Dermatologist-level classification of skin cancer with deep neural networks
Fundus photograph-based deep learning algorithms in detecting diabetic retinopathy
-
Data pre-processing: checking for data leakage
-
Preprocess images properly for the train, validation and test sets
-
Implement a weighted loss function to address class imbalance.
-
Set up a pre-trained neural network to make disease predictions on chest x-rays.
-
Assignment:
-
Labs:
-
Calculate true positives, true negatives, false positives, false negatives.
-
Calculate sensitivity and specificity
-
Calculate Positive Predictive Value (PPV) and Negative Predictive Value (NPV).
-
Understand confidence intervals, ROC curve, and F1 score.
-
Assignment:
-
Lab :
- Perform image segmentation on 3D MRI data.
- Take random sub-samples from a 3D image.
- Standardize an input image.
- Apply a pre-trained U-Net model.
- Implement a proper loss function for model training (soft dice loss).
- Evaluate model performance by calculating sensitivity and specificity.
- Assignment:
- Lab :