Feature space analysis: effects of MRI protocols.

We present a method for exploring the relationship between the image segmentation results obtained by an optimal feature space method and the MRI protocols used. The steps of the work accomplished are as follows. (1) Patients with brain tumors were imaged on a 1.5 T General Electric Signa MRI System using multiple protocols (T1 and T2-weighted fast spin-echo and FLAIR). T1-weighted images were acquired before and after gadolinium injection. (2) Image volumes were co-registered, and images of a slice through the center of the tumor were selected for processing. (3) For each patient, several image sets were defined by selecting certain MR images (e.g., 4T2's+ IT1, 4T2's+FLAIR, 2T2's+ 1T1). (4) Using each image set, the optimal feature space was generated and images were segmented into normal tissues and different tumor zones. (5) Segmentation results obtained using the different MRI sets were compared. Based on the analysis results from 27 image sets, we found that the locations of the clusters for the tumor zones and their corresponding regions in the image domain changed as a function of the MR images (MRI protocols) used. However, the segmentation results for the total lesion and normal tissues remained relatively unchanged.     

Fully automatic segmentation of multiple sclerosis lesions in brain MR FLAIR images using adaptive mixtures method and Markov random field model

In this paper, an approach is proposed for fully automatic segmentation of MS lesions in fluid attenuated inversion recovery (FLAIR) Magnetic Resonance (MR) images. The proposed approach, based on a Bayesian classifier, utilizes the adaptive mixtures method (AMM) and Markov random field (MRF) model to obtain and upgrade the class conditional probability density function (CCPDF) and the a priori probability of each class. To compare the performance of the proposed approach with those of previous approaches including manual segmentation, the similarity criteria of different slices related to 20 MS patients were calculated. Also, volumetric comparison of lesions volume between the fully automated segmentation and the gold standard was performed using correlation coefficient (CC). The results showed a better performance for the proposed approach, compared to those of previous works.     

基于模糊连接度的多发性硬化症MR图像自动分割算法

多发性硬化症(MS)是一种严重威胁中枢神经功能的疾病,利用磁共振成像技术能够无损伤地检出其病灶。为了自动地对多发性硬化症病灶进行分割,提出了基于模糊连接度的分割算法,实现了种子点的自动选取。作为多发性硬化症分割的预处理,针对脑部MR FLAIR图像的特征,基于区域增长方法,还提出了脑部组织提取算法。通过对临床患者MR图像的分割实验,表明该分割算法能够比较准确地分割多发性硬化症病灶,其分割效果明显好于模糊C-均值聚类算法和基于马尔可夫场模型的分割算法。该算法还具有无监督、运算速度快、稳健性好等优点,能够应用于多发性硬化症的临床辅助诊断。     

磁共振成像、FLAIR序列及弥散加权成像技术对多发性硬化的诊断价值分析

目的比较常规磁共振成像（MRI）、液体衰减反转恢复（FLAIR）序列及弥散加权成像（DWI）检查技术对多发性硬化（MS）的诊断价值。方法58例MS患者，其中男性34例，女性24例，年龄4～70岁，平均年龄35．95岁。使用MRI进行T1加权、T2加权、FIAIR序列及弥散加权成像检查。将4种序列图像进行比较，同时使用软件进行DWI的弥散系数（ADC）及影像分析。结果①FLAIR序列共检出病灶877个，而T1WI、T2WI和DWI分别检出病灶651、776和537个，分别为FLAIR序列检出病灶数的74％、88％和61％。各成像序列对病灶的检出率之间的差异有显著统计学意义（P〈0．0001）。②MS病灶主要分布在脑室周围白质和半卵圆中心区，占总病灶数的96．1％。其中分布在脑室周围白质的病灶数与半卵圆中心区者相比，差异无统计学意义（P〉0．05），而与脑干、小脑和胼胝体相比，差异均有显著统计学意义（均P〈0．01）。③T1WI信号多为低信号、略低信号和等信号，T2WI及FLAIR序列为高信号，DWI在急性期病灶显示为略高信号影，在慢性期可表现为等信号或低信号。④MS急性期病灶平均ADC与急性脑梗死相比差异无统计学意义（P〉0．05）。亚急性和慢性期平均ADC高于脑缺血的ADC（P〈0．001），但低于脑肿瘤的ADC（P〈0．05）。结论对MS病灶的阳性检出率，FLAIR序列优于其余3个序列；DWI可以较好地区分MS病灶分期，同时应用DWI、ADC检查对判别病灶的性质、鉴别诊断有较大帮助，是诊断MS等脱髓鞘疾病的有效影像学方法。     

Unified Approach for Multiple Sclerosis Lesion Segmentation on Brain MRI

The presence of large number of false lesion classification on segmented brain MR images is a major problem in the accurate determination of lesion volumes in multiple sclerosis (MS) brains. In order to minimize the false lesion classifications, a strategy that combines parametric and nonparametric techniques is developed and implemented. This approach uses the information from the proton density (PD)- and T2-weighted and fluid attenuation inversion recovery (FLAIR) images. This strategy involves CSF and lesion classification using the Parzen window classifier. Image processing, morphological operations, and ratio maps of PD- and T2-weighted images are used for minimizing false positives. Contextual information is exploited for minimizing the false negative lesion classifications using hidden Markov random field-expectation maximization (HMRF-EM) algorithm. Lesions are delineated using fuzzy connectivity. The performance of this algorithm is quantitatively evaluated on 23 MS patients. Similarity index, percentages of over, under, and correct estimations of lesions are computed by spatially comparing the results of present procedure with expert manual segmentation. The automated processing scheme detected 80% of the manually segmented lesions in the case of low lesion load and 93% of the lesions in those cases with high lesion load.     

Semi-Automatic Region-of-Interest Segmentation Based Computer-Aided Diagnosis of Mass Lesions from Dynamic Contrast-Enhanced Magnetic Resonance Imaging Based Breast Cancer Screening

Cancer screening with magnetic resonance imaging (MRI) is currently recommended for very high risk women. The high variability in the diagnostic accuracy of radiologists analyzing screening MRI examinations of the breast is due, at least in part, to the large amounts of data acquired. This has motivated substantial research towards the development of computer-aided diagnosis (CAD) systems for breast MRI which can assist in the diagnostic process by acting as a second reader of the examinations. This retrospective study was performed on 184 benign and 49 malignant lesions detected in a prospective MRI screening study of high risk women at Sunnybrook Health Sciences Centre. A method for performing semi-automatic lesion segmentation based on a supervised learning formulation was compared with the enhancement threshold based segmentation method in the context of a computer-aided diagnostic system. The results demonstrate that the proposed method can assist in providing increased separation between malignant and radiologically suspicious benign lesions. Separation between malignant and benign lesions based on margin measures improved from a receiver operating characteristic (ROC) curve area of 0.63 to 0.73 when the proposed segmentation method was compared with the enhancement threshold, representing a statistically significant improvement. Separation between malignant and benign lesions based on dynamic measures improved from a ROC curve area of 0.75 to 0.79 when the proposed segmentation method was compared to the enhancement threshold, also representing a statistically significant improvement. The proposed method has potential as a component of a computer-aided diagnostic system.     

Serum levels of brain-derived neurotrophic factor correlate with the number of T2 MRI lesions in multiple sclerosis

The objective of the present study was to determine if there is a relationship between serum levels of brain-derived neurotrophic factor (BDNF) and the number of T2/fluid-attenuated inversion recovery (T2/FLAIR) lesions in multiple sclerosis (MS). The use of magnetic resonance imaging (MRI) has revolutionized the study of MS. However, MRI has limitations and the use of other biomarkers such as BDNF may be useful for the clinical assessment and the study of the disease. Serum was obtained from 28 MS patients, 18-50 years old (median 38), 21 women, 0.5-10 years (median 5) of disease duration, EDSS 1-4 (median 1.5) and 28 healthy controls, 19-49 years old (median 33), 19 women. BDNF levels were measured by ELISA. T1, T2/FLAIR and gadolinium-enhanced lesions were measured by a trained radiologist. BDNF was reduced in MS patients (median [range] pg/mL; 1160 [352.6-2640]) compared to healthy controls (1640 [632.4-4268]; P = 0.03, Mann-Whitney test) and was negatively correlated (Spearman correlation test, r = -0.41; P = 0.02) with T2/FLAIR (11-81 lesions, median 42). We found that serum BDNF levels were inversely correlated with the number of T2/FLAIR lesions in patients with MS. BDNF may be a promising biomarker of MS.     

CVSnet: A machine learning approach for automated central vein sign assessment in multiple sclerosis

The central vein sign (CVS) is an efficient imaging biomarker for multiple sclerosis (MS) diagnosis, but its application in clinical routine is limited by inter‐rater variability and the expenditure of time associated with manual assessment. We describe a deep learning‐based prototype for automated assessment of the CVS in white matter MS lesions using data from three different imaging centers. We retrospectively analyzed data from 3 T magnetic resonance images acquired on four scanners from two different vendors, including adults with MS (n = 42), MS mimics (n = 33, encompassing 12 distinct neurological diseases mimicking MS) and uncertain diagnosis (n = 5). Brain white matter lesions were manually segmented on FLAIR* images. Perivenular assessment was performed according to consensus guidelines and used as ground truth, yielding 539 CVS‐positive (CVS⁺) and 448 CVS‐negative (CVS^?) lesions. A 3D convolutional neural network (“CVSnet”) was designed and trained on 47 datasets, keeping 33 for testing. FLAIR* lesion patches of CVS⁺/CVS^? lesions were used for training and validation (n = 375/298) and for testing (n = 164/150). Performance was evaluated lesion‐wise and subject‐wise and compared with a state‐of‐the‐art vesselness filtering approach through McNemar's test. The proposed CVSnet approached human performance, with lesion‐wise median balanced accuracy of 81%, and subject‐wise balanced accuracy of 89% on the validation set, and 91% on the test set. The process of CVS assessment, in previously manually segmented lesions, was ~ 600‐fold faster using the proposed CVSnet compared with human visual assessment (test set: 4 seconds vs. 40 minutes). On the validation and test sets, the lesion‐wise performance outperformed the vesselness filter method (P < 0.001). The proposed deep learning prototype shows promising performance in differentiating MS from its mimics. Our approach was evaluated using data from different hospitals, enabling larger multicenter trials to evaluate the benefit of introducing the CVS marker into MS diagnostic criteria.     

基于3D体素增强和3D alpha背景分离的多发性硬化症病灶分割方法

目的:提出一种用于T1加权像、T2加权像和流体衰减反演恢复（Flair）磁共振图像的多发性硬化症（MS）病变分割方法。方法:首先基于3D图像增强技术,将高强度MS病变区域与其他组织区域区分开来。然后利用假阳性降低方法,去除一些强度和密度不均匀的假阳性目标区域（VOI）,并利用颜色分割法去除白质之外的VOI。最后利用彩色MR技术生成3个区域,以便细化分割MS病变。结果:在CHB数据集上进行测试,得到真阳率均值为0.48,Dice相似系数均值为0.52。结论:该方法能够有效去除噪声及其他无关非病变组织,并能准确识别并分割MS病变,该方法的有效性、准确性能为后续的MS分割技术分析提供依据。同时为MS病变的预防治疗、病情跟踪提供客观、方便的诊疗方法。 【关键词】多发性硬化症;病灶分割;3D体素增强;3D alpha背景分离;颜色分割技术     

Magnetic resonance imaging in multiple sclerosis

The contribution of magnetic resonance imaging techniques to the clinical prognosis of multiple sclerosis. Magnetic resonance imaging (MRI) is a diagnostic technique with a high sensitivity for the detection of lesions, but with a poor pathological specificity. In the case of multiple sclerosis (MS), the improvement of diagnostic efficacy depends on a careful analysis of the clinical presentation and the use of increasingly stringent MRI criteria aimed at improving the specificity of the conventional MRI T2 sequences. New sequences such as fast spin-echo (also called turbo spin-echo) and FLAIR (fluid attenuated inversion recovery, a method derived from inversion recovery) have improved the visualization of lesions. MRI can under certain conditions be used to monitor the evolution of MS. Acute-phase monitoring is focused on observed changes in disease activity such as the appearance, recurrence or extension of lesions after i.v. injection of contrast medium, i.e., gadolinium (Gd)-enhanced MRI. In the chronic phase, the lesions is the aspect used as the monitoring criterion. However, MRI is still only a secondary criterion in phase III therapeutic trials due to its insufficient correlation with the disability. In neurological daily practice, conventional MRI is only of limited interest at the individual level in patient follow-up, as its prognostic value is poor. Moreover, the difficulty in determining the lesion load can only be excluded in the context of clinical trials, in which certain methodological precautions are taken. This is why techniques other than MRI are being investigated to obtain a better correlation with the clinical course of the disease, for instance the quantification of 'black holes' on T1 weighted images, and the measurement of cerebral and spinal atrophy. Adapted MRI techniques allow a weighted signal to be obtained via the movement (diffusion imaging), by the complexity of the molecular structure (magnetization transfer imaging), by chemical shift (spectroscopic imaging), or by local oxygenation (functional MRI). These new MRI techniques allow a more precise assessment of the pathological mechanisms involved in MS, such as edema, blood brain barrier break-down, demyelinisation, gliosis, cellular infiltration and axonal loss; they provide a better means of establishing the correlation between clinical impact and the destructive nature of the MS lesion. The importance of axonal loss has recently been confirmed in MS by analyzing MRI spectroscopic and neuropathological findings. In addition to magnetization transfer imaging, MR diffusion imaging and functional MRI are being intensively studied in order to assess their contribution to the study of reversibility of the degenerative process.     

An algorithm for automatic segmentation and classification of magnetic resonance brain images

In this article, we describe the development and validation of an automatic algorithm to segment brain from extracranial tissues, and to classify intracranial tissues as cerebrospinal fluid (CSF), gray matter (GM), white matter (WM) or pathology. T1 weighted spin echo, dual echo fast spin echo (T2 weighted and proton density (PD) weighted images) and fast Fluid Attenuated Inversion Recovery (FLAIR) magentic resonance (MR) images were acquired ino 100 normal patients and 9 multiple sclerosis (MS) patients. One of the normal studies had synthesized MS-like lesions superimposed. This allowed precise measurement of the accuracy of the classification. The 9 MS patients were imaged twice in one week. The algorithm was applied to these data sets to measure reproducibility. The accuracy was measured based on the synthetic lesion images, where the true voxel class was known. Ninety-six percent of normal intradural tissue voxels (GM, WM, and CSF) were labeled correctly, and 94% of pathological tissues were labeled correctly. A low coefficient of variation (COV) was found (mean, 4.1%) for measurement of brain tissues and pathology when comparing MRI scans on the 9 patients. A totally automatic segmentation algorithm has been described which accurately and reproducibly segments and classifies intradural tissues based on both synthetic and actual images.     

基于级联3D U-Net的CT和MR视交叉自动分割方法

目的:基于级联3D U-Net,利用配对患者头颈部数据［CT和磁共振图像（MRI）］,取得比仅CT数据更高分割精度的视交叉自动分割结果。方法:该级联3D U-Net由一个原始3D U-Net和改进的3D D-S U-Net（3D Deeply-Supervised U-Net）组成,实验使用了60例患者头颈部CT图像及MRI图像（T1和T2模态）,其中随机选取15例患者数据作为测试集,并使用相似性系数（DSC）评估视交叉的自动分割精度。结果:对于测试集中的所有病例,采用多模态数据（CT和MRI）的视交叉的DSC为0.645±0.085,采用单模态数据（CT）的视交叉的DSC为0.552±0.096。结论:基于级联3D U-Net的多模态自动分割模型能够较为准确地实现视交叉的自动分割,且优于仅利用单模态数据的方法,可以辅助医生提高放疗计划制定的工作效率。     

Neuroimaging and functional analyses for multiple sclerosis

For neuroimaging studies of multiple sclerosis(MS) lesions, magnetic resonance imaging (MRI) is most useful, while evoked potentials(EPs) are commonly used for functional analyses of neural damage due to MS. This review summarizes the MRI and EP findings in MS. MS lesions are visualized as high signal intensity lesions on T2-weighted images, proton density(PD)-weighted images, and fluid-attenuated inversion recovery(FLAIR) images, while such lesions demonstrate a low signal on T1-weighted images. New MS lesions are usually enhanced by gadolinium-DTPA on T1-weighted images, and the enhancement generally lasts 4 to 8 weeks. In Asian patients with MS, opticospinal MS(Asian-type MS) shows a significantly smaller numbers of brain MRI lesions than conventional MS(Western-type MS), while opticospinal MS shows a significantly higher frequency of the spinal cord atrophy on MRI than conventional MS. EPs are useful for detecting lesions located in certain portions of the central nervous system. MRI is not sensitive enough to detect small lesions in the optic nerves and spinal cord, whereas EPs are sensitive for optic nerve and spinal cord lesions. Thus, combined use of MRI and EPs is required for the diagnosis and the optimal monitoring of disease activity in MS.     

Interactive segmentation of plexiform neurofibroma tissue: method and preliminary performance evaluation

Plexiform neurofibromas (PNs) are a major manifestation of neurofibromatosis-1 (NF1), a common genetic disease involving the nervous system. Treatment decisions are mostly based on a gross assessment of changes in tumor using MRI. Accurate volumetric measurements are rarely performed in this kind of tumors mainly due to its great dispersion, size, and multiple locations. This paper presents a semi-automatic method for segmentation of PN from STIR MRI scans. The method starts with a user-based delineation of the tumor area in a single slice and automatically segments the PN lesions in the entire image based on the tumor connectivity. Experimental results on seven datasets, with lesion volumes in the range of 75-690 ml, yielded a mean absolute volume error of 10 % (after manual adjustment) as compared to manual segmentation by an expert radiologist. The mean computation and interaction time was 13 versus 63 min for manual annotation.     

Liver Hydatid CT Image Segmentation Using Smoothed Bayesian Classification Method and Modified Parametric Active Contour Model

Liver hydatid disease is a common parasitic disease in farm and pastoral areas, which seriously influences people's health. Based on CT imaging features of this disease, an iterative approach for liver segmentation and hydatid lesion extraction simultaneously is proposed. In each iteration, our algorithm consists of two main steps: 1) according to the user-defined pixel seeds in the liver and hydatid lesion, Gaussian probability model fitting and smoothed Bayesian classification are applied to get initial segmentation of liver and lesion; 2) the parametric active contour model using priori shape force field is adopted to refine initial segmentation. We make subjective and objective evaluation on the proposed algorithm validity by the experiments of liver and hydatid lesion segmentation on different patients' CT slices. In comparison with ground-truth manual segmentation results, the experimental results show the effectiveness of our method to segment liver and hydatid lesion.     

基于空间FCM与MRF方法的乳腺MRI序列三维病灶分割研究

针对乳腺DCE-MRI病灶分割,提出一种空间FCM聚类与MRF随机场相结合的三维分割方法。首先,对MRI图像进行空间FCM粗分割,提取病灶粗轮廓。然后,在其基础上进行MRF精分割,并结合病灶三维信息：用相邻切片分割结果对应标号矩阵初始化MRF精分割标号场,同时用该张切片粗分割所得隶属度矩阵对MRF精分割进行参数自适应调整。用该方法与空间FCM、水平集、模糊MRF方法对50例MRI数据进行分割对比实验,得到良、恶性病灶分割重叠率分别为76.4、75.5;相比于空间FCM的68.%、69.5水平集的70.8、72.6以及模糊MRF的72.9、73.6有明显提升。对所有175例MRI数据分割结果进行非监督评价,得到良、恶性病灶区域均匀性均大于0.92;区域内差异性良性病灶92%小于150、恶性病灶98%小于150;区域间差异性良性病灶87%大于0.25、恶性病灶90%大于0.3综上表明,该方法具有较高的分割精度。     

颅内生殖细胞瘤的MRI影像表现及诊断

目的 探讨颅内生殖细胞瘤的MRI表现,旨在提高对本病的影像诊断准确率。方法 回顾性分析2014年12月~2019年5月我院经手术病理或临床诊断性放射治疗确诊的13例颅内生殖细胞瘤患者的MRI影像资料,分析其临床表现、影像表现及诊断。结果 病变位于松果体区患者9例,MRI检查肿瘤实质部分T1WI呈稍低信号,T2WI和FLAIR 呈高或稍高信号,DWI呈等或稍高信号,增强扫描呈明显强化;肿瘤伴有囊变者1例,伴有钙化者3例,4例患者伴脑积水;3例患者出现转移灶,累及三脑室、侧脑室等,其MRI信号及强化方式与原发灶相似。病变位于鞍区患者3例,肿瘤形态、大小不一,T1WI 呈稍低信号,T2WI和FLAIR 呈稍高信号,增强扫描呈明显强化。1例患者的病变位于右侧基底节区,形态不规则,T1WI呈等信号,T2WI、FLAIR及DWI均呈稍高信号,增强扫描无强化,同侧大脑脚较对侧萎缩。结论 MRI对颅内生殖细胞瘤的影像诊断与鉴别诊断具有重要价值。     

Region-Based Nasopharyngeal Carcinoma Lesion Segmentation from MRI Using Clustering- and Classification-Based Methods with Learning

In clinical diagnosis of nasopharyngeal carcinoma (NPC) lesion, clinicians are often required to delineate boundaries of NPC on a number of tumor-bearing magnetic resonance images, which is a tedious and time-consuming procedure highly depending on expertise and experience of clinicians. Computer-aided tumor segmentation methods (either contour-based or region-based) are necessary to alleviate clinicians’ workload. For contour-based methods, a minimal user interaction to draw an initial contour inside or outside the tumor lesion for further curve evolution to match the tumor boundary is preferred, but parameters within most of these methods require manual adjustment, which is technically burdensome for clinicians without specific knowledge. Therefore, segmentation methods with a minimal user interaction as well as automatic parameters adjustment are often favored in clinical practice. In this paper, two region-based methods with parameters learning are introduced for NPC segmentation. Two hundred fifty-three MRI slices containing NPC lesion are utilized for evaluating the performance of the two methods, as well as being compared with other similar region-based tumor segmentation methods. Experimental results demonstrate the superiority of adopting learning in the two introduced methods. Also, they achieve comparable segmentation performance from a statistical point of view.     

HLA (A-B-C and -DRB1) alleles and brain MRI changes in multiple sclerosis: a longitudinal study

Several major histocompatibility complex (MHC) alleles have been postulated to influence the susceptibility to multiple sclerosis (MS), as well as its clinical/radiological course. In this longitudinal observation, we further explored the impact of human leukocyte antigen (HLA) class I/II alleles on MS outcomes, and we tested the hypothesis that HLA DRB1*1501 might uncover different strata of MS subjects harboring distinct MHC allele associations with magnetic resonance imaging (MRI) measures. Five hundred eighteen MS patients with two-digit HLA typing and at least one brain MRI were recruited for the study. T2-weighted hyperintense lesion volume (T2LV) and brain parenchymal fraction (BPF) were acquired at each time point. The association between allele count and MRI values was determined using linear regression modeling controlling for age, disease duration and gender. Analyses were also stratified by the presence/absence of HLA DRB1*1501. HLA DRB1*04 was associated with higher T2LV (P=0.006); after stratification, its significance remained only in the presence of HLA DRB1*1501 (P=0.012). The negative effect of HLA DRB1*14 on T2LV was exerted in DRB1*1501-negative group (P=0.012). Longitudinal analysis showed that HLA DRB1*10 was significantly protective on T2LV accrual in the presence of HLA DRB1*1501 (P=0.002). Although the majority of our results did not withstand multiple comparison correction, the differential impact of several HLA alleles in the presence/absence of HLA DRB1*1501 suggests that they may interact in determining the different phenotypic expressions of MS.     

基于3D U-Net 实现人体耳软骨MRI图像的解剖结构分割

自体肋软骨雕刻法是目前治疗先天性小儿畸形的临床标准疗法,而耳软骨组织工程和3D生物打印是有前景的治疗方案。可是,这些治疗方案的核心—(复合物)支架构造缺乏基于医学图像的耳软骨自动分割方法。基于3D U-Net提出改进的网络模型,能够实现MRI图像的人体耳软骨解剖结构的自动分割。该网络模型结合残差结构和多尺度融合等设计,在减少网络参数量的同时实现12个耳软骨解剖结构的精确分割。首先,使用超短回波时间(UTE)序列采集40名志愿者单侧外耳的MRI图像;然后,对所采集的图像进行预处理、耳软骨和多解剖结构手动标注;接下来,划分数据集训练改进的3D U-Net模型,其中32例数据作为训练集、4例为验证集、4例为测试集;最后,使用三维全连接条件随机场对网络输出结果进行后处理。模型经过10折交叉验证后,耳软骨12个解剖结构的自动分割结果的平均Dice相似度系数(DSC)和平均95%豪斯多夫距离(HD95)分别为0.818和1.917,相比于使用基础的3D U-Net模型,DSC指标分别提高6.0%,HD95指标降低了3.186,其中耳软骨关键结构耳轮和对耳轮的DSC指标达到了0.907和0.901。实验结果表明,所提出的深度学习方法与专家手动标注两者之间的结果非常接近。在临床应用中,根据患者健侧UTE核磁图像,本研究提出的方法既可以为现有自体肋软骨雕刻法快速、自动生成三维个性化雕刻模板,也可以为组织工程或者3D生物打印技术构建耳软骨复合物支架提供高质量的可打印模型。