SAM-UNETR: Clinically Significant Prostate Cancer Segmentation Using Transfer Learning From Large Model

Prostate cancer (PCa) is one of the leading causes of cancer-related mortality among men worldwide. Accurate and efficient segmentation of clinically significant prostate cancer (csPCa) regions from magnetic resonance imaging (MRI) plays a crucial role in diagnosis, treatment planning, and monitorin...

Descripción completa

Detalles Bibliográficos
Autores: J. A. Alzate-Grisales, A. Mora-Rubio, F. García-García, R. Tabares-Soto, M. d. l. Iglesia-Vayá
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2023
País:España
Institución:Fundación para el Fomento de la Investigación Sanitaria y Biomédica de la Comunitat Valenciana (FISABIO)
Repositorio:r-FISABIO. Repositorio Institucional de Producción Científica
OAI Identifier:oai:fisabio.fundanetsuite.com:p15772
Acceso en línea:https://fisabio.portalinvestigacion.com/publicaciones/15772
Access Level:acceso abierto
Palabra clave:Image segmentation
Training
Principal component analysis
Transfer learning
Task analysis
Magnetic resonance imaging
Lesions
Artificial intelligence
deep learning
prostate cancer
semantic segmentation
Descripción
Sumario:Prostate cancer (PCa) is one of the leading causes of cancer-related mortality among men worldwide. Accurate and efficient segmentation of clinically significant prostate cancer (csPCa) regions from magnetic resonance imaging (MRI) plays a crucial role in diagnosis, treatment planning, and monitoring of the disease, however, this is a challenging task even for the specialized clinicians. This study presents SAM-UNETR, a novel model for segmenting csPCa regions from MRI images. SAM-UNETR combines a transformer-encoder from the Segment Anything Model (SAM), a versatile segmentation model trained on 11 million images, with a residual-convolution decoder inspired by UNETR. The model uses multiple image modalities and applies prostate zone segmentation, normalization, and data augmentation as preprocessing steps. The performance of SAM-UNETR is compared with three other models using the same strategy and preprocessing. The results show that SAM-UNETR achieves superior reliability and accuracy in csPCa segmentation, especially when using transfer learning for the image encoder. This demonstrates the adaptability of large-scale models for different tasks. SAM-UNETR attains a Dice Score of 0.467 and an AUROC of 0.77 for csPCa prediction.