The automatic localization and segmentation of anatomical structures is one of the most frequently tackled tasks in medical image analysis, due to its many applications in clinical and experimental medicine. Among these, automated methods to accurately, robustly, and reproducibly localize the hippocampus in brain images are particularly interesting, after discoveries indicating the relevance of structural changes of this region as early biomarkers for Alzheimer’s disease and epilepsy.
We have developed an automatic tool aimed at localizing the hippocampus in histological images and extract horse games meaningful information that can be used to assess visual similarities between genes, under the hypotesis that similar visual aspect is a hint for similar behavior
The code is available here.
A full dissertation of this project and its results can be found in here.