Objective:To explore the clinical application value of artificial intelligence（AI）-assisted training in enhancing the accuracy of nuchal translucency（NT）identification，standardization of measurement，and diagnostic efficacy for abnormalities among ultrasound residents.Methods:A retrospective collection of 300 standard fetal NT ultrasound images was conducted at the Center for Medical Ultrasound，Suzhou Hospital Affiliated of Nanjing Medical University from January 2018 to June 2024. The AI model performed NT measurements and diagnoses once. Four sonographers of different seniority levels（including two resident physicians）independently conducted NT measurements and diagnoses twice. Prior to the experiment，the middle-age and resident sonographers had uniformly completed traditional theory training. Following the first independent measurements，the two resident sonographers received additional AI-assisted training，after which all 4 sonographers performed the second independent measurements. A fetal medicine expert evaluated blindly all the results and compared the differences in NT recognition accuracy，measurement standard rate and diagnosis accuracy between the middle-age sonographer（traditional training only）and two resident sonographers（traditional + AI-assisted training）.Results:For the middle-aged sonographer who only received traditional lecture-based training，the accuracy of NT recognition，standardization rate of measurement，or diagnostic accuracy were not significantly improved befroe and after the training，and the diffrence was not statistically significant（ χ2=0.189，1.887，0.326；all P>0.05）. In contrast，the second-year resident（Resident 2）and first-year resident（Resident 1），who received both traditional lecture-based training and AI training，demonstrated some improvements in the accuracy of NT measurement site recognition，though the differences were not statistically significant（ χ2=1.301，2.418；all P>0.05）. However，both residents did significant improvements in the standardization rate of NT measurement（ χ2=25.768，17.035；all P<0.05）. In terms of diagnostic accuracy，Resident 1 did significant improvement（ χ2=10.180， P<0.05），while Resident 2 also did some improvement，though the difference was not statistically significant（ χ2=2.573， P>0.05）. Conclusions:The AI-assisted training system enhances the ability of ultrasound resident sonographers to recognize，measure，and diagnose NT，providing a novel and efficient training model for standardized residency training in ultrasound specialties.

Objective:To explore the clinical application value of artificial intelligence（AI）-assisted training in enhancing the accuracy of nuchal translucency（NT）identification，standardization of measurement，and diagnostic efficacy for abnormalities among ultrasound residents.Methods:A retrospective collection of 300 standard fetal NT ultrasound images was conducted at the Center for Medical Ultrasound，Suzhou Hospital Affiliated of Nanjing Medical University from January 2018 to June 2024. The AI model performed NT measurements and diagnoses once. Four sonographers of different seniority levels（including two resident physicians）independently conducted NT measurements and diagnoses twice. Prior to the experiment，the middle-age and resident sonographers had uniformly completed traditional theory training. Following the first independent measurements，the two resident sonographers received additional AI-assisted training，after which all 4 sonographers performed the second independent measurements. A fetal medicine expert evaluated blindly all the results and compared the differences in NT recognition accuracy，measurement standard rate and diagnosis accuracy between the middle-age sonographer（traditional training only）and two resident sonographers（traditional + AI-assisted training）.Results:For the middle-aged sonographer who only received traditional lecture-based training，the accuracy of NT recognition，standardization rate of measurement，or diagnostic accuracy were not significantly improved befroe and after the training，and the diffrence was not statistically significant（ χ2=0.189，1.887，0.326；all P>0.05）. In contrast，the second-year resident（Resident 2）and first-year resident（Resident 1），who received both traditional lecture-based training and AI training，demonstrated some improvements in the accuracy of NT measurement site recognition，though the differences were not statistically significant（ χ2=1.301，2.418；all P>0.05）. However，both residents did significant improvements in the standardization rate of NT measurement（ χ2=25.768，17.035；all P<0.05）. In terms of diagnostic accuracy，Resident 1 did significant improvement（ χ2=10.180， P<0.05），while Resident 2 also did some improvement，though the difference was not statistically significant（ χ2=2.573， P>0.05）. Conclusions:The AI-assisted training system enhances the ability of ultrasound resident sonographers to recognize，measure，and diagnose NT，providing a novel and efficient training model for standardized residency training in ultrasound specialties.

Objective To explore the influence of bacteria lipopolysaccharide on the cytokine production of flour mite allergic rhinitis patients. Methods 8 cases with perennial allergic rhinitis were selected. Then the heparin anticoagulation venous blood was taken from the same patient and was added to fetal calf serum,with ultimate volume 1 ml. The two experimental groups were added 10μg LPS and 1 μg LPS respectively, forming the high LPS dose group and low LPS dose group,while the control group was added nothing. Results The contents of IL-4、IL-5、IL-10、IL-12、IFN-γwere tested by enzyme-linked immunosorbent assay. The findings were that there was significant difference in the productive contents of IL-4、IL-5、IL-10、IL-12 and no significant difference in that of IFN-γ between the high LPS dose group and the low LPS dose group. When compared in two groups,significant difference was found in the productive contents of IL-4 ,IL-10 and IL-12 between the two experimental groups and between the high LPS dose group and the control group, while no obvious difference existed between the low LPS group and control group. However, significant difference was altogether found in the productive content of IL-5 when compared one with another among the three groups,and the result was that low dose of LPS obviously promoted the production of cytokine while high dose of LPS restrained the production of cytokine; no significant difference was found in the production of IFN-γ in all comparisons between the three groups. Conclusion This research, through the experiments in vitro, proved that LPS could effectively adjust the cytokine production of perennial flour mite allergic rhinitis patients and the balance of Th1/Th2 ,whose effect depends on the dose of LPS. This research suggested that the practical future in which special cytokine target treatment will be adopted on perennial flour mite allergic rhinitis patients.

Objective To explore the CT classification of lacerating lung injury in blunt thoracic trauma and its clinical significance. Methods A total of 63 patients with lung lacerating injury were classified using CT features as simple type injury (complete visceral pleura, with no pneumothorax or he-mopneumothorax) and complex type injury (accompanied by visceral pleura rupture, pneumothorax or he-mopneumothorax). A retrospective analysis was done on CT manifestations and clinical data. Results Of 63 patients, 35 patients (56%) had simple type of lacerating lung injury with complete visceral pleu-ra, most of which were focal pulmonary pseudocyst lesions present in the edge of lungs and could be dis-persed quickly after conservative therapy without complications. Mean hospital stay was 16 days. Of pa-tients with complex type of lacerating lung injury, 28 patients (44.4%) were accompanied by visceral pleura rupture with larger extent of pulmonary injury, 20 (71%) by lung eontnsion, 15 (54%) by ate-lectasis or pulmonary atelectasis and three (11%) by local pulmonary infection. Thoracic puncture or closed drainage was performed in 19 patients (69%) and thoracotomy in one (4%), with mean hospital stay of 58 days. Conclusions According to CT manifestations on whether there exists visceral pleura rupture or not, the lacerating lung injury is classified as simple type injury and complex type injury. CT classification of lacerating lung injury may be helpful in selecting clinical treatment protocols and predic-ting early prognosis.

Objective To study the relationship in displaying nasopharyngeal carcinoma(NPC)lesions with different MR imagingprotocols.Methods 67cases of NPC proved by pathology were reviewed. Each patient was scanned with six MR imaging protocols (Tra T_1WI, TraT_2WI , SagT_1WI , CorFSIR , TraCE-T_1WI , CorCE-T_1WI ).Results All cases were displayed as mucosal thickening and /or soft tissue masses of nasopharynx. The involved parts were as follows: parapharyngeal spaces in 49 cases(73.1%) ,carotid sheaths in 33 cases ( 49.3% ) , prevertebral muscles in 32 cases ( 47.8% ) , medial pterygoids in 15 cases ( 22.4% ) , lateral pterygoids in 7 cases ( 10.4% ) , pterygoid plates in 9 cases ( 13.4% ) ,pterygopalatine fossae in 5 cases (7.5%), sphenoidal sinuses in 16 cases(23.9%), ethmoidal sinuses in 6 cases(9.0%), maxillary sinuses in 3 cases(4.5%),orbital cavity in 1 case (1.5% ), sphenoid bones in 12 cases(17.9%), petrous apices in 19 cases(28.4%), clivuses in 41 cases(61.2%), cavernous sinuses in 7 cases(10.4%), temporal lobes in 3 cases(4.5%) and cervical lymphnode mestases in 45 cases(67.2%). The lesions displayed by combination of TraT_2WI, SagT_1WI , CorFSIR and CorCE-T_1WI were corresponded with those displayed by the all six MR imaging protocols . Conclusion One or more MR imaging protocols can be optimized for displaying each lesion of NPC. The combination of Tra T_2WI , Sag T_1WI , CorFS IR and Cor CE -T_1WI can display NPC lesions completely.

Objective To explore the relationship between the concentrations of dust mite allergen and lipopolysaccharide (LPS) in the working place and home for the workers. Methods 30 workers were selected as the experimental group in June, 2005, divided into A and B groups, 15 workers of flour processing in A and 15 workers of leather processing in B respectively, at the same season, 20 teachers from a college were selected as the control group (C group). 360 dust specimen were collected, the concentrations of allergen Der p1, Der f1 were determined by ELISA and the LPS concentration were determined by a kinetic Limulus assay. Results Concentration of allergen Der p1 and Der f1 (median:335.1 and 118.8, 350.0 and 174.1, 31.1and 3.4, 81.5 and 9.6 ?g/g in different sites respectively) in A group was the highest, LPS in B group was the highest (median: 234, 268, 104, 54 EU/mg in different sites respectively). The concentration of allergen in the suspending dust was correlated with those in mattress and floor dust (rs=0.661, P

Along with the increasing medical image data,it is imperative to set up an effective system about medical image retrieval.Essentially,the image classification is crucial for medical image retrieval.As a distribution pattern of image gray scale,texture is an important character.Wavelet multi-scale decomposition is essentially multi-channel filtering and its multi-resolution analysis structure is identical with human visual system.So the extraction of texture feature under different resolutions after multi-band wavelets transform is of great benefit to image recognition and image retrieval.Consequently,this paper designs an image classification method based on eight-band wavelet.This method solves the key technology in the medical image retrieval,and it gains very high classification rate.