Bacteria segmentation — AI & ML exam

Solving a segmentation problem for the AI&ML exam at University of Verona. Group formed by a colleague of mine and me. You can find the dataset and the github repo.

Technical report

Here you can find a technical report with all the details, tests, results and conclusions of the project. Take a look at it!

Bacteria_segmentation_for_medical_images.pdf

Dataset

The dataset is composed by 366 images and the corresponding masks. For the images we have essentially three problems: the images have different sizes, the dataset is quite small and finally there are a lot of different light conditions, contrast and content. You can find some examples below:

Image and mask

Result

These are the results obtained with the models and the validation set.

All models performance — mean IoU as a metric

focus on LinkNet, the model that gives us the best result

Plot with the mean Iou Score for each model

Conclusion