Semiautomatic computer-aided classification of degenerative lumbar spine disease in magnetic resonance imaging

The classification of brain tumors is a difficult task in the field of medical image analysis. Improving algorithms and machine learning technology helps radiologists to easily diagnose the tumor without surgical intervention. In recent years, deep learning techniques have made excellent progress in the field of medical image processing and analysis. However, there are many difficulties in classifying brain tumors using magnetic resonance imaging; first, the difficulty of brain structure and the intertwining of tissues in it; and secondly, the difficulty of classifying brain tumors due to the high density nature of the brain. We propose a differential deep convolutional neural network model (differential deep-CNN) to classify different types of brain tumor, including abnormal and normal magnetic resonance (MR) images. Using differential operators in the differential deep-CNN architecture, we derived the additional differential feature maps in the original CNN feature maps. The derivation process led to an improvement in the performance of the proposed approach in accordance with the results of the evaluation parameters used. The advantage of the differential deep-CNN model is an analysis of a pixel directional pattern of images using contrast calculations and its high ability to classify a large database of images with high accuracy and without technical problems. Therefore, the proposed approach gives an excellent overall performance. To test and train the performance of this model, we used a dataset consisting of 25,000 brain magnetic resonance imaging (MRI) images, which includes abnormal and normal images. The experimental results showed that the proposed model achieved an accuracy of 99.25%. This study demonstrates that the proposed differential deep-CNN model can be used to facilitate the automatic classification of brain tumors.

Download Full-text

THU0492 MAGNETIC RESONANCE IMAGING OF THE SACROILIAC JOINTS IN PATIENTS WITH HYPERMOBILITY: A RETROSPECTIVE COHORT STUDY

Annals of the Rheumatic Diseases ◽

10.1136/annrheumdis-2020-eular.5686 ◽

2020 ◽

Vol 79 (Suppl 1) ◽

pp. 482.4-483

Author(s):

A. Jones ◽

C. Ciurtin ◽

H. Kazkaz ◽

M. Hall-Craggs

Keyword(s):

Magnetic Resonance Imaging ◽

Bone Marrow ◽

Back Pain ◽

Lumbar Spine ◽

Magnetic Resonance ◽

Bone Marrow Oedema ◽

Resonance Imaging ◽

Sacroiliac Joints ◽

Fatty Change ◽

Subchondral Sclerosis

Background:The incidence of inflammatory and structural lesions on magnetic resonance imaging of sacroiliac joints (MRI SIJs) in patients with hypermobility related disorders has not been fully investigated. Hypermobile patients are more susceptible to pelvic instability and biomechanical stress of the SIJs, leading to MRI SIJ changes similar to those occurring in spondyloarthritis (SpA). Patients with hypermobility and suspected SpA pose a unique challenge owing to the high prevalence of back pain in the hypermobility cohort and the absence of spinal restriction on clinical examination.Objectives:In this study, we aim to investigate the incidence of MRI SIJ lesions in patients with hypermobility.Methods:We performed a retrospective study of all patients with a confirmed diagnosis of hypermobility related disorders (including hypermobility syndrome, hypermobility spectrum disorders and Ehlers-Danlos Syndromes) referred for an MRI lumbar spine and SIJ between 2011 and 2019 to investigate long-standing back pain. MRIs were examined by a musculoskeletal (MSK) radiologist with more than 25 years of experience, who was blinded to the clinical outcome of the patients. MRI SIJs were assessed for the presence of bone marrow oedema, subchondral sclerosis, erosion, fatty change, enthesitis, ankylosis, joint fluid and capsulitis.Results:51 patients with confirmed hypermobility related disorders were referred for MRI SIJ and lumbar spine between 2011 and 2019. 3 patients demonstrated clinical features in keeping with a diagnosis of SpA and were excluded from the study. 15/48 (31.3%) of patients with hypermobility and back pain (but no clinical picture of SpA) were found to have inflammatory and/or structural lesions on MRI SIJ. The most frequent lesions were small foci of bone marrow oedema (16.6%) followed by subchondral sclerosis (12.5%) and fatty change (10.4%). The incidence of erosions was 4.2%.Conclusion:There is a relatively high incidence of inflammatory and structural lesions on MRI SIJ of patients with hypermobility. The presence of hypermobility should be taken into consideration when interpreting MRI changes in patients with suspected SpA. Further research into long-term outcomes of MRI SIJs in patients with hypermobility and back pain is required to establish the clinical significance of these findings.Disclosure of Interests: :Alexis Jones: None declared, Coziana Ciurtin Grant/research support from: Pfizer, Consultant of: Roche, Modern Biosciences, Hanadi Kazkaz: None declared, Margaret Hall-Craggs: None declared

Download Full-text