Lumbar spine magnetic resonance imaging for lumbar disc herniation diagnosis
see also Lumbar Disc Herniation Classification.
In magnetic resonance imaging (MRI), lumbar disc herniation (LDH) detection is challenging due to the various shapes, sizes, angles, and regions associated with bulges, protrusions, extrusions, and sequestrations. Lumbar abnormalities in MRI can be detected automatically by using deep learning methods. As deep learning models gain recognition, they may assist in diagnosing LDH with MRI images and provide initial interpretation in clinical settings. YOU ONLY LOOK ONCE (YOLO) model series are often used to train deep learning algorithms for real-time biomedical image detection and prediction. This study aims to confirm which YOLO models (YOLOv5, YOLOv6, and YOLOv7) perform well in detecting LDH in different regions of the lumbar intervertebral disc. Materials and methods: The methodology involves several steps, including converting DICOM images to JPEG, reviewing and selecting MRI slices for labeling and augmentation using ROBOFLOW, and constructing YOLOv5x, YOLOv6, and YOLOv7 models based on the dataset. The training dataset was combined with the radiologist's labeling and annotation, and then the deep learning models were trained using the training/validation dataset. Results: Our result showed that the 550-dataset with augmentation (AUG) or without augmentation (non-AUG) in YOLOv5x generates satisfactory training performance in LDH detection. The AUG dataset's overall performance provides slightly higher accuracy than the non-AUG. YOLOv5x showed the highest performance with 89.30% mAP compared to YOLOv6, and YOLOv7. Also, YOLOv5x in the non-AUG dataset showed the balance LDH region detections in L2-L3, L3-L4, L4-L5, and L5-S1 with above 90%. This illustrates the competitiveness of using non-AUG datasets to detect LDH. Conclusion: Using YOLOv5x and the 550 augmented dataset, LDH can be detected with promising both in non-AUG and AUG datasets. By utilizing the most appropriate YOLO model, clinicians have a greater chance of diagnosing LDH early and preventing adverse effects for their patients 1).
High-resolution MRI is sensitive in detecting disc disease and specific in characterizing various subgroups of disc herniation, especially those which are sequestrated 2)
In 1988 a study demonstrates the clinical superiority of surface coil MRI over contrast CT in the evaluation of lumbar disc herniation 3)
Latest articles
Radiology reports frequently fail to provide sufficient detail to describe disc herniation morphology. Agreement between MRI readings by clinical spine specialists and radiologists was excellent when comparing herniation vertebral level and location within level, but only fair comparing herniation morphology 4)
Lumbar spine magnetic resonance imaging with Gadolinium is a sensitive method to detect unspecific inflammatory reactions in disc herniations. However, the neuroradiological and histological evidence of peridiscal inflammation was not correlated with the severity of pain or sensorimotor deficits. Additional research is needed because the occurrence of local inflammation may indicate an ongoing degradation of herniated fragments and thus be helpful in therapeutic decision-making. 5).
T2 mapping performed better than T1ρ mapping for the detection of early IVDD. T1ρ and T2 mapping performed similarly but better than T2* mapping for advanced degeneration and morphologic changes of IVDD 6)
Analysis of muscles wasting
Axial MRI sections
The cross-sectional areas (CSAs) of the lumbar stabilizer muscles and the lumbar lordosis angle were evaluated by magnetic resonance imaging (MRI), according to the severity of the disc herniation and the patient's age. In the patients with disc herniation, the CSAs of the quadratus lumborum (QL) and the multifidus (MF) muscles were decreased. The psoas major (PM) muscle CSA was higher in the patients with sequestered discs than in those with protruded and extruded discs. A negative relationship between the sagittal curve and the PM muscle CSA was found. In addition, MF muscle CSA was found to decrease at age 45 years and over. Although disc herniation negatively affects muscle CSAs, no linear relationship was found between the severity of the herniation and the muscle CSA. In addition, the PM muscle was found to be a strong compensatory muscle in disc herniation 7)
A study showed a correlation between LDH and paraspinal muscle degeneration, while no correlation was found with asymmetry. Severe (> 50%) fat infiltration is associated with root compression, and the severity of fat filtration increases in the presence of root compression. The development of more severe degeneration due to denervation associated with root compression plays a role in the emergence of this situation. Therefore, in patients with lumbar disc herniation with radiculopathy, it can be foreseen that to stop and correct severe fat infiltration and muscle degeneration, first, nerve root compression should be corrected with appropriate medical treatment methods, and in patients in whom there is no response, the pressure should be alleviated with appropriate surgical methods 8).
FA and ADC
A meta-analysis showed a significant decrease in FA and a significant increase in ADC in patients with nerve damage due to LDH. The results favourably support the presence of nerve impairment in patients with LDH 9).
Positive sedimentation sign
Retrospective Upright MRI Study.
Objectives: Determine the relationship between lumbar disc herniation and presence of the nerve root sedimentation sign on upright kinematic MRI patients.
Methods: T2-weighted axial upright kMRI images of 100 patients with the presence of disc herniation in at least 1 lumbar disc between L1/L2 and L5/S1 were obtained. Sedimentation sign, spinal canal anterior-posterior (AP) diameter, disc height, disc herniation size, type of herniation, and zone of herniation were evaluated. A positive sedimentation sign was defined as having either the majority of nerve roots running ventrally or centrally in the canal or conglomeration of the nerve roots at the mid-disc level. Herniation types were defined as either no herniation, disc bulge, protrusion, extrusion, or sequestration. Zones of herniation were categorized as either central, lateral, or far lateral.
Results: The kappa value of intra-observer reliability was .915. The kappa value of disc levels with a negative sedimentation sign were seen more frequently (n = 326, 65.2%) than those with a positive sedimentation sign (n = 174, 34.8%). The spinal canal AP diameter was significantly decreased at the L3/L4 and L4/L5 level in patients with a positive sedimentation sign. Discs with a positive sedimentation sign had a larger average size of disc herniation compared to those with a negative sign at all levels. A relationship between positivity of the sedimentation sign and disc herniation type was significant at L2/L3, L3/L4, and L4/L5.
Patients with a positive sedimentation sign were seen to have larger disc herniations and more severely degenerated discs 10).
Limitations
Intradural disc herniation, especially large herniation, is hard to diagnose specifically despite the progression of neuroradiologic imaging techniques. A durotomy procedure should be considered if there is a missing ruptured disc or a palpable intradural mass during surgery 11)