|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: |
|
|
- google/efficientnet-b0 |
|
|
pipeline_tag: image-classification |
|
|
--- |
|
|
|
|
|
Model Description. |
|
|
This model is a fine-tuned EfficientNetB0 for classifying brain tumors from MRI scans. It was trained using transfer learning on a publicly available dataset from Kaggle. |
|
|
The model is capable of distinguishing between four classes: pituitary, glioma, meningioma, and no_tumor. |
|
|
|
|
|
Intended Use. |
|
|
This model is intended for non-commercial and research purposes only. It can be used for: |
|
|
- Classifying brain tumors in MRI images. |
|
|
- Serving as a baseline for further research. |
|
|
|
|
|
Performance. |
|
|
The model was evaluated on a held-out test set and achieved the following results: |
|
|
|
|
|
Metric Score |
|
|
Accuracy 99.31% |
|
|
Precision 99% |
|
|
Recall 99% |
|
|
F1-Score 99% |
|
|
|
|
|
Training Data. |
|
|
The model was trained on the Brain Tumor MRI Dataset available on Kaggle. |
|
|
- Dataset Link: https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor-mri-dataset |
|
|
|
|
|
Training Details |
|
|
- Base Model: EfficientNetB0 (pre-trained on ImageNet) |
|
|
- Framework: TensorFlow / Keras |
|
|
- Training Platform: Google Colaboratory |
|
|
|
