| Summary: | Researchers studying cardiovascular and metabolic disease in humans commonly usecomputer vision techniques to segment internal structures of the zebrafish animalmodel. However, there are no current image segmentation methods to target theeyes of the zebrafish. Segmenting the eyes is essential for accurate measurement ofthe eyes' size and shape following the experimental intervention. Additionally,successful segmentation of the eyes functions as a good starting point for futuresegmentation of other internal organs. To establish an effective segmentation method,the deep learning neural network architecture, Deeplab, was trained using 275 imagesof the zebrafish embryo. Besides model architecture, the training was refined withproper data pre-processing, including data augmentation to add variety and toartificially increase the training data. Consequently, the results yielded a score of95.88 percent when applying augmentations, and 95.30 percent withoutaugmentations. Despite this minor improvement in accuracy score when using theaugmented training dataset, it also produced visibly better predictions on a newdataset compared to the model trained without augmentations. Therefore, theimplemented segmentation model trained with augmentations proved to be morerobust, as the augmentations gave the model the ability to produce promising resultswhen segmenting on new data.
|
|---|
