Deep Learning Model for Automatic Identification and Classification of Distal Radius Fracture.

Distal radius fracture (DRF) is one of the most common types of wrist fractures. We aimed to construct a model for the automatic segmentation of wrist radiographs using a deep learning approach and further perform automatic identification and classification of DRF. A total of 2240 participants with anteroposterior wrist radiographs from one hospital between January 2015 and October 2021 were included. The outcomes were automatic segmentation of wrist radiographs, identification of DRF, and classification of DRF (type A, type B, type C). The Unet model and Fast-RCNN model were used for automatic segmentation. The DenseNet121 model and ResNet50 model were applied to DRF identification of DRF. The DenseNet121 model, ResNet50 model, VGG-19 model, and InceptionV3 model were used for DRF classification. The area under the curve (AUC) with 95% confidence interval (CI), accuracy, precision, and F1-score was utilized to assess the effectiveness of the identification and classification models. Of these 2240 participants, 1440 (64.3%) had DRF, of which 701 (48.7%) were type A, 278 (19.3%) were type B, and 461 (32.0%) were type C. Both the Unet model and the Fast-RCNN model showed good segmentation of wrist radiographs. For DRF identification, the AUCs of the DenseNet121 model and the ResNet50 model in the testing set were 0.941 (95%CI: 0.926-0.965) and 0.936 (95%CI: 0.913-0.955), respectively. The AUCs of the DenseNet121 model (testing set) for classification type A, type B, and type C were 0.96, 0.96, and 0.96, respectively. The DenseNet121 model may provide clinicians with a tool for interpreting wrist radiographs.

Unilateral decompressive laminectomy plus fusion using unilateral biportal endoscopic technique for single-level lumbar spinal stenosis.

PURPOSE: This study aimed to compare and analyze the effectiveness of unilateral biportal endoscopic (UBE) decompressive laminectomy plus fusion and microscope-assisted open decompressive laminectomy plus fusion. METHODS: A total of 143 patients with lumbar spinal stenosis were enrolled in this study between March 2020 and February 2021 with a minimum 2 years follow-up visit to our hospital. Sixty-five patients underwent the unilateral biportal endoscopic technique and were assigned to the UBE group, and the remaining 78 patients with microscope assistant were assigned to the Microscope group. The baseline characteristics, clinical outcomes, and radiological data were retrospectively collected and analyzed, as well as Clinical outcomes, radiological data and complications. RESULTS: There were no significant differences between the two groups in terms of baseline characteristics (P > 0.05). The UBE group was demonstrated to be significantly superior in CRP, drainage, blood loss, treatment cost and Hospital stay than the Microscope group (P < 0.05), whereas a significant longer operation time was observed (P < 0.05). The VAS-B, ODI, and JOA-L scores of the UBE group at 1 year follow-up were significantly greater than those of the Microscope group (P < 0.05). Regarding radiological data, there were no significant differences in the section area of the spinal canal and fusion grade between the two groups (P > 0.05). CONCLUSION: In view of the satisfactory clinical outcomes of patients and notable decompression at the stenosed segment, UBE is a feasible, minimally invasive technique for single level lumbar canal stenosis.

Preparation, characterization and biocompatibility of calcium peroxide-loaded polycaprolactone microparticles. / èšå·±å† é ¯åŒ è½½è¿‡æ°§åŒ–é’™å¾®ç²’çš„åˆ¶å¤‡ã€è¡¨å¾åŠå ¶ç”Ÿç‰©ç›¸å®¹æ€§ç ”ç©¶.

OBJECTIVES: To explore the physicochemical characteristics and biocompatibility of calcium peroxide (CPO)-loaded polycaprolactone (PCL) microparticle. METHODS: The CPO/PCL particles were prepared. The morphology and elemental distribution of CPO, PCL and CPO/PCL particles were observed with scanning electron microscopy and energy dispersive spectroscopy, respectively. Rat adipose mesenchymal stem cells were isolated and treated with different concentrations (0.10%, 0.25%, 0.50%, 1.00%) of CPO or CPO/PCL particles. The mesenchymal stem cells were cultured in normal media or osteogenic differentiation media under the hypoxia/normoxia conditions, and the amount of released O2 and H2O2 after CPO/PCL treatment were detected. The gene expressions of alkaline phosphatase (ALP), Runt-associated transcription factor 2 (RUNX2), osteopontin (OPN) and osteocalcin (OCN) were detected by realtime RT-PCR. SD rats were subcutaneously injected with 1.00% CPO/PCL particles and the pathological changes and infiltration of immune cells were observed with HE staining and immunohistochemistry at day 7 and day 14 after injection. RESULTS: Scanning electron microscope showed that CPO particles had a polygonal structure, PCL particles were in a small spherical plastic particle state, and CPO/PCL particles had a block-like crystal structure. Energy dispersive spectroscopy revealed that PCL particles showed no calcium mapping, while CPO/PCL particles showed obvious and uniform calcium mapping. The concentrations of O2 and H2O2 released by CPO/PCL particles were lower than those of CPO group, and the oxygen release time was longer. The expressions of Alp, Runx2, Ocn and Opn increased with the higher content of CPO/PCL particles under hypoxia in osteogenic differentiation culture and normal culture, and the induction was more obvious under osteogenic differentiation conditions (all P<0.05). HE staining results showed that the muscle tissue fibers around the injection site were scattered and disorderly distributed, with varying sizes and thicknesses at day 7 after particle injection. Significant vascular congestion, widened gaps, mild interstitial congestion, local edema, inflammatory cell infiltration, and large area vacuolization were observed in some tissues of rats. At day 14 after microparticle injection, the muscle tissue around the injection site and the tissue fibers at the microparticle implantation site were arranged neatly, and the gap size was not thickened, the vascular congestion, local inflammatory cell infiltration, and vacuolization were significantly improved compared with those at day 7. The immunohistochemical staining results showed that the expressions of CD3 and CD68 positive cells significantly increased in the surrounding muscle tissue, and were densely distributed in a large area at day 7 after particle injection. At day 14 of microparticle injection, the numbers of CD3 and CD68 positive cells in peripheral muscle tissue and tissue at the site of particle implantation were lower than those at day 7 (all P<0.01). CONCLUSIONS: CPO/PCL particles have good oxygen release activity, low damage to tissue, and excellent biocompatibility.

Comparison of staged lateral lumbar interbody fusion combined two-stage posterior screw fixation and two osteotomy strategies for adult degeneration scoliosis: a retrospective comparative study.

AIMS: The commonly used treatments of adult degeneration scoliosis (ADS) were posterior long segment screw fixation with osteotomies. Recently, lateral lumbar intervertebral fusion combined two-stage posterior screw fixation (LLIF + PSF) as a new strategy without osteotomy. Herein, this study aimed to compare the clinical and radiological outcomes among LLIF + PSF and pedicle subtraction osteotomy (PSO), posterior column osteotomies (PCO). METHODS: Totals of 139 ADS patients underwent operation with 2 years longer follow-up visit between January 2013 and January 2018 in Ningbo No.6 Hospital were enrolled into this study. 58 patients were included in PSO group, 45 in PCO group and 36 in LLIF + PSF group, The clinical and radiological data were reviewed from medical records. Baseline characteristic, perioperative radiological data (sagittal vertical axis (SVA), coronal balance (CB), Cobb angle of Mian curve (MC), Lumbar lordosis (LL), pelvic tilt (PT) and pelvic incidence-lumbar lordosis mismatch (PI-LL)), clinical outcomes (VAS of back and leg, Oswestry disability index (ODI) and Scoliosis Research Society 22-question Questionnaire (SRS-22)) and complications were evaluated and compared. RESULT: There were no significantly difference in baseline characteristics, preoperative radiological parameters and clinical outcomes among three groups. LLIF + PSF group was significantly shorter in operation time than other two groups (P < 0.05), whereas significant longer hospital stay was observed in LLIF + PSF group (P < 0.05). As for radiological parameters, LLIF + PSF group had significantly improvement in SVA, CB, MC, LL and PI-LL (P < 0.05). Moreover, LLIF + PSF group achieved significantly less correction loss in SVA, CB and PT than PSO and PCO group (1.5 ± 0.7 VS 2.0 ± 0.9 VS 2.2 ± 0.8, P < 0.05; 1.0 ± 0.4 VS 1.3 ± 0.5 VS 1.1 ± 0.7, P < 0.05 and 4.2 ± 2.8 VS 7.2 ± 3.1 VS 6.0 ± 2.8, P < 0.05). Significantly recovery in VAS of back and leg, ODI score and SRS-22 were found among all groups, however, LLIF + PSF shown significant better clinical therapy maintain at follow-up visit than other two groups (P < 0.05). There were no significantly difference in complications among groups (P = 0.66). CONCLUSION: Lateral lumbar interbody fusion combined two-stage posterior screw fixation (LLIF + PSF) can achieve comparable clinical therapy for adult degeneration scoliosis as osteotomy strategies. However, furthermore more studies need be taken for verifying the effect of LLIF + PSF in the future.