README.md

metadata

license: mit
tags:
  - vision
  - image-segmentation
  - unet
  - resnet
  - medical
  - pytorch
model-index:
  - name: BrainVision
    results:
      - task:
          type: image-segmentation
          name: Image Segmentation
        dataset:
          name: LGG MRI Segmentation Dataset
          type: lgg-mri-segmentation-dataset
          split: test
        metrics:
          - type: dice_score
            value: 0.8898
            name: Dice Score
          - type: iou_score
            value: 0.8015
            name: IoU Score
          - type: accuracy
            value: 0.9963
            name: Accuracy
          - type: precision
            value: 0.882
            name: Precision
          - type: recall
            value: 0.8978
            name: Recall

Brain Tumor Segmentation

Model Description

This model is a U-Net based deep learning model for the segmentation of brain tumors from 2D MRI slices. It is an end-to-end segmentation model designed to assist radiologists by automatically identifying and outlining tumorous regions. The model leverages transfer learning by using a pre-trained ResNet50 backbone as its encoder.

Intended Use & Limitations

This model is intended for research and educational purposes. It is a tool for exploring deep learning for medical image segmentation.

Limitations:

• The model was trained on a specific dataset and may not generalize well to other datasets from different scanners, protocols, or patient populations.
• It should not be used for clinical diagnosis without validation by a qualified medical professional.

Training Data

The model was trained on the LGG MRI Segmentation Dataset from Kaggle.

• Volume: 3,929 MRI images from 110 patients.
• Annotation: Expert-annotated binary masks for tumor regions.
• Image Size: 256x256 pixels with 3 channels (converted to RGB).

Training Procedure

The model was trained using a two-stage fine-tuning approach with PyTorch.

Model Architecture:

• Architecture: U-Net
• Encoder: ResNet50 with imagenet pre-trained weights.
• Decoder: A symmetric expanding path with skip connections.
• Output: A single-channel probability map.

Hyperparameters:

• Optimizer: AdamW
• Loss Function: A composite loss function combining Dice Loss and Binary Cross-Entropy (BCE).

$$L_{\text{combo}}=L_{\text{dice}}+L_{\text{BCE}}L\_\{\backslash text\{combo\}\}\; =\; L\_\{\backslash text\{dice\}\}\; +\; L\_\{\backslash text\{BCE\}\}$$

• Epochs:
  • Stage 1 (Frozen Encoder): 5 epochs at a learning rate of 1e−4.
  • Stage 2 (Fine-tuning): 15 epochs at a learning rate of 1e−5.
• Learning Rate Scheduler: ReduceLROnPlateau with patience=3, factor=0.1.
• Batch Size: 16

Evaluation Results

The model was evaluated on an unseen test set composed of 10% of the patient data.

Metric	Value
Dice Score	0.8898
IoU Score	0.8015
Accuracy	0.9963
Precision	0.8820
Recall	0.8978