Objective To evaluate the surgical technique and clinical value of laparoscopic bladder diverticulectomy guided by inserting ureteral catheters into the diverticulum under plasmakinetic resectoscope.Methods From December 2018 to May 2024,9 patients underwent laparoscopic bladder diverticulectomy in combination with resectoscope.Each patient had a solitary bladder diverticulum with a median maximum diameter of 6.40(5.70,7.40)cm(range:5.0～8.5 cm).Among the 9 patients,3 patients had concurrent benign prostatic hyperplasia(BPH)and simultaneously underwent transurethral plasmakinetic resection of the prostate;1 patient had concurrent both BPH and bladder calculi,requiring simultaneously underwent plasmakinetic resection of the prostate and bladder calculi removal;2 patients required ureteral reimplantation as the diverticulum was directly involving the ureteral orifice;1 case underwent ureteroscopic double-J stent implantation because the opening of the ipsilateral ureter was adjacent to the entrance of the diverticulum.Results Bladder diverticulectomy was successfully performed in the all patients.Median operative time was 160.00(120.00,317.50)min(range:85～345 min).Median estimated blood loss was 20.00(10.00,150.00)mL(range:10～300 mL).No iatrogenic injuries to adjacent organs were observed.Pelvic drains were removed 1～3 d postoperatively,with no urine leakage.Urinary catheters were maintained for 7～10 d after operation.Follow-up at 3～12 months showed no recurrence or hydronephrosis in any of the patients.Conclusion Laparoscopic resection of bladder diverticula guided by ureteral catheter placed into bladder diverticula by means of resectoscope has the advantages of less trauma,less bleeding and faster recovery,and is an effective measure for the treatment of bladder diverticula.

Objective:To develop a deep learning model based on 3D super-resolution reconstruction technology and to analyze its feasibility and effectiveness in predicting paraglottic space invasion in hypopharyngeal cancer.Methods:A retrospective study was conducted involving 382 patients with hypopharyngeal squamous cell carcinoma treated at Qilu Hospital of Shandong University between January 2014 and December 2020. The cohort included 364 males and 18 females, with a mean age of 62±7 years. Patients were divided into a training set ( n=300) and a test set ( n=82) based on enrollment time. A generative adversarial network was used to perform 3D super-resolution reconstruction on contrast-enhanced CT images, improving spatial resolution by 16 times. A 2.5D deep learning strategy was employed to construct Resnet-NR and Resnet-SR models based on conventional and super-resolution images, respectively, to predict whether the paraglottic space was invaded. Model performance was evaluated using receiver operating characteristic (ROC) curves and area under the curve (AUC). A multi-reader multi-case study was conducted to assess the impact of the artificial intelligence (AI) model on clinicians′ diagnostic capabilities. Results:The super-resolution model Resnet-SR achieved the highest accuracy in both the training set (AUC=0.87, 95% CI: 0.84-0.90) and the test set (AUC=0.88, 95% CI: 0.81-0.96), significantly outperforming traditional clinical indicators (T stage, N stage, tumor diameter, and pathological differentiation degree) (AUC range: 0.55-0.70, all P<0.05). In comparison, the conventional-resolution model Resnet-NR achieved AUCs of 0.81 (95% CI: 0.77-0.84, P=0.005) and 0.80 (95% CI: 0.71-0.89, P=0.184) in the training and test sets, respectively. Using Resnet-SR to assist clinical decision-making improved the diagnostic accuracy of junior physicians (AUC=0.793 without AI assistance vs. AUC=0.871 with AI assistance, P=0.012) and significantly reduced diagnosis time for clinicians of all experience levels (86.5 s without AI assistance vs. 82.5 s with AI assistance, t=2.01, P=0.032). Conclusion:This study successfully develops a deep learning model based on 3D super-resolution reconstruction technology, which can assist in preoperative prediction of paraglottic space invasion in hypopharyngeal cancer. The AI-assisted tool improves diagnostic accuracy for junior physicians and enhances diagnostic efficiency for clinicians across all experience levels.

Cholangiocarcinoma has an extremely poor prognosis, and the efficacy of existing treatment methods is limited. In the highly desmoplastic tumor microenvironment of cholangiocarcinoma, cancer-associated fibroblasts (CAFs) are the core regulators. Their significant heterogeneity and complex intercellular crosstalk network are not only key factors driving cholangiocarcinoma progression and drug resistance, but also highly promising therapeutic targets. This review focuses on the characteristics of CAFs in cholangiocarcinoma and the key crosstalk mechanisms between CAFs and tumor cells as well as immune cells, and summarizes the research progress and limitations of current therapeutic strategies targeting CAFs.

Objective To evaluate the surgical technique and clinical value of laparoscopic bladder diverticulectomy guided by inserting ureteral catheters into the diverticulum under plasmakinetic resectoscope.Methods From December 2018 to May 2024,9 patients underwent laparoscopic bladder diverticulectomy in combination with resectoscope.Each patient had a solitary bladder diverticulum with a median maximum diameter of 6.40(5.70,7.40)cm(range:5.0～8.5 cm).Among the 9 patients,3 patients had concurrent benign prostatic hyperplasia(BPH)and simultaneously underwent transurethral plasmakinetic resection of the prostate;1 patient had concurrent both BPH and bladder calculi,requiring simultaneously underwent plasmakinetic resection of the prostate and bladder calculi removal;2 patients required ureteral reimplantation as the diverticulum was directly involving the ureteral orifice;1 case underwent ureteroscopic double-J stent implantation because the opening of the ipsilateral ureter was adjacent to the entrance of the diverticulum.Results Bladder diverticulectomy was successfully performed in the all patients.Median operative time was 160.00(120.00,317.50)min(range:85～345 min).Median estimated blood loss was 20.00(10.00,150.00)mL(range:10～300 mL).No iatrogenic injuries to adjacent organs were observed.Pelvic drains were removed 1～3 d postoperatively,with no urine leakage.Urinary catheters were maintained for 7～10 d after operation.Follow-up at 3～12 months showed no recurrence or hydronephrosis in any of the patients.Conclusion Laparoscopic resection of bladder diverticula guided by ureteral catheter placed into bladder diverticula by means of resectoscope has the advantages of less trauma,less bleeding and faster recovery,and is an effective measure for the treatment of bladder diverticula.

Objective:To develop a deep learning model based on 3D super-resolution reconstruction technology and to analyze its feasibility and effectiveness in predicting paraglottic space invasion in hypopharyngeal cancer.Methods:A retrospective study was conducted involving 382 patients with hypopharyngeal squamous cell carcinoma treated at Qilu Hospital of Shandong University between January 2014 and December 2020. The cohort included 364 males and 18 females, with a mean age of 62±7 years. Patients were divided into a training set ( n=300) and a test set ( n=82) based on enrollment time. A generative adversarial network was used to perform 3D super-resolution reconstruction on contrast-enhanced CT images, improving spatial resolution by 16 times. A 2.5D deep learning strategy was employed to construct Resnet-NR and Resnet-SR models based on conventional and super-resolution images, respectively, to predict whether the paraglottic space was invaded. Model performance was evaluated using receiver operating characteristic (ROC) curves and area under the curve (AUC). A multi-reader multi-case study was conducted to assess the impact of the artificial intelligence (AI) model on clinicians′ diagnostic capabilities. Results:The super-resolution model Resnet-SR achieved the highest accuracy in both the training set (AUC=0.87, 95% CI: 0.84-0.90) and the test set (AUC=0.88, 95% CI: 0.81-0.96), significantly outperforming traditional clinical indicators (T stage, N stage, tumor diameter, and pathological differentiation degree) (AUC range: 0.55-0.70, all P<0.05). In comparison, the conventional-resolution model Resnet-NR achieved AUCs of 0.81 (95% CI: 0.77-0.84, P=0.005) and 0.80 (95% CI: 0.71-0.89, P=0.184) in the training and test sets, respectively. Using Resnet-SR to assist clinical decision-making improved the diagnostic accuracy of junior physicians (AUC=0.793 without AI assistance vs. AUC=0.871 with AI assistance, P=0.012) and significantly reduced diagnosis time for clinicians of all experience levels (86.5 s without AI assistance vs. 82.5 s with AI assistance, t=2.01, P=0.032). Conclusion:This study successfully develops a deep learning model based on 3D super-resolution reconstruction technology, which can assist in preoperative prediction of paraglottic space invasion in hypopharyngeal cancer. The AI-assisted tool improves diagnostic accuracy for junior physicians and enhances diagnostic efficiency for clinicians across all experience levels.

Cholangiocarcinoma has an extremely poor prognosis, and the efficacy of existing treatment methods is limited. In the highly desmoplastic tumor microenvironment of cholangiocarcinoma, cancer-associated fibroblasts (CAFs) are the core regulators. Their significant heterogeneity and complex intercellular crosstalk network are not only key factors driving cholangiocarcinoma progression and drug resistance, but also highly promising therapeutic targets. This review focuses on the characteristics of CAFs in cholangiocarcinoma and the key crosstalk mechanisms between CAFs and tumor cells as well as immune cells, and summarizes the research progress and limitations of current therapeutic strategies targeting CAFs.

Head and neck tumor is a common malignant tumor with increasing incidence and mortality worldwide. Traditional diagnostic methods for head and neck tumor are limited by the lack of specific biomarkers and the limitation of invasive detection methods, as well as high time cost and a high rate of misdiagnosis. Therefore, research on head and neck tumor diagnosis based on new technologies is needed. Hyperspectral imaging (HSI) is a non-contact optical imaging technique that captures a series of images in multiple spectral bands to generate a hyperspectral image cube. HSI has shown its corresponding potential in the early diagnosis, tumor margin identification and clinical research of head and neck cancer.

Due to the significant anatomical location and physiological functions of the larynx, laryngeal lesions can severely impact patients' voice, quality of life, and even survival prognosis, making early diagnosis and treatment crucial. The electronic laryngoscope is the most important auxiliary tool for the early diagnosis and treatment of laryngeal cancer and precancerous lesions. In recent years, the rapid development of artificial intelligence technology has led to increasing applications and research in the field of laryngoscopy, demonstrating enormous potential and value in assisting diagnosis, quality control, and post-treatment evaluation of diseases. It is expected to become a powerful assistant for endoscopists in clinical decision-making and early diagnosis and treatment of laryngeal cancer in the future.

Objective:Castleman's disease is a group of heterogeneous lymphoproliferative disorders with unclear etiology and pathogenesis.This article reports a case of Castleman's disease of the parapharyngeal space, with a comprehensive literature review of the clinical feature and typing, pathologic diagnosis, treatment, and prognosis of the disease.This case is a unicentric type, which is clinically characterized by significant enlargement of lymph nodes without systemic symptoms. The pathology was hyaline vascular type, and the treatment of unicentric type was mostly based on surgery with a better prognosis.
Adult ; Female ; Humans ; Male ; Castleman Disease/diagnosis* ; Lymph Nodes/pathology* ; Parapharyngeal Space ; Prognosis

Pathomics, the integration of digital pathology and artificial intelligence, is used to assess tumor diagnosis, treatment and prognosis by extracting, screening and analyzing the data features contained in pathological pictures. In recent years, more and more pathomics studies of head and neck neoplasms have shown great value in the areas of computer-assisted diagnosis, tumor microenvironment and biomarker identification as well as prognosis evaluation. It is expected to play an important role in clinical assistance and precise treatment of head and neck neoplasms in the future.