Crimson Flame-6 (ResNet18) - African Planes Classification
This model is a fine-tuned ResNet-18 trained to classify fetal ultrasound standard planes on the African planes dataset.
Model Performance (Test Set)
- Accuracy: 0.9600
- Macro F1 Score: 0.9471
- Macro Precision: 0.9669
- Macro Recall: 0.9375
Dataset Information
This model was trained on dataset Marc-HealthAI/african-planes-classification-dataset.
- Classes: Fetal abdomen, Fetal brain, Fetal femur, Fetal thorax, Maternal cervix, Other
- Splits: No train/validation/test splits found, so the data was pooled and re-split 70% / 15% / 15% (seed 42, grouped by Patient_num).
- Dataset Features:
['Patient_num', 'Plane', 'Train', 'Center', 'Filename', 'image']
Dataset Description
No explicit description provided in dataset metadata.
Original Dataset README Content
Maternal fetal ultrasound planes from low-resource imaging settings in five African countries
This resource is a dataset of routinely acquired maternal-fetal screening ultrasound images collected in five centers of five countries in Africa (Malawi, Egypt, Uganda, Ghana and Algeria) that is associated to the journal article Sendra-Bacells et al. "Generalisability of fetal ultrasound deep learning models to low-resource imaging settings in five African countries", Scientific Reports. The images correspond to the four most common fetal planes: abdomen, brain, femur and thorax. A CSV file is provided where image filenames are associated to plane types and patient number as well as the partitioning in training and testing splits as used in the associated publication.