Unimore logo AImageLab
Back to the research area

3D Reconstruction of Skin Lesions for Tumor Diagnosis in OCT imaging

Optical Coherence Tomography (OCT) allows to capture the internal structure of skin lesions. In this project we develop an image analysis pipeline to obtain 3D models from OCT scans. Both the external surface and the internal vascular network are reconstructed to give to the clinicians new qualitative tools for tumor diagnosis.

This project is developed in conjunction with the dermathologists of Policlinico di Modena under the direction of Prof. Giovanni Pellacani.

This research is funded by the European Project ADVANCE: Automatic Detection of VAscular Networks for Cancer Evaluation.


3D Vessels Filtering

In this work we present a method for in vivo surface reconstruction and 3D vessels segmentation from Speckle-Variance Optical Coherence Tomography imaging, applied to dermatology. This novel technology allows to capture motion underneath the skin surface revealing the presence of blood vessels. Standard OCT visualization techniques are inappropriate for this new source of information, that is crucial in early skin cancer diagnosis. We investigate 3D reconstruction techniques for better visualization of both the  external and internal structure of skin lesions, as a tool to help clinicians in the task of qualitative tumor evaluation.

In the following we present the 3D visualization of the reconstructed surface from multiple views.

 

The vascular network underneath the skin surface is visualized in three possible ways, visualized below.

Video Demo

Research Activity Info