesions Segmentation Using Attention-Based CNNs in FLAIR Images
