METHODS: We conducted a meta-analysis to identify relevant randomized controlled trials involving infrapatellar fat pad resection and infrapatellar fat pad preservation during total knee arthroplasty in electronic databases, including Web of Science, Embase, PubMed, Cochrane Controlled Trials Register, Cochrane Library, Highwire, CBM, CNKI, VIP, and Wanfang database, up to March 2020.
RESULTS: Nine randomized controlled trials, involving 783 TKAs (722 patients), were included in the systematic review. Outcome measures included patellar tendon length (PTL), Insall-Salvati ratio (ISR), rate of anterior knee pain, Knee Society Scores (KSS), and knee range of motion. The meta-analysis identified a trend toward the shortening of the patellar tendon with IPFP resection at 6 months (P = 0.0001) and 1 year (P = 0.001). We found no statistical difference in ISR (P = 0.87), rate of anterior knee pain within 6 months (p = 0.45) and 1 year (p = 0.38), KSS at 1 year (p = 0.77), and knee range of motion within 6 months (p = 0.61) and 1 year (0.46).
CONCLUSION: Based on the available level I evidence, we were unable to conclude that one surgical technique of IPFP can definitively be considered superior over the other. More adequately powered and better-designed randomized controlled trial (RCT) studies with long-term follow-up are required to produce evidence-based guidelines regarding IPFP resection.
METHODS: In this study, we propose a multi-view secondary input residual (MV-SIR) convolutional neural network model for 3D lung nodule segmentation using the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset of chest computed tomography (CT) images. Lung nodule cubes are prepared from the sample CT images. Further, from the axial, coronal, and sagittal perspectives, multi-view patches are generated with randomly selected voxels in the lung nodule cubes as centers. Our model consists of six submodels, which enable learning of 3D lung nodules sliced into three views of features; each submodel extracts voxel heterogeneity and shape heterogeneity features. We convert the segmentation of 3D lung nodules into voxel classification by inputting the multi-view patches into the model and determine whether the voxel points belong to the nodule. The structure of the secondary input residual submodel comprises a residual block followed by a secondary input module. We integrate the six submodels to classify whether voxel points belong to nodules, and then reconstruct the segmentation image.
RESULTS: The results of tests conducted using our model and comparison with other existing CNN models indicate that the MV-SIR model achieves excellent results in the 3D segmentation of pulmonary nodules, with a Dice coefficient of 0.926 and an average surface distance of 0.072.
CONCLUSION: our MV-SIR model can accurately perform 3D segmentation of lung nodules with the same segmentation accuracy as the U-net model.