After extracting definition measurements by different focus functions from the images, a novel autofocus algorithm which combines them with principal component analysis (PCA) and considers the first principal component as the final measurement, is presented in this paper. The experiment results with 70 groups of images show that this algorithm increases the difference between the definition measurements of the images and provides higher focusing accuracy in comparison with other single ones.
Algorithms ; Image Processing, Computer-Assisted ; methods ; Microscopy ; instrumentation ; methods ; Principal Component Analysis

This article used support vector machine (SVM) algorithm to recognize the particles in urine sediment in this paper. After feature extraction, cross-validation method and the contour chart of the accuracy were implemented to select the kernel function and the parameters of SVM, and according to the characteristics of SVM classifier and sample data, Multi-SVMs with two-level-classifier was successfully designed and A classification matrix was eventually obtained. The evaluation by using clinical data and comparative results with the artificial neural network have demonstrated that the proposed algorithm gets better results.
Algorithms ; Artificial Intelligence ; Humans ; Particle Size ; Pattern Recognition, Automated ; methods ; Urine ; chemistry

Objective:To investigate the effect of fat mass index (FMI) on early recovery after total knee arthroplasty (TKA).Methods:Patients who underwent primary unilateral TKA in Xi'an Honghui Hospital from July 2020 to July 2021 were retrospectively analyzed. The preoperative body composition was measured by dual energy X-ray absorptiometry and the FMI was calculated. Patients were divided into normal group (male: 3.0-6.0 kg/m 2; female: 5.0-9.0 kg/m 2), overweight group (male: 6.1-9.0 kg/m 2; female: 9.1-13.0 kg/m 2), and obese group (male: >9 kg/m 2; female: >13 kg/m 2) according to level of FMI, and the operation time, blood loss, and incidence of postoperative complications were collected. Multifactorial analysis of the effect of FMI on early recovery after TKA was performed using a generalized linear model. Draw the receiver operating characteristics (ROC) curve of BMI and FMI on the predicted effect of postoperative Western Ontario and McMaster Universities (WOMAC) osteoarthritis index scores and Knee Society Score (KSS) to compare the effect of FMI with BMI on early recovery after TKA. Results:A total of 100 patients were included in the study, 24 males and 76 females, aged 65.0±8.2 years (range, 42-81 years). There were 15 cases in normal group, 55 cases in overweight group and 30 cases in obese group. All patients successfully completed the operation and were followed up for 3.15±0.72 months (range, 2.8-3.2 months). The WOMAC scores of the obese group at 2 weeks, 1 and 2 months postoperative were 34.57±3.68, 22.03±2.79, and 15.77±2.96, which were greater than those of the normal group (28.73 ±2.58, 19.07±2.71, 12.27±3.10), as well as the overweight group (30.05±4.09, 19.33±2.42, 14.84±2.42), with statistically significant differences ( P<0.05). The KSS scores of the obese group at postoperative 1 and 2 months were 68.83±5.52 and 81.17±4.49, which were lower than those of the normal group (77.33±5.63, 87.33±4.17), as well as the overweight group (72.64±5.43, 83.73 ±5.02), with statistically significant differences ( P<0.05). The WOMAC score, KSS score, and postoperative complications at 2 months postoperatively were selected as outcome indicators to plot the ROC curve, and the ROC curve for the WOMAC score at 2 months postoperatively showed an area under the curve corresponding to FMI of 0.744 (95% CI: 0.54, 0.82), which was greater than that of BMI [0.624 (95% CI: 0.51, 0.74)], and the difference was statistically significant ( Z=2.19, P=0.021). The ROC curve for the KSS score at 2 months postoperatively showed an area under the curve corresponding to FMI of 0.718 (95% CI: 0.62, 0.82), which was greater than that of BMI [0.612 (95% CI: 0.52, 0.74)], with a statistically significant difference ( Z=2.58, P=0.016). The ROC curve for postoperative complications showed an area under the curve of 0.639 (95% CI: 0.41, 0.88) for FMI and 0.605 (95% CI: 0.37, 0.84) for BMI, with no statistically significant difference ( Z=0.48, P=0.632). Conclusion:The greater the FMI the poorer the early functional recovery after initial TKA, and FMI is more valuable than BMI in predicting the early functional recovery.

Objective:To investigate the effect of early postoperative enteral nutrition (EEN) on laparoscopic and open radical gastrectomy.Methods:From January 2015 to December 2016,68 patients with gastric cancer admited in Anqing Hospital,Anhui Medical University,were randomized into laparoscopic group (33 cases) and open group (35 cases).The following parameters were collected:(1) Surgical outcomes and complications;(2) EEN tolerance;(3) postoperative nutritional status;(4) starting time of postoperative chemotherapy.Results:There was no significant difference between groups in terms of operation time,number of lymph node,postoperative complications such as anastomotic fistula,pulmonary infection,incision infection (P ＞ 0.05);whereas the intraoperative blood loss was significantly less in laparoscopic group (P ＜ 0.01).(2) EEN tolerance:Postoperative discomforts,such as abdominal distension,diarrhea and other symptoms occurred significantly less in laparoscopic group (P ＜ 0.01),and time for TEN is significantly shorter (P ＜ 0.01).(3) Postoperative nutritional status:On the 7th day after operation,the nutrition status of the laparoscopic group improved earlier.There was significant difference regarding the detected blood level of prealbumin and C-reactive protein between the two groups (P ＜ 0.01).On the 14th day after operation,the nutritional status of the laparoscopic group improved significantly.The body weight,the right upper arm muscle circumference and the albumin were significantly different between two groups (P ＜ 0.05).(4) The number of cases receiving chemotherapy in patients with advanced gastric cancer was significantly higher in laparotomy group than that with open distal gastrectomy.Conclusion:Laparoscopic surgery for gastric cancer reduces surgical trauma,and leads to better EEN tolerance and earlier achieved TEN,which is conducive to improving postoperative nutritional status,as well as providing good conditions for adjuvant chemotherapy.

BackgroundOne of the main aims of the updated Prostate Imaging Reporting and Data System Version 2 (PI-RADS v2) is to diminish variation in the interpretation and reporting of prostate imaging, especially among readers with varied experience levels. This study aimed to retrospectively analyze diagnostic consistency and accuracy for prostate disease among six radiologists with different experience levels from a single center and to evaluate the diagnostic performance of PI-RADS v2 scores in the detection of clinically significant prostate cancer (PCa).

MethodsFrom December 2014 to March 2016, 84 PCa patients and 99 benign prostatic shyperplasia patients who underwent 3.0T multiparametric magnetic resonance imaging before biopsy were included in our study. All patients received evaluation according to the PI-RADS v2 scale (1-5 scores) from six blinded readers (with 6 months and 2, 3, 4, 5, or 17 years of experience, respectively, the last reader was a reviewer/contributor for the PI-RADS v2). The correlation among the readers' scores and the Gleason score (GS) was determined with the Kendall test. Intra-/inter-observer agreement was evaluated using κ statistics, while receiver operating characteristic curve and area under the curve analyses were performed to evaluate the diagnostic performance of the scores.

ResultsBased on the PI-RADS v2, the median κ score and standard error among all possible pairs of readers were 0.506 and 0.043, respectively; the average correlation between the six readers' scores and the GS was positive, exhibiting weak-to-moderate strength (r = 0.391, P = 0.006). The AUC values of the six radiologists were 0.883, 0.924, 0.927, 0.932, 0.929, and 0.947, respectively.

ConclusionThe inter-reader agreement for the PI-RADS v2 among the six readers with different experience is weak to moderate. Different experience levels affect the interpretation of MRI images.