Speaker: Virginia Tasso
December 5, 2025 | 11:30 am
DEIB - NECSTLab Meeting Room (Bld. 20)
Online by Zoom
Contact: Prof. Marco Santambrogio
Abstract
On Friday, December 5, 2025, we will have a new talk for the series #NECSTFridayTalk.During this talk, we will have, as speaker, Virginia Tasso, PhD at Dipartimento di Elettronica, Informazione e Bioingegneria.
Uveal Melanoma (UM), the most common intraocular cancer, is difficult to diagnose accurately due to its similarity to benign lesions and the limited access to ocular oncology experts. A late diagnosis can lead to invasive treatments that have a significant impact on patients' lives and the healthcare system.
For this reason, improving the efficiency and reliability of screening procedures is pivotal.
Typically, a diagnosis for this disease is made through manual ophthalmic image analysis, which enables non-invasive examination of ocular structures with high accuracy and precision. However, this procedure is time-consuming and requires significant expertise for accurate interpretation, which is often scarce due to the limited number of specialised ocular oncologists.
Therefore, developing automated screening solutions is paramount to speeding up the analysis process and reducing inter-operator variability.
While deep learning (DL) has shown strong results across ophthalmology, its application to UM remains underexplored, primarily due to the lack of data. This work presents a benchmark study comparing classification, detection, and segmentation models for UM diagnosis under varying data regimes. Building on recent proposals to reframe dense-prediction tasks as classification, this work extends these strategies and applies them to a real clinical setting, establishing robust baselines for automated UM diagnosis and providing practical guidance for model selection and adaptation in data-scarce environments. Building on insights from established baselines, the work proposes a domain-guided strategy to improve model diagnostic performance by establishing a training procedure that encourages models to focus on diagnostically meaningful image regions.
The NECSTLab is a DEIB laboratory, with different research lines on advanced topics in computing systems: from architectural characteristics, to hardware-software codesign methodologies, to security and dependability issues of complex system architectures.
Every week, the “NECSTFridayTalk” invites researchers, professionals or entrepreneurs to share their work experiences and projects they are implementing in the “Computing Systems”.