scholarly journals Identification of potentially painful disc fissures in magnetic resonance images using machine-learning modelling

2021 ◽  
Author(s):  
Lagerstrand Kerstin ◽  
Hebelka Hanna ◽  
Brisby Helerna
Keyword(s):  
Machine Learning ◽  
Magnetic Resonance ◽  
Diagnostic Accuracy ◽  
Negative Control ◽  
Magnetic Resonance Images ◽  
Machine Learning Algorithms ◽  
Pain Model ◽  
Accuracy And Precision ◽  
Magnetic Resonance Imaging Mri ◽  
Very High

Abstract Purpose It is suggested that non-specific low back pain (LBP) can be related to nerve ingrowth along granulation tissue in disc fissures, extending into the outer layers of the annulus fibrosus. Present study aimed to investigate if machine-learning modelling of magnetic resonance imaging (MRI) data can classify such fissures as well as pain, provoked by discography, with plausible accuracy and precision. Methods The study was based on previously collected data from 30 LBP patients (age = 26–64 years, 11 males). Pressure-controlled discography was performed in 86 discs with pain-positive discograms, categorized as concordant pain-response at a pressure ≤ 50 psi and for each patient one negative control disc. The CT-discograms were used for categorization of fissures. MRI values and standard deviations were extracted from the midsagittal part and from 5 different sub-regions of the discs. Machine-learning algorithms were trained on the extracted MRI markers to classify discs with fissures extending into the outer annulus or not, as well as to classify discs as painful or non-painful. Results Discs with outer annular fissures were classified in MRI with very high precision (mean of 10 repeated testings: 99%) and accuracy (mean: 97%) using machine-learning modelling, but the pain model only demonstrated moderate diagnostic accuracy (mean accuracy: 69%; precision: 71%). Conclusion The present study showed that machine-learning modelling based on MRI can classify outer annular fissures with very high diagnostic accuracy and, hence, enable individualized diagnostics. However, the model only demonstrated moderate diagnostic accuracy regarding pain that could be assigned to either a non-sufficient model or the used pain reference.

scholarly journals Machine Learning Approaches in Study of Multiple Sclerosis Disease Through Magnetic Resonance Images

2021 ◽  
Vol 12 ◽  
Author(s):  
Faezeh Moazami ◽  
Alain Lefevre-Utile ◽  
Costas Papaloukas ◽  
Vassili Soumelis
Keyword(s):  
Machine Learning ◽  
Magnetic Resonance ◽  
Clinical Manifestations ◽  
Magnetic Resonance Images ◽  
Learning Approaches ◽  
Resonance Imaging ◽  
Automated Diagnosis ◽  
Multiple Sclerosis Disease ◽  
Magnetic Resonance Imaging Mri ◽  
Applications Of Machine Learning

Multiple sclerosis (MS) is one of the most common autoimmune diseases which is commonly diagnosed and monitored using magnetic resonance imaging (MRI) with a combination of clinical manifestations. The purpose of this review is to highlight the main applications of Machine Learning (ML) models and their performance in the MS field using MRI. We reviewed the articles of the last decade and grouped them based on the applications of ML in MS using MRI data into four categories: 1) Automated diagnosis of MS, 2) Prediction of MS disease progression, 3) Differentiation of MS stages, 4) Differentiation of MS from similar disorders.

Does the Modified Arrhenius Model Reliably Predict Area of Tissue Ablation After Magnetic Resonance-Guided Laser Interstitial Thermal Therapy for Pediatric Lesional Epilepsy?

2021 ◽  
Author(s):  
Kelsey D Cobourn ◽  
Imazul Qadir ◽  
Islam Fayed ◽  
Hepzibha Alexander ◽  
Chima O Oluigbo
Keyword(s):  
Magnetic Resonance ◽  
Linear Regression ◽  
Magnetic Resonance Images ◽  
Thermal Therapy ◽  
Invasive Technique ◽  
Hypothalamic Hamartoma ◽  
Arrhenius Model ◽  
Laser Interstitial Thermal Therapy ◽  
Accuracy And Precision

Abstract BACKGROUND Commercial magnetic resonance-guided laser interstitial thermal therapy (MRgLITT) systems utilize a generalized Arrhenius model to estimate the area of tissue damage based on the power and time of ablation. However, the reliability of these estimates in Vivo remains unclear. OBJECTIVE To determine the accuracy and precision of the thermal damage estimate (TDE) calculated by commercially available MRgLITT systems using the generalized Arrhenius model. METHODS A single-center retrospective review of pediatric patients undergoing MRgLITT for lesional epilepsy was performed. The area of each lesion was measured on both TDE and intraoperative postablation, postcontrast T1 magnetic resonance images using ImageJ. Lesions requiring multiple ablations were excluded. The strength of the correlation between TDE and postlesioning measurements was assessed via linear regression. RESULTS A total of 32 lesions were identified in 19 patients. After exclusion, 13 pairs were available for analysis. Linear regression demonstrated a strong correlation between estimated and actual ablation areas (R2 = .97, P < .00001). The TDE underestimated the area of ablation by an average of 3.92% overall (standard error (SE) = 4.57%), but this varied depending on the type of pathologic tissue involved. TDE accuracy and precision were highest in tubers (n = 3), with average underestimation of 2.33% (SE = 0.33%). TDE underestimated the lesioning of the single hypothalamic hamartoma in our series by 52%. In periventricular nodular heterotopias, TDE overestimated ablation areas by an average of 13% (n = 2). CONCLUSION TDE reliability is variably consistent across tissue types, particularly in smaller or periventricular lesions. Further investigation is needed to understand the accuracy of this emerging minimally invasive technique.

scholarly journals Effect of GAN-based image standardization on MR knee bone-tissue classification performance

10.29007/d18s ◽  
2020 ◽  
Author(s):  
Vincent Jaouen ◽  
Guillaume Dardenne ◽  
Florent Tixier ◽  
Éric Stindel ◽  
Dimitris Visvikis
Keyword(s):  
Machine Learning ◽  
Medical Imaging ◽  
Bone Tissue ◽  
Pulse Sequences ◽  
Image Synthesis ◽  
Magnetic Resonance Images ◽  
Machine Learning Algorithms ◽  
Pool Data ◽  
Tissue Classification ◽  
High Definition

Due to their sensitivity to acquisition parameters, medical images such as magnetic resonance images (MRI), Positron Emission tomography (PET) or Computed Tomography (CT) images often suffer from a kind of variability unrelated to diagnostic power, often known as the center effect (CE). This is especially true in MRI, where units are arbitrary and image values can strongly depend on subtle variations in the pulse sequences [1]. Due to the CE it is particularly difficult in various medical imaging applications to 1) pool data coming from several centers or 2) train machine learning algorithms requiring large homogeneous training sets. There is therefore a clear need for image standardization techniques aiming at reducing this effect.Considerable improvements in image synthesis have been achieved over the recent years using (deep) machine learning. Models based on generative adversarial neural networks (GANs) now enable the generation of high definition images capable of fooling the human eye [2]. These methods are being increasingly used in medical imaging for various cross-modality (image-to-image) applications such as MR to CT synthesis [3]. However, they have been seldom used for the purpose of image standardization, i.e. for reducing the CE [4].In this work, we explore the potential advantage of embedding a standardization step using GANs prior to knee bone tissue classification in MRI. We consider image standardization as a within-domain image synthesis problem, where our objective is to learn a mapping between a domain D constituted of heterogeneous images and a reference domain R showing one or several images of desired image characteristics.Preliminary results suggest a beneficial impact of such a standardization step on segmentation performance.

Magnetic resonance imaging and computerized tomography scanning of herpes simplex encephalitis

1987 ◽  
Vol 67 (4) ◽  
pp. 592-594 ◽  
Author(s):  
Eric W. Neils ◽  
Robert Lukin ◽  
Thomas A. Tomsick ◽  
John M. Tew
Keyword(s):  
Magnetic Resonance Imaging ◽  
Herpes Simplex ◽  
Magnetic Resonance ◽  
Computerized Tomography ◽  
Herpes Simplex Encephalitis ◽  
Ct Scanning ◽  
Magnetic Resonance Images ◽  
Resonance Imaging ◽  
Content Type ◽  
Magnetic Resonance Imaging Mri

✓ The authors present two cases of herpes simplex encephalitis (HSE) in which computerized tomography (CT) scanning and magnetic resonance imaging (MRI) were performed. They also review the literature on the use of these imaging modalities in cases of HSE. The striking changes noted in these cases on T2-weighted magnetic resonance images in comparison to the CT findings suggest that MRI will help speed recognition of nonhemorrhagic HSE abnormalities.

Sign in / Sign up

Export Citation Format

Share Document