Accurate Prostate Segmentation in Large-Scale Magnetic Resonance Imaging Datasets via First-in-First-Out Feature Memory and Multi-Scale Context Modeling

Prostate cancer, a prevalent malignancy affecting males globally, underscores the critical need for precise prostate segmentation in diagnostic imaging. However, accurate delineation via MRI still faces several challenges: (1) The distinction of the prostate from surrounding soft tissues is impeded...

Full description

Saved in:
Bibliographic Details
Main Authors: Jingyi Zhu, Xukun Zhang, Xiao Luo, Zhiji Zheng, Kun Zhou, Yanlan Kang, Haiqing Li, Daoying Geng
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Journal of Imaging
Subjects:
Online Access:https://www.mdpi.com/2313-433X/11/2/61
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850081867636670464
author Jingyi Zhu
Xukun Zhang
Xiao Luo
Zhiji Zheng
Kun Zhou
Yanlan Kang
Haiqing Li
Daoying Geng
author_facet Jingyi Zhu
Xukun Zhang
Xiao Luo
Zhiji Zheng
Kun Zhou
Yanlan Kang
Haiqing Li
Daoying Geng
author_sort Jingyi Zhu
collection DOAJ
description Prostate cancer, a prevalent malignancy affecting males globally, underscores the critical need for precise prostate segmentation in diagnostic imaging. However, accurate delineation via MRI still faces several challenges: (1) The distinction of the prostate from surrounding soft tissues is impeded by subtle boundaries in MRI images. (2) Regions such as the apex and base of the prostate exhibit inherent blurriness, which complicates edge extraction and precise segmentation. The objective of this study was to precisely delineate the borders of the prostate including the apex and base regions. This study introduces a multi-scale context modeling module to enhance boundary pixel representation, thus reducing the impact of irrelevant features on segmentation outcomes. Utilizing a first-in-first-out dynamic adjustment mechanism, the proposed methodology optimizes feature vector selection, thereby enhancing segmentation outcomes for challenging apex and base regions of the prostate. Segmentation of the prostate on 2175 clinically annotated MRI datasets demonstrated that our proposed MCM-UNet outperforms existing methods. The Average Symmetric Surface Distance (ASSD) and Dice similarity coefficient (DSC) for prostate segmentation were 0.58 voxels and 91.71%, respectively. The prostate segmentation results closely matched those manually delineated by experienced radiologists. Consequently, our method significantly enhances the accuracy of prostate segmentation and holds substantial significance in the diagnosis and treatment of prostate cancer.
format Article
id doaj-art-6b1e0bdca3fd4840b1470a606dff736a
institution DOAJ
issn 2313-433X
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Journal of Imaging
spelling doaj-art-6b1e0bdca3fd4840b1470a606dff736a2025-08-20T02:44:39ZengMDPI AGJournal of Imaging2313-433X2025-02-011126110.3390/jimaging11020061Accurate Prostate Segmentation in Large-Scale Magnetic Resonance Imaging Datasets via First-in-First-Out Feature Memory and Multi-Scale Context ModelingJingyi Zhu0Xukun Zhang1Xiao Luo2Zhiji Zheng3Kun Zhou4Yanlan Kang5Haiqing Li6Daoying Geng7Academy for Engineering and Technology, Fudan University, Shanghai 200433, ChinaAcademy for Engineering and Technology, Fudan University, Shanghai 200433, ChinaAcademy for Engineering and Technology, Fudan University, Shanghai 200433, ChinaAcademy for Engineering and Technology, Fudan University, Shanghai 200433, ChinaAcademy for Engineering and Technology, Fudan University, Shanghai 200433, ChinaAcademy for Engineering and Technology, Fudan University, Shanghai 200433, ChinaDepartment of Radiology, Huashan Hospital, Fudan University, Shanghai 200400, ChinaAcademy for Engineering and Technology, Fudan University, Shanghai 200433, ChinaProstate cancer, a prevalent malignancy affecting males globally, underscores the critical need for precise prostate segmentation in diagnostic imaging. However, accurate delineation via MRI still faces several challenges: (1) The distinction of the prostate from surrounding soft tissues is impeded by subtle boundaries in MRI images. (2) Regions such as the apex and base of the prostate exhibit inherent blurriness, which complicates edge extraction and precise segmentation. The objective of this study was to precisely delineate the borders of the prostate including the apex and base regions. This study introduces a multi-scale context modeling module to enhance boundary pixel representation, thus reducing the impact of irrelevant features on segmentation outcomes. Utilizing a first-in-first-out dynamic adjustment mechanism, the proposed methodology optimizes feature vector selection, thereby enhancing segmentation outcomes for challenging apex and base regions of the prostate. Segmentation of the prostate on 2175 clinically annotated MRI datasets demonstrated that our proposed MCM-UNet outperforms existing methods. The Average Symmetric Surface Distance (ASSD) and Dice similarity coefficient (DSC) for prostate segmentation were 0.58 voxels and 91.71%, respectively. The prostate segmentation results closely matched those manually delineated by experienced radiologists. Consequently, our method significantly enhances the accuracy of prostate segmentation and holds substantial significance in the diagnosis and treatment of prostate cancer.https://www.mdpi.com/2313-433X/11/2/61prostate segmentationcontext modeling moduledynamic adjustment mechanismT2-weighted imaging
spellingShingle Jingyi Zhu
Xukun Zhang
Xiao Luo
Zhiji Zheng
Kun Zhou
Yanlan Kang
Haiqing Li
Daoying Geng
Accurate Prostate Segmentation in Large-Scale Magnetic Resonance Imaging Datasets via First-in-First-Out Feature Memory and Multi-Scale Context Modeling
Journal of Imaging
prostate segmentation
context modeling module
dynamic adjustment mechanism
T2-weighted imaging
title Accurate Prostate Segmentation in Large-Scale Magnetic Resonance Imaging Datasets via First-in-First-Out Feature Memory and Multi-Scale Context Modeling
title_full Accurate Prostate Segmentation in Large-Scale Magnetic Resonance Imaging Datasets via First-in-First-Out Feature Memory and Multi-Scale Context Modeling
title_fullStr Accurate Prostate Segmentation in Large-Scale Magnetic Resonance Imaging Datasets via First-in-First-Out Feature Memory and Multi-Scale Context Modeling
title_full_unstemmed Accurate Prostate Segmentation in Large-Scale Magnetic Resonance Imaging Datasets via First-in-First-Out Feature Memory and Multi-Scale Context Modeling
title_short Accurate Prostate Segmentation in Large-Scale Magnetic Resonance Imaging Datasets via First-in-First-Out Feature Memory and Multi-Scale Context Modeling
title_sort accurate prostate segmentation in large scale magnetic resonance imaging datasets via first in first out feature memory and multi scale context modeling
topic prostate segmentation
context modeling module
dynamic adjustment mechanism
T2-weighted imaging
url https://www.mdpi.com/2313-433X/11/2/61
work_keys_str_mv AT jingyizhu accurateprostatesegmentationinlargescalemagneticresonanceimagingdatasetsviafirstinfirstoutfeaturememoryandmultiscalecontextmodeling
AT xukunzhang accurateprostatesegmentationinlargescalemagneticresonanceimagingdatasetsviafirstinfirstoutfeaturememoryandmultiscalecontextmodeling
AT xiaoluo accurateprostatesegmentationinlargescalemagneticresonanceimagingdatasetsviafirstinfirstoutfeaturememoryandmultiscalecontextmodeling
AT zhijizheng accurateprostatesegmentationinlargescalemagneticresonanceimagingdatasetsviafirstinfirstoutfeaturememoryandmultiscalecontextmodeling
AT kunzhou accurateprostatesegmentationinlargescalemagneticresonanceimagingdatasetsviafirstinfirstoutfeaturememoryandmultiscalecontextmodeling
AT yanlankang accurateprostatesegmentationinlargescalemagneticresonanceimagingdatasetsviafirstinfirstoutfeaturememoryandmultiscalecontextmodeling
AT haiqingli accurateprostatesegmentationinlargescalemagneticresonanceimagingdatasetsviafirstinfirstoutfeaturememoryandmultiscalecontextmodeling
AT daoyinggeng accurateprostatesegmentationinlargescalemagneticresonanceimagingdatasetsviafirstinfirstoutfeaturememoryandmultiscalecontextmodeling