Localization of lumbar discs in magnetic resonance imaging (MRI) is a challenging task, due to a vast range of shape, size, number, and appearance of discs and vertebrae. Based on a review of the cutting-edge methods, the majority of applied techniques are either semi-automatic, extremely sensitive to change in parameters, or involve further modification of the results. All of the above represents a motivation for implementing deep learning-based approaches for automatic segmentation and classification of disc herniation in MR images. This paper proposes a complete automated process based on deep learning to diagnose disc herniation. The methodology includes several steps starting from segmentation of region of interest (ROI), in this case disc area, bounding box cropping and enhancement of ROI, after which the image is classified based on convolutional neural network (CNN) into adequate classes (healthy, bulge, central, right or left herniation for axial view and healthy, L4/L5, L5/S1 level of herniation in sagittal view). The results show high accuracy of segmentation for both axial view (dice = 0.961, IOU = 0.925) and sagittal view (dice = 0.897, IOU = 0.813) images. After cropping and enhancing the region of interest, accuracy of classification was 0.87 for axial view images and 0.91 for sagittal view images. Comparison with the literature shows that proposed methodology outperforms state-of-the-art results when it comes to multiclassification problems. A fully automated decision support system for disc hernia diagnosis can assist in generating diagnostic findings in a timely manner, while human mistakes caused by cognitive overload and procedure-related errors can be reduced.
28 April 2023 in Current Research in Translational Medicine
BACKGROUND: In patients with only upper (C5, C6) brachial plexus palsy (BPP), the pooled international data strongly favor nerve transfers over nerve grafts. In patients with complete BPP, some authors favor nerve grafts for the restoration of priority functions whenever there is a viable proximal stump. OBJECTIVE: To evaluate functional recovery in cases of upper and complete BPP where only direct graft repair from viable proximal stumps was performed. METHODS: The study included 36 patients (24 with complete BPP and 12 with only upper BPP) operated on over a 15-yr period. In all cases, direct graft repair from C5 to the musculocutaneous and the axillary nerve was performed. In cases with complete BPP, additional procedures included either direct graft repair from C6 to the radial nerve and the medial pectoral nerve or the dorsal scapular nerve transfer to the branch for the long head of the triceps. RESULTS: The use of C5 proximal stump grafts (in both complete and upper BPP) resulted in satisfactory elbow flexion in 26 patients (72.2%) and satisfactory shoulder abduction in 22 patients (61.1%). The use of C6 proximal stump grafts in patients with complete BPP resulted in satisfactory elbow extension in 5 (50%) and satisfactory shoulder adduction in another 5 (50%) patients. CONCLUSION: Although nerve transfers generally enable better restoration of priority functions, in cases of infraganglionary injuries, especially in shorter defects, it is also necessary to consider direct graft repair, or at least its combination with nerve transfers, as a potentially beneficial treatment modality.
- Missile injuries are among the most devastating injuries in general traumatology. Traumatic brachial plexus injuries are the most difficult injuries in peripheral nerve surgery, and most complicated to be surgically treated. Nevertheless, missile wounding is the second most common mechanism of brachial plexus injury. The aim was to evaluate functional recovery after surgical treatment of these injuries. Our series included 68 patients with 202 nerve lesions treated with 207 surgical procedures. Decision on the treatment modality (exploration, neurolysis, graft repair, or combination) was made upon intraoperative finding. Results were analyzed in 60 (88.2%) patients with 173 (85.6%) nerve lesions followed-up for two years. Functional recovery was evaluated according to functional priorities. Satisfactory functional recovery was achieved in 90.4% of cases with neurolysis and 85.7% of cases with nerve grafting. Insufficient functional recovery was verified in ulnar and radial nerve lesions after neurolysis, and in median and radial nerve lesions when graft repair was done. We conclude that the best time for surgery is between two and four months after injury, except for the gunshot wound associated with injury to the surrounding structures, which requires immediate surgical treatment. The results of neurolysis and nerve grafting were similar.
Galectin-3 (Gal-3) plays a multifaceted role in the development, progression, and prognosis of pancreatic ductal adenocarcinoma (PDAC). This review offers a comprehensive examination of its expression in PDAC, its interaction with various immune cells, signaling pathways, effects on apoptosis, and therapeutic resistance. Additionally, the prognostic significance of serum levels of Gal-3 is discussed, providing insights into its potential utilization as a biomarker. Critical analysis is also extended to the inhibitors of Gal-3 and their potential therapeutic applications in PDAC, offering new avenues for targeted treatments. The intricate nature of Gal-3’s role in PDAC reveals a complex landscape that demands a nuanced understanding for potential therapeutic interventions and monitoring.