Objective:To apply artificial intelligence（AI）in classifying ovarian tumors on ultrasound images，and compare the diagnostic results of several sonographers with varying seniority levels.Methods:A total of 645 patients diagnosed with adnexal masses via gynecological ultrasound examination at Qilu Hospital of Shandong University from January 2021 to December 2024 were enrolled. Three deep learning architectures，i.e.，Alexnet，Densenet121，and Resnet50 were developed and used to internally test the classification effectiveness of ovarian tumors，while the optimal model was selected for external testing. Two junior sonographers and two senior sonographers were recruited to independently diagnose ovarian tumors in the external test dataset. Subsequently，the benign and malignant results of the model's predictions were disclosed to each sonographer，and their revised diagnoses on the same external test data in combination with the best AI model were recorded.Results:The optimal model achieved an accuracy of 0.941，sensitivity of 0.936，and specificity of 0.944 on the internal test dataset，and maintained robust performance on the external test dataset with accuracy of 0.891，sensitivity of 0.880，and specificity of 0.907. Compared to junior sonographers，the optimal model demonstrated significantly higher sensitivity in discriminating benign from malignant ovarian tumors（0.880 vs. 0.723，0.602；all P<0.05）. No statistically significant difference was observed in diagnostic accuracy between the optimal model and senior sonographer 1（ P=0.05）. With assistance from the optimal model，junior sonographers achieved significant improvements in both sensitivity and specificity（sensitivity：0.723 vs. 0.843，0.602 vs. 0.819；specificity：0.778 vs. 0.833，0.685 vs. 0.741；all P<0.05）. Conclusions:The optimal model achieves comparable performance to that of senior sonographers in ovarian tumor classification. With model assistance，the diagnostic performance of junior sonographers is significantly improved.

Objective:To observe the effects of early enteral nutrition(EN)intervention on neurological function,nutritional status,and inflammatory stress response in patients with severe traumatic brain injury.Methods:This study was a single-center prospective study,68 patients with severe traumatic brain injury were divided into control group[received parenteral nutrition(PN)intervention,n=34]and observation group(received early EN intervention,n=34)according to the envelope lottery method.The improvement of neurological function[serum central nervous system specific(S1 00(3)protein,national institutes of health stroke scale(NIHSS)score,myelin basic protein(MBP)],nutritional status[transferrin(TRF),total protein(TP),albumin(ALB)and prealbumin(PA)],inflammatory stress indicators[C-reactive protein(CRP),procalcitonin(PCT),glutathione peroxidase(GSH-PX),malondialdehyde(MDA)],daily living activity ability,quality of life,and incidence of complications between two groups were compared.Results:Compared with the control group after intervention,the observation group had lower NIHSS scores,S100[3 protein,MBP,CRP,PCT and MDA,had higher TRF,TP,ALB,PA,GSH-PX,improved Barthel index and world health organization quality of life assessment scale-100(WHOQOL-100)score(P＜0.05).There was no difference in the incidence of complications between the two groups(P＞0.05).Conclusion:Early EN intervention in patients with severe traumatic brain injury can effectively improve neurological function,nutritional status,and reduce the body's inflammatory stress response,which is worthy of clinical reference and application.

Objective:To observe the effects of early enteral nutrition(EN)intervention on neurological function,nutritional status,and inflammatory stress response in patients with severe traumatic brain injury.Methods:This study was a single-center prospective study,68 patients with severe traumatic brain injury were divided into control group[received parenteral nutrition(PN)intervention,n=34]and observation group(received early EN intervention,n=34)according to the envelope lottery method.The improvement of neurological function[serum central nervous system specific(S1 00(3)protein,national institutes of health stroke scale(NIHSS)score,myelin basic protein(MBP)],nutritional status[transferrin(TRF),total protein(TP),albumin(ALB)and prealbumin(PA)],inflammatory stress indicators[C-reactive protein(CRP),procalcitonin(PCT),glutathione peroxidase(GSH-PX),malondialdehyde(MDA)],daily living activity ability,quality of life,and incidence of complications between two groups were compared.Results:Compared with the control group after intervention,the observation group had lower NIHSS scores,S100[3 protein,MBP,CRP,PCT and MDA,had higher TRF,TP,ALB,PA,GSH-PX,improved Barthel index and world health organization quality of life assessment scale-100(WHOQOL-100)score(P＜0.05).There was no difference in the incidence of complications between the two groups(P＞0.05).Conclusion:Early EN intervention in patients with severe traumatic brain injury can effectively improve neurological function,nutritional status,and reduce the body's inflammatory stress response,which is worthy of clinical reference and application.

Objective:To apply artificial intelligence（AI）in classifying ovarian tumors on ultrasound images，and compare the diagnostic results of several sonographers with varying seniority levels.Methods:A total of 645 patients diagnosed with adnexal masses via gynecological ultrasound examination at Qilu Hospital of Shandong University from January 2021 to December 2024 were enrolled. Three deep learning architectures，i.e.，Alexnet，Densenet121，and Resnet50 were developed and used to internally test the classification effectiveness of ovarian tumors，while the optimal model was selected for external testing. Two junior sonographers and two senior sonographers were recruited to independently diagnose ovarian tumors in the external test dataset. Subsequently，the benign and malignant results of the model's predictions were disclosed to each sonographer，and their revised diagnoses on the same external test data in combination with the best AI model were recorded.Results:The optimal model achieved an accuracy of 0.941，sensitivity of 0.936，and specificity of 0.944 on the internal test dataset，and maintained robust performance on the external test dataset with accuracy of 0.891，sensitivity of 0.880，and specificity of 0.907. Compared to junior sonographers，the optimal model demonstrated significantly higher sensitivity in discriminating benign from malignant ovarian tumors（0.880 vs. 0.723，0.602；all P<0.05）. No statistically significant difference was observed in diagnostic accuracy between the optimal model and senior sonographer 1（ P=0.05）. With assistance from the optimal model，junior sonographers achieved significant improvements in both sensitivity and specificity（sensitivity：0.723 vs. 0.843，0.602 vs. 0.819；specificity：0.778 vs. 0.833，0.685 vs. 0.741；all P<0.05）. Conclusions:The optimal model achieves comparable performance to that of senior sonographers in ovarian tumor classification. With model assistance，the diagnostic performance of junior sonographers is significantly improved.

Paroxysmal nocturnal hemoglobinuria (PNH) is an acquired clonal hematopoietic stem cell disease caused by abnormal expression of glycosylphosphatidylinositol (GPI) on the cell membrane due to mutations in the phosphatidylinositol glycan class A(PIGA) gene. It is commonly characterized by intravascular hemolysis, repeated thrombosis, and bone marrow failure, as well as multiple systemic involvement symptoms such as renal dysfunction, pulmonary hypertension, swallowing difficulties, chest pain, abdominal pain, and erectile dysfunction. Due to the rarity of PNH and its strong heterogeneity in clinical manifestations, multidisciplinary collaboration is often required for diagnosis and treatment. Peking Union Medical College Hospital, relying on the rare disease diagnosis and treatment platform, has invited multidisciplinary clinical experts to form a unified opinion on the diagnosis and treatment of PNH, and formulated the Expert Consensus of Multidisciplinary Diagnosis and Treatment for Paroxysmal Nocturnal Hemoglobinuria (2024), with the hope of promoting the standardization of PNH diagnosis and treatment.

Objective:To investigate the clinicopathological features, immunohistochemical characteristics, differential diagnosis and prognosis of gastric SWI/SNF-complex deficient undifferentiated/rhabdoid carcinomas.Methods:Two cases of gastric SWI/SNF-complex deficient undifferentiated/rhabdoid carcinoma were collected at Fudan University Shanghai Cancer Center, Shanghai, China from 2017 to 2018. The clinicopathological characteristics were analyzed. Hematoxylin and eosin, and immunohistochemical stains were performed, and the relevant literatures were reviewed.Results:The two patients were both male, aged 60 and 74 years, respectively. Their symptoms were both abdominal pain. The tumor arose in the esophagogastric junction in case 1, and the cardia to the fundus and the posterior wall of the upper part of gastric body in case 2. Both tumors were present as an ulcerative mass. The patients died of tumor 11 months and 8 months after surgery, respectively. Histologically, the tumor cells arranged in sheets, nests, cords or trabecular patterns, and pseudoavleolar structure. The tumor cells were epithelioid with uniform morphology, while the tumors showed scant stroma and massive necrosis. Variable rhabdoid cells and multinucleated giant cells were seen in both cases. SMARCA4 encoding protein BRG1 was undetectable in both tumors, while SMARCB1 encoding protein INI1 was detected. The tumor cells were diffusely positive for vimentin and negative for epithelial marker (CKpan), gastrointestinal stromal tumor markers (CD117 and DOG1), myogenic markers (desmin and myogenin), melanoma markers (S-100 protein, SOX10 and HMB45), and lymphohematopoietic markers (LCA and CD20).Conclusions:Gastric SWI/SNF-complex deficient undifferentiated/rhabdoid carcinoma is a rare and highly aggressive tumor with poor prognosis. The detection of subunits protein expression of SWI/SNF complex is important for diagnosis of the tumor.

A 558 bp cDNA fragment was amplified by RT-PCR from adult Schistosoma japonicum(Chinese strain) mRNA with a pair of primers that were designed according to published Sj21.7p gene encoding 21.7 kD protein of Schistosoma japonicum(Philippines strain). Sequence analysis indicated that this frame, named Sj21.7 (Ch), with 99% homology to Sj21.7 p, contained a complete open reading fragment (ORF) of 21.7 kD protein gene of Schistosoma japonicum(Chinese strain). The amino acid sequence shared 98% homology with 21.7 kD protein of Schistosoma japonicum. This fragment was cloned into the expression vector pET28a (+) and subsequently expressed in Escherichia coli with IPTG induction. SDS-PAGE analysis revealed that the molecular weight of this expressed product was 25.4 kD. Western blotting showed that the recombinant protein reacted well with the rabbit serum immunized with Sj worm antigen, indicating that this expressed product had good antigenicity.
Amino Acid Sequence ; Animals ; Cloning, Molecular ; Helminth Proteins ; biosynthesis ; chemistry ; genetics ; Molecular Sequence Data ; Molecular Weight ; Open Reading Frames ; Rabbits ; Recombinant Proteins ; biosynthesis ; chemistry ; immunology ; Schistosoma japonicum ; genetics ; Sequence Homology