본문으로 건너뛰기
← 뒤로

A Neural Conditional Random Field Model Using Deep Features and Learnable Functions for End-to-End MRI Prostate Zonal Segmentation.

1/5 보강
The journal of machine learning for biomedical imaging 2025 Vol.3()
Retraction 확인
출처

Hung ALY, Zhao K, Pang K, Zheng H, Du X, Miao Q

📝 환자 설명용 한 줄

The automatic segmentation of prostate MRI often produces inconsistent performance because certain image slices are more difficult to segment than others.

이 논문을 인용하기

↓ .bib ↓ .ris
APA Hung ALY, Zhao K, et al. (2025). A Neural Conditional Random Field Model Using Deep Features and Learnable Functions for End-to-End MRI Prostate Zonal Segmentation.. The journal of machine learning for biomedical imaging, 3. https://doi.org/10.59275/j.melba.2025-gc4c
MLA Hung ALY, et al.. "A Neural Conditional Random Field Model Using Deep Features and Learnable Functions for End-to-End MRI Prostate Zonal Segmentation.." The journal of machine learning for biomedical imaging, vol. 3, 2025.
PMID 40977953 ↗

Abstract

The automatic segmentation of prostate MRI often produces inconsistent performance because certain image slices are more difficult to segment than others. In this paper, we show that consistency can be improved using Conditional Random Fields (CRFs), which refine the segmentation results by considering pixel relationships pairwise. In practice, however, conventional CRFs are susceptible to noise and MRI intensity shifts due to their use of simple binary potentials involving spatial distance and intensity difference. Such heuristic potential functions are hardly expressive, limiting the network from extracting more relevant information and having more stable potential calculations. We propose a novel end-to-end Neural CRF (NCRF) model that utilizes learnable binary potential functions based on deep image features. Experiments show that our NCRF is a better model for prostate zonal segmentation than state-of-the-art CRF models. The NCRF improves segmentation accuracy in both the prostate transition zone and peripheral zone such that segmentation results are consistent across all the prostate slices, which can improve the performance of downstream tasks such as prostate cancer detection and segmentation. Our code is available at https://github.com/aL3x-O-o-Hung/NCRF.

🏷️ 키워드 / MeSH 📖 같은 키워드 OA만

🏷️ 같은 키워드 · 무료전문 — 이 논문 MeSH/keyword 기반

🟢 PMC 전문 열기