• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

使用集成CBAM的深度学习和面积量化增强脑肿瘤分割

Enhanced Brain Tumor Segmentation Using CBAM-Integrated Deep Learning and Area Quantification.

作者信息

Islam Rafiqul, Hossain Sazzad

机构信息

Department of Computer Science and Engineering, Dhaka University of Engineering & Technology, Gazipur, Bangladesh.

出版信息

Int J Biomed Imaging. 2025 Aug 1;2025:2149042. doi: 10.1155/ijbi/2149042. eCollection 2025.

DOI:10.1155/ijbi/2149042
PMID:40786983
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12334286/
Abstract

Brain tumors are complex clinical lesions with diverse morphological characteristics, making accurate segmentation from MRI scans a challenging task. Manual segmentation by radiologists is time-consuming and susceptible to human error. Consequently, automated approaches are anticipated to accurately delineate tumor boundaries and quantify tumor burden, addressing these challenges efficiently. The presented work integrates a convolutional block attention module (CBAM) into a deep learning architecture to enhance the accuracy of MRI-based brain tumor segmentation. The deep learning network is built upon a VGG19-based U-Net model, augmented with depthwise and pointwise convolutions to improve feature extraction and processing efficiency during brain tumor segmentation. Furthermore, the proposed framework enhances segmentation precision while simultaneously incorporating tumor area measurement, making it a comprehensive tool for early-stage tumor analysis. Several qualitative assessments are used to assess the performance of the model in terms of tumor segmentation analysis. The qualitative metrics typically analyze the overlap between predicted tumor masks and ground truth annotations, providing information on the segmentation algorithms' accuracy and dependability. Following segmentation, a new approach is used to compute the extent of segmented tumor areas in MRI scans. This involves counting the number of pixels within the segmented tumor masks and multiplying by their area or volume. The computed tumor areas offer quantifiable data for future investigation and clinical interpretation. In general, the proposed methodology is projected to improve segmentation accuracy, efficiency, and clinical relevance compared to existing methods, resulting in better diagnosis, treatment planning, and monitoring of patients with brain tumors.

摘要

脑肿瘤是具有多样形态特征的复杂临床病变,因此从磁共振成像(MRI)扫描中进行准确分割是一项具有挑战性的任务。放射科医生进行的手动分割既耗时又容易出现人为误差。因此,人们期望自动化方法能够准确勾勒肿瘤边界并量化肿瘤负荷,从而有效应对这些挑战。本文提出的工作将卷积块注意力模块(CBAM)集成到深度学习架构中,以提高基于MRI的脑肿瘤分割的准确性。深度学习网络基于基于VGG19的U-Net模型构建,并通过深度卷积和逐点卷积进行增强,以提高脑肿瘤分割过程中的特征提取和处理效率。此外,所提出的框架在提高分割精度的同时,还纳入了肿瘤面积测量,使其成为早期肿瘤分析的综合工具。使用了几种定性评估方法来评估模型在肿瘤分割分析方面的性能。定性指标通常分析预测的肿瘤掩码与真实标注之间的重叠情况,提供有关分割算法准确性和可靠性的信息。分割后,采用一种新方法来计算MRI扫描中分割出的肿瘤区域的范围。这涉及计算分割出的肿瘤掩码内的像素数量,并乘以其面积或体积。计算出的肿瘤面积为未来的研究和临床解读提供了可量化的数据。总体而言,与现有方法相比,预计所提出的方法将提高分割的准确性、效率和临床相关性,从而实现对脑肿瘤患者更好的诊断、治疗规划和监测。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/b45d0a62cee5/IJBI2025-2149042.011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/a6f8bbe857c7/IJBI2025-2149042.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/8bd93f1671c9/IJBI2025-2149042.002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/582000d511c0/IJBI2025-2149042.003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/3daca7b55055/IJBI2025-2149042.004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/ed2bb2b9e3a4/IJBI2025-2149042.005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/581dcd2c0e29/IJBI2025-2149042.006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/5102c9faa082/IJBI2025-2149042.007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/9cf59fddafe3/IJBI2025-2149042.008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/ce8cab4318e2/IJBI2025-2149042.009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/0dd8227172da/IJBI2025-2149042.010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/b45d0a62cee5/IJBI2025-2149042.011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/a6f8bbe857c7/IJBI2025-2149042.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/8bd93f1671c9/IJBI2025-2149042.002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/582000d511c0/IJBI2025-2149042.003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/3daca7b55055/IJBI2025-2149042.004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/ed2bb2b9e3a4/IJBI2025-2149042.005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/581dcd2c0e29/IJBI2025-2149042.006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/5102c9faa082/IJBI2025-2149042.007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/9cf59fddafe3/IJBI2025-2149042.008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/ce8cab4318e2/IJBI2025-2149042.009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/0dd8227172da/IJBI2025-2149042.010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5467/12334286/b45d0a62cee5/IJBI2025-2149042.011.jpg

相似文献

1
Enhanced Brain Tumor Segmentation Using CBAM-Integrated Deep Learning and Area Quantification.使用集成CBAM的深度学习和面积量化增强脑肿瘤分割
Int J Biomed Imaging. 2025 Aug 1;2025:2149042. doi: 10.1155/ijbi/2149042. eCollection 2025.
2
Neuro-XAI: Explainable deep learning framework based on deeplabV3+ and bayesian optimization for segmentation and classification of brain tumor in MRI scans.Neuro-XAI:基于deeplabV3+和贝叶斯优化的可解释深度学习框架,用于磁共振成像扫描中脑肿瘤的分割和分类。
J Neurosci Methods. 2024 Oct;410:110247. doi: 10.1016/j.jneumeth.2024.110247. Epub 2024 Aug 10.
3
Multi-level channel-spatial attention and light-weight scale-fusion network (MCSLF-Net): multi-level channel-spatial attention and light-weight scale-fusion transformer for 3D brain tumor segmentation.多级通道空间注意力与轻量级尺度融合网络(MCSLF-Net):用于3D脑肿瘤分割的多级通道空间注意力与轻量级尺度融合变换器
Quant Imaging Med Surg. 2025 Jul 1;15(7):6301-6325. doi: 10.21037/qims-2025-354. Epub 2025 Jun 30.
4
Short-Term Memory Impairment短期记忆障碍
5
The impact of uncertainty estimation on radiomic segmentation reproducibility and scan-rescan repeatability in kidney MRI.不确定性估计对肾脏MRI中放射组学分割再现性和扫描-重扫重复性的影响。
Med Phys. 2025 Jul;52(7):e17995. doi: 10.1002/mp.17995.
6
..
Int Ophthalmol. 2025 Jun 27;45(1):266. doi: 10.1007/s10792-025-03602-6.
7
Implementation of biomedical segmentation for brain tumor utilizing an adapted U-net model.利用改进的U-net模型实现脑肿瘤的生物医学分割。
Comput Biol Med. 2025 Aug;194:110531. doi: 10.1016/j.compbiomed.2025.110531. Epub 2025 Jun 11.
8
Point-cloud segmentation with in-silico data augmentation for prostate cancer treatment.用于前列腺癌治疗的基于计算机模拟数据增强的点云分割
Med Phys. 2025 Apr 3. doi: 10.1002/mp.17815.
9
A physics-guided modular deep-learning based automated framework for tumor segmentation in PET.基于物理引导的模块化深度学习的自动框架,用于 PET 中的肿瘤分割。
Phys Med Biol. 2020 Dec 18;65(24):245032. doi: 10.1088/1361-6560/ab8535.
10
Detection and segmentation of brain metastases on MRI using 3D-MedDCNet.使用3D-MedDCNet在磁共振成像(MRI)上检测和分割脑转移瘤
Med Phys. 2025 Jul;52(7):e18001. doi: 10.1002/mp.18001.

本文引用的文献

1
ContourTL-Net: Contour-Based Transfer Learning Algorithm for Early-Stage Brain Tumor Detection.ContourTL-Net:用于早期脑肿瘤检测的基于轮廓的迁移学习算法。
Int J Biomed Imaging. 2024 Apr 29;2024:6347920. doi: 10.1155/2024/6347920. eCollection 2024.
2
Brain tumor segmentation based on deep learning and an attention mechanism using MRI multi-modalities brain images.基于深度学习和注意力机制的 MRI 多模态脑图像脑肿瘤分割。
Sci Rep. 2021 May 25;11(1):10930. doi: 10.1038/s41598-021-90428-8.
3
An Intelligent Diagnosis Method of Brain MRI Tumor Segmentation Using Deep Convolutional Neural Network and SVM Algorithm.
基于深度卷积神经网络和支持向量机算法的脑 MRI 肿瘤分割智能诊断方法。
Comput Math Methods Med. 2020 Jul 14;2020:6789306. doi: 10.1155/2020/6789306. eCollection 2020.
4
Brain tumor segmentation and grading of lower-grade glioma using deep learning in MRI images.利用深度学习对MRI图像中的低级别胶质瘤进行脑肿瘤分割与分级
Comput Biol Med. 2020 Jun;121:103758. doi: 10.1016/j.compbiomed.2020.103758. Epub 2020 Apr 22.
5
Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithm.低级别胶质瘤基因组亚型与深度学习算法自动提取的形态特征的关联。
Comput Biol Med. 2019 Jun;109:218-225. doi: 10.1016/j.compbiomed.2019.05.002. Epub 2019 May 3.
6
Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions.用于脑磁共振成像分割的深度学习:现状与未来方向。
J Digit Imaging. 2017 Aug;30(4):449-459. doi: 10.1007/s10278-017-9983-4.
7
Radiogenomics of lower-grade glioma: algorithmically-assessed tumor shape is associated with tumor genomic subtypes and patient outcomes in a multi-institutional study with The Cancer Genome Atlas data.低级别胶质瘤的放射基因组学:在一项利用癌症基因组图谱数据的多机构研究中,通过算法评估的肿瘤形状与肿瘤基因组亚型及患者预后相关。
J Neurooncol. 2017 May;133(1):27-35. doi: 10.1007/s11060-017-2420-1. Epub 2017 May 3.
8
Brain tumor segmentation with Deep Neural Networks.基于深度神经网络的脑肿瘤分割。
Med Image Anal. 2017 Jan;35:18-31. doi: 10.1016/j.media.2016.05.004. Epub 2016 May 19.
9
State of the art survey on MRI brain tumor segmentation.磁共振脑肿瘤分割的最新技术综述。
Magn Reson Imaging. 2013 Oct;31(8):1426-38. doi: 10.1016/j.mri.2013.05.002. Epub 2013 Jun 20.
10
Standardization of analysis sets for reporting results from ADNI MRI data.ADNI MRI 数据结果报告分析集的标准化。
Alzheimers Dement. 2013 May;9(3):332-7. doi: 10.1016/j.jalz.2012.06.004. Epub 2012 Oct 27.