Prostate cancer is the most common cancer among US men. However, prostate imaging is still challenging despite the advances in multi-parametric magnetic resonance imaging (MRI), which provides both morphologic and functional information pertaining to the pathological regions. Along with whole prostate gland segmentation, distinguishing between the central gland (CG) and peripheral zone (PZ) can guide toward differential diagnosis, since the frequency and severity of tumors differ in these regions; however, their boundary is often weak and fuzzy. This work presents a preliminary study on deep learning to automatically delineate the CG and PZ, aiming at evaluating the generalization ability of convolutional neural networks (CNNs) on two multi-centric MRI prostate datasets. Especially, we compared three CNN-based architectures: SegNet, U-Net, and pix2pix. In such a context, the segmentation performances achieved with/without pre-training were compared in 4-fold cross-validation. In general, U-Net outperforms the other methods, especially when training and testing are performed on multiple datasets.

Rundo, L., Han, C., Zhang, J., Hataya, R., Nagano, Y., Militello, C., et al. (2020). CNN-based prostate zonal segmentation on t2-weighted MR images: A cross-dataset study. In A. Esposito (a cura di), Neural Approaches to Dynamics of Signal Exchanges (pp. 269-280). Springer Science and Business Media Deutschland GmbH [10.1007/978-981-13-8950-4_25].

CNN-based prostate zonal segmentation on t2-weighted MR images: A cross-dataset study

RUNDO, LEONARDO
;
Ferretti C;Nobile MS;Tangherloni A;Gilardi MC;Mauri G
Ultimo
2020

Abstract

Prostate cancer is the most common cancer among US men. However, prostate imaging is still challenging despite the advances in multi-parametric magnetic resonance imaging (MRI), which provides both morphologic and functional information pertaining to the pathological regions. Along with whole prostate gland segmentation, distinguishing between the central gland (CG) and peripheral zone (PZ) can guide toward differential diagnosis, since the frequency and severity of tumors differ in these regions; however, their boundary is often weak and fuzzy. This work presents a preliminary study on deep learning to automatically delineate the CG and PZ, aiming at evaluating the generalization ability of convolutional neural networks (CNNs) on two multi-centric MRI prostate datasets. Especially, we compared three CNN-based architectures: SegNet, U-Net, and pix2pix. In such a context, the segmentation performances achieved with/without pre-training were compared in 4-fold cross-validation. In general, U-Net outperforms the other methods, especially when training and testing are performed on multiple datasets.
Capitolo o saggio
Deep convolutional neural networks, Prostate zonal segmentation, Cross-dataset generalization
English
Neural Approaches to Dynamics of Signal Exchanges
Esposito, A., Faundez-Zanuy, M., Morabito, F.C., Pasero, E.
19-set-2019
2020
978-981-13-8949-8
151
Springer Science and Business Media Deutschland GmbH
269
280
Rundo, L., Han, C., Zhang, J., Hataya, R., Nagano, Y., Militello, C., et al. (2020). CNN-based prostate zonal segmentation on t2-weighted MR images: A cross-dataset study. In A. Esposito (a cura di), Neural Approaches to Dynamics of Signal Exchanges (pp. 269-280). Springer Science and Business Media Deutschland GmbH [10.1007/978-981-13-8950-4_25].
reserved
File in questo prodotto:
File Dimensione Formato  
Rundo2020_Chapter_CNN-BasedProstateZonalSegmenta.pdf

Solo gestori archivio

Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Dimensione 465.79 kB
Formato Adobe PDF
465.79 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/209489
Citazioni
  • Scopus 35
  • ???jsp.display-item.citation.isi??? 26
Social impact