Valentina Sisini

About

Valentina Sisini is a researcher at the forefront of applying high-performance, energy-efficient hardware acceleration to medical imaging. Her work centers on the intersection of deep learning, field-programmable gate arrays (FPGAs), and cardiovascular diagnostics, with a specific focus on the automated segmentation of aortic valve calcium lesions. Sisini’s major contributions include pioneering the use of FPGA-based Deep Processing Units (DPUs) to run deep neural networks (DNNs) for pixel-level semantic segmentation in medical contexts. Her 2025 paper, “Segmentation of Aortic Valve Calcium Lesions Using FPGA Accelerators,” has already garnered 2 citations, while her companion benchmarking study, which evaluates the Vitis AI toolchain for deploying DNNs on FPGA hardware, has received 1 citation. By demonstrating that convolutional neural networks (CNNs) can be efficiently deployed on specialized hardware, Sisini is helping to bridge the gap between advanced computer vision algorithms and real-time, point-of-care medical imaging. Her work holds promise for enabling faster, more accurate diagnoses of cardiovascular disease, showcasing how cutting-edge hardware acceleration can transform clinical practice.

Research Focus

Key Achievements

Top Papers

1. 1
   Segmentation of Aortic Valve Calcium Lesions Using FPGA Accelerators

   2 citations · 2025
2. 2
   Benchmarking a DNN for aortic valve calcium lesions segmentation on FPGA-based DPU using the vitis AI toolchain

   1 citations · 2025

Key Collaborators

Contact & Links