无线胶囊内窥镜图像小肠息肉的自动识别

息肉是小肠常见疾病之一。无线胶囊内窥镜(WCE)是检查小肠疾病的常规手段,但每次检查都会产生大量图像,却仅可能包含少数病变图像。目前WCE病变的筛查高度依赖于医生的临床经验,耗时费力,且可能发生漏检或误检,因此实现WCE图像小肠息肉的自动识别意义重大。基于深度学习框架,结合数据增强技术和迁移学习策略,提出实现小肠息肉识别的新方法。基于原始数据集(包含4 300张正常图像和429张息肉图像)和拓展数据集(包含6 920张正常图像和6 864张息肉图像),对比分析不同的深度卷积神经网络模型(AlexNet、VGGNet和GoogLeNet)对息肉的识别效果。实验结果表明,在随机初始化的卷积神经网络中,GoogLeNet模型对息肉的识别效果最好,其敏感性、特异性和准确性分别达到97.18%、98.78%和97.99%,说明增加网络深度可以有效提高识别率。但网络深度增加需要更高的硬件配置和训练时间,因此结合迁移学习策略,AlexNet模型的敏感性、特异性和准确性分别达到了96.57%、98.89%和97.74%,AUC为0.996,表明该方法能有效提高模型整体性能,同时降低对训练时间和实验配置的要求。与传统手工提取图像特征或仅基于深层卷积神经网络进行分类的方法相比,所提出的方法可以在有限的训练数据和实验环境下为小肠息肉的自动识别提供有效的解决方案,有望帮助医生高效完成基于WCE检查的消化道疾病的精准诊断。     

基于深度学习的多模态医学图像融合方法研究进展

医学图像融合方法可以将有用的信息整合到一张图上，提高单张图像的信息量。对多模态医学图像进行融合时，如何对图像进行有效的变换，提取到不同图像中独有的特征，并施以适当的融合规则是医学图像融合领域研究的重点。近年随着深度学习的快速发展，深度学习被广泛应用于医学图像领域，代替传统方法中的一些人工操作，并在图像表示、图像特征提取以及融合规则的选择方面显示出独特优势。本文针对基于深度学习的医学图像融合进展予以探讨，介绍了卷积神经网络、卷积稀疏表示、深度自编码和深度信念网络这些常用于医学图像融合的框架，对一些应用于融合过程不同步骤的深度学习方法进行分析和总结，最后，分析了当前基于深度学习的融合方法的不足并展望了未来的研究方向。     

基于深度卷积神经网络的肾透明细胞癌细胞核分割

肾透明细胞癌病理图像中细胞核的形态和位置信息对肾癌的良恶性分级诊断具有重要意义,为提高肾透明细胞癌细胞核分割的质量,本研究提出了基于深度卷积神经网络的细胞核分割方法。首先,根据标定的病理图像中细胞核轮廓,构建细胞核分割样本集;然后,深度卷积神经网络通过隐式特征学习对细胞核分割模型进行训练,避免人为设计特征;最后,利用细胞核分割模型对病理图像进行逐像素分割。实验结果表明,深度卷积神经网络的细胞核分割算法在肾透明细胞癌细胞核分割的像素准确率高达90.33%,细胞核分割性能稳定,深度卷积神经网络强大的鲁棒性和适应性使得肾透明细胞癌细胞核自动分割具有可能。     

基于深度学习的医学图像分割研究进展

医学图像分割是医学图像定量分析的关键步骤之一,因此病灶分割对临床诊断有重要意义。针对传统分割方法中存在的过多依赖医学领域的先验知识和人为评估错误等问题,提出了基于深度学习的病灶分割方法。本文总结了卷积神经网络算法应用于医学图像病灶分割的研究进展。首先,论述卷积神经网络的基本结构及其常用架构;其次介绍深度学习在医学图像病灶分割中的应用,其中包括肺结节的检测和分类,脑肿瘤分割和乳腺病灶的分割;最后,分析了目前该研究中存在的优缺点并对深度学习的发展方向进行展望。     

基于深度学习的胎儿颜面部超声标准切面自动识别

在常规胎儿超声诊断过程中,精确识别出胎儿颜面部超声标准切面(FFSP)至关重要。传统方法是由医生进行主观评估,这种人工评判的方式不仅耗费时间精力,而且严重依赖操作者经验,所以结果往往不可靠。因此,临床超声诊断亟需一种FFSP自动识别方法。提出使用深度卷积网络识别FFSP,同时还分析不同深度的网络对于FFSP的识别性能。对于这些网络模型,采用不同的训练方式:随机初始化网络参数和基于ImageNet预训练基础网络的迁移学习。在研究中,数据采集的是孕周20~36周胎儿颜面部超声图像。训练集包括1 037张标准切面图像(轴状切面375张,冠状切面257张,矢状切面405张)以及3 812张非标准切面图像,共计4 849张;测试集包括792张标准切面图像和1 626张非标准切面图像,共计2 418张。最后测试集实验结果显示,迁移学习的方法使得网络识别结果增加9.29%, 同时当网络结构由8层增加至16层时,分类结果提升3.17%,深度网络对于FFSP分类最高正确率为94.5%,相比之前研究方法的最好结果提升3.66%,表明深度卷积网络能够有效地检测出FFSP,为临床自动FFSP检测方法打下研究基础。     

深度学习在医学图像配准上的研究进展与挑战

随着影像引导手术和放射治疗的发展,临床对医学图像配准研究的需求更强烈,带来的挑战也更大。最近几年,深度学习,特别是深度卷积神经网络,在医学图像处理方面取得了优异的成绩,在医学图像配准上的研究发展迅速。本文按技术方法分类总结了基于深度学习的医学图像配准的国内外研究进展,包括了基于优化策略的相似性估计、直接估计医学图像配准的变换参数等。然后分析了深度学习方法在医学图像配准上的挑战,并提出了可能的解决办法和研究方向。     

基于卷积神经网络的语义分割在医学图像中的应用

随着网络结构的迅速发展,卷积神经网络(CNN)在图像分析领域已成为一种领先的机器学习工具。因此,基于CNN的语义分割也已成为医学图像理解中的一项关键高级任务。本文综述了基于CNN的语义分割在医学图像领域中的研究进展,回顾了多种经典的语义分割方法及其架构变化,并重点介绍了它们在该领域的贡献和意义。在此基础上,进一步总结和讨论了它们在一些重要的生理与病理解剖结构分割中的应用。最后,本文讨论了语义分割在医学图像领域应用将遭遇的挑战和潜在发展方向。     

基于深度学习的中药材饮片图像识别

目的 建立一个基于深度卷积神经网络的中药饮片图像检测识别系统.该系统对于正常情况下采集的中药饮片图像,能够自动检测识别出相应类别的中药饮片.方法 本文使用了SSD目标检测算法,构建数据集,利用标注工具进行了标注,然后在云端colab上进行调试代码、训练、测试、验证.结果 对于3种中药饮片(枸杞、甘草、陈皮)进行识别验证,平均识别率高于80％,样本集足够大可以有效提高识别准确率.结论 本文将卷积神经网络应用于中药材识别中,将传统的中医学与新兴的深度学习网络相结合,识别中药饮片的效率高,速度快,准确率高,可应用于绝大部分需要识别中药饮片类别的场景.     

结合迁移学习与深度卷积网络的心电分类研究

为解决一维深度卷积网络（1D-DCNN）在心电分类方面存在的多类疾病识别不准、难以提取最佳特征等问题,提出一种结合迁移学习与二维深度卷积网络（2D-DCNN）直接识别心电图像的方法。首先,截取R波前后75 ms内的心电信号,并将一维心电电压信号转化为二维灰度图像信号。接着,构建2D-DCNN对心电节拍样本进行分类训练,权值初始化采用在ImageNet大规模图像数据集上进行预训练的AlexNet参数值。本文提出方法在MIT-BIH心电数据库上进行性能验证,其准确率达到98%,并在不同信噪比下保持较高的准确率,证明了所述模型在心电分类上具有良好的鲁棒性。为了验证2D-DCNN的识别性能,实验部分与采用不同激活函数的1D-DCNN、近些年性能较好的深度学习方法进行比较。量化结果表明,结合迁移学习和2D-DCNN方法,比最优1D-DCNN算法,其准确率提升2%、敏感度提升0.6%、特异性提高4%;在二分类与多分类任务中,均好于现有的其他算法。     

卷积神经网络在医学图像分割中的研究进展

卷积神经网络（CNN）是目前计算机视觉和模式识别中效果最为突出的算法。CNN拥有强大的空间识别能力,可以从图像中提取高阶的空间特征,同时通过共用卷积核的方式大幅减少参数量,从而在提升网络性能的同时保持总参数量在一个合理的、可运算的范畴。部分采用无监督学习的CNN算法可以在没有先验知识的条件下实现一定程度的图像语义分割,大幅减少人工读图的负担。本研究就CNN在医学图像分割中的研究进展和使用CNN时的具体技巧及其效果进行综述。以使用CNN为核心的深度学习工具解决医学图像分割的课题为中心,展示了CNN在有监督学习、半监督学习及无监督学习中的巨大潜力,分析比较了现有方案的优点与不足,探讨了未来CNN在医学图像领域的前进方向。     

Content-based histopathology image retrieval using a kernel-based semantic annotation framework

Large amounts of histology images are captured and archived in pathology departments due to the ever expanding use of digital microscopy. The ability to manage and access these collections of digital images is regarded as a key component of next generation medical imaging systems. This paper addresses the problem of retrieving histopathology images from a large collection using an example image as query. The proposed approach automatically annotates the images in the collection, as well as the query images, with high-level semantic concepts. This semantic representation delivers an improved retrieval performance providing more meaningful results. We model the problem of automatic image annotation using kernel methods, resulting in a unified framework that includes: (1) multiple features for image representation, (2) a feature integration and selection mechanism (3) and an automatic semantic image annotation strategy. An extensive experimental evaluation demonstrated the effectiveness of the proposed framework to build meaningful image representations for learning and useful semantic annotations for image retrieval.     

乳腺超声图像本体构建研究

目的乳腺超声图像本体有助于乳腺超声图像语义标注、智能检索等。本文以乳腺超声图像为例,论述了乳腺超声图像的本体模型构建方法。方法首先通过主题词与语料高频词结合的方法确定乳腺超声图像本体的概念,然后借鉴UMLS提炼乳腺超声图像本体的语义关系。结果本研究构建的乳腺超声图像本体具有1274个概念,56种语义关系,通过PROGTéGé构建了乳腺超声图像本体。结论以主题词与语料高频词结合的方法确定的本体概念具有较好的乳腺超声图像语义刻画效果,本文所述的乳腺超声图像本体构建方法也适用于其他领域本体的构建。     

Automatic medical image annotation and keyword-based image retrieval using relevance feedback

This paper presents novel multiple keywords annotation for medical images, keyword-based medical image retrieval, and relevance feedback method for image retrieval for enhancing image retrieval performance. For semantic keyword annotation, this study proposes a novel medical image classification method combining local wavelet-based center symmetric-local binary patterns with random forests. For keyword-based image retrieval, our retrieval system use the confidence score that is assigned to each annotated keyword by combining probabilities of random forests with predefined body relation graph. To overcome the limitation of keyword-based image retrieval, we combine our image retrieval system with relevance feedback mechanism based on visual feature and pattern classifier. Compared with other annotation and relevance feedback algorithms, the proposed method shows both improved annotation performance and accurate retrieval results.     

Automatic Multilevel Medical Image Annotation and Retrieval

Image retrieval at the semantic level mostly depends on image annotation or image classification. Image annotation performance largely depends on three issues: (1) automatic image feature extraction; (2) a semantic image concept modeling; (3) algorithm for semantic image annotation. To address first issue, multilevel features are extracted to construct the feature vector, which represents the contents of the image. To address second issue, domain-dependent concept hierarchy is constructed for interpretation of image semantic concepts. To address third issue, automatic multilevel code generation is proposed for image classification and multilevel image annotation. We make use of the existing image annotation to address second and third issues. Our experiments on a specific domain of X-ray images have given encouraging results.     

基于主题模型的胶囊内镜图像序列筛查

无线胶囊内窥镜(WCE)是用于记录患者消化道影像的新技术,该技术的出现给消化道疾病诊断带来了极大帮助。但在检测过程中,每位患者所产生的约5～8万幅图像中含有大量气泡和杂质等干扰图像,极大地影响了疾病诊断的效率。目前大多数方法只针对气泡筛查,且这些方法通常不稳定、普适性较差。因此,提出一种基于主题模型的WCE图像语义分析方法筛查序列中干扰性图像。首先构建非对称自编码器提取图像特征,并利用K-Means算法对训练图像块特征聚类构建视觉单词;其次将测试图像块特征映射到视觉单词中,获得测试图像的词频矩阵,实现基于视觉单词的图像语义表达;最后利用主题模型对词频矩阵进行分析,获取图像语义分类。数据集来源于南京东部战区总医院的消化道内科30例不同患者的WCE图像序列,且由临床经验丰富的医生进行注解,其中包括3 340幅气泡图像、3 330幅杂质图像和3 330幅正常图像,以1∶1的比例随机划分为训练集和测试集,进行10次交叉验证。实验结果表明,该方法能有效筛查出干扰性图像,基于深度学习的卷积自编码器优于传统的特征提取方式,获得96.87%的精度,有效地减少医生阅片负担,提高疾病诊断效率。     

Deep Transfer Learning for Automated Intestinal Bleeding Detection in Capsule Endoscopy Imaging

Purpose: The objective of this paper was to develop a computer-aided diagnostic (CAD) tools for automated analysis of capsule endoscopic (CE) images, more precisely, detect small intestinal abnormalities like bleeding. Methods: In particular, we explore a convolutional neural network (CNN)-based deep learning framework to identify bleeding and non-bleeding CE images, where a pre-trained AlexNet neural network is used to train a transfer learning CNN that carries out the identification. Moreover, bleeding zones in a bleeding-identified image are also delineated using deep learning-based semantic segmentation that leverages a SegNet deep neural network. Results: To evaluate the performance of the proposed framework, we carry out experiments on two publicly available clinical datasets and achieve a 98.49% and 88.39% F1 score, respectively, on the capsule endoscopy.org and KID datasets. For bleeding zone identification, 94.42% global accuracy and 90.69% weighted intersection over union (IoU) are achieved. Conclusion: Finally, our performance results are compared to other recently developed state-of-the-art methods, and consistent performance advances are demonstrated in terms of performance measures for bleeding image and bleeding zone detection. Relative to the present and established practice of manual inspection and annotation of CE images by a physician, our framework enables considerable annotation time and human labor savings in bleeding detection in CE images, while providing the additional benefits of bleeding zone delineation and increased detection accuracy. Moreover, the overall cost of CE enabled by our framework will also be much lower due to the reduction of manual labor, which can make CE affordable for a larger population.     

Methods for automated concept mapping between medical databases

The retrieval and exchange of information between medical databases is often impeded by the semantic heterogeneity of concepts contained within the databases. Manual identification of equivalent database elements consumes time and resources, and may often be the rate-limiting technological step in integrating disparate data sources. By employing semantic networks as an intermediary representation of the native databases, automated mapping algorithms can identify equivalent concepts in disparate databases. The algorithms take advantage of the conceptual "context" embodied within a semantic network to produce candidate concept mappings. The performance of automated concept mapping was evaluated by creating semantic network representations for two test laboratory databases. The mapping algorithms identified all equivalent concepts that were present in the databases, and did not leave any equivalent concepts unmapped. The utilization of conceptual context to perform automated concept mapping facilitates the identification of equivalent database concepts and may help decrease the work and costs associated with retrieval and integration of information from disparate databases.     

A new method of content based medical image retrieval and its applications to CT imaging sign retrieval

This paper proposes a new method of content based medical image retrieval through considering fused, context-sensitive similarity. Firstly, we fuse the semantic and visual similarities between the query image and each image in the database as their pairwise similarities. Then, we construct a weighted graph whose nodes represent the images and edges measure their pairwise similarities. By using the shortest path algorithm over the weighted graph, we obtain a new similarity measure, context-sensitive similarity measure, between the query image and each database image to complete the retrieval process. Actually, we use the fused pairwise similarity to narrow down the semantic gap for obtaining a more accurate pairwise similarity measure, and spread it on the intrinsic data manifold to achieve the context-sensitive similarity for a better retrieval performance. The proposed method has been evaluated on the retrieval of the Common CT Imaging Signs of Lung Diseases (CISLs) and achieved not only better retrieval results but also the satisfactory computation efficiency.