Objective:To investigate the clinical effect of modified closed negative pressure suction technique combined with flap transplantation on the treatment of deep chronic refractory wounds.Methods:During March of 2015 to...Objective:To investigate the clinical effect of modified closed negative pressure suction technique combined with flap transplantation on the treatment of deep chronic refractory wounds.Methods:During March of 2015 to April of 2018,52 cases of patients with deep chronic refractory wounds were selected as research objects.They were divided into the control group and the treatment group by use of the random number table method,with 26 cases in each group.Among them,the control group was given conventional debridement combined with flap reconstruction,and the treatment group was treated with modified closed negative pressure suction technique combined with flap transplantation to observe the clinical effect.Results:(1)According to the analysis on the effect of flap transplantation,the excellent and good rate of the treatment group was 92.3%,and in the control group,it was 76.9%(p<0.05).(2)According to the statistics,the incidence of complications in the treatment group was lower than that in the control group(p<0.05).Conclusions:Modified closed negative pressure suction technique combined with flap transplantation has a good effect on the treatment of deep chronic refractory wounds with fewer complications.展开更多
目的:糖尿病足溃疡的测量是临床诊断的重要一环,高精度测量与评估是高效管理的保障。目前临床上缺乏精确、便捷的测量工具。近年来人工智能技术在图形分割与识别领域中彰显了一定的潜力。本研究旨在基于深度学习方法对糖尿病足溃疡影像...目的:糖尿病足溃疡的测量是临床诊断的重要一环,高精度测量与评估是高效管理的保障。目前临床上缺乏精确、便捷的测量工具。近年来人工智能技术在图形分割与识别领域中彰显了一定的潜力。本研究旨在基于深度学习方法对糖尿病足溃疡影像进行分析,构建糖尿病足溃疡智能测量模型并对其进行初步验证。方法:选取1 042例糖尿病足溃疡的图像,对溃疡边缘及不同的颜色区域进行人工标注,其中782张作为训练数据集,260张作为测试数据集。采用Mask RCNN溃疡组织颜色语义分割及RetinaNet标尺数字刻度目标检测来建立模型,将训练数据集输入模型并进行迭代。利用测试数据集验证智能测量模型。结果:基于深度学习建立了糖尿病足溃疡的智能测量模型,训练集和测试集组织颜色区域分割的mAP@.5IOU(mean average precision@.5 intersection over union)分别为87.9%和63.9%,标尺刻度数字检测的mAP@.5IOU分别为96.5%和83.4%。以测试集的人工测量结果为参照,智能测量结果的平均误差约3 mm。结论:糖尿病足溃疡智能测量模型测量糖尿病足溃疡具有较高的精确度及良好的鲁棒性,未来的研究可采用更大规模的数据样本对模型做进一步优化。展开更多
文摘Objective:To investigate the clinical effect of modified closed negative pressure suction technique combined with flap transplantation on the treatment of deep chronic refractory wounds.Methods:During March of 2015 to April of 2018,52 cases of patients with deep chronic refractory wounds were selected as research objects.They were divided into the control group and the treatment group by use of the random number table method,with 26 cases in each group.Among them,the control group was given conventional debridement combined with flap reconstruction,and the treatment group was treated with modified closed negative pressure suction technique combined with flap transplantation to observe the clinical effect.Results:(1)According to the analysis on the effect of flap transplantation,the excellent and good rate of the treatment group was 92.3%,and in the control group,it was 76.9%(p<0.05).(2)According to the statistics,the incidence of complications in the treatment group was lower than that in the control group(p<0.05).Conclusions:Modified closed negative pressure suction technique combined with flap transplantation has a good effect on the treatment of deep chronic refractory wounds with fewer complications.
文摘目的:糖尿病足溃疡的测量是临床诊断的重要一环,高精度测量与评估是高效管理的保障。目前临床上缺乏精确、便捷的测量工具。近年来人工智能技术在图形分割与识别领域中彰显了一定的潜力。本研究旨在基于深度学习方法对糖尿病足溃疡影像进行分析,构建糖尿病足溃疡智能测量模型并对其进行初步验证。方法:选取1 042例糖尿病足溃疡的图像,对溃疡边缘及不同的颜色区域进行人工标注,其中782张作为训练数据集,260张作为测试数据集。采用Mask RCNN溃疡组织颜色语义分割及RetinaNet标尺数字刻度目标检测来建立模型,将训练数据集输入模型并进行迭代。利用测试数据集验证智能测量模型。结果:基于深度学习建立了糖尿病足溃疡的智能测量模型,训练集和测试集组织颜色区域分割的mAP@.5IOU(mean average precision@.5 intersection over union)分别为87.9%和63.9%,标尺刻度数字检测的mAP@.5IOU分别为96.5%和83.4%。以测试集的人工测量结果为参照,智能测量结果的平均误差约3 mm。结论:糖尿病足溃疡智能测量模型测量糖尿病足溃疡具有较高的精确度及良好的鲁棒性,未来的研究可采用更大规模的数据样本对模型做进一步优化。
