ARTIFICIAL INTELLIGENCE APPLIED ON CONVENTIONAL MAGNETIC RESONANCE IMAGES IMPROVES THE CORRECT DIAGNOSIS OF CNS DISEASES MIMICKING MULTIPLE SCLEROSIS

2020 ◽  
Author(s):  
Nicoletta Anzalone
Keyword(s):  
Artificial Intelligence ◽  
Multiple Sclerosis ◽  
Magnetic Resonance ◽  
Correct Diagnosis ◽  
Magnetic Resonance Images ◽  
Cns Diseases ◽  
Conventional Magnetic Resonance

scholarly journals Detection and Diagnosis of Breast Cancer Using Artificial Intelligence Based Assessment of Maximum Intensity Projection Dynamic Contrast-Enhanced Magnetic Resonance Images

Diagnostics ◽  
2020 ◽  
Vol 10 (5) ◽  
pp. 330
Author(s):  
Mio Adachi ◽  
Tomoyuki Fujioka ◽  
Mio Mori ◽  
Kazunori Kubota ◽  
Yuka Kikuchi ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Magnetic Resonance ◽  
Diagnostic Performance ◽  
Maximum Intensity Projection ◽  
Breast Mri ◽  
Magnetic Resonance Images ◽  
Maximum Intensity ◽  
Validation Data ◽  
Dynamic Contrast Enhanced ◽  
Contrast Enhanced

We aimed to evaluate an artificial intelligence (AI) system that can detect and diagnose lesions of maximum intensity projection (MIP) in dynamic contrast-enhanced (DCE) breast magnetic resonance imaging (MRI). We retrospectively gathered MIPs of DCE breast MRI for training and validation data from 30 and 7 normal individuals, 49 and 20 benign cases, and 135 and 45 malignant cases, respectively. Breast lesions were indicated with a bounding box and labeled as benign or malignant by a radiologist, while the AI system was trained to detect and calculate possibilities of malignancy using RetinaNet. The AI system was analyzed using test sets of 13 normal, 20 benign, and 52 malignant cases. Four human readers also scored these test data with and without the assistance of the AI system for the possibility of a malignancy in each breast. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were 0.926, 0.828, and 0.925 for the AI system; 0.847, 0.841, and 0.884 for human readers without AI; and 0.889, 0.823, and 0.899 for human readers with AI using a cutoff value of 2%, respectively. The AI system showed better diagnostic performance compared to the human readers (p = 0.002), and because of the increased performance of human readers with the assistance of the AI system, the AUC of human readers was significantly higher with than without the AI system (p = 0.039). Our AI system showed a high performance ability in detecting and diagnosing lesions in MIPs of DCE breast MRI and increased the diagnostic performance of human readers.

Voxelwise analysis of conventional magnetic resonance imaging to predict future disability in early relapsing–remitting multiple sclerosis

2012 ◽  
Vol 18 (11) ◽  
pp. 1585-1591 ◽  
Author(s):  
Delphine Wybrecht ◽  
Françoise Reuter ◽  
Wafaa Zaaraoui ◽  
Anthony Faivre ◽  
Lydie Crespy ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Multiple Sclerosis ◽  
Magnetic Resonance ◽  
Physical Disability ◽  
Conventional Magnetic Resonance Imaging ◽  
Global Approach ◽  
Resonance Imaging ◽  
Conventional Magnetic Resonance ◽  
Magnetic Resonance Imaging Mri ◽  
Mri Changes

Background: The ability of conventional magnetic resonance imaging (MRI) to predict subsequent physical disability and cognitive deterioration after a clinically isolated syndrome (CIS) is weak. Objectives: We aimed to investigate whether conventional MRI changes over 1 year could predict cognitive and physical disability 5 years later in CIS. We performed analyses using a global approach (T2 lesion load, number of T2 lesions), but also a topographic approach. Methods: This study included 38 patients with a CIS. At inclusion, 10 out of 38 patients fulfilled the 2010 revised McDonald’s criteria for the diagnosis of multiple sclerosis. Expanded Disability Status Scale (EDSS) evaluation was performed at baseline, year 1 and year 5, and cognitive evaluation at baseline and year 5. T2-weighted MRI was performed at baseline and year 1. We used voxelwise analysis to analyse the predictive value of lesions location for subsequent disability. Results: Using the global approach, no correlation was found between MRI and clinical data. The occurrence or growth of new lesions in the brainstem was correlated with EDSS changes over the 5 years of follow-up. The occurrence or growth of new lesions in cerebellum, thalami, corpus callosum and frontal lobes over 1 year was correlated with cognitive impairment at 5 years. Conclusion: The assessment of lesion location at the first stage of multiple sclerosis may be of value to predict future clinical disability.

Abstract 16189: Cardiovascular Risk Prediction Using Fully Automated Artificial Intelligence Algorithms for the Assessment of Right Ventricular Function From Cardiac Magnetic Resonance Images

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
shuo wang ◽  
Hena Patel ◽  
Tamari Miller ◽  
Keith Ameyaw ◽  
Akhil Narang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Right Ventricular ◽  
Roc Analysis ◽  
Right Ventricular Ejection Fraction ◽  
Magnetic Resonance Images ◽  
Major Adverse Cardiovascular Events ◽  
Ventricular Ejection Fraction ◽  
Rv Function

Background: It is unclear whether artificial intelligence (AI) can provide automatic solutions to measure right ventricular ejection fraction (RVEF), due to the complex RV geometry. Although several deep learning (DL) algorithms are available to quantify RVEF from cardiac magnetic resonance (CMR) images, there has been no systematic comparison of these algorithms, and the prognostic value of these automated measurements is unknown. We aimed to determine whether RVEF measurements made using DL algorithms could be used to risk stratify patients similarly to measurements made by an expert. Methods: We identified from a pre-existing registry 200 patients who underwent CMR. RVEF was determined using 3 fully automated commercial DL algorithms (DL-RVEF) and also by a clinical expert (CLIN-RVEF) using conventional methodology. Each of the DL-RVEF approaches was compared against CLIN-RVEF using linear regression and Bland-Altman analyses. In addition, RVEF values were classified according to clinically important cutoffs: <35%, 35-50%, ≥50%, and rates of disagreement with the reference classification were determined. ROC analysis was performed to evaluate the ability of CLIN-RVEF and each of the DL-RVEF based classifications to predict major adverse cardiovascular events (MACE). Results: The CLIN-RVEF and the three DL-RVEFs were obtained in all patients. We found only modest correlations between DL-RVEF and CLIN-RVEF (figure). The DL-RVEF algorithms had accuracy ranging from 0.59 to 0.78 for categorizing RV function. Nevertheless, ROC analysis showed no significant differences between the 4 approaches in predicting MACE, as reflected by respective AUC values of 0.68, 0.69, 0.64 and 0.63. Conclusions: Although the automated algorithms predicted patient outcomes as well as the CLIN-RVEF, the agreement between DL-RVEF and the clinical expert’s measurements was not optimal. DL approaches need further refinements to improve automated assessment of RV function.

scholarly journals Multiple Sclerosis Of The Spinal Cord: Is Gadolinium Irreplaceable In Assessing Lesion Activity?

2013 ◽  
Vol 59 (3) ◽  
pp. 158-161
Author(s):  
Constantina Andrada Treabă ◽  
M Buruian ◽  
Rodica Bălașa ◽  
Maria Daniela Podeanu ◽  
I P Simu ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Spinal Cord ◽  
Magnetic Resonance ◽  
Contrast Enhancement ◽  
Signs And Symptoms ◽  
Magnetic Resonance Images ◽  
Type I ◽  
Focal Lesions ◽  
Spinal Cord Lesions ◽  
Active Lesion

Abstract Purpose: To evaluate the relationship between the T2 patterns of spinal cord multiple sclerosis lesions and their contrast uptake. Material and method: We retrospectively reviewed the appearance of spinal cord lesions in 29 patients (with relapsing-remitting multiple sclerosis) who had signs and symptoms of myelopathy on neurologic examination and at least one active lesion visualized on magnetic resonance examinations performed between 2004 and 2011. We correlated the T2 patterns of lesions with contrast enhancement and calculated sensitivity and specificity in predicting gadolinium enhancement. Results: Only focal patterns consisting of a lesion’s center homogenously brighter than its periphery on T2-weighed images (type I) correlated significantly with the presence of contrast enhancement (p = 0.004). Sensitivity was 0.307 and specificity 0.929. In contrast, enhancement was not significantly related to uniformly hyperintense T2 focal lesions (type II) or diffuse (type III) pattern defined as poorly delineated areas of multiple small, confluent, subtle hyperintense T2 lesions (p > 0.5 for both). Conclusions: We believe that information about the activity of multiple sclerosis spinal cord lesions in patients with myelopathy may be extracted not only from contrast enhanced, but also from non-enhanced magnetic resonance images.

scholarly journals The quality of artificial intelligence algorithms for identifying manifestations of multiple sclerosis on magnetic resonance imaging (systematic review)

2021 ◽  
Vol 15 (4) ◽  
pp. 54-65
Author(s):  
Galina N. Chernyaeva ◽  
Sergey P. Morozov ◽  
Anton V. Vladzimirskyy
Keyword(s):  
Magnetic Resonance Imaging ◽  
Artificial Intelligence ◽  
Multiple Sclerosis ◽  
Systematic Review ◽  
Magnetic Resonance ◽  
Small Sample ◽  
Clinical Test ◽  
Data Sets ◽  
Resonance Imaging ◽  
Methodological Errors

A systematic review was undertaken to summarize the data regarding accuracy and effectiveness of artificial intelligence algorithms for identifying MRI manifestations of multiple sclerosis. The review included 39 papers, whose authors put forth a multitude of corresponding algorithms and mathematical models. However, quality assessment of these developments was limited by retrospective testing on repeat data sets. Clinical test results were almost entirely absent, and there were no prospective independent studies of accuracy and applicability. The relatively high values obtained for the main measures (similarity, sensitivity and specificity coefficients, which were 7585%) were offset by the methodological errors when creating the baseline data sets, and lack of validation using independent data. Due to small sample sizes and methodological errors when measuring the result accuracy, most of the studies did not meet the criteria for evidence-based research. Studies with the highest methodological quality had algorithms that achieved a sensitivity of 51.677.0%, with a SrensenDice coefficient of 53.556.0%. These numbers are not high, but they indicate that automatic identification of multiple sclerosis manifestations on magnetic resonance imaging may be achievable. Further development of computer-aided analysis requires the creation of clinical use scenarios and testing methodology, and prospective clinical testing.

Sign in / Sign up

Export Citation Format

Share Document