Axial Magnetic Resonance Imaging Scans Research Articles

First Thousand Cases of Intracranial Radiosurgery Treated with Gamma Knife at a Tertiary Care Hospital in India

Abstract Purpose We present the profile of first 1,000 cases of intracranial radiosurgery (IRS) treated with Gamma Knife system at a government-funded tertiary care hospital in India. In addition to the information on the indications treated, this study provides an idea of the relevance of the Gamma Knife Radiosurgery (GKRS) for IRS in the fast-changing technological scenario. This study also shows the disease indications for which GKRS was the primary treatment preference. Materials and Methods Leksell Gamma Knife model 4C was used for GKRS. Leksell G-frame-based stereotactic localization was used for all patients. Axial magnetic resonance imaging scans were used for treatment planning with additional two-dimensional angiography images for patients treated for arteriovenus malformations (AVM). The patient population treated with GKRS at our center mainly comprised of patients referred from across the country. Results Acoustic schwannoma formed the largest group of patients (27%) followed by meningioma (21%), AVM (18%), pituitary adenoma (16%), brain metastasis (5.3%), trigeminal neuralgia (3%), cavernoma (2.4%), glomus jugulare (1.8%), craniopharyngioma (1.1%) and “others” (5%). Conclusion The case mix at our center is similar to the overall Indian case mix. However, it is different from the Asian data of 2018 but interestingly similar to the data from Middle East and Africa for 2018. Among the various categories of cranial disorders treated by us, pituitary adenoma tumors had minimum (14/161) and cavernoma tumors had maximum (24/24) proportion of cases managed with GKRS as primary treatment modality.

Assessing Risk of Iatrogenic Peroneal Nerve Injury in All-Inside Lateral Meniscal Repair Between Standard Vs. Arthroscopic MRI.

Various studies have examined the risk of peroneal nerve injury with use of standard magnetic resonance imaging (MRI) of the knee. However, the position of the knee during standard MRI is different from that during an actual arthroscopic lateral meniscal repair. The purpose of the present study was to evaluate and compare the risk of peroneal nerve injury during simulated all-inside lateral meniscal repairs on the basis of MRI scans made with the knee in both positions. With use of axial MRI scans made with the knee in the standard position (i.e., in 30° of flexion) and in the actual position used during arthroscopic lateral meniscal repair (i.e., in a figure-of-4 position), direct lines were drawn to simulate the passage of a straight all-inside meniscal repair device from the anteromedial and anterolateral portals to the medial and lateral borders of the popliteus tendon. The distance from the closest passage of each line to the peroneal nerve was measured. If a line touched or passed through the peroneal nerve, a risk of iatrogenic injury was noted and a new line was drawn from the same portal to the outer border of the peroneal nerve. The danger area was measured from the first line to the new line along the joint capsule. In 28 Thai patients, the shortest distances from each line to the peroneal nerve were significantly shorter on the MRI scans made with the knee in the standard position than on those made with the knee in the arthroscopic position (p < 0.05 for all). All danger areas on the MRI scans that were made with the knee in the arthroscopic position were included within the danger areas on the scans that were made with the knee in the standard position. Standard MRI scans of the knee can be used to determine the risk of peroneal nerve injury at the time of arthroscopic lateral meniscal repair, although the risks are slightly overestimated. Diagnostic Level III . See Instructions for Authors for a complete description of levels of evidence.

The Risk of Iatrogenic Posterior Neurovascular Injuries in Lateral Meniscal Repair Based on the Standard Arthroscopic Knee Position: A Magnetic Resonance Imaging Study.

Repair of the posterior horn of the lateral meniscus using an all-inside meniscal repair device involves the risk of iatrogenic posterior neurovascular injuries. Previous studies that have evaluated this risk were based on preoperative magnetic resonance imaging (MRI) with the knee in 30° of flexion and used landmarks that are impractical in the actual operative situation. To use an MRI model simulating actual knee arthroscopic conditions to (1) compare the potential risk of injuries related to the lateral border of the posterior lateral meniscus root (LMR) through the anterolateral versus anteromedial portal and (2) establish "safe" and "danger" zones to reduce the possibility of injuries to posterior neurovascular structures when performing lateral meniscal repair in relation to the lateral border of the posterior LMR. Descriptive laboratory study. Using 29 axial MRI scans of knees in the figure-of-4 position with joint fluid dilatation at the level of the lateral meniscus, direct lines were drawn to simulate a straight all-inside meniscal repair device deployed from the anterolateral and anteromedial portals to the lateral border of the posterior LMR, extending 14 mm beyond the joint capsule. If the line passed through or touched a posterior neurovascular structure, a risk of iatrogenic injuries was noted, and measurements were made to determine the safe zone in relation to the lateral border of the posterior LMR. Repairing the lateral meniscus through the anterolateral portal in relation to the lateral border of the posterior LMR resulted in a significantly greater risk of posterior neurovascular injuries compared with repairing through the anteromedial portal, with injury incidences of 68.97% and 10.35%, respectively (P = .001). The safe zones of lateral meniscal repair through the anterolateral and anteromedial portals were 4.15 ± 1.87 and 6.57 ± 0.98 mm, respectively, beyond the lateral border of the posterior LMR. The risk of posterior neurovascular injuries when repairing posterior lateral meniscal tissue was found to be significantly greater through the anterolateral portal compared with the anteromedial portal. Surgeons can use the safe zones as defined in this study to decrease the risk of iatrogenic posterior neurovascular injuries during arthroscopic lateral meniscal repair.

Deep learning for image classification between primary central nervous system lymphoma and glioblastoma in corpus callosal tumors.

It can be challenging in some situations to distinguish primary central nervous system lymphoma (PCNSL) from glioblastoma (GBM) based on magnetic resonance imaging (MRI) scans, especially those involving the corpus callosum. The objective of this study was to assess the diagnostic performance of deep learning (DL) models between PCNSLs and GBMs in corpus callosal tumors. The axial T1-weighted gadolinium-enhanced MRI scans of 274 individuals with pathologically confirmed PCNSL (n = 94) and GBM (n = 180) were examined. After image pooling, pre-operative MRI scans were randomly split with an 80/20 procedure into a training dataset (n = 709) and a testing dataset (n = 177) for DL model development. Therefore, the DL model was deployed as a web application and validated with the unseen images (n = 114) and area under the receiver operating characteristic curve (AUC); other outcomes were calculated to assess the discrimination performance. The first baseline DL model had an AUC of 0.77 for PCNSL when evaluated with unseen images. The 2nd model with ridge regression regularization and the 3rd model with drop-out regularization increased an AUC of 0.83 and 0.84. In addition, the last model with data augmentation yielded an AUC of 0.57. DL with regularization may provide useful diagnostic information to help doctors distinguish PCNSL from GBM.

Prediction of Alzheimer's disease from magnetic resonance imaging using a convolutional neural network

ObjectivesThe primary goal of this study is to examine if a convolutional neural network (CNN) can be applied as a diagnostic tool for predicting Alzheimer's Disease (AD) from magnetic resonance imaging (MRI) using the MIRIAD-dataset (Minimal Interval Resonance Imaging in Alzheimer's Disease) from one single central slice of the brain. MethodsThe MIRIAD dataset contains patients' health records represented by a set of MRI scans of the brain and further diagnostic data. Hyperparameters and configurations of CNNs were optimized to determine the best-performing model. The CNN was implemented in Python with the deep learning library ‘Keras’ using Linux/Ubuntu as the operating system. ResultsThis study obtained the following best performance metrics for predicting Alzheimer's Disease from MRI with Matthew's Correlation Coefficient (MCC) of 0.77; accuracy of 0.89; F1-score of 0.89; AUC of 0.92. The computational time for the training of a CNN takes less than 30 sec. s with a GPU (graphics processing unit). The prediction takes less than 1 sec. on a standard PC. ConclusionsThe study suggests that an axial MRI scan can be used to diagnose if a patient has Alzheimer's Disease with an AUC score of 0.92.

Brain metastases from NSCLC treated with stereotactic radiotherapy: prediction mismatch between two different radiomic platforms

Background and purposeRadiomics enables the mining of quantitative features from medical images. The influence of the radiomic feature extraction software on the final performance of models is still a poorly understood topic. This study aimed to investigate the ability of radiomic features extracted by two different radiomic platforms to predict clinical outcomes in patients treated with radiosurgery for brain metastases from non-small cell lung cancer. We developed models integrating pre-treatment magnetic resonance imaging (MRI)-derived radiomic features and clinical data. Materials and methodsPre-radiotherapy gadolinium enhanced axial T1-weighted MRI scans were used. MRI images were re-sampled, intensity-shifted, and histogram-matched before radiomic extraction by means of two different platforms (PyRadiomics and SOPHiA Radiomics). We adopted LASSO Cox regression models for multivariable analyses by creating radiomic, clinical, and combined models using three survival clinical endpoints (local control, distant progression, and overall survival). The statistical analysis was repeated 50 times with different random seeds and the median concordance index was used as performance metric of the models. ResultsWe analysed 276 metastases from 148 patients. The use of the two platforms resulted in differences in both the quality and the number of extractable features. That led to mismatches in terms of end-to-end performance, statistical significance of radiomic scores, and clinical covariates found significant in combined models. ConclusionThis study shed new light on how extracting radiomic features from the same images using two different platforms could yield several discrepancies. That may lead to acute consequences on drawing conclusions, comparing results across the literature, and translating radiomics into clinical practice.

Spontaneous Thoracic Spinal Epidural Hematoma During Pregnancy

Spontaneous Thoracic Spinal Epidural Hematoma During Pregnancy

Deep learning models for triaging hospital head MRI examinations.

The growing demand for head magnetic resonance imaging (MRI) examinations, along with a global shortage of radiologists, has led to an increase in the time taken to report head MRI scans in recent years. For many neurological conditions, this delay can result in poorer patient outcomes and inflated healthcare costs. Potentially, computer vision models could help reduce reporting times for abnormal examinations by flagging abnormalities at the time of imaging, allowing radiology departments to prioritise limited resources into reporting these scans first. To date, however, the difficulty of obtaining large, clinically-representative labelled datasets has been a bottleneck to model development. In this work, we present a deep learning framework, based on convolutional neural networks, for detecting clinically-relevant abnormalities in minimally processed, hospital-grade axial T2-weighted and axial diffusion-weighted head MRI scans. The models were trained at scale using a Transformer-based neuroradiology report classifier to generate a labelled dataset of 70,206 examinations from two large UK hospital networks, and demonstrate fast (< 5s), accurate (area under the receiver operating characteristic curve (AUC) > 0.9), and interpretable classification, with good generalisability between hospitals (ΔAUC ≤ 0.02). Through a simulation study we show that our best model would reduce the mean reporting time for abnormal examinations from 28 days to 14 days and from 9 days to 5 days at the two hospital networks, demonstrating feasibility for use in a clinical triage environment.

Morphology of the acromioclavicular-joint score (MAC)

IntroductionTo date there is no generally accepted specific definition or classification of acromioclavicular (AC) joint osteoarthritis. The aim of this study is to analyze morphological parameters using magnetic resonance imaging (MRI) and to develop a scoring system as a basis for decision making to perform an AC-joint resection.Materials and methodsIn a retrospective-monocentric matched pair study, healthy and affected subjects were investigated using T2 MRI scans in the transverse plane. There were two groups, group 1 (n = 151) included healthy asymptomatic adults with no history of trauma. In group 2, we included n = 99 patients with symptomatic AC joints, who underwent arthroscopic AC-joint resection. The central and posterior joint space width and the AC angle were measured. Morphological changes such as cartilage degeneration, cysts and bone edema were noted. Malalignment of the joint was defined as: posterior joint space width < 2 mm in conjunction with an AC angle > 12°. A scoring system consisting of the measured morphologic factors was developed.ResultsSymptomatic and asymptomatic patients showed significant differences in all measured items. We observed a significant difference in the MAC score for symptomatic and asymptomatic patients (mean 10.4 vs. 20.6, p = 0.0001). The ROC (receiver operator characteristic) analysis showed an excellent AUC of 0.899 (p = 0.001). The sensitivity of the MAC score was 0.81 and the specificity 0.86. The MAC score shows a significant moderate correlation with age (r = 0.358; p = 0.001). The correlation of age and the development of symptoms was only weak (r = 0.22, p = 0.001). Symptomatic patients showed significantly more frequent malalignment compared to asymptomatic patients (p = 0.001), but the positive predictive value that a patient with malalignment is also symptomatic is only 55%.ConclusionPatients with symptomatic AC joints showed a typical pattern of morphological changes on axial MRI scans with early posterior contact of the joint surfaces, reduction of joint space and malalignment as the basis for the development of a scoring system. The MAC score shows excellent test characteristics, and therefore, proved to be both an appropriate guidance for clinical practice as well as an excellent tool for comparative studies and is superior to the assessment of malalignment alone.Level of evidenceLevel IV, retrospective diagnostic study.

The prevalence of posterior inferior tibiofibular ligament and inferior tibiofibular transverse ligament injuries in syndesmosis-injured ankles evaluated by oblique axial magnetic resonance imaging: a retrospective study

BackgroundTransverse ligament and posterior inferior tibiofibular ligament injuries have not been investigated till date because these are difficult to evaluate using standard magnetic resonance imaging. This study aimed to investigate the prevalence of transverse ligament and posterior inferior tibiofibular ligament injuries in syndesmosis-injured ankles using oblique axial magnetic resonance imaging.MethodsThe patients who were diagnosed with syndesmosis injury using magnetic resonance imaging (MRI) within 7 days of the trauma were included. Patients with concomitant fractures were excluded. A total of 34 patients (1 woman and 33 men) with an average age of 22 years (range, 14–64 years) were included. The anterior inferior tibiofibular, interosseous, transverse, and posterior inferior tibiofibular ligaments were classified as intact, partial tear, or complete tear using usual axial and oblique axial MRIs.ResultsThere were 8 (23.5%) ankles with an intact, 21 (61.8%) ankles with a partially torn, and 5 (14.7%) ankles with a complete tear of transverse ligament. There were 20 (58.8%) ankles with an intact, 12 (35.3%) ankles with a partially torn, and 2 (5.9%) ankles with a complete tear of posterior inferior tibiofibular ligament. Overall, 50% of the transverse ligament injuries occurred without posterior inferior tibiofibular ligament involvement.ConclusionsThe oblique axial magnetic resonance imaging scan revealed that the prevalence of transverse ligament and posterior inferior tibiofibular ligament injuries in syndesmosis-injured ankles were 76.5 and 41.2%, respectively.

Anterior Thigh Pain Following Minimally Invasive Oblique Lateral Interbody Fusion: Multivariate Analysis from a Prospective Case Series.

BackgroundOblique lateral interbody fusion (OLIF) involves the antepsoas approach and psoas major muscle (PMM) retraction to insert the interbody cage orthogonally. Therefore, OLIF is often associated with postoperative anterior thigh pain (ATP) on the approach side. However, there is limited evidence on the nature and risk factors of ATP following OLIF.MethodsConsecutive patients who planned to undergo minimally invasive OLIF and percutaneous pedicle screw instrumentation for lumbar degenerative diseases were prospectively enrolled. The visual analog scale (VAS) for ATP was recorded, and a pain map was drawn daily from the operation day to postoperative day 7 in all patients. We also prospectively collected the preoperative and intraoperative data to identify the risk factors associated with ATP. Radiologically, the total cross-sectional area (CSA), retraction length, and retraction CSA of PMM were measured from the preoperative T2-weighted axial magnetic resonance imaging scans at the L4–5 intervertebral disc level. The patients were stratified into two groups based on the experience of ATP with a VAS score of ≥ 7 at any time point. Additionally, a binary logistic regression analysis was performed to identify the associated factors.ResultsThe current prospective study included 92 patients (31 men, 61 women) with a mean age of 70.4 years (range, 56–86 years), who underwent OLIF at our institution. The left-side approach was used in 73 patients (79.3%), while 19 (20.7%) underwent a right-side approach. Sixty-five of the total patients (70.6%) experienced approach-side ATP to any extent during postoperative 0–7 days following OLIF. The mean pain VAS (4.4 ± 2.1) and the prevalence (57.6%) were highest at postoperative 2 days. On postoperative day 7, there were 19 patients (20.7%) who complained of residual ATP with a mean VAS of 2.6 ± 1.8. In the multivariate analysis, the PMM retraction length was significantly associated with ATP of VAS ≥ 7 (adjusted odds ratio, 2.316; p = 0.044).ConclusionsIn this study, we prospectively collected and analyzed the ATP and associated factors following OLIF and identified the PMM retraction length as a potential independent risk factor for severe ATP in the immediate postoperative period following OLIF. Keywords: Anterior thigh pain, Psoas major muscle, Antepsoas, Oblique lateral interbody fusion, Genitofemoral nerve

Improving radiologists’ and orthopedists’ QoE in diagnosing lumbar disk herniation using 3D modeling

&lt;p&gt;This article studies and analyzes the use of 3D models, built from magnetic resonance imaging (MRI) axial scans of the lumbar intervertebral disk, that are needed for the diagnosis of disk herniation. We study the possibility of assisting radiologists and orthopedists and increasing their quality of experience (QoE) during the diagnosis process. The main aim is to build a 3D model for the desired area of interest and ask the specialists to consider the 3D models in the diagnosis process instead of considering multiple axial MRI scans. We further propose an automated framework to diagnose the lumber disk herniation using the constructed 3D models. We evaluate the effectiveness of increasing the specialists QoE by conducting a questionnaire on 14 specialists with different experiences ranging from residents to consultants. We then evaluate the effectiveness of the automated diagnosis framework by training it with a set of 83 cases and then testing it on an unseen test set. The results show that the the use of 3D models increases doctors QoE and the automated framework gets 90% of diagnosis accuracy.&lt;/p&gt;

MRI contributes to accurate and early diagnosis of non-radiographic HLA-B27 negative axial spondyloarthritis

BackgroundNonradiographic axial spondyloarthropathies (nr-axSpA) are diagnosed by the absence of radiographic sacroiliitis and the presence of bone marrow edema (BME) on magnetic resonance imaging (MRI). According to the classification criteria of the international Assessment of Spondyloarthritis Society (ASAS), structural changes to sacroiliac joints (SIJs) on MRI cannot be used as criteria in the absence of BME. However, less than half the Asian patients with clinically active axSpA show BME. The incidence of human leukocyte antigen (HLA)-B27 is low in Asian populations, which makes it more difficult to identify nr-axSpA. We used MRI to evaluate the structural damage to SIJs in patients with nr-axSpA with and without BME with the aim of identifying the best methodology for accurate diagnosis, especially in populations with less common BME and HLA-B27.MethodsOne hundred three patients with inflammatory back pain were included in this prospective study. No patient’s radiograph met the definition of positive modified New York criteria. BME and structural damage to SIJ including sclerosis and erosion were assessed independently on coronal and axial short-tau inversion recovery and T1-weighted spin echo MRI scans by two well-trained musculoskeletal radiologists using the Spondyloarthritis Research Consortium of Canada (SPARCC) score. Demographics of patients were collected. Disease characteristics and structural damage were analyzed in patients with and without BME on SIJ MRI. Receiver operating characteristic (ROC) curve analysis was used to assess the diagnostic performance of structural damage.ResultsAll individuals in the cohort had at least one abnormal finding on SIJ MRI, including BME or structural damage; 36 of 103 patients had BME. We identified a significant positive correlation between SPARCC scores and severe erosion assessed by focal joint space widening (fJSW) (p = 0.001) in these 36 patients. Fifty-eight of the 103 enrolled patients fulfilled the ASAS criteria for nr-axSpA in the either absence or presence of BME. Of these 58 patients, 57 and 19 had erosions or fJSW, respectively, and the presence of BME was significantly correlated with fJSW (phi score of 0.319 and p = 0.015). We demonstrated a significant positive correlation between fJSW and either the presence or the severity of BME in patients with nr-axSpA who met the ASAS definition. There was a positive correlation between BME and fJSW across the whole study cohort (phi score of 0.389; p < 0.001). The area under the ROC curve (AUC) for fJSW on SIJ MRI was 0.736, p < 0.001. In both HLA-B27-positive and -negative groups, BME was more common in the presence of fJSW (phi scores of 0.370 and 0.377, p = 0.018 and 0.003, respectively) and SPARCC scores were higher in patients with fJSW (p < 0.001 and p = 0.005). We also identified a positive correlation between fJSW and BME in patients with nr-axSpA and normal serum levels of C-reactive protein (phi score of 0.362 and p = 0.001).ConclusionStructural damage detected on SIJ MRI, sclerosis, erosions and fJSW may be present in patients without detectable inflammation on SIJ MRI. However, fJSW is significantly correlated with the severity of inflammation seen on SIJ MRI, which contributes to the accurate diagnosis of nr-axSpA, and it could be used as an alternative diagnostic test for nr-axSpA in the general population, especially for those who do not carry the HLA-B27 gene, Asian patients without BME, or patients with normal serum inflammatory biomarkers.

Decompression of Lumbar Central Spinal Canal Stenosis Following Minimally Invasive Transforaminal Lumbar Interbody Fusion.

This was a retrospective clinical series. The objective of this study was to evaluate radiologic changes in central spinal canal dimensions following minimally invasive transforaminal lumbar interbody fusion (MIS-TLIF) with placement of a static or an expandable interbody device. MIS-TLIF is used to treat lumbar degenerative diseases and low-grade spondylolisthesis. MIS-TLIF enables direct and indirect decompression of lumbar spinal stenosis, with patients experiencing relief from radiculopathy and neurogenic claudication. However, the effects of MIS-TLIF on the central spinal canal are not well-characterized. We identified patients who underwent MIS-TLIF for degenerative lumbar spondylolisthesis and concurrent moderate to severe spinal stenosis. We selected patients who had both preoperative and postoperative magnetic resonance imaging (MRI) and upright lateral radiographs of the lumbar spine. Measurements on axial T2-weighted MRI scans include anteroposterior and transverse dimensions of the dural sac and osseous spinal canal. Measurements on radiographs include disk height, neural foraminal height, segmental lordosis, and spondylolisthesis. We made pairwise comparisons between each of the central canal dimensions and lumbar sagittal segmental radiologic outcome measures relative to their corresponding preoperative values. Correlation coefficients were used to quantify the association between changes in lumbar sagittal segmental parameters relative to changes in radiologic outcomes of central canal dimensions. Statistical analysis was performed for "all patients" and further stratified by interbody device subgroups (static and expandable). Fifty-one patients (age 60.4 y, 68.6% female) who underwent MIS-TLIF at 55 levels (65.5% at L4-L5) were included in the analysis. Expandable interbody devices were used in 45/55 (81.8%) levels. Mean duration from surgery to postoperative MRI scan was 16.5 months (SD 11.9). MIS-TLIF was associated with significant improvements in dural sac dimensions (anteroposterior +0.31 cm, transverse +0.38 cm) and osseous spinal canal dimensions (anteroposterior +0.16 cm, transverse +0.32 cm). Sagittal lumbar segmental parameters of disk height (+0.56 cm), neural foraminal height (+0.35 cm), segmental lordosis (+4.26 degrees), and spondylolisthesis (-7.5%) were also improved following MIS-TLIF. We did not find meaningful associations between the changes in central canal dimensions relative to the corresponding changes in any of the sagittal lumbar segmental parameters. Stratified analysis by interbody device type (static and expandable) revealed similar within-group changes as in the overall cohort and minimal between-group differences. MIS-TLIF is associated with radiologic decompression of neural foraminal and central spinal canal stenosis. The mechanism for neural foraminal and central canal decompression is likely driven by a combination of direct and indirect corrective techniques.

Deep Learning Improves Speed and Accuracy of Prostate Gland Segmentations on Magnetic Resonance Imaging for Targeted Biopsy.

Purpose:Targeted biopsy improves prostate cancer diagnosis. Accurate prostate segmentation on magnetic resonance imaging (MRI) is critical for accurate biopsy. Manual gland segmentation is tedious and time-consuming. We sought to develop a deep learning model to rapidly and accurately segment the prostate on MRI and to implement it as part of routine magnetic resonance-ultrasound fusion biopsy in the clinic.Materials and Methods:A total of 905 subjects underwent multiparametric MRI at 29 institutions, followed by magnetic resonance-ultrasound fusion biopsy at 1 institution. A urologic oncology expert segmented the prostate on axial T2-weighted MRI scans. We trained a deep learning model, ProGNet, on 805 cases. We retrospectively tested ProGNet on 100 independent internal and 56 external cases. We prospectively implemented ProGNet as part of the fusion biopsy procedure for 11 patients. We compared ProGNet performance to 2 deep learning networks (U-Net and holistically-nested edge detector) and radiology technicians. The Dice similarity coefficient (DSC) was used to measure overlap with expert segmentations. DSCs were compared using paired t-tests.Results:ProGNet (DSC=0.92) outperformed U-Net (DSC=0.85, p <0.0001), holistically-nested edge detector (DSC=0.80, p <0.0001), and radiology technicians (DSC=0.89, p <0.0001) in the retrospective internal test set. In the prospective cohort, ProGNet (DSC=0.93) outperformed radiology technicians (DSC=0.90, p <0.0001). ProGNet took just 35 seconds per case (vs 10 minutes for radiology technicians) to yield a clinically utilizable segmentation file.Conclusions:This is the first study to employ a deep learning model for prostate gland segmentation for targeted biopsy in routine urological clinical practice, while reporting results and releasing the code online. Prospective and retrospective evaluations revealed increased speed and accuracy.

Predicting Autologous Hamstring Graft Diameter in the Pediatric Population Using Preoperative Magnetic Resonance Imaging and Demographic Data

Background: Anterior cruciate ligament (ACL) reconstruction before 18 years of age has been linked with an increased risk for failure when the graft diameter is <8 mm. Purpose/Hypothesis: The purpose of this study was to determine whether autologous hamstring graft size can be reliably predicted with the use of preoperative magnetic resonance imaging (MRI) measurements. We hypothesized that the average of multiple axial cross-sectional area MRI measurements for the semitendinosus tendon and gracilis tendon would alone accurately predict graft diameter. Additionally, factoring in specific demographic data to the MRI cross-sectional areas would provide a synergistic effect to the accuracy of graft diameter predictions. Study Design: Cohort study (diagnosis); Level of evidence, 2. Methods: We retrospectively reviewed 51 pediatric patients undergoing ACL reconstructions (age <18 years) performed using either a quadruple-strand semitendinosus tendon or combined double-bundle semitendinosus tendon–gracilis tendon autograft. Preoperative axial MRI scans at multiple points along the craniocaudal axis—specifically, at the level of the joint line, 3 cm cephalad to the medial tibial plateau, and 5 cm cephalad to the medial tibial plateau—were used to determine the combined cross-sectional area of the semitendinosus and gracilis tendons. The MRI measurements were analyzed using Pearson correlation as well as regression analysis to evaluate strength of correlation between measurements. Binomial linear regression was used to analyze the same predictive variables assessed by multiple regression. Results: The predicted graft diameter was within 0.5 mm of the intraoperative graft size in 37 of 51 (72.5%) patients and within 1 mm of the intraoperative graft size in 49 of 51 (96.1%). With the addition of demographics, the accuracy of predictions increased to 78.4% within 0.5 mm and 98% within 1 mm of the actual graft size. Additionally, 38 of 42 patients whose true graft diameter was ≥8 mm were correctly classified, giving a sensitivity of 90.4%. For those whose true graft diameter was <8 mm, 8 of 9 patients were correctly classified; therefore, the specificity was 88.9%. Conclusion: The results of our study suggest that taking the average of multiple preoperative MRI measurements can be used to accurately predict autologous hamstring graft size when approaching pediatric patients undergoing ACL reconstruction.

Less than 9.5-mm coracohumeral distance on axial magnetic resonance imaging scans predicts for subscapularis tear

BackgroundDiagnosis of subscapularis (SSC) tendon lesions on magnetic resonance imaging (MRI) can be challenging. A small coracohumeral distance (CHD) has been associated with SSC tears. This study was designed to define a specific threshold value for CHD to predict SSC tears on axial MRI scans.MethodsThis retrospective study included 172 shoulders of 168 patients who underwent arthroscopic surgery for rotator cuff tear or glenohumeral instability. Diagnostic arthroscopy confirmed an SSC tear in 62 cases (36.0%, test group a), rotator cuff tear tears other than SSC in 71 cases (41.3%, control group b) and glenohumeral instability without any rotator cuff tear in 39 cases (22.7%, zero-sample group c). All patients had a preoperative MRI of the shoulder (1.5T or 3T). Minimum CHD was measured on axial fat-suppressed proton density-, T2-, or T1-weigthed sequences. Receiver operating characteristics analysis was used to determine the threshold value for CHD, and sensitivity and specificity were calculated.ResultsCHD measurement had a good interobserver reliability (Intraclass correlation coefficient 0.799). Mean CHD was highly significantly (P < .001) less for test group a (mean 7.3 mm, standard deviation ± 2.2) compared with control group b (mean 11.1 mm, standard deviation ± 2.3) or zero-sample group c (mean 13.6 mm, standard deviation ± 2.9). A threshold value of CHD <9.5 mm had a sensitivity of 83.6% and a specificity of 83.9% to predict SSC tears.ConclusionA CHD <9.5 mm on MRI is predictive of SSC lesions and a valuable tool to diagnose SSC tears.

Relationship of Patellofemoral Angles and Tibiofemoral Rotational Angles With Jumper's Knee in Professional Dancers: An MRI Analysis.

Background:Jumper’s knee is a type of tendinopathy affecting the distal insertion of the quadriceps tendon (25% of cases) or the patellar tendon. It has been shown that frontal-plane measurements, such as genu valgum, genu varum, an increased quadriceps angle, a protuberant tibial tuberosity, patella alta, and short hamstring muscles, may be related to jumper’s knee.Purpose:To investigate the effects of tibiofemoral rotational angles and patellofemoral (PF) angles on the development of jumper’s knee in professional folk dancers.Study Design:Case-control study; Level of evidence, 3.Methods:We examined 26 dancers (16 male, 10 female) with knee pain using magnetic resonance imaging (MRI), for a total of 32 knees. Of the knees, 21 with quadriceps tendinopathy (QT) and 7 with patellar tendinopathy (PT) were detected. Using MRI scans, we measured PF angles (PF sulcus angle, lateral PF angle, patellar tilt angle, lateral trochlear inclination angle, lateral patellar tilt angle, and PF congruence angle) and tibiofemoral rotational angles (condylar twist angle, posterior condylar angle, femoral Insall angle, tibial Insall angle, posterior tibiofemoral angle, and angle between the Whiteside line and posterior femoral condylar line) and noted specifics such as patella alta, patella baja, and the Wiberg classification of the patellar shape between the patients with versus without QT and between patients with versus without PT to understand if there was any relationship with tendinopathy.Results:No statistically significant difference was observed in age, sex, patella alta, or the Wiberg classification between the QT groups (with vs without) and between the PT groups (with vs without) (P > .05). Having QT was found to be significantly associated with the PF sulcus angle (P = .009), and having PT was found to be significantly associated with the femoral Insall angle (P = .029).Conclusion:Jumper’s knee was found to be associated with anatomic variations of the PF sulcus angle and rotation of the patellar tendon in relation to the femur (femoral Insall angle) on axial MRI scans in professional dancers. Unlike those of other athletes, dancers’ knees are exposed more to external rotation forces because of turnout, and this can be the cause of jumper’s knee.

Relationship Between Patellar Morphology and Known Anatomic Risk Factors for Patellofemoral Instability.

Background:Patellar instability (PI) is a common problem among pediatric, adolescent, and young adult patients. Recent literature has shown a correlation between pathoanatomy and PI.Purpose/Hypothesis:The purpose of this study was to determine if there is any difference in patellar shape in patients with and without PI and if there is any association between the shape of the patella and the shape of the trochlea. Our hypothesis was that there would be no association between the shape of the patella and the likelinhood of having PI and that the shape of the trochlea would not be associated with patellar morphology.Study Design:Cross-sectional study; Level of evidence, 3.Methods:Magnetic resonance imaging (MRI) scans were analyzed for 97 study patients with PI and 100 control patients with anterior cruciate ligament tears. Radiologic measurements of trochlear morphology were collected via MRI; 15 measurements of patellar morphology were then measured using axial MRI scans. Comparisons between the control and PI groups were performed using a 2-tailed t test. Regression analysis was performed to determine if associations existed between the 15 patellar morphology measurements and the trochlear dysplasia measurements.Results:There were no statistically significant differences between the PI and control groups for the majority of patellar morphology measurements. With regression analysis, there were no statistically significant associations between the majority of patellar morphology measurements and the trochlear dysplasia measurements.Conclusion:Patellar morphology is highly variable in knees with and without PI. There was a minimal association between measurements of patellar morphology and trochlear dysplasia.

Flexor hallucis longus hypertrophy secondary to Achilles tendon tendinopathy: an MRI-based case\u2013control study

PurposeThe purpose of this study was to outline an indirect sign of advanced Achilles tendinopathy on magnetic resonance imaging (MRI), based on the hypothesis that these patients would present with secondary hypertrophy of the flexor hallucis longus muscle (FHL).MethodsMRI scans of Achilles tendon were analyzed retrospectively in two cohorts. The study group consisted of consecutive patients presenting with clinical signs of Achilles tendinopathy and no previous surgeries, while the control group were patients that had an MRI due to other reasons and no signs of tendinopathy. Two parameters from two muscle bellies were measured and compared on axial MRI scans 4–5 cm above the ankle joint line at the level of greatest thickness: area and diameter of the triceps surae (TS) and of the FHL muscle. Ratios (FHL/TS) were calculated for area (Ar) and diameter (Dm) measurements. Interobserver agreement was analyzed. A receiver operating characteristic (ROC) curve was created for both ratios to assess potential cutoff points to differentiate between the groups.ResultsA total of 60 patients for each study group were included. Both ratios Ar(FHL/TS) and Dm(FHL/TS) showed significant higher values in the tendinopathy group (p < 0.001). There were strong to very strong intraclass correlation coefficients (ICC = 0.75–0.93). A diameter ratio Dm (FHL/TS) of 2.0 or higher had a sensitivity of 49% and specificity of 90% for concomitant Achilles tendinopathy.ConclusionIn our patient cohort, FHL hypertrophy was observed in patients with Achilles tendinopathy as a possible compensatory mechanism. Measuring a diameter ratio Dm(FHL/TS) of 2.0 or higher on an axial MRI, may be indicative as an indirect sign of functional deterioration of the Achilles tendon.