In recent years, with the rapid development of artificial intelligence technology, the application of deep learning in the field of pathology has been continuously expanding. Particularly, the rise of multimodal data fusion methods has opened up new technical paths for the precise diagnosis, prognosis assessment, and individualized treatment of tumors. By integrating multi-level and multi-source data such as clinical information, pathological omics, molecular omics, and imaging omics, deep learning models can identify potential associated features and key biological mechanisms that are difficult to reveal by a single modality, thereby significantly improving the accuracy of disease classification and the scientific nature of risk stratification. This article systematically reviews the research progress of multimodal data fusion methods based on deep learning in the field of pathology in recent years, focuses on sorting out different types of fusion strategies, evaluates their advantages and challenges in practical clinical applications, and looks forward to future development trends.

Objective To analyze the characteristics of postoperative hospital-acquired infections and drug sensitivity in lung transplant recipients over the past 5 years in a single center. Methods A total of 724 lung transplant recipients at Wuxi People's Hospital from January 2019 to December 2023 were selected. Based on the principles of hospital-acquired infection diagnosis, a retrospective analysis was conducted on the hospital infection situation and infection sites of lung transplant recipients, and an analysis of the distribution of hospital-acquired infection pathogens and their antimicrobial susceptibility test status was performed. Results Among the 724 lung transplant recipients, 275 cases of hospital-acquired infection occurred, with an infection rate of 38.0%. The case-time infection rate decreased from 54.2% in 2019 to 22.8% in 2023, showing a downward trend year by year (Z=30.98, P<0.001). The main infection site was the lower respiratory tract, accounting for 73.6%. The pathogens were mainly Gram-negative bacteria, with the top four being Acinetobacter baumannii (37.1%), Pseudomonas aeruginosa (17.3%), Klebsiella pneumoniae (13.7%), and Stenotrophomonas maltophilia (13.4%), with imipenem resistance rates of 89%, 53%, 58% and 100%, respectively. Gram-positive bacteria were mainly Staphylococcus aureus (3.6%), with a methicillin resistance rate of 67%. Conclusions Over the past 5 years, the hospital-acquired infections in lung transplant recipients have shown a downward trend, mainly involving lower respiratory tract infections, with the main pathogens being Acinetobacter baumannii, Pseudomonas aeruginosa and Klebsiella pneumoniae, all of which have high resistance rates to imipenem.

Histological staining is the basis of pathological analysis,but the traditional staining method relies on chemical reagents,which not only consumes a lot of resources,but also causes harm to the environment and human health.In recent years,with the rapid development of deep learning technology,virtual staining technology,as a new method,is expected to effectively replace and supplement the traditional histological staining methods.It uses neural networks to analyze unstained tissue images,generate digital images that are highly similar to chemical staining effects,and even realize the mutual conversion between different staining modes,reducing the laboratory's dependence on chemical reagents and providing sustainable research programs.In this paper,the basic principles of virtual staining and its potential applications in histopathology are introduced in detail,and the current challenges and future research directions are discussed.

Objective:To explore the efficacy and its related factors of rituximab (RTX) in the treatment of children with frequently relapsing nephrotic syndrome/steroid-dependent nephrotic syndrome (FRNS/SDNS).Methods:It was a single-center retrospective study. The clinical data of FRNS/SDNS children first treated with RTX in the First Affiliated Hospital of Sun Yat-sen University from November 1, 2016 to September 1, 2023 were collected. The number of relapse within 1 year before and after RTX treatment, the time to first relapse after RTX treatment, and the time to B-cell reconstitution were analyzed. At the first treatment, a single dose of RTX was given at 375 mg/m 2, with a maximum dose of 500 mg, once a week, for 1 to 4 doses. The count of CD19 + lymphocytes in the peripheral blood of the children was continuously monitored. If B-cell reconstruction was performed, the decision on whether to proceed to the next course of RTX treatment was made based on clinical manifestations. Kaplan-Meier method was used to analyze relapse-free survival rate after receiving RTX. Cox proportional hazards regression model was used to analyze the related factors of relapse after RTX treatment. Results:A total of 98 FRNS/SDNS children receiving RTX treatment were enrolled, including 75 males (76.5%). The age at onset was 4.0 (1.9, 7.1) years and age of receiving RTX was 11.3 (8.5, 13.5) years. There were 90 children (91.8%) achieving complete remission, while 8 patients (8.2%) did not respond to RTX treatment, and 3 patients (3.1%) progressed to end-stage kidney disease after receiving RTX. The relapse-free survival rates at 6 months and 1 year after RTX treatment were 83.3% (75/90) and 57.9% (22/38), respectively. The frequency of relapse 1 year after RTX treatment decreased compared to 1 year before RTX treatment ( Z=-7.398, P<0.001). Compared with children without relapse during the period of B-cell depletion, relapsed children had a higher number of relapse within one year after RTX treatment ( Z=5.246, P<0.001). The time to first relapse after RTX treatment was 8.3 (4.6, 13.9) months in 51 relapse patients. Compared with children receiving 1 dose of RTX in the first course, those receiving 2 or more doses had a longer time to the first relapse ( Z=2.983, P=0.003). There was no statistically significant difference in time to the first relapse between children who received mycophenolate mofetil therapy after RTX treatment and those who didn't ( P>0.05). The reconstruction time of B cells after the first course of RTX was 6.9 (5.3, 9.0) months. Compared to children receiving one dose of RTX in the first course, those receiving two or more doses had a longer B-cell reconstitution time ( Z=2.739, P=0.006). There was no statistically significant difference in B-cell reconstitution time between children who received mycophenolate mofetil therapy after RTX treatment and those who didn't ( P>0.05). Univariate Cox regression analysis showed that recurrence after calcineurin inhibitor (CNI) treatment before RTX treatment and the number of recurrence in one year before RTX treatment were correlated factors of recurrence after RTX treatment (both P<0.05). Multivariate Cox regression analysis showed that recurrence after CNI treatment before RTX treatment was an independent correlated factor of relapse after RTX therapy ( HR=3.496, 95% CI 1.245-9.818, P=0.018). Infusion reactions occurred in 10 patients (10.2%) and infections were observed in 24 patients (24.5%) during B cell depletion. No serious adverse events occurred. Conclusions:RTX is well tolerated and effective in treating FRNS/SDNS. Recurrence after CNI treatment before RTX treatment may be an independent related factor of relapse after RTX treatment.

Renal cell carcinoma（RCC）has a relatively high incidence among genitourinary malignancies and therefore occupies a pivotal position in the diagnosis and treatment of urological tumors. Its staging，grading，and corresponding therapeutic strategies have been relatively well established. However，in clinical practice，we have observed that a subset of patients with RCC，preoperatively diagnosed as stage T1 based on imaging，are found on postoperative pathology after partial nephrectomy to have tumor extension into the renal sinus，resulting in pathological upstaging（cT 1/pT 3a）. Multiple studies have demonstrated that the overall prognosis of cT 1/pT 3a patients undergoing partial nephrectomy is inferior to that of cT 1/pT 1 patients，but shows no significant difference compared with cT 1/pT 3a patients treated with radical nephrectomy. Moreover，partial nephrectomy offers clear advantages over radical nephrectomy in terms of intraoperative blood loss and preservation of renal function parameters such as estimated glomerular filtration rate（eGFR）and serum creatinine，which translate into improved quality of life. In addition，this paper introduces predictive methods for pathological upstaging in partial RCC，including novel imaging-based approaches such as the contour irregular degree（CID）on computed tomography（CT），histopathological predictors such as Fuhrman grading，and the preliminary application of machine learning in enhancing diagnostic accuracy.

Objective:To investigate the clinical efficacy and safety of a modified injection technique for improving temporal concavity deformities.Methods:A prospective study was conducted on 157 female patients who underwent temporal concavity augmentation at the Department of Plastic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, from June 2019 to June 2022. The patients were aged from 32 to 48 (38.2±3.1) years. Granular fat was obtained through liposuction and purification. Using the midpoint of the frontotemporal line as the entry point, the granular fat tissue was injected evenly at multiple points under the skin and superficial temporal fascia. Additional granular fat was injected in the temporal edge area to ensure a smooth appearance. The visual analogue scale (VAS) was used to assess the patients' intraoperative pain levels. Follow-up visits were conducted for one year postoperatively to assess patient satisfaction with the improvement in temporal concavity, local pigmentation, and fine lines in the lateral orbital area based on preoperative and postoperative photographs. Complications, including swelling, ecchymosis, hematoma, fat embolism, infection, fat liquefaction, and subcutaneous induration, were recorded immediately after surgery and at the one-year follow-up.Results:All the 157 patients experienced mild swelling in the injection area postoperatively, which resolved within 3 to 6 days. Ecchymosis occurred in 15 patients and spontaneously resolved within 10 days. Eleven patients had asymmetry in the filled area, with 3 recovering after local massage and observation, and the remaining 8 undergoing a second fat grafting procedure. A total of 25 patients underwent more than two fat grafting procedures, including 4 who underwent three procedures. Mild local hematoma occurred in 3 patients postoperatively. The intraoperative pain VAS was (1.8±0.5) score. After treatment, the improvement scores for temporal concavity, local pigmentation, and fine lines in the lateral orbital area were (7.4±0.7), (6.8±0.7), and (7.9±0.7) scores, respectively. After one year of follow-up, no complications such as fat embolism, infection, fat liquefaction, or subcutaneous induration were observed in the 157 patients.Conclusion:The modified injection technique for improving temporal concavity deformities is safe and effective, with high patient satisfaction.

Objective:To investigate the efficacy of rigid ureteroscopic laser lithotripsy combined with N-trap(RULL+N-trap),which is scoop-shaped,in the treatment of ureteral stones with a maximum diameter ≥1.5 cm.Methods:This retrospective cohort study included patients diagnosed with ureteral calculi who underwent rigid ureteroscopic lithotripsy(RULL)combined with N-Trap stone entrapment system at the Department of Urology,Peking University Third Hospital,by the same surgical team between June 2021 and September 2024.A total of 364 patients were initially enrolled.After excluding 21 patients due to missing critical outcome variables,two distinct cohorts were established:38 patients with ureteral stones measuring ≥1.5 cm in maximum diameter,and 305 patients with stones＜1.5 cm in maximum diameter.To minimize selection bias and control for confounding variables,propensity score matching(PSM)was employed.This resulted in two well-balanced groups:31 patients with stones 1.5 cm in maximum diameter and 31 patients with stones＜1.5 cm in maximum diameter,matched on baseline demographic and clinical characteristics.The primary outcomes assessed between the two groups included stone clearance.Secondary outcomes included changes in renal function indicators,specifically serum creatinine(SCr)and estimated glomerular filtration rate(GFR),and other factors like postopera-tive hospital stay and operative time.Results:In the matched cohort,the patients with stones ≥1.5 cm in maximum diameter had significantly longer operative time compared with those with smaller stones:(85.8±28.8)min vs.(62.4±24.6)min(P＜0.05).Postoperative length of hospital stay showed no significant difference:(2.26±1.79)d vs.(2.03±0.80)d(P＞0.05).The stone clearance on postoperative day one was 90.3％in the study group vs.100.0％in the control group(P＞0.05).One month postoperatively,the stone clearance was 93.5％vs.100.0％,respectively(P＞0.05).Changes in SCr were(-6.58±16.10)μmol/L vs.(-13.70±12.50)μmol/L,and changes in GFR were(5.92±14.90)mL/(min·1.73 m2)vs.(7.47±11.20)m L/(min·1.73 m2),with no statistically significant differences observed between the two groups for either renal function marker(P＞0.05).Conclusion:Ureteroscopic lithotripsy combined with N-trap is an optional method for treating ureteral stones with a maximum diameter ≥1.5 cm.The overall therapeutic efficacy is comparable,with the added benefit of significantly reducing the economic burden on patients.

Objective:To investigate the efficacy of rigid ureteroscopic laser lithotripsy combined with N-trap(RULL+N-trap),which is scoop-shaped,in the treatment of ureteral stones with a maximum diameter ≥1.5 cm.Methods:This retrospective cohort study included patients diagnosed with ureteral calculi who underwent rigid ureteroscopic lithotripsy(RULL)combined with N-Trap stone entrapment system at the Department of Urology,Peking University Third Hospital,by the same surgical team between June 2021 and September 2024.A total of 364 patients were initially enrolled.After excluding 21 patients due to missing critical outcome variables,two distinct cohorts were established:38 patients with ureteral stones measuring ≥1.5 cm in maximum diameter,and 305 patients with stones＜1.5 cm in maximum diameter.To minimize selection bias and control for confounding variables,propensity score matching(PSM)was employed.This resulted in two well-balanced groups:31 patients with stones 1.5 cm in maximum diameter and 31 patients with stones＜1.5 cm in maximum diameter,matched on baseline demographic and clinical characteristics.The primary outcomes assessed between the two groups included stone clearance.Secondary outcomes included changes in renal function indicators,specifically serum creatinine(SCr)and estimated glomerular filtration rate(GFR),and other factors like postopera-tive hospital stay and operative time.Results:In the matched cohort,the patients with stones ≥1.5 cm in maximum diameter had significantly longer operative time compared with those with smaller stones:(85.8±28.8)min vs.(62.4±24.6)min(P＜0.05).Postoperative length of hospital stay showed no significant difference:(2.26±1.79)d vs.(2.03±0.80)d(P＞0.05).The stone clearance on postoperative day one was 90.3％in the study group vs.100.0％in the control group(P＞0.05).One month postoperatively,the stone clearance was 93.5％vs.100.0％,respectively(P＞0.05).Changes in SCr were(-6.58±16.10)μmol/L vs.(-13.70±12.50)μmol/L,and changes in GFR were(5.92±14.90)mL/(min·1.73 m2)vs.(7.47±11.20)m L/(min·1.73 m2),with no statistically significant differences observed between the two groups for either renal function marker(P＞0.05).Conclusion:Ureteroscopic lithotripsy combined with N-trap is an optional method for treating ureteral stones with a maximum diameter ≥1.5 cm.The overall therapeutic efficacy is comparable,with the added benefit of significantly reducing the economic burden on patients.

Histological staining is the basis of pathological analysis,but the traditional staining method relies on chemical reagents,which not only consumes a lot of resources,but also causes harm to the environment and human health.In recent years,with the rapid development of deep learning technology,virtual staining technology,as a new method,is expected to effectively replace and supplement the traditional histological staining methods.It uses neural networks to analyze unstained tissue images,generate digital images that are highly similar to chemical staining effects,and even realize the mutual conversion between different staining modes,reducing the laboratory's dependence on chemical reagents and providing sustainable research programs.In this paper,the basic principles of virtual staining and its potential applications in histopathology are introduced in detail,and the current challenges and future research directions are discussed.