Francesco Manigrasso

Francesco Manigrasso

Auto-generated profile, based on publicly available information

Francesco Manigrasso

Politecnico di Torino

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 September 2024 in Medical Image Analysis
Verified
Journal Article
Open access
FMFrancesco Manigrasso
Francesco Manigrasso
RMRosario Milazzo
Rosario Milazzo
ARAlessandro Sebastian Russo
Alessandro Sebastian Russo
Fabrizio LambertiFabrizio Lamberti
Fabrizio Lamberti
FSFredrik Strand
Fredrik Strand
LMLia Morra
Lia Morra
The potential and promise of deep learning systems to provide an independent assessment and relieve radiologists' burden in screening mammography have been recognized in several studies. However, the low cancer prevalence, the need to process high-resolution images, and the need to combine information from multiple views and scales still pose technical challenges. Multi-view architectures that combine information from the four mammographic views to produce an exam-level classification score are a promising approach to the automated processing of screening mammography. However, training such architectures from exam-level labels, without relying on pixel-level supervision, requires very large datasets and may result in suboptimal accuracy. Emerging architectures such as Visual Transformers (ViT) and graph-based architectures can potentially integrate ipsi-lateral and contra-lateral breast views better than traditional convolutional neural networks, thanks to their stronger ability of modeling long-range dependencies. In this paper, we extensively evaluate novel transformer-based and graph-based architectures against state-of-the-art multi-view convolutional neural networks, trained in a weakly-supervised setting on a middle-scale dataset, both in terms of performance and interpretability. Extensive experiments on the CSAW dataset suggest that, while transformer-based architecture outperform other architectures, different inductive biases lead to complementary strengths and weaknesses, as each architecture is sensitive to different signs and mammographic features. Hence, an ensemble of different architectures should be preferred over a winner-takes-all approach to achieve more accurate and robust results. Overall, the findings highlight the potential of a wide range of multi-view architectures for breast cancer classification, even in datasets of relatively modest size, although the detection of small lesions remains challenging without pixel-wise supervision or ad-hoc networks.

7 September 2021
Verified
Book Chapter
Closed access
PDF file
FMFrancesco Manigrasso
Francesco Manigrasso
FMFilomeno Davide Miro
Filomeno Davide Miro
LMLia Morra
Lia Morra
Fabrizio LambertiFabrizio Lamberti
Fabrizio Lamberti

10 September 2024
Verified
Book Chapter
Closed access
PDF file
FMFrancesco Manigrasso
Francesco Manigrasso
SSStefan Schouten
Stefan Schouten
LMLia Morra
Lia Morra
PBPeter Bloem
Peter Bloem



2 January 2026
Verified
Book Chapter
Closed access
PDF file
MDMalihe Dahmardeh
Malihe Dahmardeh
MSMohsen Saadatpour
Mohsen Saadatpour
FMFrancesco Manigrasso
Francesco Manigrasso
LMLia Morra
Lia Morra
Francesco SettiFrancesco Setti
Francesco Setti