Diffusion-weighted Imaging Images Research Articles

Semantic segmentation guided detector for segmentation, classification, and lesion mapping of acute ischemic stroke in MRI images

Background and purposeMRI images timely and accurately reflect ischemic injuries to the brain tissues and, therefore, can support clinical decision-making of acute ischemic stroke (AIS). To maximize the information provided by the MRI images, we leverage deep learning models to segment, classify, and map lesion distributions of AIS. MethodsWe evaluated brain MRI images of AIS patients from 2017 to 2020 at a tertiary teaching hospital and developed the Semantic Segmentation Guided Detector Network (SGD-Net), composed of the first U-shaped model for segmentation in diffusion-weighted imaging (DWI) and the second model for binary classification of lesion size (lacune vs. non-lacune) and circulatory territory of lesion location (anterior vs. posterior circulation). Next, we modified the two-stage deep learning model into SGD-Net Plus by automatically segmenting AIS lesions in DWI images and registering the lesion in T1-weighted images and the brain atlases. ResultsThe final enrollment (216 patients with 4606 slices) was divided into 80% for model development and 20% for testing. S1 model segmented AIS lesions in DWI images accurately with a pixel accuracy > 99% (Dice 0.806–0.828 and IoU 0.675–707). In comprehensive evaluation of classification performance, the two-stage SGD-Net outperformed the traditional one-stage models in classifying AIS lesion size (accuracy 0.867–0.956 vs. 0.511–0.867, AUROC 0.962–0.992 vs. 0.528–0.937, AUPRC 0.964–0.994 vs. 0.549–0.938) and location (accuracy 0.860–0.930 vs. 0.326–0.721, AUROC 0.936–0.988 vs. 0.493–0.833, AUPRC 0.883–0.978 vs. 0.365–0.695). The precise lesion segmentation at the first stage of the deep learning model was the basis for further application. After that, the modified two-stage model SGD-Net Plus accurately reported the volume, region percentage, and lesion percentage of each region on the selected brain atlas. Its reports provided clear descriptions and quantifications of the AIS-related brain injuries on white matter tracts, Brodmann areas, and cytoarchitectonic areas. ConclusionDomain knowledge-oriented design of artificial intelligence applications can deepen our understanding of patients’ conditions and strengthen the use of MRI for patient care. SGD-Net precisely segments AIS lesions on DWI and accurately classifies the lesions. In addition, SGD-Net Plus maps the AIS lesions and quantifies their occupancy in each brain region. They are practical tools to meet the clinical needs and enrich educational resources of neuroimage.

Automated detection and grading of prostate cancer in multiparametric MRI

Prostate cancer is a major health issue worldwide and automatic segmentation of prostate from magnetic resonance imaging (MRI) is crucial task in image guided intervention. The objective of this paper is to develop a transparent and meticulous feature learning framework for prostate cancer detection and grading of prostate cancer using multiparametric magnetic resonance imaging (MPMRI). Prostate cancer is confirmed using approved rules of prostate cancer diagnosis from MPMRI data. The clustering is done in apparent diffusion coefficient (ADC) and diffusion weighted images (DWI) to obtain a probabilistic map which confirms cancerous region. The performance of proposed work is enormously tested on the dataset that contains T2Weighted, DWI and ADC map images of 236 subjects. In this study a total of 218 regions were used for analysis which includes 53 non-cancerous regions and 165 cancerous lesions. We have obtained tumour detection accuracy of 93.2% and AUC of 0.94 by using random forest classifier. The results yield by proposed algorithm is validated by two experienced radiologists.

Subcortical motor ischemia can be detected by intraoperative MRI within 1 ​h – A feasibility study

IntroductionTo achieve a maximum extent of resection, intraoperative MRI (ioMRI) scan is frequently performed. Intraoperative diffusion-weighted imaging (DWI) is not standardly performed and has been described to be inferior to early postoperative MRI regarding the detection of ischemia. Research questionThis feasibility study evaluates the detection of ischemia by ioMRI and its clinical relevance in patients with motor-eloquent gliomas. Material and methodsOf 262 glioma patients, eight patients (3.1%) showed an amplitude loss of continuous motor evoked potential (MEP) monitoring during resection before the ioMRI scan (group loss of MEP ​= ​LOM). In these patients and a matched-pair cohort (MPC) of glioma resections without MEP loss, we performed additional ioMRI sequences including turbo-spin-echo (TSE)- and echo-planar-imaging (EPI)-DWI and perfusion-weighted imaging (PWI). The clinical outcome was measured 5 days and 3 months after surgery. ResultsThe mean ​± ​standard time between loss of MEPs and ioMRI was 63.0 ​± ​8.7 ​min (range: 40–84). Ischemia within the motor system could be detected by ioMRI in group LOM in 100% EPI-DWIs, 75% TSE-DWIs, and 66.7% PWIs. No sequence showed motor ischemia in the MPC group. All patients of group LOM and no patient of group MPC suffered from permanent motor deficit. Discussion and conclusionThe current results provide data on the time sequence of ischemia apparent in MRI sequences which is superior to previous data on symptomatic stroke patients on this topic. The early detection of ischemia adds an additional predictor for the long-term outcome of patients and shows the reason of an intraoperative loss of MEPs. Thereby the performance of intraoperative EPI-DWI might be justified after confirmation of the present data in a larger cohort.Subcortical ischemia can be detected by ioMRI after MEP loss during the resection of motor-eloquent gliomas and was clinically relevant in all cases.

Fluid-attenuated inversion recovery diffusion-weighted imaging (DWI) for evaluating chemotherapy response in patients with acute leukemia: Comparison with conventional DWI.

At present, the diagnosis and efficacy evaluation of acute leukemia (AL) are assessed by bone marrow aspiration, which is invasive and subject to sampling errors. Therefore, there is a pressing need to develop a noninvasive and accurate imaging method to evaluate bone marrow changes in patients with AL. This study aimed to compare the apparent diffusion coefficient (ADC) values obtained from fluid-attenuated inversion recovery diffusion-weighted imaging (FLAIR-DWI) and conventional DWI in the lumbar bone marrow of patients with AL and to investigate their performance for evaluating response to induction chemotherapy. A total of 28 patients with newly diagnosed AL and 25 patients with AL after induction chemotherapy underwent MRI scans at 1.5 Tesla using a conventional DWI and a FLAIR-DWI sequence on sagittal planes covering the lumbar bone marrow. Further, the ADC values from these two sequences, denoted as ADCCON and ADCFLAIR, were measured on multiple vertebrae. The percentage of leukemia cells in bone marrow was recorded, and bone marrow aspiration was performed on treated patients to determine complete remission (CR) and nonremission (NR). ADCFLAIR [(0.453 ± 0.103) × 10-3 mm2/s] was significantly lower than ADCCON [(0.486 ± 0.096) × 10-3 mm2/s] in the 28 untreated patients (t = 3.051, P = 0.005). In the 25 treated patients, ADCFLAIR and ADCCON values [(0.566 ± 0.239) × 10-3 mm2/s] and [(0.716 ± 0.235) × 10-3 mm2/s], respectively, were higher compared with the untreated patients. The ADCCON values showed a nonsignificant difference between the CR (n = 18) and NR (n = 7) groups (t = 1.409, P = 0.305). However, the ADCFLAIR values exhibited statistically significant difference (t = 2.542, P = 0.018) between the two groups. In a receiver operator characteristic (ROC) analysis, the area under the curve (AUC) using ADCFLAIR (0.770) was larger than that of ADCCON (0.611) in distinguishing the CR and NR patients following the chemotherapy. Although both ADCCON and ADCFLAIR are sensitive to tissue changes induced by chemotherapy, FLAIR-DWI outperformed conventional DWI in separating AL patients with CR from NR after chemotherapy. A possible mechanism is that FLAIR-DWI suppresses signals from free water, making the ADC measurement more sensitive to structural changes in the bone marrow.

Diffusion-tensor magnetic resonance imaging of the human heart in health and in acute myocardial infarction using diffusion-weighted echo-planar imaging technique with spin-echo signals.

Originally thought unsuitable due to proneness to myocardial motion and susceptibility artefacts, spin-echo echo planar imaging (SE-EPI) has gained attention for the cardiac diffusion-weighted imaging (DWI) and diffusion tensor imaging (DTI) offering higher SNR and lower achievable echo time (TE). The application of DTI for patients with acute myocardial infarction (AMI) using our methodology developed on the basis of the SE-EPI sequence. Twelve patients with AMI and six healthy controls were enrolled in the preliminary DTI study within the CIRCULATE STRATEGMED 2 project. Our method relied on a pilot ECG-triggered DTI examination, based on which the initial evaluation was possible and allowed proper manipulation of TE (64/47 ms for patients/control), repetition time (TR) and ECG trigger delay in the consecutive DTI. The study demonstrated that by using our algorithm it was possible to obtain DWI images showing infarct zones identified on T1-weighted images with late gadolinium-enhancement (LGE) with division into subtle and severe damage. Quantitative DTI showed increased mean diffusivity (MD) and decreased fractional anisotropy (FA) in the infarct compared to remote tissue. The application of B-matrix spatial distribution (BSD) calibration allowed the improvement of FA. Our algorithm is suitable for qualitative assessment of infarction zones with different severity. The analysis of the quantitative DTI showed that despite the lack of motion compensation blocks in the applied SE-EPI sequence, it was possible to approach the diffusion tensor parameter values reported for the myocardium.

Deep Learning-Based Diffusion-Weighted Magnetic Resonance Imaging in the Diagnosis of Ischemic Penumbra in Early Cerebral Infarction.

The prefiltered image was imported into the local higher-order singular value decomposition (HOSVD) denoising algorithm (GL-HOSVD)-optimized diffusion-weighted imaging (DWI) image, which was compared with the deviation correction nonlocal mean (NL mean) and low-level edge algorithm (LR + edge). Regarding the peak signal-to-noise ratio (PSNR), root mean square error (RMSE), sensitivity, specificity, accuracy, and consistency, the application effect of the GL-HOSVD algorithm in DWI was investigated, and its adoption effect in the examination of ischemic penumbra (IP) of early acute cerebral infarction (ACI) patients was evaluated. A total of 210 patients with ACI were selected as the research subjects, who were randomly rolled into two groups. Those who were checked by conventional DWI were set as the control group, and those who used DWI based on the GL-HOSVD denoising algorithm were set as the observation group, with 105 people in each. Positron emission tomography (PET) test results were set as the gold standard to evaluate the application value of the two examination methods. It was found that under different noise levels, the peak signal-to-noise ratio (PSNR) of the GL-HOSVD algorithm and the root mean square error (RMSE) of the FA parameter were better than those of the nonlocal means (NL-means) of deviation correction and low-rank edge algorithm (LR + edge). The sensitivity, specificity, accuracy, and consistency (8.76%, 81.25%, 87.62%, and 0.52) of the observation group were higher than those of the control group (57.78%, 53.33%, 57.14%, and 0.35) (P < 0.05). Moreover, the apparent diffusion coefficient (ADC) of the DWI images of the observation group was basically consistent with that of the PET images, while the control group had a poor display effect and low definition. In summary, under different noise levels, the GL-HOSVD algorithm had a good denoising effect and greatly reduced fringe artifacts. DWI after denoising had high sensitivity, specificity, accuracy, and consistency in the detection of IP, which was worthy of clinical application and promotion.

Quantification of infarct core signal using CT imaging in acute ischemic stroke

In stroke care, the extent of irreversible brain injury, termed infarct core, plays a key role in determining eligibility for acute treatments, such as intravenous thrombolysis and endovascular reperfusion therapies. Many of the pivotal randomized clinical trials testing those therapies used MRI Diffusion-Weighted Imaging (DWI) or CT Perfusion (CTP) to define infarct core. Unfortunately, these modalities are not available 24/7 outside of large stroke centers. As such, there is a need for accurate infarct core determination using faster and more widely available imaging modalities including Non-Contrast CT (NCCT) and CT Angiography (CTA).Prior studies have suggested that CTA provides improved predictions of infarct core relative to NCCT; however, this assertion has never been numerically quantified by automatic medical image computing pipelines using acquisition protocols not confounded by different scanner manufacturers, or other protocol settings such as exposure times, kilovoltage peak, or imprecision due to contrast bolus delays. In addition, single-phase CTA protocols are at present designed to optimize contrast opacification in the arterial phase. This approach works well to maximize the sensitivity to detect vessel occlusions, however, it may not be the ideal timing to enhance the ischemic infarct core signal (ICS).In this work, we propose an image analysis pipeline on CT-based images of 88 acute ischemic stroke (AIS) patients drawn from a single dynamic acquisition protocol acquired at the acute ischemic phase. We use the first scan at the time of the dynamic acquisition as a proxy for NCCT, and the rest of the scans as a proxy for CTA scans, with bolus imaged at different brain enhancement phases. Thus, we use the terms “NCCT” and “CTA” to refer to them. This pipeline enables us to answer the questions “Does the injection of bolus enhance the infarct core signal?” and “What is the ideal bolus timing to enhance the infarct core signal?” without being influenced by aforementioned factors such as scanner model, acquisition settings, contrast bolus delay, and human reader errors. We use reference MRI DWI images acquired after successful recanalization acting as our gold standard for infarct core.The ICS is quantified by calculating the difference in intensity distribution between the infarct core region and its symmetrical healthy counterpart on the contralateral hemisphere of the brain using a metric derived from information theory, the Kullback-Leibler divergence (KL divergence). We compare the ICS provided by NCCT and CTA and retrieve the optimal timing of CTA bolus to maximize the ICS.In our experiments, we numerically confirm that CTAs provide greater ICS compared to NCCT. Then, we find that, on average, the ideal CTA acquisition time to maximize the ICS is not the current target of standard CTA protocols, i.e., during the peak of arterial enhancement, but a few seconds afterward (median of 3 s; 95% CI [1.5, 3.0]). While there are other studies comparing the prediction potential of ischemic infarct core from NCCT and CTA images, to the best of our knowledge, this analysis is the first to perform a quantitative comparison of the ICS among CT based scans, with and without bolus injection, acquired using the same scanning sequence and a precise characterization of the bolus uptake, hence, reducing potential confounding factors.

CT and MRI features of extraocular muscle granular cell tumour: preliminary experience in eight cases

To characterise the computed tomography (CT) and magnetic resonance imaging (MRI) features, in particular the functional MRI characteristics, of extraocular muscle granular cell tumours (GCTs). The CT (n=6) and MRI (n=8) features of eight extraocular muscle GCTs cofirmed at histopathology were analysed retrospectively. The imaging findings were evaluated with emphasis on the location, size, margin, shape, extent, bony change, internal architecture, enhancement pattern, and extent of lesions. Based on diffusion-weighted imaging (DWI) and dynamic contrast-enhanced (DCE) MRI, the apparent diffusion coefficient (ADC) value of six lesions and time-intensity curve (TIC) of one lesion were reviewed. Immunohistochemistry revealed strong positivity for S-100 protein and a low Ki-67 index (2-5%) in all cases. Most of the lesions (7/8) were confined to the muscle belly with an ovoid shape. All of the tumours were isodense to cerebral grey matter and showed homogeneously mild enhancement on CT images. All lesions were hypointense to cerebral grey matter on T2-weighted imaging (T2WI) and showed homogeneously marked enhancement on contrast-enhanced T1-weighted imaging (T1WI). All lesions showed a hypo- or isointense signal on DWI images with a high b-value. The mean ADC of six lesions was (0.72±0.14)×10-3 mm2/s. The TIC of the case examined using DCE-MRI showed a plateau pattern (type II). A well-defined oval mass confined to the muscle belly with a hypointense signal on T2WI, homogeneously marked enhancement on contrast-enhanced T1WI, hypo- or isointense signal on DWI, and low ADC value is highly suggestive of a GCT.

Study on Memory Function of Stroke Patients under Exercise Relearning Based on DWI Image Analysis Based on Optimized Registration Algorithm

Objective. This paper uses an optimized registration algorithm to analyze the diffusion-weighted imaging (DWI) scan parameters of acute ischemic stroke (AIS) in the memory function of stroke patients under exercise relearning (MRP). Methods. This study used a random case-control study. 65 patients with stroke and hemiplegia were randomly divided into a control group: conventional rehabilitation intervention (32 cases), and a treatment group: MRP (33 cases). Each patient uses 4 parameters for DWI examination and obtains 4 sets of images, group 1 is the control sequence, group 2 uses parallel acquisition technology, group 3 uses parallel acquisition technology and reduces the number of excitations, group 4 uses parallel acquisition technology to reduce repetition time (TR) and echo time (TE) and enlarge the field of view, and the scan time of each group is 177, 81, 23, and 18 s in sequence. At the time of enrollment and after 12 weeks of treatment, patients in each group were evaluated with Fugl-Meyer motor function score (FMA) and modified Pap index (MBI) for hand and wrist motor function and ADL. Results. After treatment, the FMA and MBI values of the treatment group were significantly higher than those of the control group ( P &lt; 0.05 ). Conclusion. By adopting a parallel acquisition technique and reducing the number of excitations (group 3) scanning scheme, not only the scanning time is significantly shortened, but also the image quality can meet the diagnostic requirements, which has great application value for AIS patients who need emergency treatment. MRP can obviously promote the hand and wrist motor function and daily living ability of stroke hemiplegic patients.

Evaluation of the malignant potential of gliomas using diffusion-weighted and gadolinium-enhanced magnetic resonance imaging

Objective: This study aimed to determine whether the apparent diffusion coefficients (ADCs) determined by diffusion-weighted imaging (DWI) of magnetic resonance imaging (MRI) could facilitate the malignancy grading of various gliomas. Methods: Sixty patients with a primary cerebral glioma underwent diffusion-weighted and gadolinium-enhanced (Gd) T1-weighted MRI using a 1.5-T MRI scanner. Scoring was performed based on signal intensities on DWI and Gd images. The mean and minimum ADC values were calculated, and Ki-67 staining was performed for each histological sample to evaluate their tumor proliferative potential. Then, the DWI, Gd, and combined scores were analyzed and compared with the Ki-67 staining index and malignant grade. The relationships among the mean and minimum ADC values, Ki-67 staining index, and malignant grade were also evaluated. Results: The minimum ADC was inversely correlated with the Ki-67 staining index, with a low minimum ADC suggestive of tumor malignancy. The qualitative evaluation of the D score of water molecule diffusion on DWI accurately reflected the pathological grades of gliomas, with an effectiveness that was at least as good as the quantitative analysis using the minimum ADC. The diagnostic value of Gd images in determining glioma malignancy grades was inferior to that of DWI. Conclusion: Both DWI and gadolinium-enhanced images of MRI should be considered essential for the diagnosis of tumor malignancy.

Detection and Segmentation of Pelvic Bones Metastases in MRI Images for Patients With Prostate Cancer Based on Deep Learning.

ObjectiveTo establish and evaluate the 3D U-Net model for automated segmentation and detection of pelvic bone metastases in patients with prostate cancer (PCa) using diffusion-weighted imaging (DWI) and T1 weighted imaging (T1WI) images.MethodsThe model consisted of two 3D U-Net algorithms. A total of 859 patients with clinically suspected or confirmed PCa between January 2017 and December 2020 were enrolled for the first 3D U-Net development of pelvic bony structure segmentation. Then, 334 PCa patients were selected for the model development of bone metastases segmentation. Additionally, 63 patients from January to May 2021 were recruited for the external evaluation of the network. The network was developed using DWI and T1WI images as input. Dice similarity coefficient (DSC), volumetric similarity (VS), and Hausdorff distance (HD) were used to evaluate the segmentation performance. Sensitivity, specificity, and area under the curve (AUC) were used to evaluate the detection performance at the patient level; recall, precision, and F1-score were assessed at the lesion level.ResultsThe pelvic bony structures segmentation on DWI and T1WI images had mean DSC and VS values above 0.85, and the HD values were <15 mm. In the testing set, the AUC of the metastases detection at the patient level were 0.85 and 0.80 on DWI and T1WI images. At the lesion level, the F1-score achieved 87.6% and 87.8% concerning metastases detection on DWI and T1WI images, respectively. In the external dataset, the AUC of the model for M-staging was 0.94 and 0.89 on DWI and T1WI images.ConclusionThe deep learning-based 3D U-Net network yields accurate detection and segmentation of pelvic bone metastases for PCa patients on DWI and T1WI images, which lays a foundation for the whole-body skeletal metastases assessment.

An MRI-based radiomics signature and clinical characteristics for survival prediction in early-stage cervical cancer.

To investigate the prognostic role of magnetic resonance imaging (MRI)-based radiomics signature and clinical characteristics for overall survival (OS) and disease-free survival (DFS) in the early-stage cervical cancer. A total of 207 cervical cancer patients (training cohort: n = 144; validation cohort: n = 63) were enrolled. 792 radiomics features were extracted from T2W and diffusion-weighted imaging (DWI). 19 clinicopathological parameters were collected from the electronic medical record system. Least absolute shrinkage and selection operator (LASSO) regression analysis was used to select significant features to construct prognostic model for OS and DFS. Kaplan-Meier (KM) analysis and log-rank test were applied to identify the association between the radiomics score (Rad-score) and survival time. Nomogram discrimination and calibration were evaluated as well. Associations between radiomics features and clinical parameters were investigated by heatmaps. A radiomics signature derived from joint T2W and DWI images showed better prognostic performance than that from either T2W or DWI image alone. Higher Rad-score was associated with worse OS (p < 0.05) and DFS (p < 0.05) in the training and validation set. The joint models outperformed both radiomics model and clinicopathological model alone for 3-year OS and DFS estimation. The calibration curves reached an agreement. Heatmap analysis demonstrated significant associations between radiomics features and clinical characteristics. The MRI-based radiomics nomogram showed a good performance on survival prediction for the OS and DFS in the early-stage cervical cancer. The prediction of the prognostic models could be improved by combining with clinical characteristics, suggesting its potential for clinical application. This is the first study to build the radiomics-derived models based on T2W and DWI images for the prediction of survival outcomes on the early-stage cervical cancer patients, and further construct a combined risk scoring system incorporating the clinical features.

Application of MRI Image Based on Computer Semiautomatic Segmentation Algorithm in the Classification Prediction of Breast Cancer Histology.

Objective The study aimed to investigate the predictive classification accuracy of computer semiautomatic segmentation algorithm for the histological grade of breast tumors through the magnetic resonance imaging (MRI) examination. Methods Five dynamic contrast-enhanced (DCE) MRI regions of interest (ROIs) were captured using computer semiautomatic segmentation method, referring to the entire tumor area, tumor border area, proximal gland area, middle gland area, and distal gland area. According to the mutual information maximum protocol, the corresponding five ROIs were extracted from diffusion weighted imaging (DWI) combined with DCE-MRI images. To use the features in the nonoverlapping area of DWI image and DCE-MRI image as elements, a single-variable logistic regression model was established corresponding to element characteristics. After multiple training, the model was evaluated using the receiver operating characteristic (ROC) curve and area under curve (AUC). Results This DCE-MRI combined with DWI was superior to DCE-MRI and DW in the prediction of tumor area features. To use DCE-MRI or DWI alone was less effective than DCE-MRI combined with DWI. The DWI combined DCE-MRI demonstrated good regional segmentation effects in the tumour area, with luminal A value being 0.767 and the area under curve (AUC) value being 0.758. After optimization, the AUC value of the tumor area was 0.929, indicating that classification effects can be enhanced by combining the two imaging methods, which complemented each other. Conclusions The DWI combined DCE-MRI imaging has improved the early diagnosis effects of breast cancer by predicting the occurrence of breast cancer through the labeling of biomarkers.

Assessment of Isocitrate Dehydrogenase 1 Genotype and Cell Proliferation in Gliomas Using Multiple Diffusion Magnetic Resonance Imaging.

Objectives: To compare the efficacy of parameters from multiple diffusion magnetic resonance imaging (dMRI) for prediction of isocitrate dehydrogenase 1 (IDH1) genotype and assessment of cell proliferation in gliomas.Methods: Ninety-one patients with glioma underwent diffusion weighted imaging (DWI), multi-b-value DWI, and diffusion kurtosis imaging (DKI)/neurite orientation dispersion and density imaging (NODDI) on 3.0T MRI. Each parameter was compared between IDH1-mutant and IDH1 wild-type groups by Mann–Whitney U test in lower-grade gliomas (LrGGs) and glioblastomas (GBMs), respectively. Further, performance of each parameter was compared for glioma grading under the same IDH1 genotype. Spearman correlation coefficient between Ki-67 labeling index (LI) and each parameter was calculated.Results: The diagnostic performance was better achieved with apparent diffusion coefficient (ADC), slow ADC (D), fast ADC (D∗), perfusion fraction (f), distributed diffusion coefficient (DDC), heterogeneity index (α), mean diffusivity (MD), mean kurtosis (MK), and intracellular volume fraction (ICVF) for distinguishing IDH1 genotypes in LrGGs, with statistically insignificant AUC values from 0.750 to 0.817. In GBMs, no difference between the two groups was found. For IDH1-mutant group, all parameters, except for fractional anisotropy (FA) and D∗, significantly discriminated LrGGs from GBMs (P < 0.05). However, for IDH1 wild-type group, only ADC statistically discriminated the two (P = 0.048). In addition, MK has maximal correlation coefficient (r = 0.567, P < 0.001) with Ki-67 LI.Conclusion: dMRI-derived parameters are promising biomarkers for predicting IDH1 genotype in LrGGs, and MK has shown great potential in assessing glioma cell proliferation.

Development and validation of the 3D U-Net algorithm for segmentation of pelvic lymph nodes on diffusion-weighted images

BackgroundThe 3D U-Net model has been proved to perform well in the automatic organ segmentation. The aim of this study is to evaluate the feasibility of the 3D U-Net algorithm for the automated detection and segmentation of lymph nodes (LNs) on pelvic diffusion-weighted imaging (DWI) images.MethodsA total of 393 DWI images of patients suspected of having prostate cancer (PCa) between January 2019 and December 2020 were collected for model development. Seventy-seven DWI images from another group of PCa patients imaged between January 2021 and April 2021 were collected for temporal validation. Segmentation performance was assessed using the Dice score, positive predictive value (PPV), true positive rate (TPR), and volumetric similarity (VS), Hausdorff distance (HD), the Average distance (AVD), and the Mahalanobis distance (MHD) with manual annotation of pelvic LNs as the reference. The accuracy with which the suspicious metastatic LNs (short diameter > 0.8 cm) were detected was evaluated using the area under the curve (AUC) at the patient level, and the precision, recall, and F1-score were determined at the lesion level. The consistency of LN staging on an hold-out test dataset between the model and radiologist was assessed using Cohen’s kappa coefficient.ResultsIn the testing set used for model development, the Dice score, TPR, PPV, VS, HD, AVD and MHD values for the segmentation of suspicious LNs were 0.85, 0.82, 0.80, 0.86, 2.02 (mm), 2.01 (mm), and 1.54 (mm) respectively. The precision, recall, and F1-score for the detection of suspicious LNs were 0.97, 0.98 and 0.97, respectively. In the temporal validation dataset, the AUC of the model for identifying PCa patients with suspicious LNs was 0.963 (95% CI: 0.892–0.993). High consistency of LN staging (Kappa = 0.922) was achieved between the model and expert radiologist.ConclusionThe 3D U-Net algorithm can accurately detect and segment pelvic LNs based on DWI images.

To Determine the Diagnostic Accuracy of Diffusion-Weighted Imaging in the Diagnosis of Prostate Carcinoma Taking Histopathology As the Gold Standard.

IntroductionCarcinoma of the prostate is the most common malignancy among males. Serum prostate-specific antigen (PSA) levels and digital rectal examination (DRE) are the initial investigations for the detection of prostate cancer. In recent years, some investigators have used color Doppler ultrasound and diffusion-weighted imaging (DWI) for the diagnosis of prostate cancer and avoided invasive and painful investigation, i.e., biopsy. The purpose of the study is to determine the validity of DWI in detecting prostatic cancer taking histopathology as the gold standard.Material and methodsThis cross-sectional study was conducted prospectively in the radiology department of a tertiary care hospital from January 1, 2019, to December 31, 2020. This study was approved by the Departmental Research Committee. A total of 272 male patients were included in our study who have elevated PSA levels (>4.0 ng/ml) with symptoms of hematuria and urinary retention. All included subjects were sent to the radiology department for DWI imaging. The DWI imaging was analyzed for prostate cancer and the results were correlated with histopathological diagnosis.ResultsThe average age of patients was 50.28±9.93 years. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of DWI in the diagnoses of prostate cancer were 86.7%, 87.8%, 75.8%, 93.8%, and 87.5%, respectively.ConclusionDWI is an informative and non-invasive imaging modality with high diagnostic accuracy for the diagnosis of prostate carcinoma.

Pre-Treatment Apparent Diffusion Coefficient Histogram Metrics as a Predictor of Local Tumor Control After Proton Beam Therapy in Patients With Hepatocellular Carcinomas

Apparent diffusion coefficient (ADC) values extractable by diffusion-weighted imaging (DWI) are reported as useful in predicting the outcome of surgery and radiofrequency ablation (RFA) in hepatocellular carcinoma (HCC). However, their relationship with local tumor control (LC) after proton beam therapy (PBT) has not been fully evaluated. This study aimed to investigate interobserver variability in ADC histogram metrics and their usefulness in predicting LC in HCC patients who underwent PBT.The ADC maps of the liver of HCC patients who underwent PBT between 2015 and 2020 were reviewed. The inclusion criteria were imaging DWI at 1.5T within 6 weeks before PBT and the largest tumor dimension between 2 and 10 cm. Twenty-nine patients and 32 tumors were eligible. Axial DWI was acquired using a single-shot spin-echo echo-planar sequence and the b values of 0 and 1000 s mm-2. The ADC maps generated were transferred to a workstation. Five board-certified radiation oncologists (ROs) contoured the whole tumor regions-of-interest (ROIs) on these maps, using anatomical images obtained together as reference. For each ROI, the minimum (ADCmin), mean (ADCmean), maximum (ADCmax), and the 5th (ADC5), 25th (ADC25), 50th (ADC50), 75th (ADC75), and 95th (ADC95) percentiles were extracted. The intraclass correlation coefficient (2,1) (ICC) was calculated to determine interobserver reproducibility: ICC of 0.75 - 0.90 was considered good and > 0.90 excellent. The ADC metrics were averaged among 5 ROs. The optimal cut-off values that determined LC, i.e., non-progressive disease (PD) based on the modified RECIST, were identified using receiver-operating characteristics (ROC) analysis. The LC rates were calculated using the Kaplan-Meier method, and statistical significance was assessed by log-rank test.The median calculated biologically effective dose (α / β = 10) was 97 GyE. With a median follow-up of 39 months (5 - 62), 5 tumors had local PD. The ADCmin, ADCmean, ADCmax, ADC5, ADC25, ADC50, ADC75, and ADC95 of all tumors ranged between 0 - 1131, 748 - 1726, 1566 - 3149, 396 - 1430, 600 - 1566, 723 - 1719, 858 - 1874, and 1166 - 2426 (×10-6 mm 2 s-1), respectively. The ICC were 0.761, 0.969, 0.513, 0.864, 0.978, 0.983, 0.974, and 0.859, respectively. For ADCmean, ADC25, ADC50, and ADC75 which showed excellent reproducibility, the optimal cut-off values to determine LC were 1025, 1005, 1156, and 1132 (×10-6 mm 2 s-1), respectively. The tumors with higher ADC metrics had higher 2-year LC rates than their counterparts (100 % vs 40 %, P = 0.002; 100% vs 74%, P = 0.011; 100% vs 76%, P = 0.024; 100% vs 25%, P < 0.001, respectively).ADCmean, ADC25, ADC50, and ADC75 showed excellent interobserver reproducibility. Pre-treatment ADC histogram metrics may be useful in predicting LC after PBT in HCC.

Deep learning based multiplexed sensitivity-encoding (DL-MUSE) for high-resolution multi-shot DWI

PurposeA phase correction method for high-resolution multi-shot (MSH) diffusion weighted imaging (DWI) is proposed. The efficacy and generalization capability of the method were validated on both healthy volunteers and patients. Theory and methodsConventionally, inter-shot phase variations for MSH echo-planar imaging (EPI) DWI are corrected by model-based algorithms. However, many acquisition imperfections are hard to measure accurately for conventional model-based methods, making the phase estimation and artifacts suppression unreliable. We propose a deep learning multiplexed sensitivity-encoding (DL-MUSE) framework to improve the phase estimations based on convolutional neural network (CNN) reconstruction. Aliasing-free single-shot (SSH) DW images, which have been used routinely in clinical settings, were used for training before the aliasing correction of MSH-DWI images. A dual-channel U-net comprising multiple convolutional layers was used for the phase estimation of MSH-EPI. The network was trained on a dataset containing 30 healthy volunteers and tested on another dataset of 52 healthy subjects and 15 patients with lesions or tumors with different shot numbers (4, 6 and 8). To further validate the generalization capability of our network, we acquired a dataset with different numbers of shots, TEs, partial Fourier factors, resolutions, ETLs, FOVs, coil numbers, and image orientations from two sites. We also compared the reconstruction performance of our proposed method with that of the conventional MUSE and SSH-EPI qualitatively and quantitatively. ResultsOur results show that DL-MUSE is capable of correcting inter-shot phase errors with high and robust performance. Compared to conventional model-based MUSE, our method, by applying deep learning-based phase corrections, showed reduced distortion, noise level, and signal loss in high b-value DWIs. The improvements of image quality become more evident as the shot number increases from 4 to 8, especially in those central regions of the images, where g-factor artifacts are severe. Furthermore, the proposed method could provide the information about the orientation of the white matter with better consistency and achieve finer fibers delineation compared to the SSH-EPI method. Besides, the experiments on volunteers and patients from two different sites demonstrated the generalizability of our proposed method preliminarily. ConclusionA deep learning-based reconstruction algorithm for MSH-EPI images, which helps improve image quality greatly, was proposed. Results from healthy volunteers and tumor patients demonstrated the feasibility and generalization performances of our method for high-resolution MSH-EPI DWI, which can be used for routine clinical applications as well as neuroimaging research.

Calculation of Apparent Diffusion Coefficients in Prostate Cancer Using Deep Learning Algorithms: A Pilot Study.

BackgroundApparent diffusion coefficients (ADCs) obtained with diffusion-weighted imaging (DWI) are highly valuable for the detection and staging of prostate cancer and for assessing the response to treatment. However, DWI suffers from significant anatomic distortions and susceptibility artifacts, resulting in reduced accuracy and reproducibility of the ADC calculations. The current methods for improving the DWI quality are heavily dependent on software, hardware, and additional scan time. Therefore, their clinical application is limited. An accelerated ADC generation method that maintains calculation accuracy and repeatability without heavy dependence on magnetic resonance imaging scanners is of great clinical value.ObjectivesWe aimed to establish and evaluate a supervised learning framework for synthesizing ADC images using generative adversarial networks.MethodsThis prospective study included 200 patients with suspected prostate cancer (training set: 150 patients; test set #1: 50 patients) and 10 healthy volunteers (test set #2) who underwent both full field-of-view (FOV) diffusion-weighted imaging (f-DWI) and zoomed-FOV DWI (z-DWI) with b-values of 50, 1,000, and 1,500 s/mm2. ADC values based on f-DWI and z-DWI (f-ADC and z-ADC) were calculated. Herein we propose an ADC synthesis method based on generative adversarial networks that uses f-DWI with a single b-value to generate synthesized ADC (s-ADC) values using z-ADC as a reference. The image quality of the s-ADC sets was evaluated using the peak signal-to-noise ratio (PSNR), root mean squared error (RMSE), structural similarity (SSIM), and feature similarity (FSIM). The distortions of each ADC set were evaluated using the T2-weighted image reference. The calculation reproducibility of the different ADC sets was compared using the intraclass correlation coefficient. The tumor detection and classification abilities of each ADC set were evaluated using a receiver operating characteristic curve analysis and a Spearman correlation coefficient.ResultsThe s-ADCb1000 had a significantly lower RMSE score and higher PSNR, SSIM, and FSIM scores than the s-ADCb50 and s-ADCb1500 (all P < 0.001). Both z-ADC and s-ADCb1000 had less distortion and better quantitative ADC value reproducibility for all the evaluated tissues, and they demonstrated better tumor detection and classification performance than f-ADC.ConclusionThe deep learning algorithm might be a feasible method for generating ADC maps, as an alternative to z-ADC maps, without depending on hardware systems and additional scan time requirements.

Automatic brain extraction and hemisphere segmentation in rat brain MR images after stroke using deformable models.

Experimental ischemic stroke models play an essential role in understanding the mechanisms of cerebral ischemia and evaluating the development of pathological extent. An important precursor to the investigation of ischemic strokes associated with rodents is the brain extraction and hemisphere segmentation in rat brain diffusion-weighted imaging (DWI) and T2-weighted MRI (T2WI) images. Accurate and reliable image segmentation tools for extracting the rat brain and hemispheres in the MR images are critical in subsequent processes, such as lesion identification and injury analysis. This study is an attempt to investigate rat brain extraction and hemisphere segmentation algorithms that are practicable in both DWI and T2WI images. To automatically perform brain extraction, the proposed framework is based on an efficient geometric deformable model. By introducing an additional image force in response to the rat brain characteristics into the skull stripping model, we establish a unique rat brain extraction scheme in DWI and T2WI images. For the subsequent hemisphere segmentation, we develop an efficient brain feature detection algorithm to approximately separate the rat brain. A refinement process is enforced by constructing a gradient vector flow in the proximity of the midsurface, where a parametric active contour is attracted to achieve hemisphere segmentation. Extensive experiments with 55 DWI and T2WI subjects were executed in comparison with the state-of-the-art methods. Experimental results indicated that our rat brain extraction and hemisphere segmentation schemes outperformed the competitive methods and exhibited high performance both qualitatively and quantitatively. For rat brain extraction, the average Dice scores were 97.13% and 97.42% in DWI and T2WI image volumes, respectively. Rat hemisphere segmentation results based on the Hausdorff distance metric revealed average values of 0.17 and 0.15mm for DWI and T2WI subjects, respectively. We believe that the established frameworks are advantageous to facilitate preclinical stroke investigation and relevant neuroscience research that requires accurate brain extraction and hemisphere segmentation using rat DWI and T2WI images.