The chapter Zhouyu in Guoyu says "Qi of the heaven and the earth moves without losing its order." With lucidity ascending and turbidity descending， Qi moves in a normal state， and Yin and Yang consolidate the foundation of the body. The mutual interference between lucidity and turbidity leads to the disorder of Qi movement， thus causing diseases. It is a pathological state of disorder between ascending and descending， as well as between entering and exiting， gradually evolving into a state of turbidity affecting lucidity and transforming into pathogen， which can be used to interpret and analyze the core of disease pathogenesis. The theory of lucidity and turbidity is connected with the harmony of nutrient and defensive aspects， Qi circulation， and sweat pore associating with Qi movement， and it has common implications with immune responses and nutrient metabolism system， intestinal mucosal barrier function， and mitochondrial energy synthesis. Modern studies have shown that intestinal flora imbalance， bile acid receptor inactivation， macrophage polarization imbalance， epithelial-mesenchymal transition， ferroptosis and other related microscopic pathological mechanisms are involved in the development and progression of ulcerative colitis. By delving into the common meaning of the classic theory of mutual interference between lucidity and turbidity in traditional Chinese medicine and modern medical pathological mechanisms， this paper summarizes the correspondence between the micropathological mechanism and the theory of mutual interference between lucidity and turbidity in the regulation and mamagement of ulcerative colitis. The combined use of sweet and warm medicinal materials consolidates the middle Qi and activates Qi circulation， thus ascending lucidity and descending turbidity. The combined use of pungent medicinal materials for dispersing and bitter medicinal materials for descending simultaneously raises warm and clear Qi. Wind-extinguishing medicinal materials facilitate the ascending of Qi and the opening of sweat pores. Accordingly， turbidity descends and lucidity ascends. The prescriptions incorporating these medication principles are in agreement with the therapeutic approach of following the normal flow of lucidity and turbidity. This paper clarifies the scientific connotation and micropathologic mechanism of ulcerative colitis from the perspective of mutual interference between lucidity and turbidity， providing new theories and prescriptions for the clinical diagnosis， treatment， and prevention of ulcerative colitis.

Congenital lower urinary tract obstruction (CLUTO) is a spectrum of fetal malformations caused by anatomical abnormalities of the urethra, characterized by high rates of perinatal complications and mortality. The 2024 joint guideline from the European Association of Urology (EAU) and the European Society for Paediatric Urology (ESPU) introduced systematic revisions to the comprehensive management of CLUTO. Key updates encompass advancements in prenatal and postnatal screening and precise diagnosis, refined fetal prognosis assessment, clearer indications and modality selection for prenatal intervention, optimization of postnatal treatment strategies, and the establishment of a lifelong follow-up framework within an integrated care pathway. This article elucidates these key updates by comparing the 2024 EAU/ESPU guideline with the 2022 European Rare Kidney Disease Reference Network (ERKNet) consensus. It also discusses ongoing controversies and future research directions. The aim is to provide clinicians with the latest evidence-based insights to inform practice, ultimately improving outcomes and quality of life for children with CLUTO.
Humans ; Urology ; Female ; Urethral Obstruction/therapy* ; Pregnancy ; Child ; Europe ; Prenatal Diagnosis ; Infant, Newborn ; Urethra/abnormalities*

The rapid development of information technology has brought new opportunities and challenges to medical educa-tion.As one of the key technologies leading the future,artificial intelligence(AI)is becoming a crucial force to promote the high-quality development of education.Host Defense and Immunity teaching team actively explores and practices the teaching innovation,and takes measures such as building a knowledge graph,constructing a learning map,forming a ideological and political map,introducing AI teaching assistants,using AI tools,and analyzing student conditions.As a result,the students'enthusiasm increased,and the average mastery rate of the knowledge points reached as high as 86.13%.Meanwhile,this paper further considers the thoughts and prospects of digital intelligence empowerment courses in aspects such as teacher development,industry-education integration,safety norms,and the relationship with human intelligence,with the aim of better serving the cultivation of innovative medical talents.

Anaplastic lymphoma kinase (ALK) rearranged renal cell carcinoma (ALK-RCC) is an exceedingly rare malignancy, recently classified as a distinct molecular entity in the 5th edition of the WHO classification for urinary and male genital tumors. Due to its non-specific clinical symptoms and diverse histopathological patterns, accurate diagnosis is difficult. This paper reports a case of ALK-RCC with morphology and immunophenotype resembling papillary renal cell carcinoma. After second-generation sequencing, EML4-ALK gene fusion was found, and positive staining for ALK was confirmed by immunohistochemistry subsequently. Following informed consent from the patient, targeted therapy with crizotinib was initiated. During a 17-month follow-up period, no recurrence or metastasis was observed.

A 13-year-old boy was admitted to the hospital due to 1 month after trauma in a traffic accident on September 29，2017. After admission，due to a large amount of pleural effusion through the chest tube，thoracoscopic exploration and fiberboard dissection were performed，and the postoperative pleural effusion was not significantly reduced. The creatinine of pleural effusion was 913 μmol/L，CT showed that left hydronephrosis and perirenal encapsulated effusion were closely related to the ureter，so ureteral injury and urinothorax were considered. Retrograde ureterography revealed a defect of left ureter，approximately 6 cm in length，and left nephrectomy + left kidney rupture repair + renal autotransplantation was performed. 7 years later，the patient recovered well and the renal blood supply was good，no left hydronephrosis was found by MRU. Early diagnosis of ureteral injury is challenging，especially when accompanied by urinothorax. When life is stable，early diagnosis and treatment can reduce the loss of renal function after combined trauma. Renal autotransplantation is safe and effective for the treatment of long segmental ureteral defects.

Objective:To develop a convolutional neural network model of whole slide imaging of cerebrospinal fluid cells for rapid and accurate identification and classification of tumor cells in cerebrospinal fluid.Methods:A total of 8 692 cerebrospinal fluid cytology smears from Huashan Hospital Affiliated to Fudan University from January 2nd, 2019, to December 27th, 2024. As randomly assigned, the training set included 4 941 benign and 1 745 malignant samples, while the validation set comprised of 1 368 benign and 638 malignant samples. Whole-slide digital images were acquired using a cytopathology scanner, cells (clusters) were annotated for classification, and a deep learning model was constructed via tiled image patches for cell detection and classification. Model performance was evaluated using accuracy, sensitivity, specificity, and other indicators. The classification efficiency of manual microscopy was compared.Results:The model achieved a mean precision of 96.75% for cerebrospinal fluid cell classification. For malignant tumor cells, the classification accuracy was 96.61% (mAP=98.36%, AUC=0.97). Subtype classification accuracies for epithelial/epithelioid tumors and small round cell tumors were 97.13% (AUC=0.98) and 95.58% (AUC=0.93), respectively. Compared with manual microscopy, which took (9.70±0.82) minutes for classifying 200 cells, (18.27±1.21) minutes for 500 cells, and often exceeded 60 minutes or infeasible for full slides, the AI model took (3.46±0.49) seconds for 200 cells, (6.76±0.82) seconds for 500 cells, and a median of 48.57 seconds for full slides ( P<0.001), representing an efficiency improvement of approximately 161-170 times, significantly enhancing diagnostic efficiency. Conclusion:This fully automated hierarchical deep learning model enables efficient and accurate tumor cell identification and classification in CSF, providing an effective auxiliary tool for the rapid diagnosis of meningeal carcinomatosis.

The rapid development of information technology has brought new opportunities and challenges to medical educa-tion.As one of the key technologies leading the future,artificial intelligence(AI)is becoming a crucial force to promote the high-quality development of education.Host Defense and Immunity teaching team actively explores and practices the teaching innovation,and takes measures such as building a knowledge graph,constructing a learning map,forming a ideological and political map,introducing AI teaching assistants,using AI tools,and analyzing student conditions.As a result,the students'enthusiasm increased,and the average mastery rate of the knowledge points reached as high as 86.13%.Meanwhile,this paper further considers the thoughts and prospects of digital intelligence empowerment courses in aspects such as teacher development,industry-education integration,safety norms,and the relationship with human intelligence,with the aim of better serving the cultivation of innovative medical talents.

Anaplastic lymphoma kinase (ALK) rearranged renal cell carcinoma (ALK-RCC) is an exceedingly rare malignancy, recently classified as a distinct molecular entity in the 5th edition of the WHO classification for urinary and male genital tumors. Due to its non-specific clinical symptoms and diverse histopathological patterns, accurate diagnosis is difficult. This paper reports a case of ALK-RCC with morphology and immunophenotype resembling papillary renal cell carcinoma. After second-generation sequencing, EML4-ALK gene fusion was found, and positive staining for ALK was confirmed by immunohistochemistry subsequently. Following informed consent from the patient, targeted therapy with crizotinib was initiated. During a 17-month follow-up period, no recurrence or metastasis was observed.

A 13-year-old boy was admitted to the hospital due to 1 month after trauma in a traffic accident on September 29，2017. After admission，due to a large amount of pleural effusion through the chest tube，thoracoscopic exploration and fiberboard dissection were performed，and the postoperative pleural effusion was not significantly reduced. The creatinine of pleural effusion was 913 μmol/L，CT showed that left hydronephrosis and perirenal encapsulated effusion were closely related to the ureter，so ureteral injury and urinothorax were considered. Retrograde ureterography revealed a defect of left ureter，approximately 6 cm in length，and left nephrectomy + left kidney rupture repair + renal autotransplantation was performed. 7 years later，the patient recovered well and the renal blood supply was good，no left hydronephrosis was found by MRU. Early diagnosis of ureteral injury is challenging，especially when accompanied by urinothorax. When life is stable，early diagnosis and treatment can reduce the loss of renal function after combined trauma. Renal autotransplantation is safe and effective for the treatment of long segmental ureteral defects.

Objective:To develop a convolutional neural network model of whole slide imaging of cerebrospinal fluid cells for rapid and accurate identification and classification of tumor cells in cerebrospinal fluid.Methods:A total of 8 692 cerebrospinal fluid cytology smears from Huashan Hospital Affiliated to Fudan University from January 2nd, 2019, to December 27th, 2024. As randomly assigned, the training set included 4 941 benign and 1 745 malignant samples, while the validation set comprised of 1 368 benign and 638 malignant samples. Whole-slide digital images were acquired using a cytopathology scanner, cells (clusters) were annotated for classification, and a deep learning model was constructed via tiled image patches for cell detection and classification. Model performance was evaluated using accuracy, sensitivity, specificity, and other indicators. The classification efficiency of manual microscopy was compared.Results:The model achieved a mean precision of 96.75% for cerebrospinal fluid cell classification. For malignant tumor cells, the classification accuracy was 96.61% (mAP=98.36%, AUC=0.97). Subtype classification accuracies for epithelial/epithelioid tumors and small round cell tumors were 97.13% (AUC=0.98) and 95.58% (AUC=0.93), respectively. Compared with manual microscopy, which took (9.70±0.82) minutes for classifying 200 cells, (18.27±1.21) minutes for 500 cells, and often exceeded 60 minutes or infeasible for full slides, the AI model took (3.46±0.49) seconds for 200 cells, (6.76±0.82) seconds for 500 cells, and a median of 48.57 seconds for full slides ( P<0.001), representing an efficiency improvement of approximately 161-170 times, significantly enhancing diagnostic efficiency. Conclusion:This fully automated hierarchical deep learning model enables efficient and accurate tumor cell identification and classification in CSF, providing an effective auxiliary tool for the rapid diagnosis of meningeal carcinomatosis.