Covid-19 Prediction

Chest X-Ray Pneumonia Classification

5856 chest X-ray images are used
Three research questions which are tried to be answered:
- Do different networks result similar/same performance?
- Does applying transfer learning influence performance?
- Does using deep networks without pretraining on ImageNet have similar performance with the pretrained version?
Data preprocessing methods are conducted to have better results in further modeling studies.
Different models are run and finally, the models are evaluated with appropriate metrics and the results are interpreted accordingly
Future works:
- To use a source dataset which is in the similar domain with the target dataset during transfer learning
- To increase the number of images is data augmentation
- To train the deep networks partially

Medical Image Segmentation: A Comparative Study of SAM and MedSAM Models

130 breast cancer images with ground truth are utilized
SAM and MedSAM models are used to segment cancerous regions
Predictions are made using SAM and MedSAM
Images are segmented as cancerous and non-cancerous based on the predictions
The segmented regions are visualed
Different performance metrics appropriate for segmentation are defined and evaluated

Compared the performance of MedSAM and SAM
Seen that MedSAM improves the performance of SAM for 130 breast cancer images
Future works:
- Evaluating the performance of the models with other datasets
- Fine-tuning MedSAM with additional breast cancer datasets
- Building other networks such as U-Net

Lung CT images which are taken from Tongji Hospital, Wuhan, China for January 2020, and April 2020 are analyzed
The whole image dataset consists of 349 CT images from 296 patients diagnosed with Covid-19 and 397 CT images from non-covid patients
The images are resized to train the model faster as 100x100 and converted into torch tensors
The whole dataset is splitted into train, validation, and test datasets

A convolutional neural network with 3 convolutional and 3 pooling layers, and a final fully connected layer is used
Batch normalization after convolutional layers are applied to speed up training
ReLU activation function is used after hidden layers to eliminate vanishing gradient problem
Softmax activation function in final layer to turn the vector into probabilities that sum up to 1
Cross entropy loss function is chosen since it is wiser to use it in classification problems
Adam and SGD optimizers are used

Pneumonia Classification

Image Segmentation