The convolutional neural network (CNN) could be used on computer-aided diagnosis of lung tumor with positron emission tomography (PET)/computed tomography (CT), which can provide accurate quantitative analysis to compensate for visual inertia and defects in gray-scale sensitivity, and help doctors diagnose accurately. Firstly, parameter migration method is used to build three CNNs (CT-CNN, PET-CNN, and PET/CT-CNN) for lung tumor recognition in CT, PET, and PET/CT image, respectively. Then, we aimed at CT-CNN to obtain the appropriate model parameters for CNN training through analysis the influence of model parameters such as epochs, batchsize and image scale on recognition rate and training time. Finally, three single CNNs are used to construct ensemble CNN, and then lung tumor PET/CT recognition was completed through relative majority vote method and the performance between ensemble CNN and single CNN was compared. The experiment results show that the ensemble CNN is better than single CNN on computer-aided diagnosis of lung tumor.
ObjectiveTo explore the independent risk factors for postoperative retention of urinary catheters in the ward of lung tumor patients due to urinary retention under the concept of enhanced recovery after surgery (ERAS).MethodsSeventy-five patients with lung tumors who had urinary catheters left in the postoperative ward between June 2019 and August 2019 were selected as a case group, and 75 patients with lung tumors who did not have urinary catheters in the perioperative period as a control group. Independent risk factors for indwelling urinary catheters in the postoperative ward were screened by univariate and multiple-variate logistic stepwise regression analysis.ResultsThere were 45 males and 30 females in the case group with an average age of 55.33±10.78 years, 28 males and 47 females in the control group with an average age of 57.12±10.06 years. Univariate analysis showed that gender, operative time>2 h, intraoperative fluid volume≥1 200 mL, and fluid volume within 6 h of returning to the ward after surgery>1 200 mL were associated with the occurrence of indwelling urinary catheters in patients with lung tumors in postoperative wards (P<0.05). Multiple-variate logistic regression showed that male (OR=2.311, 95%CI 1.173-4.552, P=0.015), infusion volume within 6 h of returning to the ward after surgery>1 200 mL (OR=2.491, 95%CI 1.149-5.401, P=0.021) and intraoperative infusion volume≥1 200 mL (OR=2.105, 95%CI 1.022-4.340, P=0.044) were independent risk factors for postoperative retention of urinary catheters in patients with lung tumors.ConclusionThe occurrence of indwelling urinary catheter in lung tumor patients under the ERAS concept is the result of a combination of factors, and patients who are male, have infusion volume>1 200 mL within 6 h of returning to the ward after surgery, and have intraoperative infusion volume≥1 200mL are the high-risk group for postoperative ward indwelling urinary catheter, and health care personnel should strengthen the assessment and observation, provide targeted health education, appropriately control the perioperative fluid volume, and take other measures to reduce the occurrence of indwelling urinary catheters due to urinary retention postoperatively in ward.