Ovarian cancer is a prevalent gynecological malignancy with high mortality and low survival rates. The absence of specific symptoms in early stages often leads to late-stage diagnoses. Standard treatment typically includes surgery followed by platinum and paclitaxel chemotherapy. Exosomes, nanoscale vesicles released by various cell types, are key in intercellular communication, carrying biologically active molecules like proteins, lipids, enzymes, mRNA, and miRNAs. They are involved in tumor microenvironment remodeling, angiogenesis, metastasis, and chemoresistance in ovarian cancer. Emerging research highlights exosomes as drug carriers and therapeutic targets to suppress anti-tumor immune responses. Surface-enhanced Raman scattering (SERS) enables multiplexed, sensitive, and rapid detection of exosome surface proteins, offering advantages such as low background noise, no photobleaching, robustness, and high sensitivity over other detection methods. This review explores the relationship between exosomes and chemoresistance in ovarian cancer, examining the mechanisms by which exosomes contribute to drug resistance and their clinical implications. The goal is to provide new insights into chemoresistance mechanisms, improve diagnosis and intervention strategies, and enhance chemotherapy sensitivity in clinical treatments. In addition, the prospects of exosomes as drug carriers to resist chemical resistance and improve the survival of ovarian cancer patients are summarized. This article emphasizes the role of SERS in detecting ovarian cancer exosomes and advances in exosome detection.

Ovarian cancer is a prevalent gynecological malignancy with high mortality and low survival rates.The absence of specific symptoms in early stages often leads to late-stage diagnoses.Standard treatment typically includes surgery followed by platinum and paclitaxel chemotherapy.Exosomes,nanoscale vesicles released by various cell types,are key in intercellular communication,carrying biologically active molecules like proteins,lipids,enzymes,mRNA,and miRNAs.They are involved in tumor microenvi-ronment remodeling,angiogenesis,metastasis,and chemoresistance in ovarian cancer.Emerging research highlights exosomes as drug carriers and therapeutic targets to suppress anti-tumor immune responses.Surface-enhanced Raman scattering(SERS)enables multiplexed,sensitive,and rapid detec-tion of exosome surface proteins,offering advantages such as low background noise,no photobleaching,robustness,and high sensitivity over other detection methods.This review explores the relationship between exosomes and chemoresistance in ovarian cancer,examining the mechanisms by which exo-somes contribute to drug resistance and their clinical implications.The goal is to provide new insights into chemoresistance mechanisms,improve diagnosis and intervention strategies,and enhance chemotherapy sensitivity in clinical treatments.In addition,the prospects of exosomes as drug carriers to resist chemical resistance and improve the survival of ovarian cancer patients are summarized.This article emphasizes the role of SERS in detecting ovarian cancer exosomes and advances in exosome detection.

Objective:To evaluate the diagnostic value of intestinal tissue metagenomic next-generation sequencing (mNGS) in severe diarrhea following haploidentical allogeneic hematopoietic stem cell transplantation (allo-HSCT) .Methods:Sixteen patients who developed severe diarrhea or hematochezia after haploidentical allo-HSCT at the First Affiliated Hospital of Fujian Medical University (June 2023–August 2024) were enrolled. All underwent gastrointestinal endoscopy and mNGS for microbial detection. Clinical, endoscopic, pathological, and microbiological data were analyzed to evaluate the diagnostic value of mNGS and treatment outcomes following targeted therapy.Results:The study included 16 patients (12 males, 4 females; median age 32.5 years, range 3–60 years). Diarrhea occurred a median of 3.93 months post-transplant (range 1.63–10.40 months). Stool cultures were negative except for one case with Candida. One patient tested positive for Clostridium difficile antigen. Endoscopy revealed mucosal congestion, edema, erosion, and bleeding, with focal inflammation on pathology. mNGS detected pathogens in 87.5% (14/16) of cases, including mixed infections in 78.5% (11/14). Common pathogens were Klebsiella pneumoniae, Enterococcus faecium, Escherichia coli, Rhizopus microsporus, EBV, and CMV. Targeted treatment adjustments led to symptom improvement in 87.5% of patients.Conclusion:Allo-HSCT patients are prone to infectious diarrhea due to immunosuppression. Molecular analysis of endoscopic biopsy tissues using mNGS can accurately identify pathogens, guide targeted therapy, and improve clinical outcomes.

Objective:To develop a deep learning-based system for real-time recognition and classification of portal hypertensive gastropathy (PHG) and evaluate its ability to assist junior endoscopists.Methods:A total of 2 848 gastroscopy images from 832 patients with liver cirrhosis were selected from Digestive Endoscopy Center databases of Renmin Hospital of Wuhan University, Wuhan Hospital of Traditional Chinese and Western Medicine, and the Second Hospital of Jingzhou from January 2015 to October 2023. This system referred to 3 endoscopic features of Baveno Ⅱ scoring system. Three models were developed respectively for gastric antral vascular ectasia (GAVE), mosaic-like pattern (MLP), and red marks (RM). The specific classification references were as follows: (1) GAVE model: 0 no, 1 yes; (2) MLP model: 0 no, 1 mild, 2 severe; (3) RM model: 0 no, 1 isolated, 2 fused. The classification results for endoscopic characteristics of PHG of 3 endoscopy experts were taken as the gold standard. The yolov8-m model was used for training. The training dataset, validation dataset, and test dataset were allocated at a ratio of 8∶1∶1. The test dataset was used to evaluate the performance of models and their auxiliary effects on endoscopists. The accuracy, recall, precision, specificity and Kappa coefficient were calculated. Results:The accuracy, recall, specificity of GAVE model were 96.0% (48/50), 87.5% (7/8) and 97.6% (41/42). There was no significant difference between its accuracy and the gold standard ( χ2=316.226, P=1.000). The precision of GAVE1 and GAVE0 were 87.5% (7/8) and 97.6% (41/42) respectively. The accuracy of MLP model was 84.1% (132/157), and there was no significant difference compared with the gold standard ( χ2=3.286, P=0.193). The precision and recall of MLP2 were 88.2% (15/17) and 75.0% (15/20). The precision and recall of MLP1 were 77.9% (60/77) and 88.2% (60/68). The precision and recall of MLP0 were 90.5% (57/63) and 82.6% (57/69). The accuracy of RM model was 87.9% (123/140), and there was no significant difference compared with the gold standard ( χ2=2.891, P=0.409). The precision and recall of RM2 were 94.7% (18/19) and 78.3% (18/23). The precision and recall of RM1 were 72.2% (26/36) and 81.3% (26/32). The precision and recall of RM0 were 92.9% (79/85) and 92.9% (79/85). The mean accuracy of the three junior endoscopists, with and without the assistance of the GAVE model, MLP model, and RM model, respectively increased from 95.3% to 99.3%, from 83.9% to 91.9%, and from 81.9% to 83.1%. The overall consistency analysis of the 3 junior endoscopists with the gold standard indicated that the consistency of the GAVE model before and after assistance was extremely strong (both an overall Kappa of 1.000); the consistency before assistance of the MLP model was moderate (with an overall Kappa of 0.601), which increased to extremely strong after assistance (with an overall Kappa of 0.964); and the consistency of the RM model before and after assistance was also relatively strong (with an overall Kappa of 0.792 before and 0.798 after). Conclusion:The deep learning system accurately identifies and classifies PHG features and significantly enhances diagnostic performance of junior endoscopists.

Objective:To develop and evaluate a deep learning-based automatic measurement model for panoramic ultrasound biomicroscopy (UBM) images.Methods:A diagnostic test study was conducted.Preoperative UBM examination results of 372 patients who underwent implantable collamer lens (ICL) implantation were collected at the Eye Center of Renmin Hospital of Wuhan University between February 2021 and March 2023.A total of 1 368 panoramic UBM images were obtained to establish an image database.The dataset was divided into a training set (760 images), a validation set (86 images) and an internal test set (522 images).An expert panel consisting of three ophthalmologists annotated the images.The UNet+ + network was used to automatically segment anterior segment tissues, such as the cornea, lens and iris.In addition, image processing techniques and geometric localization algorithms were developed to automatically identify the anatomical landmarks of pupil diameter (PD), anterior chamber depth (ACD), angle-to-angle distance (ATA) and sulcus-to-sulcus distance (STS) to complete the measurement of these parameters.Additionally, 480 panoramic UBM images of 135 patients (240 eyes) from Aier Eye Hospital of Wuhan University were used as an external test set to further evaluate the performance of the model in different centers.The consistency between the measurements from the model and expert panel, the Pentacam system was assessed.Finally, 150 images were randomly selected from the external test set for a human-machine comparison to further evaluate the model's performance.This study adhered to the Declaration of Helsinki.The study protocol was approved by the Ethics Committee of Renmin Hospital of Wuhan University (No.WDRY-2022-K109) and Aier eye Hospital of Wuhan University (No.2023IRBKY120903).Written informed consent was obtained from each subject.Results:In the internal test dataset and external test dataset, with manual labeling as the reference standard, the model achieved a mean Dice coefficient of not less than 0.882.At least 95.65% of the anatomical landmark localization results had Euclidean distance differences within 250 μm.The intraclass correlation coefficients (ICCs) for the measurements of PD, ACD, angle-to-angle ATA, and STS were at least 0.958, with mean relative errors not exceeding 2.407%.With the Pentacam measurements as the reference standard, the ICCs for PD in the internal and external test sets were 0.540 and 0.466, respectively, while the ICCs for ACD were 0.946 and 0.908, respectively.In the human-machine comparison, the ICCs between the model's measurements and those of senior experts were all not lower than 0.969.Conclusions:The deep learning-based model can automatically measure anterior segment parameters from preoperative panoramic UBM images of patients undergoing ICL surgery.The model demonstrates a consistency comparable to that of senior experts, while providing higher efficiency.In terms of ACD measurement, the model shows good agreement between the measurements obtained from the model and Pentacam system.

Objective:To develop a deep learning-based system for real-time recognition and classification of portal hypertensive gastropathy (PHG) and evaluate its ability to assist junior endoscopists.Methods:A total of 2 848 gastroscopy images from 832 patients with liver cirrhosis were selected from Digestive Endoscopy Center databases of Renmin Hospital of Wuhan University, Wuhan Hospital of Traditional Chinese and Western Medicine, and the Second Hospital of Jingzhou from January 2015 to October 2023. This system referred to 3 endoscopic features of Baveno Ⅱ scoring system. Three models were developed respectively for gastric antral vascular ectasia (GAVE), mosaic-like pattern (MLP), and red marks (RM). The specific classification references were as follows: (1) GAVE model: 0 no, 1 yes; (2) MLP model: 0 no, 1 mild, 2 severe; (3) RM model: 0 no, 1 isolated, 2 fused. The classification results for endoscopic characteristics of PHG of 3 endoscopy experts were taken as the gold standard. The yolov8-m model was used for training. The training dataset, validation dataset, and test dataset were allocated at a ratio of 8∶1∶1. The test dataset was used to evaluate the performance of models and their auxiliary effects on endoscopists. The accuracy, recall, precision, specificity and Kappa coefficient were calculated. Results:The accuracy, recall, specificity of GAVE model were 96.0% (48/50), 87.5% (7/8) and 97.6% (41/42). There was no significant difference between its accuracy and the gold standard ( χ2=316.226, P=1.000). The precision of GAVE1 and GAVE0 were 87.5% (7/8) and 97.6% (41/42) respectively. The accuracy of MLP model was 84.1% (132/157), and there was no significant difference compared with the gold standard ( χ2=3.286, P=0.193). The precision and recall of MLP2 were 88.2% (15/17) and 75.0% (15/20). The precision and recall of MLP1 were 77.9% (60/77) and 88.2% (60/68). The precision and recall of MLP0 were 90.5% (57/63) and 82.6% (57/69). The accuracy of RM model was 87.9% (123/140), and there was no significant difference compared with the gold standard ( χ2=2.891, P=0.409). The precision and recall of RM2 were 94.7% (18/19) and 78.3% (18/23). The precision and recall of RM1 were 72.2% (26/36) and 81.3% (26/32). The precision and recall of RM0 were 92.9% (79/85) and 92.9% (79/85). The mean accuracy of the three junior endoscopists, with and without the assistance of the GAVE model, MLP model, and RM model, respectively increased from 95.3% to 99.3%, from 83.9% to 91.9%, and from 81.9% to 83.1%. The overall consistency analysis of the 3 junior endoscopists with the gold standard indicated that the consistency of the GAVE model before and after assistance was extremely strong (both an overall Kappa of 1.000); the consistency before assistance of the MLP model was moderate (with an overall Kappa of 0.601), which increased to extremely strong after assistance (with an overall Kappa of 0.964); and the consistency of the RM model before and after assistance was also relatively strong (with an overall Kappa of 0.792 before and 0.798 after). Conclusion:The deep learning system accurately identifies and classifies PHG features and significantly enhances diagnostic performance of junior endoscopists.

Objective:To develop and evaluate a deep learning-based automatic measurement model for panoramic ultrasound biomicroscopy (UBM) images.Methods:A diagnostic test study was conducted.Preoperative UBM examination results of 372 patients who underwent implantable collamer lens (ICL) implantation were collected at the Eye Center of Renmin Hospital of Wuhan University between February 2021 and March 2023.A total of 1 368 panoramic UBM images were obtained to establish an image database.The dataset was divided into a training set (760 images), a validation set (86 images) and an internal test set (522 images).An expert panel consisting of three ophthalmologists annotated the images.The UNet+ + network was used to automatically segment anterior segment tissues, such as the cornea, lens and iris.In addition, image processing techniques and geometric localization algorithms were developed to automatically identify the anatomical landmarks of pupil diameter (PD), anterior chamber depth (ACD), angle-to-angle distance (ATA) and sulcus-to-sulcus distance (STS) to complete the measurement of these parameters.Additionally, 480 panoramic UBM images of 135 patients (240 eyes) from Aier Eye Hospital of Wuhan University were used as an external test set to further evaluate the performance of the model in different centers.The consistency between the measurements from the model and expert panel, the Pentacam system was assessed.Finally, 150 images were randomly selected from the external test set for a human-machine comparison to further evaluate the model's performance.This study adhered to the Declaration of Helsinki.The study protocol was approved by the Ethics Committee of Renmin Hospital of Wuhan University (No.WDRY-2022-K109) and Aier eye Hospital of Wuhan University (No.2023IRBKY120903).Written informed consent was obtained from each subject.Results:In the internal test dataset and external test dataset, with manual labeling as the reference standard, the model achieved a mean Dice coefficient of not less than 0.882.At least 95.65% of the anatomical landmark localization results had Euclidean distance differences within 250 μm.The intraclass correlation coefficients (ICCs) for the measurements of PD, ACD, angle-to-angle ATA, and STS were at least 0.958, with mean relative errors not exceeding 2.407%.With the Pentacam measurements as the reference standard, the ICCs for PD in the internal and external test sets were 0.540 and 0.466, respectively, while the ICCs for ACD were 0.946 and 0.908, respectively.In the human-machine comparison, the ICCs between the model's measurements and those of senior experts were all not lower than 0.969.Conclusions:The deep learning-based model can automatically measure anterior segment parameters from preoperative panoramic UBM images of patients undergoing ICL surgery.The model demonstrates a consistency comparable to that of senior experts, while providing higher efficiency.In terms of ACD measurement, the model shows good agreement between the measurements obtained from the model and Pentacam system.

Objective:To evaluate the diagnostic value of intestinal tissue metagenomic next-generation sequencing (mNGS) in severe diarrhea following haploidentical allogeneic hematopoietic stem cell transplantation (allo-HSCT) .Methods:Sixteen patients who developed severe diarrhea or hematochezia after haploidentical allo-HSCT at the First Affiliated Hospital of Fujian Medical University (June 2023–August 2024) were enrolled. All underwent gastrointestinal endoscopy and mNGS for microbial detection. Clinical, endoscopic, pathological, and microbiological data were analyzed to evaluate the diagnostic value of mNGS and treatment outcomes following targeted therapy.Results:The study included 16 patients (12 males, 4 females; median age 32.5 years, range 3–60 years). Diarrhea occurred a median of 3.93 months post-transplant (range 1.63–10.40 months). Stool cultures were negative except for one case with Candida. One patient tested positive for Clostridium difficile antigen. Endoscopy revealed mucosal congestion, edema, erosion, and bleeding, with focal inflammation on pathology. mNGS detected pathogens in 87.5% (14/16) of cases, including mixed infections in 78.5% (11/14). Common pathogens were Klebsiella pneumoniae, Enterococcus faecium, Escherichia coli, Rhizopus microsporus, EBV, and CMV. Targeted treatment adjustments led to symptom improvement in 87.5% of patients.Conclusion:Allo-HSCT patients are prone to infectious diarrhea due to immunosuppression. Molecular analysis of endoscopic biopsy tissues using mNGS can accurately identify pathogens, guide targeted therapy, and improve clinical outcomes.

Objective:To explore the clinical application value of a deep learning algorithm-based ultrasound biomicroscopy (UBM) image analysis system for primary angles-closure glaucoma (PACG) anterior located ciliary body.Methods:A diagnostic test study was conducted.A total of 2 132 UBM images from 726 eyes of 378 PACG patients who underwent UBM examination were collected at Renmin Hospital of Wuhan University from August 2022 to December 2023.The dataset was divided into a training set of 1 599 images and a test set of 533 images, and a deep learning algorithm was employed to construct a model.An additional 334 UBM images from 101 eyes of 69 PACG patients treated at Huangshi Aier Eye Hospital were selected to conduct external testing.A separate set of another 110 UBM images were selected for a human-machine competition to compare the accuracy and speed between anterior located ciliary body evaluation system and three senior ophthalmologists.Furthermore, eight junior ophthalmologists assessed the 110 UBM images independently without and with the assistance of the model, and the differences between the two evaluations were analyzed to assess the assisstance effect of the model.This study adhered to the Declaration of Helsinki.The study protocol was approved by the Ethics Committee of Renmin Hospital of Wuhan University (No.WDRY-2022-K109).Results:The model achieved an accuracy of 93.43% for anterior located ciliary body identification in the internal test set, with a sensitivity of 84.30% and a specificity of 97.78%.The model also performed well on the external test set with an accuracy of 92.81%.In the human-machine competition, the model's accuracy was comparable to that of the senior ophthalmologists and outperformed two of the three senior ophthalmologists.The average total time of the three senior ophthalmologists was 726.73 seconds, approximately 12.47 times longer than the model's 58.30 seconds.With model assistance, the diagnostic accuracy of the eight junior ophthalmologists was 86.71%, which was significantly higher than 76.25% without model assistance ( χ2=-7.550, P<0.001).And the image evaluation time was (714.91±213.82)seconds, which was significantly lower than (987.90±238.56)seconds without model assistance ( t=2.774, P<0.05). Conclusions:The UBM image analysis system based on a deep learning algorithm demonstrates high accuracy in diagnosing anterior located ciliary body in PACG and provides a strong support for the UBM image recognition training of junior ophthalmologists.

Objective:To construct an artificial intelligence (AI)-assisted system based on deep learning for corneal in vivo confocal microscopy (IVCM) image recognition and to evaluate its value in clinical applications. Methods:A diagnostic study was conducted.A total of 18 860 corneal images were collected from 331 subjects who underwent IVCM examination at Renmin Hospital of Wuhan University and Zhongnan Hospital of Wuhan University from May 2021 to September 2022.The collected images were used for model training and testing after being reviewed and classified by corneal experts.The model design included a low-quality image filtering model, a corneal image diagnosis model, and a 4-layer identification model for corneal epithelium, Bowman membrane, stroma, and endothelium, to initially determine normal and abnormal corneal images and corresponding corneal layers.A human-machine competition was conducted with another 360 database-independent IVCM images to compare the accuracy and time spent on image recognition by three senior ophthalmologists and the AI system.In addition, 8 trainees without IVCM training and with less than three years of clinical experience were selected to recognize the same 360 images without and with model assistance to analyze the effectiveness of model assistance.This study adhered to the Declaration of Helsinki.The study protocol was approved by the Ethics Committee of Renmin Hospital of Wuhan University (No.WDRY2021-K148).Results:The accuracy of this diagnostic model in screening high-quality images was 0.954.Its overall accuracy in identifying normal/abnormal corneal images was 0.916 and 0.896 in the internal and external test sets, respectively.Its accuracy reached 0.983, 0.925 in the internal test sets and 0.988, 0.929 in the external test sets in identifying corneal layers of normal and abnormal images, respectively.In the human-machine competition, the overall recognition accuracy of the model was 0.878, which was similar to the average accuracy of the three senior physicians and was approximately 300 times faster than the experts in recognition speed.Trainees assisted by the system achieved an accuracy of 0.816±0.043 in identifying corneal layers of normal and abnormal images, which was significantly higher than 0.669±0.061 without model assistance ( t=6.304, P<0.001). Conclusions:A deep learning-based assistant system for corneal IVCM image recognition is successfully constructed.This system can discriminate normal/abnormal corneal images and diagnose the corresponding corneal layer of the images, which can improve the efficiency of clinical diagnosis and assist doctors in training and learning.