With the emergence of deep learning techniques based on convolutional neural networks, artificial intelligence (AI) has driven transformative developments in the field of medical image analysis. Recently, large language models (LLMs) such as ChatGPT have also started to achieve distinction in this domain. Increasing research shows the undeniable role of AI in reshaping various aspects of medical image analysis, including processes such as image enhancement, segmentation, detection in image preprocessing, and postprocessing related to medical diagnosis and prognosis in clinical settings. However, despite the significant progress in AI research, studies investigating the recent advances in AI technology in the aforementioned aspects, the changes in research hotspot trajectories, and the performance of studies in addressing key clinical challenges in this field are limited. This article provides an overview of recent advances in AI for medical image analysis and discusses the methodological profiles, advantages, disadvantages, and future trends of AI technologies.
Artificial Intelligence ; Humans ; Image Processing, Computer-Assisted/methods* ; Neural Networks, Computer ; Deep Learning ; Diagnostic Imaging/methods*

Objective:To investigate the clinical outcomes of using autologous mandibular outer cortex "sandwich" grafting to augment mandible for correcting lower facial asymmetry with normal occlusal relationships.Methods:A retrospective analysis was conducted on the clinical data of patients with lower facial asymmetry treated at the Department of Plastic Surgery, the Affiliated Friendship Plastic Surgery Hospital of Nanjing Medical University, from January 2016 to December 2019. Preoperative cone-beam CT (CBCT) scans of the maxillofacial region were obtained to acquire three-dimensional data of the maxillofacial skeleton. Computer-aided design was used to determine the osteotomy range of the mandibular outer cortex and design osteotomy guide template. The outer cortex of the larger mandibular side (donor site) was harvested according to the osteotomy guide template and sectioned. The segmented mandibular outer cortex was then contoured to match the arc of the recipient side’s mandibular outer cortex and fixed to the inner side of the recipient mandibular outer cortex, thus increasing the width and thickness of the expanded mandible. Follow-up was conducted at 7th day and 6 months postoperatively, CBCT scan was performed to measure the changes in ramus height (Co-Go), mandibular body length (Go-Me), and mandibular outer cortex thickness, and volume, and the patient satisfaction with facial appearance (1 to 5 points, with higher scores indicating higher satisfaction), were assessed to evaluate surgical outcomes. Statistical analysis was performed using SPSS 12.0 software. Paired t-tests were used to compare patient satisfaction scores preoperatively and six months postoperatively. Repeated measurement ANOVA was used to compare Co-Go and Go-Me measurements preoperatively, 7th day, and 6 months postoperatively. If a statistically significant difference is found, further analysis using post-hoc testing(Tukey’s HSD test) will be conducted to examine the data. Results:Sixteen patients with lower facial asymmetry were included, comprising of 5 males and 11 females, aged 18 to 40 years, with an average age of 25.2 years. Surgical method included contralateral mandibular outer cortex "sandwich" grafting to the expanded mandible in 9 cases and simultaneous genioplasty in 7 cases. Follow-up ranged from 6 months to 5 years, with an average follow-up of 18.6 months. All patients experienced numbness of the lower lip postoperatively, which resolved within six months, and no severe complications occurred. The symmetry of lower facial contour improved significantly and remained stable. Patient satisfaction score for facial appearance increased from (1.63±0.62) points preoperatively to (4.19±0.75) points six months postoperatively( P<0.01). The differences in Co-Go on the donor side and Go-Me on the recipient side across the three time points(preoperatively, 7th day and 6 months postoperatively) were not statistically significant(all P>0.05). However, the differences in Go-Me on the donor side and Co-Go on the recipient side across the three time points were statistically significant(all P<0.05). On the donor side, the mandibular outer cortex thickness decreased by a maximum of 6 mm on 7th day postoperatively and increased by a maximum of 2 mm at 6 months postoperatively compared to 7th day. On the recipient side, mandibular outer cortex thickness increased by a maximum of 6 mm on 7th day postoperatively and decreased by a maximum of 2 mm at six months postoperatively compared to 7th day. The volume of the mandibular outer cortex on the recipient side increased by (4 415.94±1 017.21)mm 3 at 7th day postoperatively compared to preoperatively, and decreased by (202.63±300.85)mm 3 at 6 months postoperatively. Conclusion:For lower facial asymmetrical with normal occlusal relationships and no occlusal plane deviation, contralateral mandibular outer cortex "sandwich" bone grafting can effectively increase the width and volume of the mandible on the grafted side, achieving favorable clinical outcomes.

Objective:To investigate the clinical outcomes of using autologous mandibular outer cortex "sandwich" grafting to augment mandible for correcting lower facial asymmetry with normal occlusal relationships.Methods:A retrospective analysis was conducted on the clinical data of patients with lower facial asymmetry treated at the Department of Plastic Surgery, the Affiliated Friendship Plastic Surgery Hospital of Nanjing Medical University, from January 2016 to December 2019. Preoperative cone-beam CT (CBCT) scans of the maxillofacial region were obtained to acquire three-dimensional data of the maxillofacial skeleton. Computer-aided design was used to determine the osteotomy range of the mandibular outer cortex and design osteotomy guide template. The outer cortex of the larger mandibular side (donor site) was harvested according to the osteotomy guide template and sectioned. The segmented mandibular outer cortex was then contoured to match the arc of the recipient side’s mandibular outer cortex and fixed to the inner side of the recipient mandibular outer cortex, thus increasing the width and thickness of the expanded mandible. Follow-up was conducted at 7th day and 6 months postoperatively, CBCT scan was performed to measure the changes in ramus height (Co-Go), mandibular body length (Go-Me), and mandibular outer cortex thickness, and volume, and the patient satisfaction with facial appearance (1 to 5 points, with higher scores indicating higher satisfaction), were assessed to evaluate surgical outcomes. Statistical analysis was performed using SPSS 12.0 software. Paired t-tests were used to compare patient satisfaction scores preoperatively and six months postoperatively. Repeated measurement ANOVA was used to compare Co-Go and Go-Me measurements preoperatively, 7th day, and 6 months postoperatively. If a statistically significant difference is found, further analysis using post-hoc testing(Tukey’s HSD test) will be conducted to examine the data. Results:Sixteen patients with lower facial asymmetry were included, comprising of 5 males and 11 females, aged 18 to 40 years, with an average age of 25.2 years. Surgical method included contralateral mandibular outer cortex "sandwich" grafting to the expanded mandible in 9 cases and simultaneous genioplasty in 7 cases. Follow-up ranged from 6 months to 5 years, with an average follow-up of 18.6 months. All patients experienced numbness of the lower lip postoperatively, which resolved within six months, and no severe complications occurred. The symmetry of lower facial contour improved significantly and remained stable. Patient satisfaction score for facial appearance increased from (1.63±0.62) points preoperatively to (4.19±0.75) points six months postoperatively( P<0.01). The differences in Co-Go on the donor side and Go-Me on the recipient side across the three time points(preoperatively, 7th day and 6 months postoperatively) were not statistically significant(all P>0.05). However, the differences in Go-Me on the donor side and Co-Go on the recipient side across the three time points were statistically significant(all P<0.05). On the donor side, the mandibular outer cortex thickness decreased by a maximum of 6 mm on 7th day postoperatively and increased by a maximum of 2 mm at 6 months postoperatively compared to 7th day. On the recipient side, mandibular outer cortex thickness increased by a maximum of 6 mm on 7th day postoperatively and decreased by a maximum of 2 mm at six months postoperatively compared to 7th day. The volume of the mandibular outer cortex on the recipient side increased by (4 415.94±1 017.21)mm 3 at 7th day postoperatively compared to preoperatively, and decreased by (202.63±300.85)mm 3 at 6 months postoperatively. Conclusion:For lower facial asymmetrical with normal occlusal relationships and no occlusal plane deviation, contralateral mandibular outer cortex "sandwich" bone grafting can effectively increase the width and volume of the mandible on the grafted side, achieving favorable clinical outcomes.

Objective:To evaluate the effectiveness of correcting breast ptosis using the rotational filling of an inferolaterally pedicled tongue-shaped parenchymal flap via a double periareolar incision.Methods:A retrospective study was conducted on 34 female patients (68 breasts) with breast ptosis treated at the Department of Plastic Surgery at the Affiliated Friendship Plastic Surgery Hospital of Nanjing Medical University from January 2016 to June 2023. The patients＇ ages ranged from 23 to 53 years, with an average of (37.4±7.9) years. All patients underwent correction of breast ptosis using an inferolaterally pedicled tongue-shaped parenchymal flap via a double periareolar incision. Pre-operative and post-operative measurements were taken to assess the corrective outcomes, including mammary base width (MBW), areola diameter (AD), nipple-to-nipple distance (NN), suprasternal notch-to-nipple distance (SSN-N), nipple-to-inframammary fold distance (N-IMF), and thoracic circumference at the nipple level (TN). Patients＇ satisfaction was assessed using the BREAST-questionnaire (BREAST-Q) module.Results:Postoperative first-stage wound healing was achieved in all 34 patients without complications such as hematoma, infection, or nipple necrosis. The follow-up period ranged from 6 to 60 months, with a median of 12 months. Early postoperative observations showed periareolar folds, which disappeared within 3 to 6 months in 31 cases, while mild periareolar folds, persisted for up to 12 months in 3 cases. Four patients reported reduced nipple sensation postoperatively. Measurements showed a statistically significant increase in TN and a reduction in NN, SSN-N, AD, N-IMF, and MBW compared to preoperative values (all P<0.001). BREAST-Q scores indicated significant improvements in satisfaction with breasts, psychosocial well-being and physical well-being, with preoperative scores of (21.6±8.9), (42.4±11.9) and (49.7±12.9) scores increasing to (82.3±8.5), (81.9±8.1) and (81.2±8.3) scores, respectively (all P<0.001). Conclusions:The double periareolar incision technique with rotational filling of an inferolaterally pedicled tongue-shaped glandular flap is a safe and effective method for correcting breast ptosis.

ObjectiveTo study the accumulation and absorption of dry matter and nutrients in Curcuma phaeocaulis from Sichuan， the origin of Curcumae Radix （tuber） and Curcumae Rhizoma （rhizome）， to explore the growth and development laws and nutrient demand characteristics of the medicinal species， and thus to lay a theoretical basis for rational fertilization. MethodThe plant growth indexes， dry matter accumulation， and nutrient content of C. phaeocaulis at different growth stages in Sichuan were measured and analyzed. ResultThis medicinal species featured the dominant growth of aboveground leaves and stems before October and growth of underground part （particularly the rhizomes and tubers） from October. During the whole growth period， the accumulation of nitrogen， phosphorus， potassium， calcium， magnesium， iron， manganese， zinc， and copper per plant was 2 450.31， 907.09， 3 171.18， 625.94， 493.38， 14.53， 2.24 ， 2.93， 0.46 mg， respectively， with the order of potassium > nitrogen > phosphorus > calcium > magnesium > iron > zinc > manganese > copper. ConclusionThe species needs sufficient potassium and nitrogen， appropriate amount of phosphorus， calcium， and magnesium， a small amount of iron， and very little zinc， manganese， and copper for growth， and potassium is particularly important. Nitrogen， phosphorus， and potassium fertilizers supply macroelements and nitrogen fertilizer should be supplemented at seedling stage， leafy stage， early rhizome expansion stage， tuber expansion stage， and the second expansion stage of rhizome. Phosphorus and potassium fertilizers should be applied at seedling stage， tuber expansion stage， secondary expansion stage of rhizome， and dry matter accumulation stage of tuber and rhizome. At seedling stage， leafy stage， early rhizome expansion stage， tuber expansion stage， and the second expansion stage of rhizome， a variety of medium and trace elements-containing foliar fertilizers should be used.

Objective:To establish autoverification rules for coagulation tests in multicenter cooperative units, in order to reduce workload for manual review of suspected results and shorten turnaround time (TAT) of test reports, while ensure the accuracy of results.Methods:A total of 14 394 blood samples were collected from fourteen hospitals during December 2019 to March 2020. These samples included: Rules Establishment Group 11 230 cases, including 1 182 cases for Delta check rules; Rules Validation Group 3 164 cases, including 487cases for Delta check; Clinical Application Trial Group 77 269 cases. Samples were analyzed for coagulation tests using Sysmex CS series automatic coagulation analyzers, and the clinical information, instrument parameters, test results, clinical diagnosis, medication history of anticoagulant and other relative results such as HCT, TG, TBIL, DBIL were summarized; on the basis of historical data, the 2.5 and 97.5 percentile of all data arranged from low to high were initially accumulated; on the basis of clinical suggestions, critical values and specific drug use as well as relative guidelines, autoverification rules and limits were established.The rules were then input into middleware, in which Stage I/Stage II validation was done. Positive coincidence, negative coincidence, false negative, false positive, autoverification pass rate, passing accuracy (coincidence of autoverification and manual verification) were calculated. Autoverification rules underwent trial application in coagulation results reports.Results:(1) The autoverification algorisms involve 33 rules regarding PT/INR, APTT, FBG, D-dimer, FDP,Delta check, reaction curve and sample abnormalities; (2)Autoverification Establishment Group showed autoverification pass rate was 68.42% (7 684/11 230), the false negative rate was 0%(0/11230), coincidence of autoverification and manual verification was 98.51%(11 063/11 230), in which positive coincidence and negative coincidence were respectively 30.09% (3 379/11 230) and 68.42%(7 684/11 230); Autoverification Validation Group showed autoverification pass rate was 60.37%(1 910/3 164), the false negative rate was 0%(0/11 230), coincidence of autoverification and manual verification was 97.79%(3 094/3 164), in which positive coincidence and negative coincidence were respectively 37.42%(1 184/3 164) and 60.37%(1 910/3 164); (3) Trialed implementation of these autoverification rules on 77 269 coagulation samples showed that the average TAT shortened by 8.5 min-83.1 min.Conclusions:This study established 33 autoverification rules in coagulation tests. Validation showedthese rules could ensure test quality while shortening TAT and lighten manual workload.

Objective To study the sleep improvement function of DHA-PC.Methods The mice were randomly divid-ed into control, vehicle, DHA+Lecithin (60+200 mg/kg) and DHA-PC(50,100,200 mg/kg) groups.Ten mice were enrolled in each group .The mice of control were administered with normal food , the vehicle group was orally given normal saline at the dosage of 0.2 ml/10 g, while both DHA-PC and DHA+Lecithin were orally given corresponding drugs at the dosage of 0.2 ml/10 g.All the groups were treated for 30 days except control group .The direct sleep-inducing test, the test of lengthening sleep time induced by pentobarbital sodium , the test of pentobarbital sodium subthreshold-hypnosis and the test of barbital sodium sleep latency were conducted to observe the inductive effect of DHA -PC.Results Neither the effect on mice body mass nor directly-induced sleep was observed .DHA-PC (50,100, and 200 mg/kg) could prolong sleep time to (56.2 ±13.7),(57.9 ±25.4) and(64.1 ±18.4) min, respectively,compared to vehicle(32.9 ±10.8)min (P<0.05).DHA+Lecithin could not prolong sleep time (38.6 ±11.7)min compared to (32.9 ±10.8)min of vehicle.There was significant difference compared with DHA-PC at the dosage of 200 mg/kg (64.1 ±18.4)min (P<0.05).DHA-PC (200 mg/kg) enhanced pentobarbital sodium subthreshold-hypnosis (70%) compared to vehicle (10%) (P<0.05),so did DHA+Lecithin (60%) compared to vehicle (10%) (P<0.05).Both DHA-PC (200 mg/kg)[(22.9 ±4.1)min ] and DHA+Lecithin [(19.5 ±2.7) min ]could shorten sleep latency compared to vehicle (31.3 ±6.9) min(P<0.01), and the sleep latency of DHA +Lecithin (19.5 ±2.7) min was shorter than that of DHA-PC(50,100 mg/kg).Conclusion DHA-PC has some effect some sleep improvement in mice .

Sixty patients who underwent brain and neck CT angiograpby (CTA) were randomly divided into two groups: conventional protocol group and optimizing protocol group with 30 in each. The images were evaluated by two radiologists independently. The images of optimizing group avoided the artifact disturbance of the brachiocephalic vein effectively and greatly improved the imaging quality of arteria carotis communis and arteria vertebralis initial segment. Compared with the conventional group the differences were statistically significuat(P <0.05). The optimization of 64-MDCT brain and neck CTA is feasible and effective.

Objective To analyze the clinical features and two HLA-DQB1alleles in their associa-tions with vitiligo.Methods Clinical data of243patients with vitiligo were collected and the HLA-DQB1al-leles were determined by a PCR-SSP assay in both patients and control groups.Results The mean age of the first onset was23.1years for the males,and23.7years for the females.The localized type was the major form in the initial stage.The segmental type mainly occurred in childhood.Age of the first onset was younger in pa-tients with familial history than those in patients without familial history.HLA-DQB1*0201allele was associ-ated with non-segmental type only.Conclusions①The pathogenesis might be different between non-segmen-tal and segmental vitiligo.②Polygenic inheritance may explain vitiligo with familial history.There might be a difference of genetic background between vitiligo with or without familial history.③HLA-DQB1*0201allele may be the susceptible gene or have close linkage with susceptible gene in vitiligo vulgaris.

Objective:To determine the content of ginsenoside R g1 ,R e and Paeoniflorin by HPLC in Shenshao tablet.Methods: HPLC Symmetry C 18 column was used and CH 3CN H 3PO 4 (11∶89) as mobile phase. The flow rate was 0.8mL/min, the column temperature at 30 ?C and the detective wavelength 203nm and 230nm. Results:The content of ginsenoside R g1 ,R e, and paeoniflorin can be determined by HPLC. The linear concentration ranges of these compound were 0.960?g～4.800?g, 0.912?g～4.560?g,1.050?g～ 5.250 ?g. The average recoveries were 105.2%, 98.5% and 103.5%, respectively.Conclusion: This method is simple and accurate and can be used to determine the content of Shenshao Tablet.