1.Algorithm for brain MRI tumor detection based on improved YOLOv7
Jingyi BAI ; Yirong WU ; Xiaolong LI ; Shuifa SUN
Chinese Journal of Medical Physics 2025;42(3):336-346
Brain MRI data is characterized by large volumes and susceptibility to noise and artifacts,which pose significant challenges of improving the speed and accuracy of brain tumor detection and analysis due to the tumors'diverse types,shapes,and boundaries that are both similar and highly variable.Therefore,a series of improvements based on YOLOv7 algorithm are proposed for enhancing detection precision and speed:(1)employing partial convolution during feature extraction to reduce the model's parameters and improve overall detection speed;(2)in light of the complex variability of brain tumors,introducing a three-dimensional spatial attention mechanism during feature extraction to enhance the model's focus on critical image features;(3)replacing the original IoU loss function with WIoU to increase the attention to medium-quality anchor boxes during bounding box regression for further improving detection accuracy.Experiments conducted on two public brain tumor datasets,Brain_Tumor and Glioma_of_test,show that the improved model achieves mAP of 96.9%and 92.8%,which are 1.4%and 2.4%higher than the original YOLOv7 model,and the frames per second reach 162.7 and 158.1,showing improvements of 6.4 and 18.2,respectively.These enhancements enable more effective detection of brain tumors in MRI images.
2.Algorithm for brain MRI tumor detection based on improved YOLOv7
Jingyi BAI ; Yirong WU ; Xiaolong LI ; Shuifa SUN
Chinese Journal of Medical Physics 2025;42(3):336-346
Brain MRI data is characterized by large volumes and susceptibility to noise and artifacts,which pose significant challenges of improving the speed and accuracy of brain tumor detection and analysis due to the tumors'diverse types,shapes,and boundaries that are both similar and highly variable.Therefore,a series of improvements based on YOLOv7 algorithm are proposed for enhancing detection precision and speed:(1)employing partial convolution during feature extraction to reduce the model's parameters and improve overall detection speed;(2)in light of the complex variability of brain tumors,introducing a three-dimensional spatial attention mechanism during feature extraction to enhance the model's focus on critical image features;(3)replacing the original IoU loss function with WIoU to increase the attention to medium-quality anchor boxes during bounding box regression for further improving detection accuracy.Experiments conducted on two public brain tumor datasets,Brain_Tumor and Glioma_of_test,show that the improved model achieves mAP of 96.9%and 92.8%,which are 1.4%and 2.4%higher than the original YOLOv7 model,and the frames per second reach 162.7 and 158.1,showing improvements of 6.4 and 18.2,respectively.These enhancements enable more effective detection of brain tumors in MRI images.
3.Clinical application of modified alar reduction with external incision
Peidong GAN ; Shuifa YANG ; Yangyan YI ; Juanmin YANG ; Zhaohui WANG ; Shu WU
Chinese Journal of Plastic Surgery 2020;36(9):1034-1038
Objective:To investigate the effect of modified alar reduction with external incision to correct alar hypertrophy.Methods:From January 2017 to January 2019, 16 patients(1 male and 15 females, aged 21 to 39 with alar hypertrophy were treated in the plastic surgery department of the Second Affiliated Hospital of Nanchang University. Modified alar reduction with external incision were applied. In order to rotate the free alar lobules, the incision was extended in nasal lobules to the vestibular floor and remove part of the vestibular tissue of the alar lobules during the operation. Then the free alar was moved into the nostril to make the alar junction shift inward and upward, and reposition the alar junction to correct the alar hypertrophy and the wide nasal base. Photos of patients in frontal, side, and basal view before operation, 1 month, 6 months after operation. Intercanthal distance (ICD)、interinter-alar width (IW)、nasal base width (BW) were measured. The ratios of IW, BW and ICD before operation, 1 month, and 6 months after operation, and the narrowing rate of IW and BW at 1 month and 6 months after operation were summarized. The incision scar was evaluated with reference to the Vancouver Scar Scale. Normally distributed variables were compared using an paired t test. Nonparametric continuous variables were compared using Wilcoxon rank sum test. When P<0.05, the difference is considered statistically significant. Results:Sixteen patients were followed up for 6 to 12 months, averaged of 8 months. The IW/ICD of 16 patients at preoperation, after operation 1 month and 6 months were 1.160±0.080, 1.049±0.047 (0.110±0.049 decrease than before operation) and 1.038±0.047 (0.120±0.049 decrease than before operation). The differences were statistically significant ( P<0.05). The IW constriction rates were 9.3% at 1 month after operation and 10.2% at 6 months after operation. BW/ICD at preoperation, after operation 1 month and 6 months were 1.035±0.047, 0.960±0.039(0.072±0.019 smaller than preoperation), and 0.950±0.034(0.079±0.020 smaller than preoperation). Compared with preoperative data, the difference was statistically significant ( P<0.05). The BW reduction rates were 7.0% at 1 month after operation and 7.6% at 6 months after operation. The Vancouver Scar Scale score was 3(2.25, 3) at 1 month after operation, 1(0.25, 1) at 3 months after operation and 1(0, 1) at 6 months after operation. The differences were statistically significant ( P<0.05). There was a statistically significant difference between 3 months after surgery and 1 month after surgery ( Z=-3.472, P=0.001). There was no statistically significant difference between 6 months after surgery and 3 months after surgery ( Z=-1.414, P=0.157). All patients had no significant postoperative complications such as incision infection, asymmetry of nasal alae, obstruction of nasal ventilation, etc. Postoperative alar and nasal base profiles were significantly improved. Conclusions:Modified alar reduction with external incision can effectively treat alar hypertrophy without obvious postoperative complications. It is a good operation to correct alar hypertrophy.
4.Clinical application of modified alar reduction with external incision
Peidong GAN ; Shuifa YANG ; Yangyan YI ; Juanmin YANG ; Zhaohui WANG ; Shu WU
Chinese Journal of Plastic Surgery 2020;36(9):1034-1038
Objective:To investigate the effect of modified alar reduction with external incision to correct alar hypertrophy.Methods:From January 2017 to January 2019, 16 patients(1 male and 15 females, aged 21 to 39 with alar hypertrophy were treated in the plastic surgery department of the Second Affiliated Hospital of Nanchang University. Modified alar reduction with external incision were applied. In order to rotate the free alar lobules, the incision was extended in nasal lobules to the vestibular floor and remove part of the vestibular tissue of the alar lobules during the operation. Then the free alar was moved into the nostril to make the alar junction shift inward and upward, and reposition the alar junction to correct the alar hypertrophy and the wide nasal base. Photos of patients in frontal, side, and basal view before operation, 1 month, 6 months after operation. Intercanthal distance (ICD)、interinter-alar width (IW)、nasal base width (BW) were measured. The ratios of IW, BW and ICD before operation, 1 month, and 6 months after operation, and the narrowing rate of IW and BW at 1 month and 6 months after operation were summarized. The incision scar was evaluated with reference to the Vancouver Scar Scale. Normally distributed variables were compared using an paired t test. Nonparametric continuous variables were compared using Wilcoxon rank sum test. When P<0.05, the difference is considered statistically significant. Results:Sixteen patients were followed up for 6 to 12 months, averaged of 8 months. The IW/ICD of 16 patients at preoperation, after operation 1 month and 6 months were 1.160±0.080, 1.049±0.047 (0.110±0.049 decrease than before operation) and 1.038±0.047 (0.120±0.049 decrease than before operation). The differences were statistically significant ( P<0.05). The IW constriction rates were 9.3% at 1 month after operation and 10.2% at 6 months after operation. BW/ICD at preoperation, after operation 1 month and 6 months were 1.035±0.047, 0.960±0.039(0.072±0.019 smaller than preoperation), and 0.950±0.034(0.079±0.020 smaller than preoperation). Compared with preoperative data, the difference was statistically significant ( P<0.05). The BW reduction rates were 7.0% at 1 month after operation and 7.6% at 6 months after operation. The Vancouver Scar Scale score was 3(2.25, 3) at 1 month after operation, 1(0.25, 1) at 3 months after operation and 1(0, 1) at 6 months after operation. The differences were statistically significant ( P<0.05). There was a statistically significant difference between 3 months after surgery and 1 month after surgery ( Z=-3.472, P=0.001). There was no statistically significant difference between 6 months after surgery and 3 months after surgery ( Z=-1.414, P=0.157). All patients had no significant postoperative complications such as incision infection, asymmetry of nasal alae, obstruction of nasal ventilation, etc. Postoperative alar and nasal base profiles were significantly improved. Conclusions:Modified alar reduction with external incision can effectively treat alar hypertrophy without obvious postoperative complications. It is a good operation to correct alar hypertrophy.
5.How long can the effect of rifampicin on the plasma concentration of voriconazole last?
Zhiqiang LIN ; Tingting CHEN ; Shuifa WU ; Limian HONG
Adverse Drug Reactions Journal 2020;22(10):573-576
A 56-year-old male patient with tuberculosis complicated by infection did not get better after treatment with moxifloxacin combined with rifampicin, isoniazid, ethambutol, and pyrazinamide. The invasive pulmonary aspergillosis was diagnosed by bronchoalveolar lavage fluid culture and detection of 1, 3-beta-D-glucan, galactomannan antigen, and Aspergillus antibody. Moxifloxacin and anti-tuberculosis drugs were discontinued and an IV infusion of voriconazole (the dose was 300 mg once per 12 hours on the first day, the maintenance dose was 150 mg once per 12 hours) was given. On the 5th day of medication, the plasma concentration of voriconazole was zero. The consultation pharmacist considered that the voriconazole plasma concentration was related to rifampicin. The next day, the dose of voriconazole was adjusted to 200 mg once per 12 hours. Two days later, the plasma concentration of voriconazole was 1.3 mg/L. The patient′s cough and expectoration were relieved, but he still repeatedly developed high fever. On the 9th day of increase of voriconazole dose, intravenous infusion of methylprednisolone 40 mg once daily was given because connective tissue disease could not be excluded by consulting rheumatologists. The patient′s temperature returned to normal the next day and the plasma concentration of voriconazole was 3.0 mg/L. Clinical pharmacists and physicians reviewed the literature and reached a consensus: the induction effect of rifampicin on drug metabolizing enzymes in the body can last for 7-10 days or even longer after discontinuation of the drug, the monitoring of plasma concentration of voriconazole should be strengthened in patients treated with rifampicin sequential voriconazole, and the dose of voriconazole should be adjusted according to the plasma concentration until the induction effect of rifampicin on drug metabolizing enzymes completely disappears and the plasma concentration of voriconazole reaches a steady state.
6.How long can the effect of rifampicin on the plasma concentration of voriconazole last?
Zhiqiang LIN ; Tingting CHEN ; Shuifa WU ; Limian HONG
Adverse Drug Reactions Journal 2020;22(10):573-576
A 56-year-old male patient with tuberculosis complicated by infection did not get better after treatment with moxifloxacin combined with rifampicin, isoniazid, ethambutol, and pyrazinamide. The invasive pulmonary aspergillosis was diagnosed by bronchoalveolar lavage fluid culture and detection of 1, 3-beta-D-glucan, galactomannan antigen, and Aspergillus antibody. Moxifloxacin and anti-tuberculosis drugs were discontinued and an IV infusion of voriconazole (the dose was 300 mg once per 12 hours on the first day, the maintenance dose was 150 mg once per 12 hours) was given. On the 5th day of medication, the plasma concentration of voriconazole was zero. The consultation pharmacist considered that the voriconazole plasma concentration was related to rifampicin. The next day, the dose of voriconazole was adjusted to 200 mg once per 12 hours. Two days later, the plasma concentration of voriconazole was 1.3 mg/L. The patient′s cough and expectoration were relieved, but he still repeatedly developed high fever. On the 9th day of increase of voriconazole dose, intravenous infusion of methylprednisolone 40 mg once daily was given because connective tissue disease could not be excluded by consulting rheumatologists. The patient′s temperature returned to normal the next day and the plasma concentration of voriconazole was 3.0 mg/L. Clinical pharmacists and physicians reviewed the literature and reached a consensus: the induction effect of rifampicin on drug metabolizing enzymes in the body can last for 7-10 days or even longer after discontinuation of the drug, the monitoring of plasma concentration of voriconazole should be strengthened in patients treated with rifampicin sequential voriconazole, and the dose of voriconazole should be adjusted according to the plasma concentration until the induction effect of rifampicin on drug metabolizing enzymes completely disappears and the plasma concentration of voriconazole reaches a steady state.
7.Effect of Schwann cell-derived neurotrophic factor on the biological characteristics of skeletal satellite cells in rats
Jiang WU ; Min ZHU ; Chongtao ZHU ; Bin CHEN ; Xinmin XU ; Yongqin XU ; Yangjun OU ; Hua LIAO ; Xiaozhong QIU ; Jiakai ZHU ; Shuifa PANG
Chinese Journal of Microsurgery 2012;35(4):299-302
Objective To study the effects of Schwann cell-derived neurotrophic factor(SDNF) on myoblast stem cells(called satellite cells,SCs) in vitro. Methods After setting up SCs culture system in vitro, SCs which treated with various SDNF concentrations culture medium were dynamically evaluated by cell morphology,MTT growth curve and fusion rate. Results The ability of SCs preceding their participation in muscle repair include proliferation and differentiation, 200 ng/ml SDNF stimulated cell proliferation more than the other medium,but 50 ng/ml,100 ng/ml,200 ng/ml,400 ng/ml SDNF made SCs differentiation significantly for their high myotube fusion rate. Conclusion SDNF can regulate the proliferation and differentiation of rat skeletal satellite cellsin vitro,but in differentiation significantly.SDNF might play a role in slowing down denervated muscle atrophy.

Result Analysis
Print
Save
E-mail