Comparing diagnostic accuracy of luminal water imaging with diffusion‐weighted and dynamic contrast‐enhanced MRI in prostate cancer: A quantitative MRI study

Luminal water imaging (LWI) is a new MRI T₂ mapping technique that has been developed with the aim of diagnosis of prostate carcinoma (PCa). This technique measures the fractional amount of luminal water in prostate tissue, and has shown promising preliminary results in detection of PCa. To include LWI in clinical settings, further investigation on the accuracy of this technique is required. In this study, we compare the diagnostic accuracy of LWI with those of diffusion‐weighted imaging (DWI) and dynamic contrast‐enhanced (DCE) MRI in detection and grading of PCa. Fifteen patients with biopsy‐proven PCa consented to participate in this ethics‐board‐approved prospective study. Patients were examined with LWI, DWI, and DCE sequences at 3 T prior to radical prostatectomy. Maps of MRI parameters were generated and registered to whole‐mount histology. Receiver operating characteristic (ROC) analysis was used to evaluate the diagnostic accuracy of individual and combined MR parameters. Correlation with Gleason score (GS) was evaluated using Spearman's rank correlation test. The results show that area under the ROC curve (AUC) obtained from LWI was equal to or higher than the AUC obtained from DWI, DCE, or their combination, in peripheral zone (0.98 versus 0.90, 0.89, and 0.91 respectively), transition zone (0.99 versus 0.98, n/a, and 0.98), and the entire prostate (0.85 versus 0.81, 0.75, and 0.84). The strongest correlation with GS was achieved from LWI (ρ = ?0.81 ± 0.09, P < 0.001). Results of this pilot study show that LWI performs equally well as, or better than, DWI and DCE in detection of PCa. LWI provides significantly higher correlation with GS than DWI and DCE. This technique can potentially be included in clinical MRI protocols to improve characterization of tumors. However, considering the small size of the patient population in this study, a further study with a larger cohort of patients and broader range of GS is required to confirm the findings and draw a firm conclusion on the applicability of LWI in clinical settings.     

基于多模态磁共振放射组学与临床指标的前列腺癌智能检测及风险预测模型建立

目的：利用多模态磁共振放射组学开发前列腺癌自动检测模型,并使用列线图构建多因素回归模型,将前列腺MRI放射组学特征与临床多个检测指标进行整合,从而对患前列腺癌风险性进行预测。方法：回顾性研究于2019年2月～2021年10月病理证实为前列腺癌和其他前列腺良性肿瘤的患者133例。所有病例均行前列腺直肠指检(DRE)、前列腺特异性抗原(PSA)、游离前列腺特异性抗原(F-PSA)、FPSA/PSA检测。治疗前多模态前列腺MRI图像(DWI+DCE+T₂WI)用于提取放射特征,最大相关最小冗余(m RMR)算法用于消除混杂变量,使用最小绝对收缩和选择算子(LASSO)逻辑回归进行放射特征选择。通过曲线下面积(AUC)、准确性、特异性、敏感性评估放射特征的诊断性能;通过多元logistic回归选择临床指标和放射组学特征模型来制定放射组学列线图,并使用校准曲线和Hosmer-lemeshow试验验证其可靠性。结果：两名观察者测量的所有数据ICC均在0.80以上。所有前列腺MRI图像随机分为训练组和验证组(7:3)。在训练组中,DWI、DCE和T₂WI的...     

Combined DCE‐MRI and single‐voxel 2D MRS for differentiation between benign and malignant breast lesions

Dynamic contrast‐enhanced (DCE) magnetic resonance imaging (MRI) and proton (1H) magnetic resonance spectroscopy (MRS) provide structural and biochemical information, including vascular volume, vascular permeability and tissue metabolism. In this study, we performed analysis of the enhancement characteristic from DCE‐MRI and the biochemical information provided by two‐dimensional (2D) Localized Correlated Spectroscopy (L‐COSY) MRS to determine the sensitivity and specificity of using DCE‐MRI alone compared to the combination with 2D MRS. The metabolite ratios from the 2D MRS spectra were analyzed using multivariate statistical analyses to determine a method capable of automatic separation of the patient cohort into malignant and benign lesions. A total of 24 lesions were studied with 21 diagnosed accurately using the enhancement characteristics alone resulting in sensitivity and specificity of 100% and 73%, respectively. Analysis of the 2D MRS data demonstrated a significant difference (p < 0.05) in 12 of 18 metabolite ratios analyzed for malignant compared to benign lesions. Previous research focused on utilizing the choline signal to noise ratio (SNR) as a marker for malignancy has been verified using 2D MRS in this study. Using Fisher's linear discriminant test using water (WAT)/olefinic fat diagonal (UFD), choline (CHO)/fat (FAT), CHO/UFD, and FAT/methyl fat (FMETD) as predictors the sensitivity and specificity increased to 92% and 100%, respectively. Using the Classification and Regression Tree (CART) statistical analysis the resulting sensitivity and specificity were 100% and 91%, respectively, with the most accurate predictor for differentiating malignant and benign determined to be FAT/FMETD. The cases within the study that presented a indeterminate diagnosis using DCE‐MRI alone were able to be accurately diagnosed when the metabolic information from 2D MRS was incorporated. The results suggest improved breast cancer detection through the combination of morphological and enhancement information from DCE‐MRI and metabolic information from 2D MRS. Copyright © 2010 John Wiley & Sons, Ltd.     

Classification of prostatic diseases by means of multivariate analysis on in vivo proton MRSI and DCE‐MRI data

Multivariate analysis has been applied on proton magnetic resonance spectroscopic imaging (¹H‐MRSI) and dynamic contrast enhanced MRI (DCE‐MRI) data of patients with different prostatic diseases such as chronic inflammation, fibrosis and adenocarcinoma. Multivariate analysis offers a global view of the entire range of information coming from both the imaging and spectroscopic side of NMR technology, leading to an integrated picture of the system relying upon the entire metabolic and dynamic profile of the studied samples. In this study, we show how this approach, applied to ¹H‐MRSI/DCE‐MRI results, allows us to differentiate among the various prostatic diseases in a non‐invasive way with a 100% accuracy. These findings suggest that multivariate analysis of ¹H‐MRSI/DCE‐MRI can significantly improve the diagnostic accuracy for these pathological entities. From a more theoretical point of view, the complementation of a single biomarker approach with an integrated picture of the entire metabolic and dynamic profile allows for a more realistic appreciation of pathological entities. Copyright © 2009 John Wiley & Sons, Ltd.     

MRI对胰腺导管内乳头状粘液瘤良恶性的诊断价值

目的 探讨MRI对胰腺导管内乳头状粘液性肿瘤（IPMN）良恶性的鉴别诊断价值。方法 收集2012年1月~2018年6月我院经手术病理证实的IPMN患者24例,均行MRI检查（包括MRI平扫、三期增强以及MRCP）,分析IPMN MRI表现、IPMN良恶性因素,并采用ROC曲线分析IPMN肿瘤最大径及胰管扩张直径与肿瘤良恶性关系。结果 24例IPMN患者中,良性14例,恶性10例。良性与恶性在性别、肿瘤分型、病变位置间比较,差异无统计学意义（P＞0.05）;恶性年龄大于良性,差异有统计学意义（P＜0.05）。IPMN恶性肿瘤最大径为（55.70±10.73）mm,大于良性的（34.20±7.65）mm,差异有统计学意义（P＜0.05）;IPMN肿瘤最大径与肿瘤良恶性关系ROC曲线分析得出:曲线下面积（AUC）为0.87,肿瘤最大径最佳临界值为46.40 mm,敏感度为85.68%,特异性为83.35%。IPMN恶性主胰管扩张最大径为（8.91±3.22）mm,大于良性的（4.82±1.33）mm,差异有统计学意义（P＜0.05）;IPMN胰管扩张直径与肿瘤良恶性关系ROC曲线分析得出:AUC为0.88,胰管扩张最大径最佳临界值为7.35 mm,敏感度为70.00%,特异性为85.73%。结论 MRI能很好显示胰管扩张、囊性病变、管壁内结节等特征,在评估IPMN良恶性中具有敏感性。     

Three‐dimensional dynamic contrast‐enhanced MRI for the accurate,extensive quantification of microvascular permeability in atherosclerotic plaques

Atherosclerotic plaques that cause stroke and myocardial infarction are characterized by increased microvascular permeability and inflammation. Dynamic contrast‐enhanced MRI (DCE‐MRI) has been proposed as a method to quantify vessel wall microvascular permeability in vivo. Until now, most DCE‐MRI studies of atherosclerosis have been limited to two‐dimensional (2D) multi‐slice imaging. Although providing the high spatial resolution required to image the arterial vessel wall, these approaches do not allow the quantification of plaque permeability with extensive anatomical coverage, an essential feature when imaging heterogeneous diseases, such as atherosclerosis. To our knowledge, we present the first systematic evaluation of three‐dimensional (3D), high‐resolution, DCE‐MRI for the extensive quantification of plaque permeability along an entire vascular bed, with validation in atherosclerotic rabbits. We compare two acquisitions: 3D turbo field echo (TFE) with motion‐sensitized‐driven equilibrium (MSDE) preparation and 3D turbo spin echo (TSE). We find 3D TFE DCE‐MRI to be superior to 3D TSE DCE‐MRI in terms of temporal stability metrics. Both sequences show good intra‐ and inter‐observer reliability, and significant correlation with ex vivo permeability measurements by Evans Blue near‐infrared fluorescence (NIRF). In addition, we explore the feasibility of using compressed sensing to accelerate 3D DCE‐MRI of atherosclerosis, to improve its temporal resolution and therefore the accuracy of permeability quantification. Using retrospective under‐sampling and reconstructions, we show that compressed sensing alone may allow the acceleration of 3D DCE‐MRI by up to four‐fold. We anticipate that the development of high‐spatial‐resolution 3D DCE‐MRI with prospective compressed sensing acceleration may allow for the more accurate and extensive quantification of atherosclerotic plaque permeability along an entire vascular bed. We foresee that this approach may allow for the comprehensive and accurate evaluation of plaque permeability in patients, and may be a useful tool to assess the therapeutic response to approved and novel drugs for cardiovascular disease. Copyright © 2015 John Wiley & Sons, Ltd.     

Computer-aided diagnosis of prostate cancer in the peripheral zone using multiparametric MRI

This study evaluated a computer-assisted diagnosis (CADx) system for determining a likelihood measure of prostate cancer presence in the peripheral zone (PZ) based on multiparametric magnetic resonance (MR) imaging, including T2-weighted, diffusion-weighted and dynamic contrast-enhanced MRI at 1.5 T. Based on a feature set derived from grey-level images, including first-order statistics, Haralick features, gradient features, semi-quantitative and quantitative (pharmacokinetic modelling) dynamic parameters, four kinds of classifiers were trained and compared: nonlinear support vector machine (SVM), linear discriminant analysis, k-nearest neighbours and na?ve Bayes classifiers. A set of feature selection methods based on t-test, mutual information and minimum-redundancy-maximum-relevancy criteria were also compared. The aim was to discriminate between the relevant features as well as to create an efficient classifier using these features. The diagnostic performances of these different CADx schemes were evaluated based on a receiver operating characteristic (ROC) curve analysis. The evaluation database consisted of 30 sets of multiparametric MR images acquired from radical prostatectomy patients. Using histologic sections as the gold standard, both cancer and nonmalignant (but suspicious) tissues were annotated in consensus on all MR images by two radiologists, a histopathologist and a researcher. Benign tissue regions of interest (ROIs) were also delineated in the remaining prostate PZ. This resulted in a series of 42 cancer ROIs, 49 benign but suspicious ROIs and 124 nonsuspicious benign ROIs. From the outputs of all evaluated feature selection methods on the test bench, a restrictive set of about 15 highly informative features coming from all MR sequences was discriminated, thus confirming the validity of the multiparametric approach. Quantitative evaluation of the diagnostic performance yielded a maximal area under the ROC curve (AUC) of 0.89 (0.81-0.94) for the discrimination of the malignant versus nonmalignant tissues and 0.82 (0.73-0.90) for the discrimination of the malignant versus suspicious tissues when combining the t-test feature selection approach with a SVM classifier. A preliminary comparison showed that the optimal CADx scheme mimicked, in terms of AUC, the human experts in differentiating malignant from suspicious tissues, thus demonstrating its potential for assisting cancer identification in the PZ.     

常规MRI联合分段读出平面回波弥散加权成像在颞骨良恶性肿瘤鉴别诊断中的应用价值

目的 探讨常规MRI联合分段读出平面回波弥散加权成像(RESOLVE-DWI)鉴别颞骨良、恶性肿瘤的价值。方法 回顾性研究。纳入2014年1月-2019年12月复旦大学附属眼耳鼻喉科医院经病理学证实的96例颞骨肿瘤患者临床和影像资料。患者均在手术前2周内行颞骨常规MRI及RESOLVE-DWI检查,分别观察肿瘤大小(最大层面测量的病灶最大径)、形态、信号均匀性、边界及强化程度等图像特征,以及记录通过后处理软件在表观弥散加权成像图像上选择肿瘤实性区域手动绘制类圆形感兴趣区的表观弥散系数(ADC)。采用χ²检验和独立样本t检验比较良、恶性肿瘤的MRI信号特征及ADC值。绘制单独及联合常规MRI征像和RESOLVE-DWI测量的ADC值诊断颞骨良、恶性肿瘤的受试者工作特征曲线(ROC),并使用Delong检验比较诊断效能。结果 良性肿瘤59例,男28例、女31例,年龄(44.63±12.97)岁,肿瘤大小(2.39±0.89)cm,类圆形/浅分叶41例、不规则形18例,边界清晰52例、模糊7例,信号均匀37例、不均匀22例,轻中度强化34例、明显强化25例;恶性肿瘤37例,男18例、女19例,年龄(50.27±17.25)岁,肿瘤大小(2.58±1.16)cm,类圆形/浅分叶23例、不规则形14例,边界清晰17例、模糊20例,信号均匀27例、不均匀10例,轻中度强化9例、明显强化28例。良、恶性颞骨肿瘤间,除肿瘤边界和强化程度差异有统计学意义(P值均＜0.01)外,患者年龄、性别以及MRI图像其他特征间差异均无统计学意义(P值均>0.05)。颞骨恶性肿瘤的ADC值为(0.91 ± 0.23) ×10^-3 mm²/s,低于良性肿瘤组的 (1.09 ± 0.32) ×10^-3 mm²/s,差异有统计学意义(t=2.974, P＜0.01)。单独应用常规MRI和RESOLVE-DWI测量的ADC值诊断良、恶性颞骨肿瘤的ROC曲线下面积(AUC)分别为0.771(95%可信区间0.639~0.903)和0.727(95%可信区间0.565~0.889),其灵敏度、特异度及准确度分别为68.42%、85.71%、75.08%和63.16%、71.43%、66.35%。联合应用常规MRI征象及RESOLVE-DWI测量的ADC值诊断良、恶性颞骨肿瘤的AUC值为0.907(95%可信区间0.816~0.998),其灵敏度、特异度及准确度分别为89.47%、80.95%和86.19%。联合应用常规MRI及RESOLVE-DWI的AUC显著高于分别单独应用常规MRI和RESOLVE-DWI(Z=2.463、2.243, P值均＜0.05)。结论 常规MRI及RESOLVE-DWI在鉴别颞骨良、恶性肿瘤中具有重要价值,二者联合应用能有效提高其鉴别诊断效能。     

Relationship between diffusion parameters derived from intravoxel incoherent motion MRI and perfusion measured by dynamic contrast‐enhanced MRI of soft tissue tumors

Our aim was to evaluate the link between diffusion parameters measured by intravoxel incoherent motion (IVIM) diffusion‐weighted imaging (DWI) and the perfusion metrics obtained with dynamic contrast‐enhanced (DCE) MRI in soft tissue tumors (STTs). Twenty‐eight patients affected by histopathologically confirmed STT were included in a prospective study. All patients underwent both DCE MRI and IVIM DWI. The perfusion fraction f, diffusion coefficient D and perfusion‐related diffusion coefficient D* were estimated using a bi‐exponential function to fit the DWI data. DCE MRI was acquired with a temporal resolution of 3–5 s. Maps of the initial area under the gadolinium concentration curve (IAUGC), time to peak (TTP) and maximum slope of increase (MSI) were derived using commercial software. The relationships between the DCE MRI and IVIM DWI measurements were assessed by Spearman's test. To exclude false positive results under multiple testing, the false discovery rate (FDR) procedure was applied. The Mann–Whitney test was used to evaluate the differences between all variables in patients with non‐myxoid and myxoid STT. No significant relationship was found between IVIM parameters and any DCE MRI parameters. Higher f and D*f values were found in non‐myxoid tumors compared with myxoid tumors (p = 0.004 and p = 0.003, respectively). MSI was significantly higher in non‐myxoid tumors than in myxoid tumors (p = 0.029). From the visual assessments of single clinical cases, both f and D*f maps were in satisfactory agreement with DCE maps in the extreme cases of an avascular mass and a highly vascularized mass, whereas, for tumors with slight vascularity or with a highly heterogeneous perfusion pattern, this association was not straightforward. Although IVIM DWI was demonstrated to be feasible in STT, our data did not support evident relationships between perfusion‐related IVIM parameters and perfusion measured by DCE MRI. Copyright © 2015 John Wiley & Sons, Ltd.     

Multi‐parametric MRI characterization of inflammation in murine skeletal muscle

Myopathies often display a common set of complex pathologies that include muscle weakness, inflammation, compromised membrane integrity, fat deposition, and fibrosis. Multi‐parametric, quantitative, non‐invasive imaging approaches may be able to resolve these individual pathological components. The goal of this study was to use multi‐parametric MRI to investigate inflammation as an isolated pathological feature. Proton relaxation, diffusion tensor imaging (DTI), quantitative magnetization transfer (qMT‐MRI), and dynamic contrast enhanced (DCE‐MRI) parameters were calculated from data acquired in a single imaging session conducted 6–8 hours following the injection of λ‐carrageenan, a local inflammatory agent. T₂ increased in the inflamed muscle and transitioned to bi‐exponential behavior. In diffusion measurements, all three eigenvalues and the apparent diffusion coefficient increased, but λ₃ had the largest relative change. Analysis of the qMT data revealed that the T₁ of the free pool and the observed T₁ both increased in the inflamed tissue, while the ratio of exchanging spins in the solid pool to those in the free water pool (the pool size ratio) significantly decreased. DCE‐MRI data also supported observations of an increase in extracellular volume. These findings enriched the understanding of the relation between multiple quantitative MRI parameters and an isolated inflammatory pathology, and may potentially be employed for other single or complex myopathy models. Copyright © 2014 John Wiley & Sons, Ltd.     

Gaussian mixture model‐based classification of dynamic contrast enhanced MRI data for identifying diverse tumor microenvironments: preliminary results

Tumor hypoxia develops heterogeneously, affects radiation sensitivity and the development of metastases. Prognostic information derived from the in vivo characterization of the spatial distribution of hypoxic areas in solid tumors can be of value for radiation therapy planning and for monitoring the early treatment response. Tumor hypoxia is caused by an imbalance between the supply and consumption of oxygen. The tumor oxygen supply is inherently linked to its vasculature and perfusion which can be evaluated by dynamic contrast enhanced (DCE‐) MRI using the contrast agent Gd‐DTPA. Thus, we hypothesize that DCE‐MRI data may provide surrogate information regarding tumor hypoxia. In this study, DCE‐MRI data from a rat prostate tumor model were analysed with a Gaussian mixture model (GMM)‐based classification to identify perfused, hypoxic and necrotic areas for a total of ten tumor slices from six rats, of which one slice was used as training data for GMM classifications. The results of pattern recognition analyzes were validated by comparison to corresponding Ak_ep maps defining the perfused area (0.84 ± 0.09 overlap), hematoxylin and eosin (H&E)‐stained tissue sections defining necrosis (0.64 ± 0.15 overlap) and pimonidazole‐stained sections defining hypoxia (0.72 ± 0.17 overlap), respectively. Our preliminary data indicate the feasibility of a GMM‐based classification to identify tumor hypoxia, necrosis and perfusion/permeability from non‐invasively acquired, in vivo DCE‐MRI data alone, possibly obviating the need for invasive procedures, such as biopsies, or exposure to radioactivity, such as positron emission tomography (PET) exams. Copyright © 2013 John Wiley & Sons, Ltd.     

In vivo detection of the effects of preconditioning on LNCaP tumors by a TNF‐α nanoparticle construct using MRI

The outcome of systemic and local therapies (e.g. chemotherapy, radiotherapy, surgery, focal ablation) for prostate cancer can be significantly improved by using tumor‐specific adjuvants prior to treatment (“preconditioning”). We propose to use dynamic contrast enhanced magnetic resonance imaging (DCE‐MRI) to monitor the in vivo response of a mouse model of prostate cancer treated with a vascular disruptive agent, TNF‐α, delivered on a gold nanoparticle (NP‐TNF). Six male nude mice bearing 4–5 week old LNCaP tumors were scanned at 9.4 T. DCE‐MRI was performed two days before and 4–5 h after treatment with NP‐TNF. An intraperitoneal (i.p.) bolus of gadolinium‐DTPA (Gd) was administered and contrast enhancement was measured for 90 min. Concentration–time curves of Gd were calculated and the area under the Gd curve (AUGC) was determined pre‐ and post‐treatment. NP‐TNF treatment caused an increase in contrast uptake in tumors. Interestingly, the early concentration (10 min post Gd bolus i.p.) was similar in both untreated and treated conditions; however, 90 min after injection, [Gd] was 3.4 times higher than before treatment. AUGC doubled from (11 ± 6) [Gd] × min before treatment to (22 ± 9) [Gd] × min after treatment. An increase in signal enhancement was also observed in the muscle but to a lesser degree. We also evaluated the kinetics of intravenous Gd administration in mice bearing a jugular vein catheter to mimic the delivery method used in clinical trials. The overall treatment effects were independent of the delivery pathway of the contrast agent. In conclusion, we show that DCE‐MRI is suitable to detect changes associated with a vascular disruptive agent in a mouse model of prostate cancer. The ability to characterize the effects of nanoparticle therapy in vivo with non‐destructive methods is important, as such compounds, in combination with treatment strategies, are progressing towards clinical trials. Copyright © 2014 John Wiley & Sons, Ltd.     

Stratification of the aggressiveness of prostate cancer using pre‐biopsy multiparametric MRI (mpMRI)

Risk stratification, based on the Gleason score (GS) of a prostate biopsy, is an important decision‐making tool in prostate cancer management. As low‐grade disease may not need active intervention, the ability to identify aggressive cancers on imaging could limit the need for prostate biopsies. We assessed the ability of multiparametric MRI (mpMRI) in pre‐biopsy risk stratification of men with prostate cancer. One hundred and twenty men suspected to have prostate cancer underwent mpMRI (diffusion MRI and MR spectroscopic imaging) prior to biopsy. Twenty‐six had cancer and were stratified into three groups based on GS: low grade (GS ≤ 6), intermediate grade (GS = 7) and high grade (GS ≥ 8). A total of 910 regions of interest (ROIs) from the peripheral zone (PZ, range 25–45) were analyzed from these 26 patients. The metabolite ratio [citrate/(choline + creatine)] and apparent diffusion coefficient (ADC) of voxels were calculated for the PZ regions corresponding to the biopsy cores and compared with histology. The median metabolite ratios for low‐grade, intermediate‐grade and high‐grade cancer were 0.29 (range: 0.16, 0.61), 0.17 (range: 0.13, 0.32) and 0.13 (range: 0.05, 0.23), respectively (p = 0.004). The corresponding mean ADCs (×10^–3 mm²/s) for low‐grade, intermediate‐grade and high‐grade cancer were 0.99 ± 0.08, 0.86 ± 0.11 and 0.69 ± 0.12, respectively (p < 0.0001). The combined ADC and metabolite ratio model showed strong discriminatory ability to differentiate subjects with GS ≤ 6 from subjects with GS ≥ 7 with an area under the curve of 94%. These data indicate that pre‐biopsy mpMRI may stratify PCa aggressiveness noninvasively. As the recent literature data suggest that men with GS ≤ 6 cancer may not need radical therapy, our data may help limit the need for biopsy and allow informed decision making for clinical intervention. Copyright © 2015 John Wiley & Sons, Ltd.     

In vivo diffusion MRI detects early spinal cord axonal pathology in a mouse model of amyotrophic lateral sclerosis

Diffusion magnetic resonance imaging (MRI) exhibits contrast that identifies macro‐ and microstructural changes in neurodegenerative diseases. Previous studies have shown that MR diffusion tensor imaging (DTI) can observe changes in spinal cord white matter in animals and humans affected with symptomatic amyotrophic lateral sclerosis (ALS). The goal of this preclinical work was to investigate the sensitivity of DTI for the detection of signs of tissue damage before symptoms appear. High‐field MRI data were acquired using a 9.4‐T animal scanner to examine the spinal cord of an ALS mouse model at pre‐ and post‐symptomatic stages (days 80 and 120, respectively). The MRI results were validated using yellow fluorescent protein (YFP) via optical microscopy of spinal cord tissue slices collected from the YFP,G93A‐SOD1 mouse strain. DTI maps of diffusion‐weighted imaging (DWI) signal intensity, mean diffusivity (MD), fractional anisotropy (FA), axial diffusivity (AD) and radial diffusivity (RD) were computed for axial slices of the lumbar region of the spinal cord. Significant changes were observed in FA (6.7% decrease, p < 0.01), AD (19.5% decrease, p < 0.01) and RD (16.1% increase, p < 0.001) at postnatal day 80 (P80). These differences were correlated with changes in axonal fluorescence intensity and membrane cellular markers. This study demonstrates the value of DTI as a potential tool to detect the underlying pathological progression associated with ALS, and may accelerate the discovery of therapeutic strategies for patients with this disease.     

Improved Assessment of Ex Vivo Brainstem Neuroanatomy With High‐Resolution MRI and DTI at 7 Tesla

The aim of the present work was to provide the topography of the main gray nuclei and white matter tracts of the human brainstem at 7 Tesla (7 T) high‐field magnetic resonance imaging (MRI) using structural imaging (T1) and diffusion tensor imaging (DTI). Both imaging techniques represent a new field of increasing interest for its potential neuroanatomic and neuropathologic value. Brainstems were obtained postmortem from human donors, fixated by intracarotid perfusion of 10% neutral buffered formalin, and scanned in a Bruker BioSpec 7 T horizontal scanner. 3D‐data sets were acquired using the modified driven equilibrium Fourier transform (MDEFT) sequence and Spin Echo‐DTI (SE‐DTI) sequence was used for DTI acquisition. High‐resolution structural MRI and DTI of the human brainstem acquired postmortem reveals its basic cyto‐ and myeloar‐chitectonic organization, only visualized to this moment by histological techniques and higher magnetic field strengths. Brainstem structures that are usually not observed with lower magnetic fields were now topographically identified at midbrain, pons, and medullar levels. The application of high‐resolution structural MRI will contribute to precisely determine the extension and topography of brain lesions. Indeed, the current findings will be useful to interpret future high‐resolution in vivo MRI studies in living humans. Anat Rec, 2011. © 2011 Wiley‐Liss, Inc.     

A 3D Radiomics-Based Artificial Neural Network Model for Benign Versus Malignant Vertebral Compression Fracture Classification in MRI

To train an artificial neural network model using 3D radiomic features to differentiate benign from malignant vertebral compression fractures (VCFs) on MRI. This retrospective study analyzed sagittal T1-weighted lumbar spine MRIs from 91 patients (average age of 64.24 ± 11.75 years) diagnosed with benign or malignant VCFs from 2010 to 2019, of them 47 (51.6%) had benign VCFs and 44 (48.4%) had malignant VCFs. The lumbar fractures were three-dimensionally segmented and had their radiomic features extracted and selected with the wrapper method. The training set consisted of 100 fractured vertebral bodies from 61 patients (average age of 63.2 ± 12.5 years), and the test set was comprised of 30 fractured vertebral bodies from 30 patients (average age of 66.4 ± 9.9 years). Classification was performed with the multilayer perceptron neural network with a back-propagation algorithm. To validate the model, the tenfold cross-validation technique and an independent test set (holdout) were used. The performance of the model was evaluated using the average with a 95% confidence interval for the ROC AUC, accuracy, sensitivity, and specificity (considering the threshold = 0.5). In the internal validation test, the best model reached a ROC AUC of 0.98, an accuracy of 95% (95/100), a sensitivity of 93.5% (43/46), and specificity of 96.3% (52/54). In the validation with independent test set, the model achieved a ROC AUC of 0.97, an accuracy of 93.3% (28/30), a sensitivity of 93.3% (14/15), and a specificity of 93.3% (14/15). The model proposed in this study using radiomic features could differentiate benign from malignant vertebral compression fractures with excellent performance and is promising as an aid to radiologists in the characterization of VCFs.

     

Assessment of vessel permeability by combining dynamic contrast‐enhanced and arterial spin labeling MRI

The forward volumetric transfer constant (K^trans), a physiological parameter extracted from dynamic contrast‐enhanced (DCE) MRI, is weighted by vessel permeability and tissue blood flow. The permeability × surface area product per unit mass of tissue (PS) in brain tumors was estimated in this study by combining the blood flow obtained through pseudo‐continuous arterial spin labeling (PCASL) and K^trans obtained through DCE MRI. An analytical analysis and a numerical simulation were conducted to understand how errors in the flow and K^trans estimates would propagate to the resulting PS. Fourteen pediatric patients with brain tumors were scanned on a clinical 3‐T MRI scanner. PCASL perfusion imaging was performed using a three‐dimensional (3D) fast‐spin‐echo readout module to determine blood flow. DCE imaging was performed using a 3D spoiled gradient‐echo sequence, and the K^trans map was obtained with the extended Tofts model. The numerical analysis demonstrated that the uncertainty of PS was predominantly dependent on that of K^trans and was relatively insensitive to the flow. The average PS values of the whole tumors ranged from 0.006 to 0.217 min^?1, with a mean of 0.050 min^?1 among the patients. The mean K^trans value was 18% lower than the PS value, with a maximum discrepancy of 25%. When the parametric maps were compared on a voxel‐by‐voxel basis, the discrepancies between PS and K^trans appeared to be heterogeneous within the tumors. The PS values could be more than two‐fold higher than the K^trans values for voxels with high K^trans levels. This study proposes a method that is easy to implement in clinical practice and has the potential to improve the quantification of the microvascular properties of brain tumors. Copyright © 2015 John Wiley & Sons, Ltd.     

Automated Classification of Rheumatoid Arthritis,Osteoarthritis, and Normal Hand Radiographs with Deep Learning Methods

Rheumatoid arthritis and hand osteoarthritis are two different arthritis that causes pain, function limitation, and permanent joint damage in the hands. Plain hand radiographs are the most commonly used imaging methods for the diagnosis, differential diagnosis, and monitoring of rheumatoid arthritis and osteoarthritis. In this retrospective study, the You Only Look Once (YOLO) algorithm was used to obtain hand images from original radiographs without data loss, and classification was made by applying transfer learning with a pre-trained VGG-16 network. The data augmentation method was applied during training. The results of the study were evaluated with performance metrics such as accuracy, sensitivity, specificity, and precision calculated from the confusion matrix, and AUC (area under the ROC curve) calculated from ROC (receiver operating characteristic) curve. In the classification of rheumatoid arthritis and normal hand radiographs, 90.7%, 92.6%, 88.7%, 89.3%, and 0.97 accuracy, sensitivity, specificity, precision, and AUC results, respectively, and in the classification of osteoarthritis and normal hand radiographs, 90.8%, 91.4%, 90.2%, 91.4%, and 0.96 accuracy, sensitivity, specificity, precision, and AUC results were obtained, respectively. In the classification of rheumatoid arthritis, osteoarthritis, and normal hand radiographs, an 80.6% accuracy result was obtained. In this study, to develop an end-to-end computerized method, the YOLOv4 algorithm was used for object detection, and a pre-trained VGG-16 network was used for the classification of hand radiographs. This computer-aided diagnosis method can assist clinicians in interpreting hand radiographs, especially in rheumatoid arthritis and osteoarthritis.

     

Dynamic contrast‐enhanced MRI model selection for predicting tumor aggressiveness in papillary thyroid cancers

The purpose of this study was to identify the optimal tracer kinetic model from T₁‐weighted dynamic contrast‐enhanced magnetic resonance imaging (DCE‐MRI) data and evaluate whether parameters estimated from the optimal model predict tumor aggressiveness determined from histopathology in patients with papillary thyroid carcinoma (PTC) prior to surgery. In this prospective study, 18 PTC patients underwent pretreatment DCE‐MRI on a 3 T MR scanner prior to thyroidectomy. This study was approved by the institutional review board and informed consent was obtained from all patients. The two‐compartment exchange model, compartmental tissue uptake model, extended Tofts model (ETM) and standard Tofts model were compared on a voxel‐wise basis to determine the optimal model using the corrected Akaike information criterion (AICc) for PTC. The optimal model is the one with the lowest AICc. Statistical analysis included paired and unpaired t‐tests and a one‐way analysis of variance. Bonferroni correction was applied for multiple comparisons. Receiver operating characteristic (ROC) curves were generated from the optimal model parameters to differentiate PTC with and without aggressive features, and AUCs were compared. ETM performed best with the lowest AICc and the highest Akaike weight (0.44) among the four models. ETM was preferred in 44% of all 3419 voxels. The ETM estimates of K^trans in PTCs with the aggressive feature extrathyroidal extension (ETE) were significantly higher than those without ETE (0.78 ± 0.29 vs. 0.34 ± 0.18 min^?1, P = 0.005). From ROC analysis, cut‐off values of K^trans, v_e and v_p, which discriminated between PTCs with and without ETE, were determined at 0.45 min^?1, 0.28 and 0.014 respectively. The sensitivities and specificities were 86 and 82% (K^trans), 71 and 82% (v_e), and 86 and 55% (v_p), respectively. Their respective AUCs were 0.90, 0.71 and 0.71. We conclude that ETM K^trans has shown potential to classify tumors with and without aggressive ETE in patients with PTC.