Pubblicazioni

Autori:

Visani, Valentina; Nanni, Loris; Loreggia, Andrea; Calabrese, Massimiliano; Pizzini, Francesca Benedetta; Veronese, Mattia; Castellaro, Marco

Titolo:

Weakly Supervised Segmentation Improves the Estimate of the Choroid Plexus Volume: Application to Multiple Sclerosis

Anno:

2025

Tipologia prodotto:

Contributo in atti di convegno

Tipologia ANVUR:

Contributo in Atti di convegno

Lingua:

Inglese

Nome rivista:

SMART INNOVATION, SYSTEMS AND TECHNOLOGIES

ISSN Rivista:

2190-3018

N° Volume:

412

Titolo del Convegno:

12th KES International Conference on Innovation in Medicine and Healthcare-KES-InMed

Luogo:

Madeira, PORTUGAL

Periodo:

JUN 19-21, 2024

Editore:

Springer

Casa editrice:

Springer

ISBN:

9789819774975

Intervallo pagine:

127-137

Parole chiave:

NETWORKS

Breve descrizione dei contenuti:

The Choroid Plexus (ChP) is a brain vascular tissue responsible for regulatory processes. Modifications in ChP Volume (ChPV) have been associated with neurodegenerative disorders, making ChPV a potential biomarker for monitoring disease progression and severity. The current gold-standard technique to quantify ChPV is manual segmentation on T1-weighted Magnetic Resonance Images. However, this method is time-consuming and prone to variability between different operators. Recently, deep learning methods have emerged as state-of-the-art systems for Magnetic Resonance image segmentation. In this study, we demonstrate that deep learning models can be effectively trained using weakly labeled data, specifically bounding box annotations that lack precise contour information. To explore this concept, we trained a series of models using various strategies that leverage bounding box annotations for segmentation tasks. A model trained on a dataset with manual segmentation masks achieved a lower performance compared with the same model trained with a weakly supervised strategy based on bounding box images. While acknowledging that the increase may not be substantial, it is essential to take into account our limited number of images. This limitation becomes intriguing when considering that compiling extensive datasets is considerably easier using rough ROIs rather than finely segmented ones.

Id prodotto:

145839

Handle IRIS:

11562/1162328

ultima modifica:

21 agosto 2025

Citazione bibliografica:

Visani, Valentina; Nanni, Loris; Loreggia, Andrea; Calabrese, Massimiliano; Pizzini, Francesca Benedetta; Veronese, Mattia; Castellaro, Marco, Weakly Supervised Segmentation Improves the Estimate of the Choroid Plexus Volume: Application to Multiple Sclerosis in «SMART INNOVATION, SYSTEMS AND TECHNOLOGIES» vol. 412 Springer  in INNOVATION IN MEDICINE AND HEALTHCARE, KES-INMED 2024 , Springer , Atti di "12th KES International Conference on Innovation in Medicine and Healthcare-KES-InMed" , Madeira, PORTUGAL , JUN 19-21, 2024 , 2025 , pp. 127-137

Consulta la scheda completa presente nel repository istituzionale della Ricerca di Ateneo