The problem of prostate segmentation from Magnetic Resonance Imaging (MRI) is an intense research area, due to the increased use of MRI in the diagnosis and treatment planning of prostate cancer. The lack of clear boundaries and huge variation of texture and shapes between patients makes the task very challenging, and the 3D nature of the data makes 2D segmentation algorithms suboptimal for the task. With this paper, we propose a novel architecture to fill the gap between the most recent advances in 2D computer vision and 3D semantic segmentation. In particular, the designed model retrieves multi-scale 3D features with dilated convolutions and makes use of a self-attention transformer to gain a global field of view. The proposed Long-Range 3D Self-Attention block allows the convolutional neural network to build significant features by merging together contextual information collected at various scales. Experimental results show that the proposed method improves the state-of-the-art segmentation accuracy on MRI prostate segmentation.

Long-Range 3D Self-Attention for MRI Prostate Segmentation / Pollastri, Federico; Cipriano, Marco; Bolelli, Federico; Grana, Costantino. - 2022-:(2022). (Intervento presentato al convegno 19th IEEE International Symposium on Biomedical Imaging, ISBI 2022 tenutosi a Kolkata, India nel Mar 28-31) [10.1109/ISBI52829.2022.9761448].

Long-Range 3D Self-Attention for MRI Prostate Segmentation

Pollastri Federico;Cipriano Marco;Bolelli Federico;Grana Costantino
2022

Abstract

The problem of prostate segmentation from Magnetic Resonance Imaging (MRI) is an intense research area, due to the increased use of MRI in the diagnosis and treatment planning of prostate cancer. The lack of clear boundaries and huge variation of texture and shapes between patients makes the task very challenging, and the 3D nature of the data makes 2D segmentation algorithms suboptimal for the task. With this paper, we propose a novel architecture to fill the gap between the most recent advances in 2D computer vision and 3D semantic segmentation. In particular, the designed model retrieves multi-scale 3D features with dilated convolutions and makes use of a self-attention transformer to gain a global field of view. The proposed Long-Range 3D Self-Attention block allows the convolutional neural network to build significant features by merging together contextual information collected at various scales. Experimental results show that the proposed method improves the state-of-the-art segmentation accuracy on MRI prostate segmentation.
2022
19th IEEE International Symposium on Biomedical Imaging, ISBI 2022
Kolkata, India
Mar 28-31
2022-
Pollastri, Federico; Cipriano, Marco; Bolelli, Federico; Grana, Costantino
Long-Range 3D Self-Attention for MRI Prostate Segmentation / Pollastri, Federico; Cipriano, Marco; Bolelli, Federico; Grana, Costantino. - 2022-:(2022). (Intervento presentato al convegno 19th IEEE International Symposium on Biomedical Imaging, ISBI 2022 tenutosi a Kolkata, India nel Mar 28-31) [10.1109/ISBI52829.2022.9761448].
File in questo prodotto:
File Dimensione Formato  
2022_ISBI_Long_Range_3D_Self_Attention_for_MRI_Prostate_Segmentation.pdf

Open access

Tipologia: Versione originale dell'autore proposta per la pubblicazione
Dimensione 428.01 kB
Formato Adobe PDF
428.01 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1259776
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 3
social impact