MRI In Diagnosis Research Articles

Factors limiting Magnetic Resonance Imaging (MRI) diagnosis of Placenta Accreta Spectrum (PAS)

PAS disorders are characterized by an abnormal adherence of the placenta to the uterine myometrium. Ultrasonography (US) is the primary antenatal diagnostic tool to evaluate this interface. MRI is an important adjunct, particularly when US is inconclusive or when there is a high index of suspicion for PAS, however, its diagnostic accuracy varies greatly. This study aims to determine if there are factors that limit MRI diagnosis of PAS.

Analysis of high-resolution reconstruction of medical images based on deep convolutional neural networks in lung cancer diagnostics

Background and objectiveTo study the diagnostic effect of 64-slice spiral CT and MRI high-resolution images based on deep convolutional neural networks(CNN) in lung cancer. MethodsIn this paper, we Select 74 patients with highly suspected lung cancer who were treated in our hospital from January 2017 to January 2021 as the research objects. The enhanced 64-slice spiral CT and MRI were used to detect and diagnose respectively, and the images and accuracy of CT diagnosis and MRI diagnosis were retrospectively analyzed. ResultsThe accuracy of CT diagnosis is 94.6% (70/74), and the accuracy of MRI diagnosis is 89.2% (66/74). CT examination has the advantages of non-invasive, convenient operation and fast examination. MRI is showing there are advantages in the relationship between the chest wall and the mediastinum, and the relationship between the lesion and the large blood vessels. ConclusionEnhanced CT and MRI examinations based on convolutional neural networks(CNN) to improve image clarity have high application value in the diagnosis of lung cancer patients, but the focus of performance is different.

High-field MRI using standard pulse sequences has moderate to substantial interobserver agreement and good accuracy for differentiation between intracranial extra-axial histiocytic sarcoma and meningioma in dogs.

Intracranial extra-axial histiocytic sarcoma shares common MRI features with meningioma. As histiocytic sarcoma carries a generally worse prognosis than meningioma, the ability to differentiate between these two neoplasms is of clinical value. The aim of this retrospective diagnostic accuracy and observer agreement study was to evaluate the accuracy and reliability of high-field MRI to differentiate between these two tumors, using standard pulse sequences and published MRI features. A total of 51 dogs were included (26 meningiomas and 25 histiocytic sarcomas). Magnetic resonance imaging examinations were independently assessed by three experienced board-certified radiologists, evaluating 18 imaging features. They were asked to assign each case to one of three categories (meningioma, histiocytic sarcoma, and undetermined). Agreement for the MRI diagnosis across all three reviewers was moderate (κ 0.54) while paired interobserver agreement ranged from moderate to substantial (κ 0.58-0.74) with percent agreement ranging between 86.1% and 87.7%. Overall, the probability of correctly diagnosing meningioma in a dog with this tumor ranged between 79.2% and 94.4%, and the probability of correctly diagnosing histiocytic sarcoma in a dog with this tumor ranged between 76.0% and 92.3%. The overall probability to diagnose the correct tumor, irrespective of type, ranged between 79.2% and 89.7%. Histiocytic sarcomas tended to have more extensive edema and more often had combined perilesional and distant meningeal enhancement affecting both pachy- and leptomeninges, while for meningiomas, meningeal enhancement tended to more commonly be perilesional and pachymeningeal. Imaging features that seemed more useful to make a correct diagnosis included "location/type of meningeal enhancement," "osseous changes in the adjacent neurocranium," "cystic changes," and "herniation severity."

LINC01087 indicates a poor prognosis of glioma patients with preoperative MRI

Long intergenic non-coding RNA 01,087 (LINC01087) has been concerned as an oncogene in breast cancer, while its mechanism in glioma has been little surveyed. Thus, we searched the prognostic value and functional action of LINC01087 in glioma. Glioma patients after preoperative MRI diagnosis were enrolled, and LINC01087, microRNA (miR)-1277-5p, and alkaline ceramidase 3 (ACER3) levels were tested in glioma cancer tissue. The correlation between LINC01087 expression and the survival of patients were analyzed. LINC01087, miR-1277-5p, and ACER3 levels in U251 cells were altered via transfection, and cell malignant phenotypes were monitored. The relationship between miR-1277-5p and LINC01087 or ACER3 was detected. The LINC01087 and ACER3 expression was in up-regulation and the miR-1277-5p expression was in down-regulation in clinical glioma samples. High expression of LINC01087 was associated with poor prognosis of glioma patients with preoperative MRI. LINC01087 silencing restrained tumor malignancy in glioma cells. Mechanistically, LINC01087 directly interacted with miR-1277-5p. ACER3 was a known target of miR-1277-5p. Moreover, rescue assays reveal that miR-1277-5p overexpression (or ACER3 overexpression) reversed the effects of LINC01087 upregulation (or miR-1277-5p upregulation) on glioma cells. LINC01087 has prognostic significance in glioma and silencing LINC01087 deters glioma development through elevating miR-1277-5p to reduce ACER3 expression.

Establishment of a multi-parameters MRI model for predicting small lymph nodes metastases (

PurposeTo evaluate the potential role of MR findings and DWI parameters in predicting small regional lymph nodes metastases (with short-axis diameter < 10 mm) in pancreatic ductal adenocarcinomas (PDACs).MethodsA total of 127 patients, 82 in training group and 45 in testing group, with histopathologically diagnosed PDACs who underwent pancreatectomy were retrospectively analyzed. PDACs were divided into two groups of positive and negative lymph node metastases (LNM) based on the pathological results. Pancreatic cancer characteristics, short axis of largest lymph node, and DWI parameters of PDACs were evaluated.ResultsUnivariate and multivariate analyses showed that extrapancreatic distance of tumor invasion, short-axis diameter of the largest lymph node, and mean diffusivity of tumor were independently associated with small LNM in patients with PDACs. The combining MRI diagnostic model yielded AUCs of 0.836 and 0.873, and accuracies of 81.7% and 80% in the training and testing groups. The AUC of the MRI model for predicting LNM was higher than that of subjective MRI diagnosis in the training group (rater 1, P = 0.01; rater 2, 0.008) and in a testing group (rater 1, P = 0.036; rater 2, 0.024). Comparing the subjective diagnosis, the error rate of the MRI model was decreased. The defined LNM-positive group by the MRI model showed significantly inferior overall survival compared to the negative group (P = 0.006).ConclusionsThe MRI model showed excellent performance for individualized and noninvasive prediction of small regional LNM in PDACs. It may be used to identify PDACs with small LNM and contribute to determining an appropriate treatment strategy for PDACs.

Monte Carlo Algorithm-Based Multimodal Magnetic Resonance Imaging Prognosis Prediction in Analysis of Rehabilitation Effect of Exercise Learning on Stroke Patients and Influencing Factors of Memory Function

Based on Monte Carlo algorithm and multimodal MRI diagnosis, the effect of motor learning on motor memory function recovery in stroke patients was investigated in this research. A total of 26 stroke patients with hemiplegia treated in hospital in the past three years were recruited. Patients were rolled into routine group (13 cases) and experimental group (13 cases) according to different follow-up rehabilitation methods. All patients were treated with intravenous thrombolysis. After treatment, the conventional group received conventional rehabilitation therapy and the experimental group received restraint induced exercise therapy (CIMT). Then, T1-weighted imaging, T2-weighted imaging, 3D anatomical imaging, and resting state examinations were performed on the patients before and after treatment. All image data and image processing were performed by the Monte Carlo algorithm. Before treatment and six weeks after rehabilitation treatment, the patients’ mental state and memory function were tested using Addenbrooke’s Cognitive Examination (ACE-III) and Montreal Cognitive Assessment (MoCA). In addition, the Fugl-Meyer motor assessment, the simple test for evaluating hand function, and the modified Barthel index were used to evaluate the patient’s ability of daily living. After processing, the quality of multimode MRI image was improved obviously, and the lesion was more prominent. The fractional amplitude of low frequency fluctuation of supplement motor area in stroke patients increased after treatment combined with exercise rehabilitation ( P &lt; 0.05 ) and ReHo decreased compared with that before treatment. The connection function of the left and right hippocampus was enhanced. The difference in ACE-III (experimental group: 16 versus 21; control group: 17.1 versus 19) scores between the two groups after treatment and before treatment was remarkable ( P &lt; 0.05 ), but the score of patients in experimental group improved better. The MoCA (experimental group: 24.38 versus 26.47; control group: 23.13 versus 23.37) scores of the two groups of patients changed greatly from those before treatment ( P &lt; 0.05 ), and the MoCA score ratio between the two groups was also statistically different (26.47 versus 23.37; P &lt; 0.05 ). There was a statistical difference in the living ability of the two groups of patients before and after treatment ( P &lt; 0.05 ). The Monte Carlo algorithm had a good processing effect on multimodal MRI images. The recovery of the experimental group was evidently better, and the difference between the two groups was substantial ( P &lt; 0.05 ). CIMT had a good effect on the recovery of exercise rehabilitation and memory function of patients with ischemic stroke.

Abstract 9828: Active Surveillance of Cardiotoxicity with Cardiac Biomarkers During Chimeric Antigen Receptor T-Cell Therapy

Introduction: Chimeric Antigen receptor T- Cell (CAR-T) immunotherapy has been a breakthrough for various hematological malignancies. Cardiotoxicites such as heart failure, arrhythmia and acute coronary syndrome occur in approximately 1/3 of patients who develop cytokine release syndrome (CRS) following CAR-T. High grade CRS (Grade ≥ 2) and elevated troponin level are associated with increased risk of cardiotoxicity. It is unclear whether active cardiotoxicity surveillance with serial cardiac biomarker measurements during CAR-T would allow early detection of cardiotoxicity. Methods: This was retrospective cohort study involving patients diagnosed with non-Hodgkin lymphoma treated with CAR-T therapy (Axicabtagene ciloleucel- Yescarta, tisagenlecleucel- Kymriah, Brexucabtagene autoleucel- Tecartus). Baseline cardiac workup with electrocardiogram (ECG), transthoracic echocardiogram (TTE), troponin (Reference &lt;0.03ng/mL), B-natriuretic peptide (BNP, &lt;100pg/mL) were uniformly performed in all participants. Follow up ECG, Troponin and BNP were obtained at day 5 after CAR-T and at development of CRS Grade ≥2. When clinically indicated, cardiac MRI with gadolinium contrast was performed. Cardiac MRI diagnosis of myocarditis was based on Lake Louise Criteria. Results: A total of 47patients undergoing CAR-T therapy were studied. Baseline comorbidities were not predictive of CRS or cardiac events. There were 39 patients with low grade CRS (82.9%) and 8 patients (17.0%) with grade 2 CRS. Five patients had elevated troponin I levels (Grade 1 CRS - 3; Grade 2 CRS - 2). Cardiac MRIs were performed in three patients (two normal studies, one with mild myocarditis). Five patients (10.6%) had an adverse cardiac event (Myocarditis with heart failure - 1; new-onset atrial fibrillation - 3; Type 2 myocardial infarction -1). Conclusion: Adverse cardiac events are a relatively common occurrence in patients receiving CART therapy. Active surveillance for cardiotoxicity using cardiac biomarkers in CAR-T patients may play an adjunctive role in the early identification of adverse cardiac events. Larger studies are needed to adjudicate the use of such screening measures in these high-risk patients.

CT and MRI Imaging Features and Diagnosis of Gallbladder Neuroendocrine Tumors

CT and MRI Imaging Features and Diagnosis of Gallbladder Neuroendocrine Tumors

CT and MRI Diagnosis of Invasive Fibromatosis of Abdomen

CT and MRI Diagnosis of Invasive Fibromatosis of Abdomen

MRI diagnosis of spontaneous intraventricular tension-pneumocephalus in a 10-month-old male Saarloos Wolfdog.

A 10-month-old male Saarloos Wolfdog was presented with a history of multiple neurologic deficits that had acutely progressed. Neurologic examination findings localized signs to the cerebrum and brainstem. Magnetic resonance imaging revealed markedly enlarged and gas-filled lateral ventricles with a mass effect leading to cerebellar herniation. A right-sided defect of the cribriform plate with a dysplastic ethmoturbinate was identified as the inlet of air and origin of the intraventricular tension pneumocephalus. Surgical findings were consistent with a ruptured, congenital, nasal meningocele.

Features of various posterior cranial fossa tumors on Magnetic Resonance Imaging and their correlation with histopathological diagnosis

Purpose: To evaluate the features of various posterior cranial fossa tumors on Magnetic Resonance Imaging and correlate the MR diagnosis with histopathological diagnosis.&#x0D; Methodology: The MRI evaluation of patients clinically presenting with nonspecific symptoms of raised intracranial pressure was done. The MR imaging protocol included: T1W, T2W, FLAIR and post Gd T1W FS. The MRI diagnosis was correlated with histopathological diagnosis. Descriptive statistical analysis was carried out in the present study.&#x0D; Findings: Histopathological confirmation was obtained in 38 of 46 cases. The eight patients in whom histopathologic examination was not obtained included four cases of metastasis and four cases of pontine glioma. In metastases, the primary was known. In pontine gliomas the characteristic MR findings were present and due to increased frequency of complications the risky biopsy in this area was not performed. &#x0D; Unique contribution to theory, practice and policy (recommendations): The MR imaging diagnosis was found to correlate with the histopathologic diagnosis in most instances. MR imaging was found to be highly sensitive in evaluating tumor related complications. MRI showed the full extent of the tumor and involvement of the surrounding tissues, thus helping in the management of tumors. Hence it is recommended to perform MRI in cases of increased intracranial hypertension to make early and accurate diagnosis possible and hence improve the patient management.

Neural Networks Oblige Diagnosis of the Ischemic CVA’s by MRI

In present time the technological &amp; computing evolution are promoted for new opportunities that will help to improve the standard of life between the new medical accomplishments, in particular and the standard of diagnostic evaluations. MRI is one of the imaging equipment for the diagnosis which has become more beneficial for technological development, because of this and due to the standard of a diagnosis manufacturer, that is one of the most engaging apparatus in the clinical application. The attentiveness in that pathology &amp; in the general the encephalon picture analysis as the preventive diagnosis. The present research paper suggests the evaluation of the ability of ANN for the automatic identification of an ICVA by tissue images density obtained by MRI. In this examination the diagnosis and their medical reports were used to train the ANN classifier which extracted features from the given images. In this stage the ANN significantly contributes to the ICVA of MRI diagnosis aid, so since the test occurrence automatic identification of ischemic lesions that has been performed with the accuracy results that will be false positive and false negative.

VP26.10: A rare case of fetal stroke

This study reports a rare case of fetal massive intra cranial hemorrhage diagnosed in the third trimester of pregnancy. Fetal intra cranial hemorrhage (ICH) refers to hemorrhage anywhere within the cranium detected in utero. In most cases the etiology of fetal ICH remains unclear but maternal trauma, maternal vitamin K deficiency, thrombocytopenia, fetal coagulation disorders, vascular anomalies, severe fetal hypoxia, and infections are possible predisposing factors. Ultrasonography (US) is the imaging modality of choice for the diagnosis of fetal ICH and MRI provides additional information that is useful in management. The prognosis of these hemorrhages is poor with risk of stillbirth, neonatal death or postnatal neurodevelopmental deficiencies. Please note: The publisher is not responsible for the content or functionality of any supporting information supplied by the authors. Any queries (other than missing content) should be directed to the corresponding author for the article.

Comparison of diagnostic efficacy of ultrasound, ultrasound elastography and magnetic resonance imaging for breast lesions

Study aimed to evaluate and compare the performance of ultrasound, ultrasound elastography and magnetic resonance imaging in the diagnosis of breast cancer & its differentiation from benign lesions Material & Method: This cross-sectional observational study was conducted at department of Radiodiagnosis, Era’s Lucknow Medical college. The study was conducted for 18 month from January 2019 to june 2020. Patients detected with breast lesions and willing to be part of study were included in the study. The patients with cystic nodules and non-consenting patients were excluded from the present study. All the patients were subjected to B-mode USG assessment followed with Real Time ultrasound Elastography and 0.5 Tesla MRI scan. Fine needle aspiration cytology (FNAC) or biopsy was performed and the specimen were evaluated cytologically/histopathologically to confirm the diagnosis Result: Histopathologically, 18 (36%) cases were diagnosed as malignant and remaining 32 (64%) were diagnosed as benign. Among 18 malignant cases, maximum (n=11) were intraductal carcinoma (NOS), followed by well-differentiated intraductal carcinoma (n=6) and invasive lobular carcinoma (n=1) respectively. Among 32 benign cases, maximum (n=20) were fibroadenoma, followed by breast abscess (n=3), galactocele, intraductal papilloma and simple cyst (n=2 each). There was 1 case each diagnosed as fibroadenolipoma, fibrocystic and phyllode respectively. Diagnostic efficacy of USG in terms of sensitivity, specificity, positive and negative predictive value was 77.8%, 87.5%, 77.8% and 87.5% respectively. The accuracy of USG diagnosis was 84%. Diagnostic efficacy of USG elastography in terms of sensitivity, specificity, positive and negative predictive value was 83.3%, 96.9%, 93.8% and 91.2% respectively. The accuracy of elastography diagnosis was 92%. Diagnostic efficacy of MRI in terms of sensitivity, specificity, positive and negative predictive value was 94.4%, 90.6%, 85.0% and 96.7% respectively. The accuracy of MRI diagnosis was 92%. Conclusion: In low-resource settings, USG elastography can emerge as a suitable alternative to MRI in diagnosis of malignant breast masses with highly appreciable positive and negative predictive values. Study Design: Observational Study.

Sensitivity and Specificity of MRI in Intraspinal Tumor Patients

Background: Cancer is the leading cause of death worldwide, causing a global 10 million deaths just in 2018. Cancer has no cure, but is preventable if diagnosed early. Among the methods of diagnosing cancer, MRI or Magnetic Resonance Imaging is one of the most accurate ones. This study was done with the aim of evaluating the diagnostic usefulness of MRI in detection of intraspinal tumor and comparison with histopathological findings. Aim of the study: The study aimed to determine the sensitivity and specificity of MRI in respect to intraspinal tumor patients. Methods: The study was conducted at the Department of Radiology and Imaging, NITOR, Dhaka, Bangladesh, during the period of July 2019 to December 2020 with a sample size of 100 clinically suspected cases of intraspinal tumor aged between 10-70 years. Results: Among the participants, male: female ratio was 3:2. Thirty-Four (34) % of patients belonged to the age group of 41-50 years. 10% were from the youngest age group of 11-20 years, and 6% were from the oldest age group of 61-70 years. The mean age of the participants was 38.89 years. Weakness of the limbs was present in 92% of the participants, back pain was present in 90% percent of the participants. 58% of the participants had tumors in intradural extramedullary region. According to the MRI diagnosis, 55.56% of the participants had Sequestrated disc, 33.33% had Chronic Inflammatory lesion, and 11.11 % had Epidural abscess. According to the histopathological diagnosis of the patients, 32% had schwannoma tumors, 27% had meningioma tumors, 17% had ependymoma tumors, 5% had metastasis tumors, and 2% neurofibroma and hemangioma were present among the participants. After cross analysis of the MRI diagnosis with histopathological diagnosis, 76 cases were true positive, 2 cases were false positive, 6 cases were false negative and 16 cases were true negative. Sensitivity was found 92.68%, specificity was 88.88 % and accuracy was 82.60%. Conclusion: This study.......

Resistance exercise relieves symptoms of vestibular migraine patients with MRI diagnosis: A randomized parallel-controlled single-blind clinical trial

To investigate the efficacy of resistance exercise on symptoms of vestibular migraine (VM) among migraine patients, a total of 385 VM patients were recruited, among whom 312 were eligible to participate in the current study. Patients were randomly allocated into either resistance exercise or relaxation control groups, and received respective interventions two times per week for 12 weeks. Patients were followed up at two and four months, respectively, to evaluate treatment effects. Primary outcomes included Dizziness Handicap Inventory (DHI), the number of vertiginous attacks in the previous week and Vertigo Severity Scale (VSS). Secondary endpoints included depression and anxiety symptoms, which were measured using the scores of the Beck Anxiety Inventory (BAI) and the Beck Depression Inventory (BDI). Serum concentrations of pro-inflammatory cytokines, including tumor necrosis factor-α (TNF-α) and interferon-γ (IFN-γ), were also assessed. Resistance exercise was slightly more pronounced in alleviating VM symptoms than relaxation control at two-month follow-up. While at four-month follow-up, the extents of the symptom attenuation were obviously better in the resistance exercise group than the relaxation control, in terms of VSS and DHI scores, as well as BDI and BAI scores. Serum levels of both TNF-α and IFN-γ were also significantly lower in patients in the resistance group than those in the relaxation control group. Our study favors an exercise-oriented treatment scheme in rehabilitating therapy for patients suffering from VM, and sheds light on the molecular mechanism potentially involving TNF-α and IFN-γ related inflammation pathways.

Comparison Between Gadolinium Enhanced Susceptibility Weighted Imaging And Conventional T1-Weighted Imaging In Optimizing The Recognition Of Active Plaques Of Multiple Sclerosis

Background: The Gd-SWI sequence is a new important magnetic resonance imaging sequence that has been applied currently due to its ability to optimize the recognition of active plaques of MS and has a higher accurate performance than gadolinium T1WI that is currently used in clinical practice. Aim: comparing the performance of the Gd-SWI sequence with the performance of other used sequences in clinical practice in detection of blood brain barrier (BBB) dysfunctions in MS plaques.Methods: in this retrospective study, Twenty four patients were involved (16 females and 8males, their age ranging from 20- 42 years with the mean age 26.33 years), they were divided into two groups: 8 active cases and 22 inactive cases clinically and radiologically proven MS cases for MRI diagnosis and follow up. Results: Two thirds of the studied group (66.7 %) had inactive lesions and one third (33.3 %) had active ones with (12.5 %) of both active and inactive lesions were progressive. There was higher ability of post-contrast SWI to demonstrate active plaques than post-contrast TIWI and there was highly statistically significance and good agreement (kappa=0.71) with 89.5% percent of agreement between post contrast enhanced lesions by SWI and T1 and statistically highly significant difference (p < 0.001).Conclusions: Gadolinium –SWI technique improved detection accuracy of MS- contrast-enhanced plaques better than Gd-T1 SE, including their locations and morphologies.

The Efficacy of 18F-FDG PET/CT and Superparamagnetic Nanoferric Oxide MRI in the Diagnosis of Lung Cancer and the Value of 18F-FDG PET/CT in the Prediction of Lymph Node Metastasis

In China, lung cancer is one of the leading causes of death among residents. Early diagnosis is of great significance for early interventional treatment and prolonging survival. PET/CT uses positron radiopharmaceuticals to observe the physiological and biochemical changes of the drug and its metabolites in the body and finally diagnoses the disease. 18F-FDG is a commonly used imaging agent, but its short isotopic half-life limits clinical high-throughput testing. This study retrospectively analyzed the imaging material of 100 lung cancer patients pathologically confirmed. Patients with lymph node metastasis were classified into the LM group (n = 30 cases), and those with no lymph node metastasis were classified into the NLM group (n = 70 cases). The results showed that MRI of superparamagnetic nanoferric oxide was better than diagnosis of lung cancer by the 18F-FDG PET/CT and had a high predictive power for lymph node metastasis. These turned out to be high-value lung cancer diagnosis of superparamagnetic nanoferric oxide MRI and high-capacity lymph node metastasis prediction of 18F-FDG PET/CT, which were worthy of implementation.

Semantic image segmentation of brain MRI with deep learning.

Previous studies on brain MRI image segmentation, such as threshold method, boundary detection method, and region method did not achieve good performance in complex scenes. Based on the deep learning segmentation technology, this study constructed a neural network model by using the algorithm of atrous convolution combined with conditional random field (CRF) to segment the thalamus, caudate nucleus, and lenticular nucleus in brain MRI, which laid a good foundation for MRI diagnosis of brain diseases. A total of 1 200 MRI-Flair images of the brain were randomly selected, and 3 anatomical structures of thalamus, caudate nucleus, and lenticular nucleus were manually labeled, of which 1 000 were used as training data sets and 200 were used as test data sets. The neural network model was established by using deep convolutional neural networks (DCNN) combined with CRF algorithm. The training data set was input into the model, and the parameterized neural network model was obtained after iteration for 30 000 times. The test data set was used to evaluate, test, and output the predicted image. The model optimization results showed that the new brain MRI segmentation model DeepXAG had the highest accuracy. Therefore, DeepXAG was selected as the segmentation algorithm. The mean intersection over union (mIOU) of the DeepXAG model was 72.3%, which was significantly higher than other classical segmentation algorithms (CRF-RNN1, FCN-8s2, DPN3, RefineNet4, and PSPNet5). The DeepXAG algorithm has good accuracy and robustness in segmenting the anatomical structure of brain MRI images.

Accuracy of MRI in the Differential Diagnosis of Wilms Tumor

Background &amp; Objective: Renal tumors are a common finding in diagnostic imaging; these lesions usually are solid or cystic, benign or malignant, and the correct diagnosis may be difficult. The current study aims at to determine the diagnostic accuracy of magnetic resonance imaging for the diagnosis of Wilms tumor taking histopathology as gold standard. Methodology: This cross-sectional study was carried at the Department of Radiology, The Children’s Hospital &amp; Institute of Child Health Lahore over 6 months from March 2019 to September 2019. The study involved 125 children of both genders aged between 2 years to 14 years presenting with a neoplastic mass in the retroperitoneum on ultrasound abdomen during initial workup. These children were assessed on MRI for the diagnosis of Wilms tumor. Later the diagnosis was confirmed on histopathology which was taken as gold standard and the diagnosis of MRI was judged accordingly as true/false and positive/negative. A written informed consent was obtained from every patient. Results: The mean age of the children was 5.8±3.9 years having a male predominance with male to female ratio of 1.8:1. Wilms tumor was suspected in 13 (10.4%) children on MRI. The diagnosis of Wilms tumor was confirmed in 13 (10.4%) children on histopathology. MRI was found to be 76.9% sensitive, 97.3% specific and 95.2% accurate with positive and negative predictive values of 76.9% and 97.3% respectively. Conclusion: In the present study, MRI was found to be 95.2% accurate in the differential diagnosis of Wilms tumor in children presenting with retroperitoneal mass which along with its non-invasive and radiation free nature advocates the preferred use of MRI in the diagnostic evaluation of such children in future oncologic practice. Keywords: Retroperitoneal Tumor, Wilms Tumor, MRI, Diagnostic Accuracy