Foto del docente

Stefano Diciotti

Associate Professor

Department of Electrical, Electronic, and Information Engineering "Guglielmo Marconi"

Academic discipline: ING-INF/06 Electronic and Informatics Bioengineering

Research

Keywords: artificial intelligence machine learning brain complexity magnetic resonance imaging fractal analysis medical imaging computed tomography of the lungs deep learning generative adversarial networks self-supervised learning

The main research themes are in the fields of computational medical imaging and artificial intelligence (AI) in Life Sciences:

- Fractal analysis for quantifying brain complexity during maturation, aging and in neurological disorders

Background: The brain is an anatomical structure that shows a high degree of statistical self- similarity and the fractal geometry describes the complexity of structures which show strict or statistical self-similarity in a proper interval of spatial scales. Fractal descriptors have the potential to represent a useful tool in detecting subtle brain changes as well as in tracking the progression of neurodegeneration.

Purpose: To design, develop, and apply novel fractal descriptors that reliable quantify the structural and functional complexity of the brain in healthy subjects and in patients with neurological disorders

- AI methods tailored for improving diagnostic accuracy and characterization of neurological disorders

Background: Clinical datasets have often a small size for deep learning applications. However, several AI techniques including transfer learning, generative adversarial networks, etc. enable to overcome, at least in part, this limitation.

Purpose: To design, develop, and apply dedicated AI methods for improving the training and generalization abilities of deep learning models in small size datasets in various neurological disorders.

- AI for augmented reality in robot-assisted surgery

Background: Three-dimensional models reconstructed from MRI and CT images are useful to guide the surgeon during crucial surgical steps. Recent research activities to improve 3D-guided robotic surgery focus on the development of augmented reality systems able to visualize 3D models in the surgical field with in vivo co-registration during robotic surgery. However, the 3D model does not follow automatically the real organ during its mobilization and traction during surgery. Thus, this non-automated augmented reality may increase the surgical time due to the need of several re-adjustments of the 3D model over the surgical field during the dissection.

Purpose: To design, develop, and validate an AI-based augmented reality system able to automatically co-register, in real time, a digital 3D-model of biological structures and the surgical field.

Latest news

At the moment no news are available.