AIM:To support probe-based confocal laser endomi-croscopy (pCLE) diagnosis by designing software for the automated classification of colonic polyps. METHODS:Intravenous fluorescein pCLE imaging of colorectal lesions w...AIM:To support probe-based confocal laser endomi-croscopy (pCLE) diagnosis by designing software for the automated classification of colonic polyps. METHODS:Intravenous fluorescein pCLE imaging of colorectal lesions was performed on patients under-going screening and surveillance colonoscopies, followed by polypectomies. All resected specimens were reviewed by a reference gastrointestinal pathologist blinded to pCLE information. Histopathology was used as the criterion standard for the differentiation between neoplastic and non-neoplastic lesions. The pCLE video sequences, recorded for each polyp, were analyzed off-line by 2 expert endoscopists who were blinded to the endoscopic characteristics and histopathology. These pCLE videos, along with their histopathology diagnosis, were used to train the automated classification software which is a content-based image retrieval technique followed by k-nearest neighbor classification. The performance of the off-line diagnosis of pCLE videos established by the 2 expert endoscopists was compared with that of automated pCLE software classification. All evaluations were performed using leave-one-patient- out cross-validation to avoid bias. RESULTS:Colorectal lesions (135) were imaged in 71 patients. Based on histopathology, 93 of these 135 lesions were neoplastic and 42 were non-neoplastic. The study found no statistical significance for the difference between the performance of automated pCLE software classification (accuracy 89.6%, sensitivity 92.5%, specificity 83.3%, using leave-one-patient-out cross-validation) and the performance of the off-line diagnosis of pCLE videos established by the 2 expert endoscopists (accuracy 89.6%, sensitivity 91.4%, specificity 85.7%). There was very low power (< 6%) to detect the observed differences. The 95% confidence intervals for equivalence testing were:-0.073 to 0.073 for accuracy, -0.068 to 0.089 for sensitivity and -0.18 to 0.13 for specificity. The classification software proposed in this study is not a "black box" but an informative tool based on the query by example model that produces, as intermediate results, visually similar annotated videos that are directly interpretable by the endoscopist. CONCLUSION:The proposed software for automated classification of pCLE videos of colonic polyps achieves high performance, comparable to that of off-line diagnosis of pCLE videos established by expert endoscopists.展开更多
Objective： Probe-based confoeal laser endomicroscopy （pCLE） technique may improve the diagnosis of gastric mucosal lesions allowing acquisition of high-resolution in vivo images at the cellular and mierovaseular le...Objective： Probe-based confoeal laser endomicroscopy （pCLE） technique may improve the diagnosis of gastric mucosal lesions allowing acquisition of high-resolution in vivo images at the cellular and mierovaseular levels. This study aims to evaluate the accuracy of pCLE for the differential diagnosis of non-neoplastic and neoplastic gastric lesions.Methods： Twenty gastric mucosal lesions from 10 patients were evaluated during endoscopic procedure and were examined by pCLE. Diagnostic pCLE was followed by biopsies or endoscopic resection of suspected lesions. A senior pathologist evaluated the specimens and was blinded to the pCLE results.Results： Patients＇ mean age was 68.3 （range, 42-83） years and six were men. Thirteen suspicious flat or elevated lesions （classified as 0-Is, 0-IIa or 0-IIa ＋ IIc） and seven pre-malignant lesions （atrophy and intestinal metaplasia） were evaluated. One patient was studied during his long-term follow-up after partial gastrectomy and presented severe atrophy, intestinal metaplasia, and xanthomas at the stump mucosa. The location of gastric lesions was in the body （n=10 lesions）, the antrum （n=9） and the incisura angularis （n=1）. All neoplastic lesions and all but one benign lesion were properly diagnosed by pCLE. pCLE incorrectly diagnosed one small antrum lesion as adenoma, however the final diagnosis was intestinal metaplasia. The final histological diagnosis was neoplastic in 9 and benign lesions in 11. In this small case series, pCLE accuracy was 95% （19/20 lesions）.Conclusions： pCLE is accurate for real time histology of gastric lesions, pCLE may change the management of patients with gastric mucosal lesions, guiding biopsies and endoscopic resection, and avoiding further diagnostic workup or unnecessary therapy.展开更多
BACKGROUND Early detection of esophageal squamous neoplasms(ESN)is essential for improving patient prognosis.Optical diagnosis of ESN remains challenging.Probebased confocal laser endomicroscopy(pCLE)enables accurate ...BACKGROUND Early detection of esophageal squamous neoplasms(ESN)is essential for improving patient prognosis.Optical diagnosis of ESN remains challenging.Probebased confocal laser endomicroscopy(pCLE)enables accurate in vivo histological observation and optical biopsy of ESN.However,interpretation of pCLE images requires histopathological expertise and extensive training.Artificial intelligence(AI)has been widely applied in digestive endoscopy;however,AI for pCLE diagnosis of ESN has not been reported.AIM To develop a pCLE computer-aided diagnostic system for ESN and assess its diagnostic performance and assistant efficiency for nonexpert endoscopists.METHODS The intelligent confocal laser endomicroscopy(iCLE)system consists of image recognition(based on inception-ResNet V2),video diagnosis,and quality judgment modules.This system was developed using pCLE images and videos and evaluated through image and prospective video recognition tests.Patients between June 2020 and January 2023 were prospectively enrolled.Expert and nonexpert endoscopists and the iCLE independently performed diagnoses for pCLE videos,with histopathology as the gold standard.Thereafter,the non-expert endoscopists performed a second assessment with iCLE assistance.RESULTS A total of 25056 images from 2803 patients were selected for iCLE training and validation.Another 2442 images from 226 patients were used for testing.iCLE achieved a high accuracy of 98.3%,sensitivity of 95.3%and specificity of 98.8%for diagnosing ESN images.A total of 2581 patients underwent upper gastrointestinal pCLE examination and were prospectively screened;54 patients with suspected ESN were enrolled.Overall,187 videos from 67 lesions were assessed by iCLE,three nonexpert and three expert endoscopists.iCLE achieved a high accuracy,sensitivity and specificity of 90.9%,92.0%,and 90.2%,respectively.Compared to experts,iCLE showed significantly higher sensitivity(92.0%vs 80.4%;P<0.001)and negative predictive value(94.4%vs 87.7%;P=0.003).With iCLE assistance,nonexpert endoscopists showed significant improvements in accuracy(from 83.6%to 88.6%)and sensitivity(from 76.0%to 89.8%).CONCLUSION iCLE system demonstrated high diagnostic performance for ESN.It can assist nonexpert endoscopists in improving the diagnostic efficiency of pCLE for ESN and has the potential for reducing unnecessary biopsies.展开更多
The risk of developing neoplasia leading to colorectal cancer is significantly increased in ulcerative colitis (UC) and most likely in Crohn's disease. Several endoscopic surveillance strategies have been implemen...The risk of developing neoplasia leading to colorectal cancer is significantly increased in ulcerative colitis (UC) and most likely in Crohn's disease. Several endoscopic surveillance strategies have been implemented to identify these lesions. The main issue is that colitisassociated neoplasms often occurs in flat mucosa, often being detected on taking random biopsies rather than by identification of these lesions via endoscopic imaging. The standard diagnostic procedure in long lasting UC is to take four biopsies every 10 cm. Image enhancement methods, such as chromoendoscopy and virtual histology using endomicroscopy, have greatly im- proved neoplasia detection rates and may contribute toreduced random biopsies by taking targeted "smart" biopsies. Chromoendoscopy may effectively be performed by experienced endoscopists for routine screening of UC patients. By contrast, endomicroscopy is often only available in selected specialized endoscopic centers. Importantly, advanced endoscopic imaging has the poten- tial to increase the detection rate of neoplasia whereas the interplay between endoscopic experience and interpretation of histological biopsy evaluation allows the physician to make a proper diagnosis and to find the appropriate therapeutic approach. Colitis-associated intraepithelial neoplasms may occur in flat mucosa of endoscopically normal appearance or may arise as dysplasia-associated lesion or mass (DALM), which may be indistinguishable from sporadic adenomas in healthy or non-colitis mucosa [adenoma-like mass (ALM)]. The aim of this review was to summarize endoscopic and histological characteristics of DALM and ALM in the context of therapeutic procedures.展开更多
This paper presents a probe-based force-controlled nanoindentation method to fabricate ordered micro/nanostructures.Both the experimental and finite element simulation approaches are employed to investigate the influe...This paper presents a probe-based force-controlled nanoindentation method to fabricate ordered micro/nanostructures.Both the experimental and finite element simulation approaches are employed to investigate the influence of the interval between the adjacent indentations and the rotation angle of the probe on the formed micro/nanostructures.The non-contacting part between indenter and the sample material and the height of the material pile-up are two competing factors to determine the depth relationship between the adjacent indentations.For the one array indentations,nanostructures with good depth consistency and periodicity can be formed after the depth of the indentation becoming stable,and the variation of the rotation angle results in the large difference between the morphology of the formed nanostructures at the bottom of the one array indentation.In addition,for the indentation arrays,the nanostructures with good consistency and periodicity of the shape and depth can be generated with the spacing greater than 1μm.Finally,Raman tests are also carried out based on the obtained ordered micro/nanostructures with Rhodamine probe molecule.The indentation arrays with a smaller spacing lead to better the enhancement effect of the substrate,which has the potential applications in the fields of biological or chemical molecular detection.展开更多
BACKGROUND Transanal total mesorectal excision(TaTME)allows patients with ultralow rectal cancer to be treated with sphincter-saving surgery.However,accurate delineation of the distal resection margin(DRM),which is es...BACKGROUND Transanal total mesorectal excision(TaTME)allows patients with ultralow rectal cancer to be treated with sphincter-saving surgery.However,accurate delineation of the distal resection margin(DRM),which is essential to achieve R0 resection for low rectal cancer in TaTME,is technically demanding.AIM To assess the feasibility of optical biopsy using probe-based confocal laser endomicroscopy(pCLE)to select the DRM during TaTME for low rectal cancer.METHODS A total of 43 consecutive patients who were diagnosed with low rectal cancer and scheduled for TaTME were prospectively enrolled from January 2019 to January 2021.pCLE was used to determine the distal edge of the tumor as well as the DRM during surgery.The final pathological report was used as the gold standard.The diagnostic accuracy of pCLE examination was calculated.RESULTS A total of 86 pCLE videos of 43 patients were included in the analyses.The sensitivity,specificity and accuracy of real-time pCLE examination were 90.00%[95%confidence interval(CI):76.34%-97.21%],86.96%(95%CI:73.74%-95.06%)and 88.37%(95%CI:79.65%-94.28%),respectively.The accuracy of blinded pCLE reinterpretation was 86.05%(95%CI:76.89%-92.58%).Furthermore,our results show satisfactory interobserver agreement(κ=0.767,standard error=0.069)for the detection of cancer tissue by pCLE.There were no positive DRMs(≤1 mm)in this study.The median DRM was 7 mm[interquartile range(IQR)=5-10 mm].The median Wexner score was 5(IQR=3-6)at 6 mo after stoma closure.CONCLUSION Real-time in vivo pCLE examination is feasible and safe for selecting the DRM during TaTME for low rectal cancer(clinical trial registration number:NCT04016948).展开更多
文摘AIM:To support probe-based confocal laser endomi-croscopy (pCLE) diagnosis by designing software for the automated classification of colonic polyps. METHODS:Intravenous fluorescein pCLE imaging of colorectal lesions was performed on patients under-going screening and surveillance colonoscopies, followed by polypectomies. All resected specimens were reviewed by a reference gastrointestinal pathologist blinded to pCLE information. Histopathology was used as the criterion standard for the differentiation between neoplastic and non-neoplastic lesions. The pCLE video sequences, recorded for each polyp, were analyzed off-line by 2 expert endoscopists who were blinded to the endoscopic characteristics and histopathology. These pCLE videos, along with their histopathology diagnosis, were used to train the automated classification software which is a content-based image retrieval technique followed by k-nearest neighbor classification. The performance of the off-line diagnosis of pCLE videos established by the 2 expert endoscopists was compared with that of automated pCLE software classification. All evaluations were performed using leave-one-patient- out cross-validation to avoid bias. RESULTS:Colorectal lesions (135) were imaged in 71 patients. Based on histopathology, 93 of these 135 lesions were neoplastic and 42 were non-neoplastic. The study found no statistical significance for the difference between the performance of automated pCLE software classification (accuracy 89.6%, sensitivity 92.5%, specificity 83.3%, using leave-one-patient-out cross-validation) and the performance of the off-line diagnosis of pCLE videos established by the 2 expert endoscopists (accuracy 89.6%, sensitivity 91.4%, specificity 85.7%). There was very low power (< 6%) to detect the observed differences. The 95% confidence intervals for equivalence testing were:-0.073 to 0.073 for accuracy, -0.068 to 0.089 for sensitivity and -0.18 to 0.13 for specificity. The classification software proposed in this study is not a "black box" but an informative tool based on the query by example model that produces, as intermediate results, visually similar annotated videos that are directly interpretable by the endoscopist. CONCLUSION:The proposed software for automated classification of pCLE videos of colonic polyps achieves high performance, comparable to that of off-line diagnosis of pCLE videos established by expert endoscopists.
基金partially supported by FINEP(Financiadora de Estudos e Projetos)from Brazilian Ministry of Health
文摘Objective： Probe-based confoeal laser endomicroscopy （pCLE） technique may improve the diagnosis of gastric mucosal lesions allowing acquisition of high-resolution in vivo images at the cellular and mierovaseular levels. This study aims to evaluate the accuracy of pCLE for the differential diagnosis of non-neoplastic and neoplastic gastric lesions.Methods： Twenty gastric mucosal lesions from 10 patients were evaluated during endoscopic procedure and were examined by pCLE. Diagnostic pCLE was followed by biopsies or endoscopic resection of suspected lesions. A senior pathologist evaluated the specimens and was blinded to the pCLE results.Results： Patients＇ mean age was 68.3 （range, 42-83） years and six were men. Thirteen suspicious flat or elevated lesions （classified as 0-Is, 0-IIa or 0-IIa ＋ IIc） and seven pre-malignant lesions （atrophy and intestinal metaplasia） were evaluated. One patient was studied during his long-term follow-up after partial gastrectomy and presented severe atrophy, intestinal metaplasia, and xanthomas at the stump mucosa. The location of gastric lesions was in the body （n=10 lesions）, the antrum （n=9） and the incisura angularis （n=1）. All neoplastic lesions and all but one benign lesion were properly diagnosed by pCLE. pCLE incorrectly diagnosed one small antrum lesion as adenoma, however the final diagnosis was intestinal metaplasia. The final histological diagnosis was neoplastic in 9 and benign lesions in 11. In this small case series, pCLE accuracy was 95% （19/20 lesions）.Conclusions： pCLE is accurate for real time histology of gastric lesions, pCLE may change the management of patients with gastric mucosal lesions, guiding biopsies and endoscopic resection, and avoiding further diagnostic workup or unnecessary therapy.
基金Supported by the National Key Research and Development Program of China,No.2023YFC2413800the Taishan Scholars Program of Shandong Province,No.tsqn202306344the National Natural Science Foundation of China,No.82270580 and No.82070552.
文摘BACKGROUND Early detection of esophageal squamous neoplasms(ESN)is essential for improving patient prognosis.Optical diagnosis of ESN remains challenging.Probebased confocal laser endomicroscopy(pCLE)enables accurate in vivo histological observation and optical biopsy of ESN.However,interpretation of pCLE images requires histopathological expertise and extensive training.Artificial intelligence(AI)has been widely applied in digestive endoscopy;however,AI for pCLE diagnosis of ESN has not been reported.AIM To develop a pCLE computer-aided diagnostic system for ESN and assess its diagnostic performance and assistant efficiency for nonexpert endoscopists.METHODS The intelligent confocal laser endomicroscopy(iCLE)system consists of image recognition(based on inception-ResNet V2),video diagnosis,and quality judgment modules.This system was developed using pCLE images and videos and evaluated through image and prospective video recognition tests.Patients between June 2020 and January 2023 were prospectively enrolled.Expert and nonexpert endoscopists and the iCLE independently performed diagnoses for pCLE videos,with histopathology as the gold standard.Thereafter,the non-expert endoscopists performed a second assessment with iCLE assistance.RESULTS A total of 25056 images from 2803 patients were selected for iCLE training and validation.Another 2442 images from 226 patients were used for testing.iCLE achieved a high accuracy of 98.3%,sensitivity of 95.3%and specificity of 98.8%for diagnosing ESN images.A total of 2581 patients underwent upper gastrointestinal pCLE examination and were prospectively screened;54 patients with suspected ESN were enrolled.Overall,187 videos from 67 lesions were assessed by iCLE,three nonexpert and three expert endoscopists.iCLE achieved a high accuracy,sensitivity and specificity of 90.9%,92.0%,and 90.2%,respectively.Compared to experts,iCLE showed significantly higher sensitivity(92.0%vs 80.4%;P<0.001)and negative predictive value(94.4%vs 87.7%;P=0.003).With iCLE assistance,nonexpert endoscopists showed significant improvements in accuracy(from 83.6%to 88.6%)and sensitivity(from 76.0%to 89.8%).CONCLUSION iCLE system demonstrated high diagnostic performance for ESN.It can assist nonexpert endoscopists in improving the diagnostic efficiency of pCLE for ESN and has the potential for reducing unnecessary biopsies.
文摘The risk of developing neoplasia leading to colorectal cancer is significantly increased in ulcerative colitis (UC) and most likely in Crohn's disease. Several endoscopic surveillance strategies have been implemented to identify these lesions. The main issue is that colitisassociated neoplasms often occurs in flat mucosa, often being detected on taking random biopsies rather than by identification of these lesions via endoscopic imaging. The standard diagnostic procedure in long lasting UC is to take four biopsies every 10 cm. Image enhancement methods, such as chromoendoscopy and virtual histology using endomicroscopy, have greatly im- proved neoplasia detection rates and may contribute toreduced random biopsies by taking targeted "smart" biopsies. Chromoendoscopy may effectively be performed by experienced endoscopists for routine screening of UC patients. By contrast, endomicroscopy is often only available in selected specialized endoscopic centers. Importantly, advanced endoscopic imaging has the poten- tial to increase the detection rate of neoplasia whereas the interplay between endoscopic experience and interpretation of histological biopsy evaluation allows the physician to make a proper diagnosis and to find the appropriate therapeutic approach. Colitis-associated intraepithelial neoplasms may occur in flat mucosa of endoscopically normal appearance or may arise as dysplasia-associated lesion or mass (DALM), which may be indistinguishable from sporadic adenomas in healthy or non-colitis mucosa [adenoma-like mass (ALM)]. The aim of this review was to summarize endoscopic and histological characteristics of DALM and ALM in the context of therapeutic procedures.
基金National Natural Science Foundation of China(Grant Nos.52035004,51911530206,51905047)Heilongjiang Provincial Natural Science Foundation of China(Grant No.YQ2020E015)+1 种基金Self-Planned Task of State Key Laboratory of Robotics and System(HIT)(Grant No.SKLRS202001C)Young Elite Scientist Sponsorship Program by CAST(Grant No.YESS20200155).
文摘This paper presents a probe-based force-controlled nanoindentation method to fabricate ordered micro/nanostructures.Both the experimental and finite element simulation approaches are employed to investigate the influence of the interval between the adjacent indentations and the rotation angle of the probe on the formed micro/nanostructures.The non-contacting part between indenter and the sample material and the height of the material pile-up are two competing factors to determine the depth relationship between the adjacent indentations.For the one array indentations,nanostructures with good depth consistency and periodicity can be formed after the depth of the indentation becoming stable,and the variation of the rotation angle results in the large difference between the morphology of the formed nanostructures at the bottom of the one array indentation.In addition,for the indentation arrays,the nanostructures with good consistency and periodicity of the shape and depth can be generated with the spacing greater than 1μm.Finally,Raman tests are also carried out based on the obtained ordered micro/nanostructures with Rhodamine probe molecule.The indentation arrays with a smaller spacing lead to better the enhancement effect of the substrate,which has the potential applications in the fields of biological or chemical molecular detection.
基金Supported by the National Natural Science Foundation of China,No.82273360the Science and Technology Planning Project of Guangzhou City,No.202206010085+1 种基金the Clinical Research Project of Southern Medical University,No.LC2016PY010the Clinical Research Project of Nanfang Hospital,No.2018CR034.
文摘BACKGROUND Transanal total mesorectal excision(TaTME)allows patients with ultralow rectal cancer to be treated with sphincter-saving surgery.However,accurate delineation of the distal resection margin(DRM),which is essential to achieve R0 resection for low rectal cancer in TaTME,is technically demanding.AIM To assess the feasibility of optical biopsy using probe-based confocal laser endomicroscopy(pCLE)to select the DRM during TaTME for low rectal cancer.METHODS A total of 43 consecutive patients who were diagnosed with low rectal cancer and scheduled for TaTME were prospectively enrolled from January 2019 to January 2021.pCLE was used to determine the distal edge of the tumor as well as the DRM during surgery.The final pathological report was used as the gold standard.The diagnostic accuracy of pCLE examination was calculated.RESULTS A total of 86 pCLE videos of 43 patients were included in the analyses.The sensitivity,specificity and accuracy of real-time pCLE examination were 90.00%[95%confidence interval(CI):76.34%-97.21%],86.96%(95%CI:73.74%-95.06%)and 88.37%(95%CI:79.65%-94.28%),respectively.The accuracy of blinded pCLE reinterpretation was 86.05%(95%CI:76.89%-92.58%).Furthermore,our results show satisfactory interobserver agreement(κ=0.767,standard error=0.069)for the detection of cancer tissue by pCLE.There were no positive DRMs(≤1 mm)in this study.The median DRM was 7 mm[interquartile range(IQR)=5-10 mm].The median Wexner score was 5(IQR=3-6)at 6 mo after stoma closure.CONCLUSION Real-time in vivo pCLE examination is feasible and safe for selecting the DRM during TaTME for low rectal cancer(clinical trial registration number:NCT04016948).
