A CT-Based Deep Learning Radiomics Nomogram to Predict Histological Grades of Head and Neck Squamous Cell Carcinoma.

RATIONALE AND OBJECTIVES: Accurate pretreatment assessment of histological differentiation grade of head and neck squamous cell carcinoma (HNSCC) is crucial for prognosis evaluation. This study aimed to construct and validate a contrast-enhanced computed tomography (CECT)-based deep learning radiomics nomogram (DLRN) to predict histological differentiation grades of HNSCC. MATERIALS AND METHODS: A total of 204 patients with HNSCC who underwent CECT scans were enrolled in this study. The participants recruited from two hospitals were split into a training set (n=124, 74 well/moderately differentiated and 50 poorly differentiated) of patients from one hospital and an external test set of patients from the other hospital (n=80, 49 well/moderately differentiated and 31 poorly differentiated). CECT-based manually-extracted radiomics (MER) features and deep learning (DL) features were extracted and selected. The selected MER features and DL features were then combined to construct a DLRN via multivariate logistic regression. The predictive performance of the DLRN was assessed using ROCs and decision curve analysis (DCA). RESULTS: Three MER features and seven DL features were finally selected. The DLRN incorporating the selected MER and DL features showed good predictive value for the histological differentiation grades of HNSCC (well/moderately differentiated vs. poorly differentiated) in both the training (AUC, 0.878) and test (AUC, 0.822) sets. DCA demonstrated that the DLRN was clinically useful for predicting histological differentiation grades of HNSCC. CONCLUSION: A CECT-based DLRN was constructed to predict histological differentiation grades of HNSCC. The DLRN showed good predictive efficacy and might be useful for prognostic evaluation of patients with HNSCC.

Compressive myelopathy and compression fracture of aggressive vertebral hemangioma after parturition: A case report and review of literature.

RATIONALE: Compressive myelopathy and compression fracture of aggressive vertebral hemangioma after parturition is a rare condition. Vertebral body compression fracture and high serum progesterone lead to extraosseous hemangioma enlargment cause narrowing the spinal canal which contribute to compressive myelopathy relate to pregnancy. PATIENT CONCERNS: We report a case of compressive myelopathy and compression fracture of aggressive vertebral hemangioma after parturition in a 35-year-old woman. The patient complained unable to walk and experienced intense pain in the back. DIAGNOSIS: Based on the clinical features and imaging studies, the patient underwent a T4-T6 laminectomy. Histopathology consistent with vertebral hemangioma. INTERVENTIONS: The patient underwent laminectomy for decompression. After subperiosteal dissection of the paraspinal muscles and exposure of the laminae, there was no involvement of the lamina by the tumor. The epidural tumor was removed through the spaces lateral to the thecal sac. Vertebroplasty was performed through T5 pedicles bilaterally and 7 ml of polymethylmethacrylate (PMMA) cement was injected. T4-T6 pedicle screw fixation was performed for segmental fixation and fusion. OUTCOMES: Six months after resection of the tumor the patient remained asymptomatic. She reported no low back pain and had returned to her normal daily activities, with no radiographic evidence of recurrence on MRI. Physical examination revealed that superficial and deep sensation was restored to normal levels in the lower extremities. LESSONS: The occurrence of compressive myelopathy of pregnancy related vertebral hemangiomas is quite unusual. It can lead to serious neurologic deficits if not treated immediately. So, prompt diagnosis is important in planning optimal therapy and preventing morbidity for patients.

Levodopa/benserazide microsphere (LBM) prevents L-dopa induced dyskinesia by inactivation of the DR1/PKA/P-tau pathway in 6-OHDA-lesioned Parkinson's rats.

L-3, 4-dihydroxyphenylalanine (L-dopa) is the gold standard for symptomatic treatment of Parkinson's disease (PD), but long-term therapy is associated with the emergence of L-dopa-induced dyskinesia (LID). In the present study, L-dopa and benserazide were loaded by poly (lactic-co-glycolic acid) microspheres (LBM), which can release levodopa and benserazide in a sustained manner in order to continuous stimulate dopaminergic receptors. We investigated the role of striatal DR1/PKA/P-tau signal transduction in the molecular event underlying LID in the 6-OHDA-lesioned rat model of PD. We found that animals rendered dyskinetic by L-dopa treatment, administration of LBM prevented the severity of AIM score, as well as improvement in motor function. Moreover, we also showed L-dopa elicits profound alterations in the activity of three LID molecular markers, namely DR1/PKA/P-tau (ser396). These modifications are totally prevented by LBM treatment, a similar way to achieve continuous dopaminergic delivery (CDD). In conclusion, our experiments provided evidence that intermittent administration of L-dopa, but not continuous delivery, and DR1/PKA/p-tau (ser396) activation played a critical role in the molecular and behavioural induction of LID in 6-OHDA-lesioned rats. In addition, LBM treatment prevented the development of LID by inhibiting the expression of DR1/PKA/p-tau, as well as PPEB mRNA in dyskintic rats.