脑肿瘤及脑肿瘤图像分类的研究进展

脑肿瘤分类的方法很多,目前尚无统一的分类方法,并且各种肿瘤的组织发生与病理特征不同,其良性与恶性以及物学特性也不一样。通常按组织学可分类如下：（1）发源于神经胶质的肿瘤：星形细胞瘤、少支胶质细胞瘤、髓母细胞瘤等。（2）发源于脑膜的肿瘤：脑膜瘤、脑膜肉瘤、蛛网膜囊肿等。（3）发源于垂体的肿瘤：厌色细胞腺瘤,嗜酸、嗜碱性细胞腺瘤。（4）发源于颅神经的肿瘤：听神经瘤、三又神经瘤等各种神经鞘瘤。（5）发源于胚胎残余组织：颅咽管瘤、脊索瘤、皮样囊肿等。（6）发源于血管细胞：血管瘤及血管网织细胞瘤等。（7）由其它部位转移或侵入的肿瘤：各种转移瘤及鼻咽癌等。     

脑肿瘤及脑肿瘤图像分类的研究进展

脑肿瘤分类的方法很多,目前尚无统一的分类方法,并且各种肿瘤的组织发生与病理特征不同,其良性与恶性以及物学特性也不一样。通常按组织学可分类如下:(1)发源于神经胶质的肿瘤:星形细胞瘤、少支胶质细胞瘤、髓母细胞瘤等。(2)发源于脑膜的肿瘤:脑膜瘤、脑膜肉瘤、蛛网膜囊肿等。(3)发源于垂体的肿瘤:厌色细胞腺瘤,嗜酸、嗜碱性细胞腺瘤。(4)发源于颅神经的肿瘤:听神经瘤、三叉神经瘤等各种神经鞘瘤。(5)发源于胚胎残余组织:颅咽管瘤、脊索瘤、皮样囊肿等。(6)发源于血管细胞:血管瘤及血管网织细胞瘤等。(7)由其它部位转移或侵入的肿瘤:各种转移瘤及鼻咽癌等。     

基于Snake模型的医学图像分割

基于Snake模型的图像分割技术是近年来图像处理领域的研究热点之一。Snake模型承载上层先验知识并融合了图像的底层特征,针对医学图像的特殊性,能有效地应用于医学图像的分割中。本文对各种基于Snake模型的改进算法和进化模型进行了研究,并重点梳理了最新的研究成果,以利于把握基于Snake模型的医学图像分割方法的脉络和发展方向。     

一种新的基于蒙特卡罗模拟和光子传输模型的图像分割算法

本文以蒙特卡罗模拟方法为基础,结合组织光学的光子传输模型,提出了一种新的图像分割算法,该算法将复杂的图像分割问题简化为大量简单的光子传输随机实验,通过分析传输规律来获取目标区域.在随后的实验中,结合细胞核提取这一问题建立了一个简单的光学传输模型,并依据此模型分别对人造图和实际图进行了分割.人造图的分割结果表明了该算法的可行性,说明了该算法的一些优点;而实际图的分割结果则反映了该算法的不足之处,文章针对其中存在的问题和算法待改进之处进行了分析.     

基于知识的颅内出血（ICH）三维医学图像分割方法

本文描述一种基于知识的三维医学图像自动分割方法,用于进行人体颅内出血(Intracranial Hemorrhage,ICH)的分割和分析。首先,数字化CT胶片,并自动对数字化后的胶片按照有无异常分类。然后,阀值结合模糊C均值聚类算法将图像分类成多个具有统一亮度的区域。最后,在先验知识以及预定义的规则的基础上,借助基于知识的专家系统将各个区域标记为背景、钙化点、血肿、颅骨、脑干。     

基于双模型融合的大熊猫头部图像分割

在大熊猫(Ailuropoda melanoleuca)的迁地保护和种群饲养管理中,及时、快速地进行个体识别和行为监测,对其健康管理具有至关重要的作用。圈养大熊猫健康状况通常由专门的饲养人员肉眼观测,人力成本高、效率低并且缺乏时效性。基于图像的动物个体识别与行为分析技术效率高、时间成本低,已经成为新的监测发展趋势。已有研究提出,通过大熊猫面部图像的检测和分析,可实现个体识别和行为分类。但该方法依然存在检测精度不足导致识别准确率难以提升的问题。本文提出一种基于YOLOv3和Mask R-CNN的双模型融合方法,实现了大熊猫头部图像分割和精准检测。包含3个部分：YOLOv3完成头部检测,Mask R-CNN完成大熊猫轮廓分割,然后将两个模型的输出进行交并比融合。结果显示,头部检测准确率为82.6%,大熊猫轮廓分割准确率为95.2%,总体头部轮廓分割准确率为87.1%。该方法对大熊猫头部图像的识别率和分割准确率高,为大熊猫的个体识别、性别分类提供了帮助,为行为分析提供了技术参考。     

基于K-means聚类算法的叶螨图像分割与识别

【目的】叶螨(spider mite)是为害多种农作物的主要害虫,叶螨识别传统方法依靠肉眼,比较费时费力,为研究快速自动识别方法,引入计算机图像分析算法。【方法】该方法基于K-means聚类算法对田间作物上的叶螨图像进行分割与识别。【结果】对比传统RGB彩色分割方法,K-means聚类算法能够有效地对叶片上叶螨图像进行分割和识别。K-means聚类算法平均识别时间为3.56 s,平均识别准确率93.95%。识别时间 T 随图像总像素 Pi 的增加而增加。【结论】K-means聚类组合算法能够应用于叶螨图像分割与识别。     

基于F3Net显著性目标检测的蝴蝶图像前背景自动分割

[目的]具有复杂背景的蝴蝶图像前背景分割难度大.本研究旨在探索基于深度学习显著性目标检测的蝴蝶图像自动分割方法.[方法]应用DUTS-TR数据集训练F3Net显著性目标检测算法构建前背景预测模型,然后将模型用于具有复杂背景的蝴蝶图像数据集实现蝴蝶前背景自动分割.在此基础上,采用迁移学习方法,保持ResNet骨架不变,利...     

基于最大熵和改进PCNN的医学图像自动分割算法研究与实现

本文提出了基于最大熵和改进的PCNN(Pulse Coupled Neural Network)相结合的新方法,采用最大熵确定PCNN网络的循环迭代次数.提出的方法无需考虑PCNN参数的选择,可有效的自动分割各种医学图像,同时利用最大熵得到最优分割结果.该方法对于PCNN理论在医学图像分割领域的应用有着重要的意义.     

基于改进C-V模型的超声心动图像轮廓的提取方法

目的:通过超声图像预处理和对图像分割方法的改进,完成超声心动图中心腔轮廓的提取。方法:首先,运用基于斑点指数的滤波方法对超声图像进行去噪。其次,对超声图像进行分段非线性灰度变换,提高图像对比度。最后,利用改进的基于C-V模型的水平集算法对超声图像进行分割,得到精确的初始轮廓。结果:1基于斑点指数的图像滤波方法可以在不丢失细节的情况下对超声图像进行噪声滤除。2分段非线性灰度变换可以有效提高超声图像的对比度。3改进的C-V模型可以成功的对含有斑点噪声的超声图像进行分割。结论:本文的超声图像预处理方法和分割算法可以有效提取心腔轮廓,降低斑点噪声对图像分割结果的影响。     

A Review on Convolutional Neural Networks for Brain Tumor Segmentation: Methods,Datasets, Libraries,and Future Directions

ObjectivesAccurate and reliable segmentation of brain tumors from MRI images helps in planning an enhanced treatment and increases the life expectancy of patients. However, the manual segmentation of brain tumors is subjective and more prone to errors. Nonetheless, the recent advances in convolutional neural network (CNN)-based methods have exhibited outstanding potential in robust segmentation of brain tumors. This article comprehensively investigates recent advances in CNN-based methods for automatic segmentation of brain tumors from MRI images. It examines popular deep learning (DL) libraries/tools for an expeditious and effortless implementation of CNN models. Furthermore, a critical assessment of current DL architectures is delineated along with the scope of improvement.MethodsIn this work, more than 50 scientific papers from 2014-2020 are selected using Google Scholar and PubMed. Also, the leading journals related to our work along with proceedings from major conferences such as MICCAI, MIUA and ECCV are retrieved. This research investigated various annual challenges too related to this work including Multimodal Brain Tumor Segmentation Challenge (MICCAI BRATS) and Ischemic Stroke Lesion Segmentation Challenge (ISLES).ResultAfter a systematic literature search pertinent to the theme, we found that principally there exist three variations of CNN architecture for brain tumor segmentation: single-path and multi-path, fully convolutional, and cascaded CNNs. The respective performances of most automated methods based on CNN are appraised on the BraTS dataset, provided as a part of the MICCAI Multimodal Brain Tumor Segmentation challenge held annually since 2012.ConclusionNotwithstanding the remarkable potential of CNN-based methods, reliable and robust segmentation of brain tumors continues to be an intractable challenge. This is due to the intricate anatomy of the brain, variability in its appearance, and imperfection in image acquisition. Moreover, owing to the small size of MRI datasets, CNN-based methods cannot operate with their full capacity, as demonstrated with large scale datasets, such as ImageNet.     

Walsh Hadamard Transform for Simple Linear Iterative Clustering (SLIC) Superpixel Based Spectral Clustering of Multimodal MRI Brain Tumor Segmentation

The automated brain tumor segmentation methods are challenging due to the diverse nature of tumors. Recently, the graph based spectral clustering method is utilized for brain tumor segmentation to make high-quality segmentation output. In this paper, a new Walsh Hadamard Transform (WHT) texture for superpixel based spectral clustering is proposed for segmentation of a brain tumor from multimodal MRI images. First, the selected kernels of WHT are utilized for creating texture saliency maps and it becomes the input for the Simple Linear Iterative Clustering (SLIC) algorithm, to generate more precise texture based superpixels. Then the texture superpixels become nodes in the graph of spectral clustering for segmenting brain tumors of MRI images. Finally, the original members of superpixels are recovered to represent Complete Tumor (CT), Tumor Core (TC) and Enhancing Tumor (ET) tissues. The observational results are taken out on BRATS 2015 datasets and evaluated using the Dice Score (DS), Hausdorff Distance (HD) and Volumetric Difference (VD) metrics. The proposed method produces competitive results than other existing clustering methods.     

A Hybrid CNN-SVM Threshold Segmentation Approach for Tumor Detection and Classification of MRI Brain Images

ObjectiveIn this research paper, the brain MRI images are going to classify by considering the excellence of CNN on a public dataset to classify Benign and Malignant tumors.Materials and MethodsDeep learning (DL) methods due to good performance in the last few years have become more popular for Image classification. Convolution Neural Network (CNN), with several methods, can extract features without using handcrafted models, and eventually, show better accuracy of classification. The proposed hybrid model combined CNN and support vector machine (SVM) in terms of classification and with threshold-based segmentation in terms of detection.ResultThe findings of previous studies are based on different models with their accuracy as Rough Extreme Learning Machine (RELM)-94.233%, Deep CNN (DCNN)-95%, Deep Neural Network (DNN) and Discrete Wavelet Autoencoder (DWA)-96%, k-nearest neighbors (kNN)-96.6%, CNN-97.5%. The overall accuracy of the hybrid CNN-SVM is obtained as 98.4959%.ConclusionIn today's world, brain cancer is one of the most dangerous diseases with the highest death rate, detection and classification of brain tumors due to abnormal growth of cells, shapes, orientation, and the location is a challengeable task in medical imaging. Magnetic resonance imaging (MRI) is a typical method of medical imaging for brain tumor analysis. Conventional machine learning (ML) techniques categorize brain cancer based on some handicraft property with the radiologist specialist choice. That can lead to failure in the execution and also decrease the effectiveness of an Algorithm. With a brief look came to know that the proposed hybrid model provides more effective and improvement techniques for classification.     

SegNet and Salp Water Optimization-driven Deep Belief Network for Segmentation and Classification of Brain Tumor

Classification of brain tumor in Magnetic Resonance Imaging (MRI) images is highly popular in treatment planning, early diagnosis, and outcome evaluation. It is very difficult for classifying and diagnosing tumors from several images. Thus, an automatic prediction strategy is essential in classifying brain tumors as malignant, core, edema, or benign. In this research, a novel approach using Salp Water Optimization-based Deep Belief network (SWO-based DBN) is introduced to classify brain tumor. At the initial stage, the input image is pre-processed to eradicate the artifacts present in input image. Following pre-processing, the segmentation is executed by SegNet, where the SegNet is trained using the proposed SWO. Moreover, the Convolutional Neural Network (CNN) features are employed to mine the features for future processing. At last, the introduced SWO-based DBN technique efficiently categorizes the brain tumor with respect to the extracted features. Thereafter, the produced output of the introduced SegNet + SWO-based DBN is made use of in brain tumor segmentation and classification. The developed technique produced better results with highest values of accuracy at 0.933, specificity at 0.880, and sensitivity at 0.938 using BRATS, 2018 datasets and accuracy at 0.921, specificity at 0.853, and sensitivity at 0.928 for BRATS, 2020 dataset.     

脑脓肿与脑转移瘤的CT、M租诊断与鉴别诊断

目的：探索CT与MRI对脑脓肿及脑转移瘤的诊断及鉴别诊断价值。方法：对经病理及临床确诊的脑转移瘤及脑脓肿各20例,分别进行CT、MRI的平扫及增强扫描,对其影像表现进行比较分析,研究鉴别诊断的可能性。结果：脑脓肿多以全身或局部感染为首发症状,影像学表现病灶多为单发,平扫以囊性或囊实性表现为主,呈环状强化,壁薄,光滑,无壁结节。周围水肿以轻、中度片状水肿为主。脑转移瘤多以颅内压增高为首发症状,影像学表现多为多发,平扫以低、等密度为主,较小者呈结节状强化,边缘规则,较大者呈环状、花环状、结节状强化,壁厚薄不均,可见壁结节,周围大片状指状水肿。结论：脑脓肿及脑转移瘤具有不同的影像表现,CT及MRI具有较大的诊断意义。     

右美托咪啶复合芬太尼及七氟烷用于脑肿瘤手术的麻醉效果及对血流动力学的影响

目的:探讨右美托咪啶复合芬太尼及七氟烷用于脑肿瘤手术的麻醉效果及对血流动力学的影响。方法:择期全麻下行脑肿瘤切除术患者40例,随机分为右美托咪啶组(D组)和丙泊酚组(P组)各20例。麻醉诱导前D组静脉输注右美托咪啶0.5μg/kg,P组给予同等容量的生理盐水,均15 min泵注完成。静脉注射咪唑安定、芬太尼、顺式阿曲库铵、依托咪酯行麻醉诱导。术中均用芬太尼、七氟烷、顺式阿曲库铵维持麻醉,D组持续静脉输注右美托咪啶0.2~1.0μg·kg-1·h-1,P组给予丙泊酚3~10 mg·kg-1·h-1,调整右美托咪啶及丙泊酚用量,使BIS值维持于40~50。于麻醉用药前(基础值)(T0)、麻醉诱导气管插管前(T1)、气管插管后(T2)、切开硬脑膜(T3)、取瘤(T4)、术毕(T5)、拔气管导管时(T6)记录心率(HR)、血压(SBP、DBP)。记录手术时间、输液量、出血量、苏醒时间、拔管时间及拔管后10 min警觉/镇静(OAA/S)评分。结果:与T0比较,D组T1、T3、T4时SBP、DBP明显降低(P0.05),HR明显减慢(P0.05),但仍接近正常值,P组T1时SBP、DBP明显降低(P0.05),HR明显减慢(P0.05),T2、T5、T6时SBP、DBP明显升高(P0.05),HR明显加快(P0.05)。与P组比较,T2~T6时D组SBP、DBP明显低于P组(P0.05),HR明显慢于P组(P0.05)。D组苏醒时间、拔管时间明显短于P组(P0.05),拔管后10min OAA/S评分显著高于P组(P0.05)。结论:右美托咪啶或丙泊酚复合芬太尼、七氟烷麻醉用于脑肿瘤手术均能够提供满意的麻醉效果,右美托咪啶能抑制气管插管、拔管等引起的血流动力学反应,术后苏醒快且苏醒质量高。     

MR 脑图像海马自动分割法在AD 早期诊断中的应用研究

目的:研究磁共振(Magnetic resonance,MR)脑图像中海马的自动分割方法及海马的形态学分析方法,为阿尔茨海默病(Alzheimer’s disease,AD)的早期诊断提供依据。方法:对20例AD患者和60名正常对照者行MRI T1 WI 3D容积扫描,建立海马的三维主动表观模型,并以此模型对每个个体脑部磁共振图像上的海马进行自动识别和三维分割,分别建立正常对照组和AD组的海马统计形状模型,比较AD组与正常对照组间海马形状的差异性。结果:海马三维分割方法与手动分割方法在海马体积测量上无统计学差别(P>0.05);AD患者海马头部发生萎缩(P<0.05)。结论:基于主动表观模型的MR脑图像海马自动识别和三维分割法是准确可靠的;海马头部萎缩可作为AD诊断的依据之一。     

目标导向液体管理策略对脑肿瘤切除术患者血乳酸水平、血流动力学及认知功能的影响

摘要 目的：探讨目标导向液体管理策略对脑肿瘤切除术患者血乳酸水平、血流动力学及认知功能的影响。方法：选择2016年1月至2019年10月于山东第一医科大学第二附属医院行脑肿瘤切除术的患者110例,以随机数字表法分为对照组和研究组,每组55例,对照组患者接受常规输液管理,研究组患者接受目标导向液体管理,观察两组患者晶体液用量、胶体液用量、输液总量、失血量、尿量情况,对比两组麻醉诱导前（T0）、气管插管即刻（T1）、切开硬脑膜即刻（T2）和手术结束时（T3）动脉乳酸（aLac）、静脉乳酸（vLac）、动静脉乳酸差值（△Lac）、脑乳酸生成率（Lac PR）、血流动力学水平以及两组患者术前、术后1 d、术后3 d、术后7 d 简易智力状态量表（MMSE）评分。结果：研究组胶体液用量、输液总量及尿量显著高于对照组（P<0.05）。T1、T2、T3时间点研究组aLac、vLac、△Lac、Lac PR显著低于对照组（P＜0.05）。T3时间点研究组心脏指数（CI）、平均动脉压（MAP）、动脉血氧含量（CaO₂）显著高于对照组（P＜0.05）。术后1 d、术后3 d、术后7 d研究组MMSE评分显著高于对照组（P＜0.05）。结论：目标导向液体管理策略能够降低脑肿瘤切除术患者术后血液中乳酸水平,改善患者血流动力学,减轻手术及麻醉对患者认知功能的影响。     

Three-dimensional Cell Culture Model for Measuring the Effects of Interstitial Fluid Flow on Tumor Cell Invasion

The growth and progression of most solid tumors depend on the initial transformation of the cancer cells and their response to stroma-associated signaling in the tumor microenvironment ¹. Previously, research on the tumor microenvironment has focused primarily on tumor-stromal interactions ^1-2. However, the tumor microenvironment also includes a variety of biophysical forces, whose effects remain poorly understood. These forces are biomechanical consequences of tumor growth that lead to changes in gene expression, cell division, differentiation and invasion³. Matrix density ⁴, stiffness ^5-6, and structure ^6-7, interstitial fluid pressure ⁸, and interstitial fluid flow ⁸ are all altered during cancer progression.Interstitial fluid flow in particular is higher in tumors compared to normal tissues ^8-10. The estimated interstitial fluid flow velocities were measured and found to be in the range of 0.1-3 μm s^-1, depending on tumor size and differentiation ^{9, 11}. This is due to elevated interstitial fluid pressure caused by tumor-induced angiogenesis and increased vascular permeability ¹². Interstitial fluid flow has been shown to increase invasion of cancer cells ^13-14, vascular fibroblasts and smooth muscle cells ¹⁵. This invasion may be due to autologous chemotactic gradients created around cells in 3-D ¹⁶ or increased matrix metalloproteinase (MMP) expression ¹⁵, chemokine secretion and cell adhesion molecule expression ¹⁷. However, the mechanism by which cells sense fluid flow is not well understood. In addition to altering tumor cell behavior, interstitial fluid flow modulates the activity of other cells in the tumor microenvironment. It is associated with (a) driving differentiation of fibroblasts into tumor-promoting myofibroblasts ¹⁸, (b) transporting of antigens and other soluble factors to lymph nodes ¹⁹, and (c) modulating lymphatic endothelial cell morphogenesis ²⁰.The technique presented here imposes interstitial fluid flow on cells in vitro and quantifies its effects on invasion (Figure 1). This method has been published in multiple studies to measure the effects of fluid flow on stromal and cancer cell invasion ^{13-15, 17}. By changing the matrix composition, cell type, and cell concentration, this method can be applied to other diseases and physiological systems to study the effects of interstitial flow on cellular processes such as invasion, differentiation, proliferation, and gene expression.     

Finite Element Model to Reproduce the Effect of Pre-Stress and Needle Insertion Velocity During Infusions into Brain Phantom Gel

Convection-enhanced delivery (CED) is a technique to bypass the blood-brain barrier and deliver therapeutic agents into the brain. However, animal studies and preliminary clinical trials have reported reduced efficacy to transport drugs in specific regions, attributed mainly to backflow, in which an annular zone is formed outside the catheter and the fluid preferentially flows toward the surface of the brain rather than through the tissue toward the targeted area. In this study, a finite element model of backflow was updated by implementing the pre-stress generated during needle insertion, which allows considering the effect of needle insertion velocity during CED infusions in agarose gel. The nonlinear mechanical properties of the agarose solutions were obtained by fitting experimental data from stress-relaxation tests. Additional experimental measurements of backflow lengths were used to adjust the pre-stress model. The developed model was able to reproduce changes of backflow length under different insertions velocities and flow rates. These findings reveal the relevance of considering the pre-stress in the tissue located around the needle surface during CED infusions into the brain.