Background and Objectives: Intervertebral disc degeneration (IDD) is a common cause of symptomatic axial low back pain. Magnetic resonance imaging (MRI) is currently the standard for the investigation and diagnosis of IDD. Deep learning artificial intelligence models represent a potential tool for rapidly and automatically detecting and visualizing IDD. This study investigated the use of deep convolutional neural networks (CNNs) for the detection, classification, and grading of IDD. Methods: Sagittal images of 1000 IDD T2-weighted MRI images from 515 adult patients with symptomatic low back pain were separated into 800 MRI images using annotation techniques to create a training dataset (80%) and 200 MRI images to create a test dataset (20%). The training dataset was cleaned, labeled, and annotated by a radiologist. All lumbar discs were classified for disc degeneration based on the Pfirrmann grading system. The deep learning CNN model was used for training in detecting and grading IDD. The results of the training with the CNN model were verified by testing the grading of the dataset using an automatic model. Results: The training dataset of the sagittal intervertebral disc lumbar MRI images found 220 IDDs of grade I, 530 of grade II, 170 of grade III, 160 of grade IV, and 20 of grade V. The deep CNN model was able to detect and classify lumbar IDD with an accuracy of more than 95%. Conclusion: The deep CNN model can reliably automatically grade routine T2-weighted MRIs using the Pfirrmann grading system, providing a quick and efficient method for lumbar IDD classification.
Introduction and importance: Forestier's disease, also known as a vertebral ankylosing hyperostosis or Diffuse Idiopathic Skeletal Hyperostosis (DISH), is a non-inflammatory enthesopathy that affects primarily elderly males and ossifies the anterolateral spine while sparing the intervertebral discs and joint spaces, especially at the cervical spine. Forestier's disease has resulted in the growth of large anterior cervical osteophytes that may compress the pharyngoesophageal region, producing dysphagia. However, symptomatic Forestier's disease presenting with dysphagia and cervical myelopathy is rarely observed. Case presentation A 48-year-old male presented with progressive dysphagia and cervical myelopathy. Based on the presence of radiographic study, Forestier's disease was suspected. Large anterior cervical osteophytes at C4–C6 levels compressed the pharyngoesophageal structure posteriorly. Multilevel degenerative discs compressing the C4 to C6 spinal cord were also seen on sagittal MRI T2-weighted images. Anterior cervical osteophytectomy with anterior cervical discectomy and fusion (ACDF) were performed. The patient made a complete neurological recovery and had no recurrent symptoms at the 5-year follow-up. The patient was extremely satisfied with this treatment and can improved his quality of life (QOL). Clinical discussion Treatment of symptomatic Forestier's disease with secondary dysphagia and cervical myelopathy is rare evidenced by the dearth of reports on surgical treatment. Surgical intervention appears to be safe, effective, and able to halt disease progression. Conclusion Anterior cervical osteophytectomy combined with ACDF with plate fixation is a preferred technique in both neural decompression and swallowing improvement. Surgical intervention, we consider, provides superior results than prolonged non-surgical treatments.
The aim of this study is to present a rare case of chordoma in the odontoid process in which the tumor involved the odontoid process and compressed the spinal cord at the craniocervical junction. We report on the effectiveness and successful outcome of anterior microscopic tumor resection combined with posterior occipitocervical fixation and review the current standard treatment. A 39-year-old man presented with sudden dyspnea and quadriparesis caused by an unknown tumor compression at C2. Radiographic examination revealed a large destructive mass at C2 and heterogeneous enhancement. The patient received urgent surgical intervention by microscopic-assisted anterior tumor resection and posterior spinal fixation from the occiput to the C5 level. The pathohistologic reports for cytokeratins, epithelial membrane antigen, and S-100 protein were positive. The final diagnosis was chordoma of the odontoid process. At the 2-year follow-up, the patient's condition had improved, and a postoperative MRI showed no indication of tumor regrowth. Chordoma of the odontoid process or C2 body is very rare. The current standard management is wide tumor resection to prevent recurrence. The combined approach of anterior tumor resection with microscopic assistance and posterior stabilization of the occiput to C5 is the optimal treatment for this condition. Chordomas are uncommon malignant bone tumors with an annual incidence of just 0.8 per 1,000,000 population. It is mostly found along the central neural axial skeleton, from the clivus to the sacrococcygeal region. In adults, half of chordomas involve the sacrococcygeal region, 35% occur at the base of the skull near the spheno-occipital area, and 15% are found in the vertebral column, 1-5 that is, the second cervical spine (axis). 1,[6][7][8][9] This disease's recurrent hereditary origins were unknown until recently. 7,10 The condition's rarity, as well as the complex anatomy of the head and neck, makes diagnosis challenging. 11,12 Despite total excision, certain chordomas persist in other sites, such as the skull base, moveable spine, or sacrococcygeal bone, where high-dose radiation may be considered if surgery is not an alternative. 5,7,[13][14][15][16] This report presents a case of
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.