Transfer learning from T1-weighted to T2-weighted Magnetic resonance sequences for brain image segmentation

Magnetic resonance(MR)imaging is a widely employed medical imaging technique that produces detailed anatomical images of the human body.The segmentation of MR im-ages plays a crucial role in medical image analysis,as it enables accurate diagnosis,treatment planning,and monitoring of various diseases and conditions.Due to the lack of sufficient medical images,it is challenging to achieve an accurate segmentation,especially with the application of deep learning networks.The aim of this work is to study transfer learning from T1-weighted(T1-w)to T2-weighted(T2-w)MR sequences to enhance bone segmentation with minimal required computation resources.With the use of an excitation-based convolutional neural networks,four transfer learning mechanisms are proposed:transfer learning without fine tuning,open fine tuning,conservative fine tuning,and hybrid transfer learning.Moreover,a multi-parametric segmentation model is proposed using T2-w MR as an intensity-based augmentation technique.The novelty of this work emerges in the hybrid transfer learning approach that overcomes the overfitting issue and preserves the features of both modalities with minimal computation time and resources.The segmentation results are evaluated using 14 clinical 3D brain MR and CT images.The results reveal that hybrid transfer learning is superior for bone segmentation in terms of performance and computation time with DSCs of 0.5393±0.0007.Although T2-w-based augmentation has no significant impact on the performance of T1-w MR segmentation,it helps in improving T2-w MR segmentation and developing a multi-sequences segmentation model.

An enhanced artificial bee colony optimizer and its application to multi-level threshold image segmentation

A modified artificial bee colony optimizer(MABC)is proposed for image segmentation by using a pool of optimal foraging strategies to balance the exploration and exploitation tradeoff.The main idea of MABC is to enrichartificial bee foraging behaviors by combining local search and comprehensive learning using multi-dimensional PSO-based equation.With comprehensive learning,the bees incorporate the information of global best solution into the solution search equation to improve the exploration while the local search enables the bees deeply exploit around the promising area,which provides a proper balance between exploration and exploitation.The experimental results on comparing the MABC to several successful EA and SI algorithms on a set of benchmarks demonstrated the effectiveness of the proposed algorithm.Furthermore,we applied the MABC algorithm to image segmentation problem.Experimental results verify the effectiveness of the proposed algorithm.

Convolutional neural network-based segmentation network applied to image recognition of angiodysplasias lesion under capsule endoscopy

BACKGROUND Small intestinal vascular malformations(angiodysplasias)are common causes of small intestinal bleeding.While capsule endoscopy has become the primary diagnostic method for angiodysplasia,manual reading of the entire gastrointestinal tract is time-consuming and requires a heavy workload,which affects the accuracy of diagnosis.AIM To evaluate whether artificial intelligence can assist the diagnosis and increase the detection rate of angiodysplasias in the small intestine,achieve automatic disease detection,and shorten the capsule endoscopy(CE)reading time.METHODS A convolutional neural network semantic segmentation model with a feature fusion method,which automatically recognizes the category of vascular dysplasia under CE and draws the lesion contour,thus improving the efficiency and accuracy of identifying small intestinal vascular malformation lesions,was proposed.Resnet-50 was used as the skeleton network to design the fusion mechanism,fuse the shallow and depth features,and classify the images at the pixel level to achieve the segmentation and recognition of vascular dysplasia.The training set and test set were constructed and compared with PSPNet,Deeplab3+,and UperNet.RESULTS The test set constructed in the study achieved satisfactory results,where pixel accuracy was 99%,mean intersection over union was 0.69,negative predictive value was 98.74%,and positive predictive value was 94.27%.The model parameter was 46.38 M,the float calculation was 467.2 G,and the time length to segment and recognize a picture was 0.6 s.CONCLUSION Constructing a segmentation network based on deep learning to segment and recognize angiodysplasias lesions is an effective and feasible method for diagnosing angiodysplasias lesions.

Illumination-Free Clustering Using Improved Slime Mould Algorithm for Acute Lymphoblastic Leukemia Image Segmentation

Partitional clustering techniques such as K-Means(KM),Fuzzy C-Means(FCM),and Rough K-Means(RKM)are very simple and effective techniques for image segmentation.But,because their initial cluster centers are randomly determined,it is often seen that certain clusters converge to local optima.In addition to that,pathology image segmentation is also problematic due to uneven lighting,stain,and camera settings during the microscopic image capturing process.Therefore,this study proposes an Improved Slime Mould Algorithm(ISMA)based on opposition based learning and differential evolution’s mutation strategy to perform illumination-free White Blood Cell(WBC)segmentation.The ISMA helps to overcome the local optima trapping problem of the partitional clustering techniques to some extent.This paper also performs a depth analysis by considering only color components of many well-known color spaces for clustering to find the effect of illumination over color pathology image clustering.Numerical and visual results encourage the utilization of illumination-free or color component-based clustering approaches for image segmentation.ISMA-KM and“ab”color channels of CIELab color space provide best results with above-99%accuracy for only nucleus segmentation.Whereas,for entire WBC segmentation,ISMA-KM and the“CbCr”color component of YCbCr color space provide the best results with an accuracy of above 99%.Furthermore,ISMA-KM and ISMA-RKM have the lowest and highest execution times,respectively.On the other hand,ISMA provides competitive outcomes over CEC2019 benchmark test functions compared to recent well-established and efficient Nature-Inspired Optimization Algorithms(NIOAs).

Improving the Segmentation of Arabic Handwriting Using Ligature Detection Technique

Recognizing handwritten characters remains a critical and formidable challenge within the realm of computervision. Although considerable strides have been made in enhancing English handwritten character recognitionthrough various techniques, deciphering Arabic handwritten characters is particularly intricate. This complexityarises from the diverse array of writing styles among individuals, coupled with the various shapes that a singlecharacter can take when positioned differently within document images, rendering the task more perplexing. Inthis study, a novel segmentation method for Arabic handwritten scripts is suggested. This work aims to locatethe local minima of the vertical and diagonal word image densities to precisely identify the segmentation pointsbetween the cursive letters. The proposed method starts with pre-processing the word image without affectingits main features, then calculates the directions pixel density of the word image by scanning it vertically and fromangles 30° to 90° to count the pixel density fromall directions and address the problem of overlapping letters, whichis a commonly attitude in writing Arabic texts by many people. Local minima and thresholds are also determinedto identify the ideal segmentation area. The proposed technique is tested on samples obtained fromtwo datasets: Aself-curated image dataset and the IFN/ENIT dataset. The results demonstrate that the proposed method achievesa significant improvement in the proportions of cursive segmentation of 92.96% on our dataset, as well as 89.37%on the IFN/ENIT dataset.

Classification and detection of dental images using meta-learning

Meta-learning of dental X-rays is a machine learning technique that can be used to train models to perform new tasks quickly and with minimal input.Instead of just memorizing a task,this is accomplished through teaching a model how to learn.Algorithms for meta-learning are typically trained on a collection of training problems,each of which has a limited number of labelled instances.Multiple Xray classification tasks,including the detection of pneumonia,coronavirus disease 2019,and other disorders,have demonstrated the effectiveness of meta-learning.Meta-learning has the benefit of allowing models to be trained on dental X-ray datasets that are too few for more conventional machine learning methods.Due to the high cost and lengthy collection process associated with dental imaging datasets,this is significant for dental X-ray classification jobs.The ability to train models that are more resistant to fresh input is another benefit of meta-learning.

Artificial intelligence-based medical image segmentation for 3D printing and naked eye 3D visualization

Image segmentation for 3D printing and 3D visualization has become an essential component in many fields of medical research,teaching,and clinical practice.Medical image segmentation requires sophisticated computerized quantifications and visualization tools.Recently,with the development of artificial intelligence(AI)technology,tumors or organs can be quickly and accurately detected and automatically contoured from medical images.This paper introduces a platform-independent,multi-modality image registration,segmentation,and 3D visualization program,named artificial intelligence-based medical image segmentation for 3D printing and naked eye 3D visualization(AIMIS3D).YOLOV3 algorithm was used to recognize prostate organ from T2-weighted MRI images with proper training.Prostate cancer and bladder cancer were segmented based on U-net from MRI images.CT images of osteosarcoma were loaded into the platform for the segmentation of lumbar spine,osteosarcoma,vessels,and local nerves for 3D printing.Breast displacement during each radiation therapy was quantitatively evaluated by automatically identifying the position of the 3D printed plastic breast bra.Brain vessel from multimodality MRI images was segmented by using model-based transfer learning for 3D printing and naked eye 3D visualization in AIMIS3D platform.

Intelligent detection method for workpiece defect based on industrial CT image

In order to solve the problem of internal defect detection in industry, an intelligent detection method for workpiece defect based on industrial computed tomography (CT) images is proposed. The industrial CT slice image is preprocessed first with the combination of adaptive median filtering and adaptive weighted average filtering by analyzing the characteristics of the industrial CT slice images. Then an image segmentation algorithm based on gray change rate is used to segment low contrast information in industrial CT images, and the feature of workpiece defect is extracted by using Hu invariant moment. On this basis, the radial basis function (RBF) neural network model is established and the firefly algorithm is used for optimization, and the intelligent identification of the internal defects of the workpiece is completed. Simulation results show that this method can effectively improve the accuracy of defect identification and provide a theoretical basis for the detection of internal defects in industry.

Optimizing Fully Convolutional Encoder-Decoder Network for Segmentation of Diabetic Eye Disease

In the emerging field of image segmentation,Fully Convolutional Networks(FCNs)have recently become prominent.However,their effectiveness is intimately linked with the correct selection and fine-tuning of hyperparameters,which can often be a cumbersome manual task.The main aim of this study is to propose a more efficient,less labour-intensive approach to hyperparameter optimization in FCNs for segmenting fundus images.To this end,our research introduces a hyperparameter-optimized Fully Convolutional Encoder-Decoder Network(FCEDN).The optimization is handled by a novel Genetic Grey Wolf Optimization(G-GWO)algorithm.This algorithm employs the Genetic Algorithm(GA)to generate a diverse set of initial positions.It leverages Grey Wolf Optimization(GWO)to fine-tune these positions within the discrete search space.Testing on the Indian Diabetic Retinopathy Image Dataset(IDRiD),Diabetic Retinopathy,Hypertension,Age-related macular degeneration and Glacuoma ImageS(DR-HAGIS),and Ocular Disease Intelligent Recognition(ODIR)datasets showed that the G-GWO method outperformed four other variants of GWO,GA,and PSO-based hyperparameter optimization techniques.The proposed model achieved impressive segmentation results,with accuracy rates of 98.5%for IDRiD,98.7%for DR-HAGIS,and 98.4%,98.8%,and 98.5%for different sub-datasets within ODIR.These results suggest that the proposed hyperparameter-optimized FCEDN model,driven by the G-GWO algorithm,is more efficient than recent deep-learning models for image segmentation tasks.It thereby presents the potential for increased automation and accuracy in the segmentation of fundus images,mitigating the need for extensive manual hyperparameter adjustments.

Stacked Gated Recurrent Unit Classifier with CT Images for Liver Cancer Classification

Liver cancer is one of the major diseases with increased mortality in recent years,across the globe.Manual detection of liver cancer is a tedious and laborious task due to which Computer Aided Diagnosis(CAD)models have been developed to detect the presence of liver cancer accurately and classify its stages.Besides,liver cancer segmentation outcome,using medical images,is employed in the assessment of tumor volume,further treatment plans,and response moni-toring.Hence,there is a need exists to develop automated tools for liver cancer detection in a precise manner.With this motivation,the current study introduces an Intelligent Artificial Intelligence with Equilibrium Optimizer based Liver cancer Classification(IAIEO-LCC)model.The proposed IAIEO-LCC technique initially performs Median Filtering(MF)-based pre-processing and data augmentation process.Besides,Kapur’s entropy-based segmentation technique is used to identify the affected regions in liver.Moreover,VGG-19 based feature extractor and Equilibrium Optimizer(EO)-based hyperparameter tuning processes are also involved to derive the feature vectors.At last,Stacked Gated Recurrent Unit(SGRU)classifier is exploited to detect and classify the liver cancer effectively.In order to demonstrate the superiority of the proposed IAIEO-LCC technique in terms of performance,a wide range of simulations was conducted and the results were inspected under different measures.The comparison study results infer that the proposed IAIEO-LCC technique achieved an improved accuracy of 98.52%.

An Intelligent Decision Support System for Lung Cancer Diagnosis

Lung cancer is the leading cause of cancer-related death around the globe.The treatment and survival rates among lung cancer patients are significantly impacted by early diagnosis.Most diagnostic techniques can identify and classify only one type of lung cancer.It is crucial to close this gap with a system that detects all lung cancer types.This paper proposes an intelligent decision support system for this purpose.This system aims to support the quick and early detection and classification of all lung cancer types and subtypes to improve treatment and save lives.Its algorithm uses a Convolutional Neural Network(CNN)tool to perform deep learning and a Random Forest Algorithm(RFA)to help classify the type of cancer present using several extracted features,including histograms and energy.Numerous simulation experiments were conducted on MATLAB,evidencing that this system achieves 98.7%accuracy and over 98%precision and recall.A comparative assessment assessing accuracy,recall,precision,specificity,and F-score between the proposed algorithm and works from the literature shows that the proposed system in this study outperforms existing methods in all considered metrics.This study found that using CNNs and RFAs is highly effective in detecting lung cancer,given the high accuracy,precision,and recall results.These results lead us to believe that bringing this kind of technology to doctors diagnosing lung cancer is critical.

基于改进HRNet的遥感影像冬小麦语义分割方法

冬小麦在影像中呈现田块碎小且分布零散等空间特征,同时影像包含的复杂地物对冬小麦识别造成干扰,易出现识别精度低且边界分割模糊等问题。为及时准确获取大范围冬小麦空间分布信息,该研究以高分二号卫星影像作为数据源,提出一种CAHRNet(change attention high-resolution Net)语义分割模型。采用HRNet(high-resolution Net)替换ResNet作为模型的主干网络,网络的并行交互方式易获取高分辨率的特征信息;联合OCR(object-contextual representations)模块聚合上下文信息,以增强像素点与目标对象区域的关联性;3)引入坐标注意力(coordinate attention)机制,使网络模型充分利用有效的空间位置信息,以保留分割区域的边缘细节,提高对分布零散、形状多变的冬小麦田块的特征提取能力。试验结果表明,在自制的高分辨率遥感数据集上,CAHRNet模型的平均交并比(mean intersection over union,MIoU)和像素准确率(pixel accuracy, PA)分别达到81.72%和97.08%,MIoU相较U-Net、DeepLabv3+分别提高了9.09、2.44个百分点;PA相较U-Net、DeepLabv3+分别提高6.80、1.59个百分点,说明CAHRNet模型具有较高的分割识别精度,可为进一步准确获取冬小麦作物分布信息提供技术支撑。

人工智能辅助染色体核型分析技术在产前诊断中的应用研究

背景染色体异常是导致出生缺陷的常见原因,核型分析仍是产前诊断染色体异常的重要方法,也是出生缺陷防控的有效手段,但目前核型分析尤其是染色体图像分割分类主要依靠人工,费时费力。人工智能(AI)是核型分析的一种新方式,研究其在产前染色体核型诊断中的价值具有重要意义。目的探讨AI在产前染色体核型诊断中的应用效果和临床价值。方法选取2020—2022年在无锡市妇幼保健院医学遗传与产前诊断科接受介入性产前诊断、行羊水染色体核型分析的1000例孕妇。采用双线模式:一线AI阅片后,由1名遗传医师审核,二线由另1名遗传医师应用Ikaros核型分析工作站阅片,记录各自的诊断结果及所需时间。样本的最终诊断结果以一线的人工审核和二线的人工阅片结果为准。结果1000例羊水样本中,AI诊断正常核型735例、非整倍体233例、结构异常0例、嵌合体32例。AI辅助遗传医师的诊断结果与遗传医师应用Ikaros系统的诊断结果完全一致,正常核型、非整倍体、结构异常、嵌合体分别是689、233、45、33例。与AI辅助遗传医师相比,AI诊断具有强一致性(Kappa值=0.895,95%CI=0.866~0.924,P<0.01)。AI诊断准确率为95.4%,灵敏度为95.4%,阳性预测值为100.0%。其中,诊断正常核型、非整倍体、结构异常、嵌合体的灵敏度分别为100.0%、100.0%、0、97.0%;阳性预测值分别为100.0%、100.0%、0、100.0%。AI平均诊断用时少于AI辅助遗传医师和Ikaros辅助遗传医师(P<0.001);AI辅助遗传医师平均诊断用时少于Ikaros辅助遗传医师组(P<0.001)。结论AI分析羊水核型的自动化程度高,但识别染色体结构异常的能力有待提高,建议采用AI联合遗传医师阅片的方式应用于临床,以保证产前诊断的质量并提高效率。

复杂作业环境下钢包的位置姿态安全信息感知

对恶劣环境下钢包运行动作姿态信息的有效感知是钢铁安全生产管控智能化需要解决的重要问题。总结钢包运行的时序信息特征,将钢包运行时的复杂安全信息分解为一系列可识别的基础动作,在此基础上构建钢包动作识别数据集。选用时序动作检测模型识别钢包动作信息,并根据钢包运行的视觉特性及精准定位需求将原网络目标检测分支替换为改进后的你只看一次(You Only Look Once,YOLOv8)图像分割模型。试验结果表明,改进后的模型所占存储容量减少63.98%,计算需求降低40.6%;识别准确率和召回率分别提高了0.95%与0.51%,且mAP50达到98.6%,能满足钢包实时精准定位的需求。改进后的时序动作检测模型各类动作平均识别准确率达到87.44%。研究表明,所提出时空动作检测改进模型能有效检测复杂环境内钢包的位置信息与基础动作信息,可以满足钢包复杂工序识别、目标追踪、碰撞预警、倾覆洞穿预警等安全检测任务的需求,降低安全管控所需的人力物力成本。

拉普拉斯卷积的双路径特征融合遥感图像智能解译方法

由于遥感图像存在多尺度变化和目标边缘模糊等问题,对其进行智能解译仍然是一项极具挑战性的工作。传统的语义分割方法在处理这些问题时存在局限性,难以有效捕捉全局和局部信息。针对上述问题,文中提出一种双路径特征融合分割方法 DFNet。首先,使用Swin Transformer作为主干提取全局语义特征,以处理像素之间的长距离依赖关系,从而促进对图像中不同区域相关性的理解;其次,将拉普拉斯卷积嵌入到空间分支,以捕获局部细节信息,加强目标地物边缘信息表达;最后,引入多尺度双向特征融合模块,充分利用图像中的全局和局部信息,以增强多尺度信息的获取能力。在实验中,使用了三个公开的高分辨率遥感图像数据集进行验证,并通过消融实验验证了所提模型不同模块的作用。实验结果表明,所提方法在Uavid数据集、Potsdam数据集、LoveDA数据集的mIoU达到了71.32%、85.58%、54.01%,提高了语义分割的性能,使分割结果更为精细。

高精度视觉感应技术在水肥一体机中的应用

以农田水肥智能化管理为研究对象,构建了一种高精度视觉感应式水肥一体机。采用高精度视觉感应技术获取作物生长状态参数图像,基于超像素图像分割技术,对复杂的作物生长状态图像特征向量进行提取,采用模糊聚类算法对图像进行分割处理,根据目标图像的像素值统计结果进行生长状态预测,并结合环境参数信息,构建灌溉过程土壤电导率EC和pH预测模型。测试结果表明:水肥一体机控制系统能够有效预测作物对水肥需求,提高了灌溉过程混肥精度,可节约灌溉用水量、提升生产效率、降低人工成本。

基于RGB模型的汽车指针仪表示数的识别

本文对汽车指针仪表示数的识别,提出了一种基于RGB彩色空间图像处理的识别方案。首先,根据仪表盘图像的R、G、B分量的直方图,利用该分量的欧几里德距离法分割仪表盘的圆心和指针;然后,提取圆心的骨架和圆心的坐标,建立新的坐标系;最后,将指针的质心和仪表盘的圆心连成一条直线,通过直线位置识别指针读数。实验证明:该方法可用于指针式汽车仪表的自动化测试。

人工智能在视网膜图像自动分割和疾病诊断中的应用指南(2024)

人工智能技术的快速发展推动了医学的智能化进程。近年来,随着机器学习和深度学习等技术的不断提高,人工智能技术在眼底疾病诊疗中得到了快速发展和应用。眼底疾病主要包括视网膜血管病、黄斑疾病、视网膜脱离、视网膜色素变性等,早期诊断及治疗对改善眼底疾病的预后具有重大意义。本文就人工智能在视网膜图像自动分割和疾病诊断中的应用形成指南,为人工智能在该领域中的进一步研究和应用提供参考。

基于解耦区域校准的高分辨率超像素生成算法

超像素分割是计算机视觉领域的一项重要任务,该任务将具有相似属性的像素分组到称为超像素的簇中.图像超像素不仅可以增益图像注释,而且还是各种下游应用的基础,如分割、光流估计和深度估计.尽管超像素分割技术取得了显著进展,特别是随着深度学习方法的出现,但现有解决方案由于GPU内存和计算能力的限制,一直无法有效处理高分辨率图像.针对这个问题,作者提出了一种名为区域解耦校准的高分辨率超像素网络(Patch Calibration Network,PCNet)的新型深度学习框架,通过采用解耦的一致性学习策略,解决了现有方法的局限性.这种方法允许通过从低分辨率输入预测高分辨率输出来高效生成高分辨率超像素结果,从而绕过了GPU内存限制.PCNet的一个关键贡献是解耦的区域块校准(DPC)分支,它将高分辨率图像块作为额外输入,以保留细节并增强边界像素分配.为了改善边界像素的识别,作者利用二进制掩模设计了一种动态引导训练机制.这种机制鼓励网络专注于区域内的主要边界,将任务从多类分类简化为二分类问题.这一创新策略不仅减少了网络优化的复杂性,而且显著提高了边界检测的精度.本文通过在包括Mapillary Vistas、BIG和新创建的Face-Human数据集在内的多样化数据集上进行广泛的实验,证明了PCNet的有效性.结果表明,PCNet能够成功处理5K分辨率图像,并与现有的最先进的SCN方法相比,实现了更优越的性能,后者在处理高分辨率输入时存在困难.作者的贡献包括开发了PCNet,一种针对高分辨率超像素分割的深度学习解决方案,引入了解耦的区域校准架构,并构建了一个超高分辨率基准测试集,用于评估高分辨率场景中超像素分割算法的性能.本文首先回顾了超像素分割领域的相关工作,然后详细介绍了PCNet框架,接着展示了实验结果并与最先进的方法进行了比较.结论部分总结了研究结果并概述了未来研究的潜在方向.代码、预训练模型和新的基准数据集的可用性无疑将促进高分辨率超像素分割领域的进一步发展.总之,本文在超像素分割领域提供了一个重要的进步,提供了一种能够高效、准确处理高分辨率图像的解决方案.所提出的PCNet框架,凭借其创新的DPC分支和动态引导训练机制,为未来在计算机视觉领域的研究和应用提供了一个有前景的方向.本文的代码、预训练模型以及新构建的评估基准数据集可在https://github.com/wangyxxjtu/PCNet上获取.

深度学习对膝骨关节炎MRI图像智能分割和测量分析的作用及意义

背景:MRI对诊断早期膝骨关节炎有重要意义。利用深度学习方法进行膝骨关节炎的MRI图像识别和智能分割,是目前人工智能在影像诊断方面的研究热点。目的:通过对膝骨关节炎病例MRI图像的深度学习,能够全自动分割膝关节的股骨、胫骨、髌骨、软骨、半月板、韧带、肌肉及关节积液,并测量膝关节积液体积和肌肉含量。方法:筛选出100个正常膝关节和100个膝骨关节炎患者数据,按照8︰1︰1的比例随机分为训练集(traindataset,n=160)、调优集(validation dataset,n=20)和测试集(test dataset,n=20)。采用Coarse-to-Fine序贯训练的方法训练3D-UNET网络深度学习模型,先训练一个膝关节矢状面MRI粗略分割模型,将得到的粗略分割结果作为掩膜(mask),再训练精细分割模型。输入膝关节矢状面T1WI、T2WI图像和各结构的标注文件,运用DeepLab v3,分割骨、软骨、韧带、半月板、肌肉、积液,最后显示三维重建,显示自动测量结果(肌肉的含量、积液的体积),完成深度学习的应用程序。再筛选出26例正常人和38例膝骨关节炎患者的膝关节MRI数据进行测试验证。结果与结论:①26例正常人中女13例,男13例,平均年龄(34.88±11.75)岁,膝关节中肌肉含量平均值(1051322.94±2007249.00)mL,均值中位数为631165.21 mL;积液的体积平均值(291.85±559.59)mL,均值中位数0 mL。②38例膝骨关节炎患者中女30例,男8例,平均年龄(68.53±9.87)岁;肌肉含量平均值(782409.18±331392.56)mL,均值中位数689105.66 mL;积液的体积平均值(1625.23±5014.03)mL,均值中位数178.72 mL。③正常人的肌肉含量与膝骨关节炎患者的相差不大,差异无显著性意义;而膝骨关节炎患者积液的体积高于正常人,差异有显著性意义(P<0.05)。④提示通过深度学习对膝骨关节炎MRI图像进行智能分割,可摒弃以往手工分割的缺陷;对膝骨关节炎的评估需要更加精细化,将图像分割处理得更加精细,以提高结果的精度。