- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Computer-assisted assessment of colonic polyp histopathology using probe-based confocal laser endomicroscopy
摘要： Introduction Probe-based confocal laser endomicroscopy (pCLE) is a promising modality for classifying polyp histology in vivo, but decision making in real-time is hampered by high-magnification targeting and by the learning curve for image interpretation. The aim of this study is to test the feasibility of a system combining the use of a low-magnification, wider field-of-view pCLE probe and a computer-assisted diagnosis (CAD) algorithm that automatically classifies colonic polyps. Methods This feasibility study utilized images of polyps from 26 patients who underwent colonoscopy with pCLE. The pCLE images were reviewed offline by two expert and five junior endoscopists blinded to index histopathology. A subset of images was used to train classification software based on the consensus of two GI histopathologists. Images were processed to extract image features as inputs to a linear support vector machine classifier. We compared the CAD algorithm’s prediction accuracy against the classification accuracy of the endoscopists. Results We utilized 96 neoplastic and 93 non-neoplastic confocal images from 27 neoplastic and 20 non-neoplastic polyps. The CAD algorithm had sensitivity of 95%, specificity of 94%, and accuracy of 94%. The expert endoscopists had sensitivities of 98% and 95%, specificities of 98% and 96%, and accuracies of 98% and 96%, while the junior endoscopists had, on average, a sensitivity of 60%, specificity of 85%, and accuracy of 73%. Conclusion The CAD algorithm showed comparable performance to offline review by expert endoscopists and improved performance when compared to junior endoscopists and may be useful for assisting clinical decision making in real time.
关键词： Machine learning,Colorectal cancer,Polyp histology,Confocal laser endomicroscopy
更新于2025-09-12 10:27:22
-
Pancreatic Cysts: Diagnostic Role of EUS-Guided Microforceps Biopsy and Confocal Laser Endomicroscopy
摘要： Frequent use of high-quality cross-sectional imaging has led to a significant rise in diagnosis of pancreatic cystic lesions (PCLs). Despite the fact that enormous effort has been put into the research of PCLs within the last two decades and multiple guidelines have been developed, our clinical decision-making especially in regard to mucinous lesions remains limited. Currently, clinical assessment, cross-sectional imaging and EUS with fluid analysis (if appropriate) belong to the standard care in patients with PCLs. For differentiation of mucinous from nonmucinous cysts, the sensitivity of cytological investigation and CEA in the cyst fluid is 42% and 52-79%, respectively. Due to the limited accuracy, further diagnostic tools are warranted. Two EUS-guided approaches have been introduced recently. Through-the-(19-gauge EUS) needle Moray microforceps have been developed, and several studies have acknowledged their contribution to the correct diagnosis as they help to overcome limited cellularity of the EUS-guided cyst fluid aspiration and traditional cytology. Confocal laser endomicroscopy offers real-time images and seems to be a promising method for the diagnosis and differential diagnosis of pancreatic PCLs. Example images of the needle-based confocal laser endomicroscopy criteria for the diagnosis of PCLs have been suggested recently. Before both, Moray microforceps and confocal laser endomicroscopy can be widely accepted, further studies are necessary to determine the real diagnostic yield and the clinical efficacy.
关键词： diagnostic accuracy,EUS-guided microforceps biopsy,mucinous lesions,confocal laser endomicroscopy,pancreatic cystic lesions
更新于2025-09-12 10:27:22
-
Machine Learning-Based Classification of the Health State of Mice Colon in Cancer Study from Confocal Laser Endomicroscopy
摘要： In this article, we address the problem of the classification of the health state of the colon’s wall of mice, possibly injured by cancer with machine learning approaches. This problem is essential for translational research on cancer and is a priori challenging since the amount of data is usually limited in all preclinical studies for practical and ethical reasons. Three states considered including cancer, health, and inflammatory on tissues. Fully automated machine learning-based methods are proposed, including deep learning, transfer learning, and shallow learning with SVM. These methods addressed different training strategies corresponding to clinical questions such as the automatic clinical state prediction on unseen data using a pre-trained model, or in an alternative setting, real-time estimation of the clinical state of individual tissue samples during the examination. Experimental results show the best performance of 99.93% correct recognition rate obtained for the second strategy as well as the performance of 98.49% which were achieved for the more difficult first case.
关键词： classification,confocal laser endomicroscopy,machine learning,cancer study,health state,mice colon
更新于2025-09-12 10:27:22
-
Endoscopic ultrasound‐guided needle‐based confocal laser endomicroscopy in gastrointestinal subepithelial lesions ‐ a feasibility study
摘要： Background and Aim: Needle-based confocal laser endomicroscopy (nCLE) allows for real-time optical biopsies during endoscopic ultrasound-guided fine needle aspiration (EUS-FNA). Little is known about the nCLE imaging of gastrointestinal subepithelial lesions (GI-SELs); therefore, we determined its feasibility. Methods: We performed EUS, next nCLE, and finally FNA in 25 patients with GI-SELs between November 2015 and December 2018. We retrospectively compared nCLE findings with pathologic findings of EUS-FNA or surgical specimens. For concordance analysis, two endoscopists independently validated representative nCLE images 5 months or more after examinations. Results: The adequate sample acquisition rate of EUS-FNA was 67% per needle pass and 96% per patient. EUS-FNA was diagnostic in 80% (20/25), suspicious in 4% (1/25), and nondiagnostic in 16% (4/25). The nCLE image acquisition rate was 100% and its concordance rate with final pathology was 88% (22/25), which was not significantly different from diagnostic and suspicious EUS-FNA. nCLE could differentiate GI stromal tumors from leiomyoma, in that GISTs were characterized by contrast-enhanced densely populated spindle cell tumors with unenhanced rod-shaped nuclei in 93% of 14 patients, whereas leiomyomas were characterized by narrower spindle cell tumors with fewer and smaller unenhanced nuclei in 100% of 3 patients. In rectal metastasis from lung adenocarcinoma, some pleomorphic dark nests were observed. At concordance analysis between the two endoscopists’ validation results, the ? value was 0.560 (P<0.001), indicating moderate agreement. There were no adverse events associated with nCLE and EUS-FNA. Conclusion: nCLE can be safe and useful for the on-site detection of abnormalities of GI-SELs (UMIN 000013857).
关键词： gastrointestinal subepithelial lesion,endoscopic ultrasound-guided fine needle aspiration,needle-based confocal laser endomicroscopy,gastrointestinal stromal tumor
更新于2025-09-11 14:15:04
-
Probe-based confocal laser endomicroscopy in diagnosis of desquamative interstitial pneumonia in nonsmoker
摘要： used for differential diagnosis of desquamative interstitial pneumonia in nonsmokers. Desquamative interstitial pneumonia is a rare disease that is predominantly associated with smoking. Surgical biopsy is usually recommended for the diagnosis of this disorder. Probe-based confocal laser endomicroscopy (pCLE) is a new method of minimally invasive in vivo microscopic image of airways and alveoli. We use this method for desquamative interstitial pneumonia in nonsmoker. The pCLE image shows thickened intra-alveolar septae and clusters of autofluorescent cells within the alveoli, which is unusual for non-smoking patients. We think this pattern can be
关键词： idiopathic interstitial pneumonias,interstitial lung diseases,desquamative interstitial pneumonia,optical biopsy,confocal laser endomicroscopy
更新于2025-09-11 14:15:04
-
Diagnostic utility of probe-based confocal laser endomicroscopy in superficial non-ampullary duodenal epithelial tumors
摘要： Background and study aims Endoscopic diagnosis of superficial non-ampullary duodenal epithelial tumors (SNADETs) has not been established. Probe-based confocal laser endomicroscopy (pCLE: Cellvizio) provides real-time endomicroscopic analysis. We developed and validated a new pCLE classification of SNADET based on abnormal findings. Patients and methods pCLE scanning of 20 SNADET lesions including 16 adenomas and four carcinomas was retrospectively evaluated to explore abnormal pCLE findings in relation to histological features. Diagnostic yield of pCLE findings was prospectively evaluated in an additional 20 SNADET lesions including 16 adenomas and four carcinomas. Results In a retrospective study, we identified four abnormal pCLE findings of SNADETs: (1) dark epithelium, (2) columnar cells irregularly extending to the lumen, (3) distorted crypt structure, and (4) fluorescein leakage. Dark epithelium distinguished neoplastic lesions (adenomas and carcinomas) from non-neoplastic duodenal mucosa with a sensitivity of 90 % and a specificity of 100 %. Distorted crypt structure distinguished carcinomas from adenomas and non-neoplastic duodenal mucosa with a sensitivity of 100 % and a specificity of 94 %. In the prospective study, the sensitivity and the specificity of the dark epithelium for the diagnosis of neoplastic lesions (adenomas + carcinomas) was 75 % and 100 %. Sensitivity and the specificity of the distorted crypt structure for discrimination of carcinoma from adenoma were 100 % and 94 %, respectively. Conclusions The pCLE findings correlated with the histopathology of the SNADETs. Dark epithelium and distorted crypt structure were informative pCLE findings to predict presence of neoplasia and cancer in the SNADET, respectively.
关键词： SNADET,probe-based confocal laser endomicroscopy,endoscopic diagnosis,pCLE,duodenal epithelial tumors
更新于2025-09-11 14:15:04
-
Intraoperative Probe-Based Confocal Endomicroscopy to Histologically Differentiate Thyroid From Parathyroid Tissue Before Resection
摘要： Background. Frozen section is the standard method to histologically distinguish parathyroid tissue from thyroid tissue during endocrine neck surgery. Frozen section can be time-consuming and costly. Its drawback is that it is to be performed only after the removal of a suspected pathological tissue. This study demonstrates the use of probe-based confocal laser endomicroscopy (pCLE) to confirm histology prior to tissue resection. Design. A prospective, single-institution, nonrandomized study was conducted. No sample size calculation was performed for this observational trial. The primary objective was the description of histological rendering of normal and pathological tissues through pCLE. Real-time in vivo fluorescence microscopy imaging was performed with the CystoFlex UHD probe after intravenous injection of 2.5 mL of 10% fluorescein sodium. Results. Eleven patients with hyperparathyroidism and thyroid conditions were included. A total of 104 videos showing thyroid, parathyroid, adipose tissue, muscle, laryngeal nerve, and lymph nodes were recorded. Videos were compared with visual information and pathological samples (when sampling was indicated). Thyroid tissue could be identified based on the presence of colloid follicles (intensely fluorescent area surrounded by a small ridge of low-fluorescence epithelial cells) including the pathognomonic aspect of resorption vacuole. Parathyroid tissue could be identified based on a regular, “diamond-shaped” capillary network encompassing parathyroid chief cells. Blinded reinterpretation of pCLE videos demonstrated an 89.3% sensitivity and a 90% specificity as compared with histology in tissue recognition. Conclusion. This pilot study describes representative renderings of intraoperative pCLE to nontraumatically differentiate thyroid, parathyroid, and lymph nodes before surgical removal.
关键词： parathyroidectomy,thyroid surgery,pCLE,in vivo fluorescence microscopy,probe-based confocal laser endomicroscopy
更新于2025-09-10 09:29:36
-
Functional Capillary Density for in Vivo Estimation of Intestinal Perfusion using Real-Time Confocal Endomicroscopy
摘要： Background and aim: Confocal Laser Endomicroscopy (CLE) has been successfully used to appreciate microcirculation changes of the digestive mucosa. Our aim was to evaluate CLE scanning complemented by functional capillary density area (FCD-A) estimation to define the micro-vessel status in a reiterate, long-lasting porcine model of bowel ischemia. Materials and methods: A laparotomy was performed in 4 pigs, and a segmental (3–4 cm) ischemia of the sigmoid colon was induced with vascular clamps. Ischemic and perfused regions were clinically defined. After an injection of 5 ml of sodium fluorescein 10% (Fluocyne, SERB, Paris, France), the Cellvizio? confocal probe (Mauna Kea Technologies, Paris, France) was directly applied onto the mucosa’s surface through a full-thickness enterotomy. Both ischemic area (IA) and control region-perfused area (PA) – were scanned and video sequences were recorded. Results: Confocal evaluation of the ischemic area revealed a different aspect of the mucosal tissue when compared to the normal perfused area. Statistically, FCD-A at the perfused area was significantly higher when compared to the ischemic area, irrespective of the time point. After 1 hour, FCD-A was (0.189 ± 0.094 vs. 0.365 ± 0.030; p=0.0001), after 2 hours (0.252 ± 0.056 vs. 0.389 ± 0.024; p<0.0001), after 3 hours (0.252 ± 0.050 vs. 0.353 ± 0.030; p=0.0001) and after 4 hours (0.262 ± 0.044 vs. 0.358 ± 0.019; p<0.0001), at ischemic and perfused areas respectively. Conclusions: Confocal imaging allows real-time discrimination between perfused and ischemic areas of the bowel using morphological clues, while the functional capillary density area adds a quantitative measurement.
关键词： Cellvizio? system,Quantitative assessment of bowel perfusion,Functional capillary density area,Confocal laser endomicroscopy
更新于2025-09-04 15:30:14