Search

Blue light imaging (BLI) has been shown to improve the characterization of colorectal polyps among the endoscopy experts. We aimed to determine if this technology could be taught to endoscopy trainees while maintaining high accuracy and interobserver agreement.Twenty-one gastroenterology trainees (fellows) from two academic institutions participated in this prospective study. Each trainee completed a web-based learning comprising four modules: pre-test, didactic videos explaining the BLI Adenoma Serrated International Classification (BASIC), interactive examples, and post-test assessment. The pre- and post-test modules consisted of reviewing video images of colon polyps in high definition white light imaging and BLI and then applying the BASIC classification to determine if the polyps were likely to be adenomatous. Confidence in adenoma identification (rated '1' to '5'), accuracy in polyp (adenoma vs. non-adenoma) identification, and agreement in characterization per BASIC criteria were derived.Trainee accuracy in the adenoma diagnosis improved from 74.7% (pre-test) to 85.4% (post-test) (P 0.01). There was a trend towards higher accuracy in polyp characterization with subsequent years of training (1st year fellows 77.4%, 2nd year 88.5%, and final year 94.0%) with consistent improvements after the e-learning across years of trainees. Overall, trainees were able to identify adenoma with a high sensitivity of 86.9%, specificity 83.9%, positive predictive value of 84.4%, and negative predictive value of 86.5%. However, their interobserver agreement in adenoma diagnosis was moderate (k = 0.52).The novel BLI classification can be easily taught to gastroenterology trainees using an online module and accuracy improves with years of training reaching90% for colorectal polyp characterization.

BACKGROUND: Blue Light Imaging (BLI) is a new imaging technology that enhances mucosal surface and vessel patterns. A specific BLI classification was recently developed to enable better characterisation of colorectal polyps (BLI Adenoma Serrated International Classification (BASIC)). The aim of this study was to validate the diagnostic performance of BASIC in predicting polyp histology in experienced and trainee endoscopists. METHODS: Five experienced and five trainee endoscopists evaluated high-definition white light (HDWL) and BLI images from 45 small polyps to assess baseline accuracy, sensitivity, specificity, and positive and negative predictive values (NPVs) of polyp histology. Each endoscopist was trained with the BLI classification before repeating the exercise. Results were compared pre- and post-training. RESULTS: The overall pre-training accuracy improved from 87% to 94%. The sensitivity and NPV of adenoma diagnosis also improved significantly from 79% to 96% and 81% to 95% with BASIC training. This improvement was noted in both groups. The interobserver level of agreement was very good (K = 0.90) in the experienced cohort and good (K = 0.66) in the trainee group post-training. CONCLUSIONS: BLI is a useful tool for optical diagnosis, and the use of BASIC with adequate training can significantly improve the accuracy, sensitivity and NPV of adenoma diagnosis. ispartof: UNITED EUROPEAN GASTROENTEROLOGY JOURNAL vol:7 issue:2 pages:316-325 ispartof: location:England status: published

Artificial intelligence (AI) and its application in medicine has grown large interest. Within gastrointestinal (GI) endoscopy, the field of colonoscopy and polyp detection is the most investigated, however, upper GI follows the lead. Since endoscopy is performed by humans, it is inherently an imperfect procedure. Computer-aided diagnosis may improve its quality by helping prevent missing lesions and supporting optical diagnosis for those detected. An entire evolution in AI systems has been established in the last decades, resulting in optimization of the diagnostic performance with lower variability and matching or even outperformance of expert endoscopists. This shows a great potential for future quality improvement of endoscopy, given the outstanding diagnostic features of AI. With this narrative review, we highlight the potential benefit of AI to improve overall quality in daily endoscopy and describe the most recent developments for characterization and diagnosis as well as the recent conditions for regulatory approval. ispartof: DIGESTIVE ENDOSCOPY vol:33 issue:2 pages:242-253 ispartof: location:Australia status: published

In a quest to use Raman spectroscopy as an optical diagnostic tool, we recorded Raman spectra of 32 dengue virus (DENV)-infected and 28 healthy sera samples in the near-infrared spectral range (540 to 1700 cm−1) using laser at 785 nm as the excitation source. We observed clear differences in the Raman spectra of DENV-infected sera as compared with those of healthy individuals. Here, as a result of our study, we report 12 unique Raman bands associated with DENV-infected sera that are not reported earlier. After applying analysis of variance and t-test (p

Background and Aim The aim of this randomized trial was to evaluate the performance of self‐training versus didactic training in order to increase the diagnostic accuracy of diminutive/small colonic polyp histological prediction by trainees. Methods Sixteen trainees reviewed 78 videos (48 iSCAN‐OE and 30 NBI) of diminutive/small polyps in a pretraining assessment. Trainees were randomized to receive computer‐based self‐learning (n = 8) or didactic training (n = 8) using identical teaching materials and videos. The same 78 videos, in a different randomized order, were assessed. The NICE (NBI International Colorectal Endoscopic) and SIMPLE (Simplified Identification Method for Polyp Labeling during Endoscopy) classification systems were used to classify diminutive/small polyps. Results A higher proportion of high‐confidence predictions of polyps was made by the self‐training group versus the didactic group using both the SIMPLE classification (77.1% [95% CI 73.4–80.3] vs 69.9% [95% CI 66.1–73.5%] [P = 0.005]) and the NICE classification (77% [95% CI 73.2–80.4%] vs 69.8% [95% CI 66–73.4%] [P = 0.006]). When using NICE, sensitivity of the self‐training group compared with the didactic group was 72% versus 83% (P = 0.0005), and the accuracy was 66.1% versus 69.1%. The training improved the confidence of participants and SIMPLE was preferred over NICE. Conclusion Self‐learning for the prediction of diminutive/small polyp histology is a method of training that can achieve results similar to didactic training. Availability of adequate self‐learning teaching modules could enable widespread implementation of optical diagnosis in clinical practice.

Background and aim To evaluate the effectiveness of systematic training in the application of narrow-band imaging (NBI) International Colorectal Endoscopic (NICE) classification for the prediction of the histology of colorectal polyps. Methods This is a single-center study. In total, 260 still images of colorectal polyps from 225 patients were included. Two series of 130 images obtained using NBI and white light without magnification were distributed to 10 endoscopists-five highly experienced endoscopists (HEE group) and five less experienced endoscopists (LEE group)-for assessment using the NICE classification, before and after systematic training. Results Before systematic training, accuracy in both groups was 79.54% and specificity was relatively poor (HEE: 62.46%, LEE: 69.23%, P = 0.297). After systematic training, specificity significantly improved (HEE: 96.61%, LEE: 97.54%, P = 0.000 and P = 0.013, respectively). Accuracy also significantly increased to 94.93% and 96.46% in the HEE and LEE groups, respectively. Sensitivity and negative predictive value did not significantly improve in the post-test; however, both were high in both the pre- and post-test. The κ-values in both groups were excellent (HEE: 0.93, LEE: 0.91). Among the components of the NICE classification, surface pattern yielded the highest performance, whereas color yielded the lowest. Conclusion Systematic, feedback-based, training programs can help achieve high accuracy and good interobserver agreement in the application of the NICE classification for the prediction of the histology of colorectal polyps by endoscopists with different levels of experience.

Solid pseudopapillary tumor (SPT) of the pancreas is an epithelial tumor with low-grade malignant potential and present more common in females. At present, the gold standard for accurate diagnosis of pancreatic tumor was mostly depending on the pathological and/or cytological evaluation. In this work, TPEF microscopy was applied to obtain the images of human normal pancreas and SPT of the pancreas without hematoxylin and eosin (H&E) staining, for the purpose of identifying the organization structural, cell morphological, and cytoplasm changing, which were then compared to their corresponding H&E stained histopathological results. Our results showed that high-resolution TPEF imaging of the pancreatic SPT can clearly distinguish the pathological features from normal pancreas in unstained histological sections, and the results are consistent with the histological results. Moreover, we measured the nuclear-cytoplasmic ratios of the pancreatic SPT and normal pancreas to characterize their difference in the cytomorphological feature. It indicated that this technique can achieve the consistent information of pathological diagnosis, and has the potential to substantially improve the optical diagnosis and treatment of the pancreatic SPT without H&E staining in the future. SCANNING 38:245-250, 2016. © 2015 Wiley Periodicals, Inc.

Background and Aim A ‘resect and discard’ strategy using non-magnifying narrow band imaging (N-NBI) has been proposed for reducing screening colonoscopy costs, but it does not take into consideration advanced histology and magnifying NBI (M-NBI) that can potentially further improve the ‘resect and discard’ strategy. We conducted a pilot study to investigate the feasibility of M-NBI for the new ‘resect and discard’ strategy with consideration for advanced histology. Methods The present study involved 63 patients. For each polyp, optical diagnosis was independently made using N-NBI and M-NBI, a decision (discard or send for pathology) was made based on the M-NBI findings, and histological and optical diagnosis results were compared. Results Sensitivity, specificity and accuracy (95% confidence interval) of M-NBI for lesions with advanced histology were 1.00 (0.36–1.00), 0.92 (0.91–0.92) and 0.92 (0.90–0.92), respectively. Whereas the management of 86% of small polyps could be decided without formal histopathology, lesions with advanced histology were not discarded using M-NBI. The diagnostic accuracy of M-NBI in distinguishing neoplastic from non-neoplastic lesions was higher than that of N-NBI. Conclusions We propose a new resect and discard strategy with advanced histology using M-NBI that is a promising strategy to reduce the costs of histopathology and to minimize the risk of discarding important lesions.

State-of-the-art image-processing methods offer new possibilities for diagnosing diseases using scattered light. The optical diagnosis of rheumatism is taken as an example to show that the diagnostic sensitivity can be improved using overlapped pseudocolored images of different wavelengths, provided that multispectral images are recorded to compensate for any motion-related artefacts that occur during examination. (© 2010 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim)

Breast cancer is the leading cancer affecting women. Conventional screening and diagnostic methods are shown to suffer from well-described limitations. The aim of this study was to evaluate Raman spectroscopic models, which were developed earlier, by blinded tissue samples. We have recorded Raman spectra of 69 blinded tissue samples. In each sample, six or more spectra were recorded at different locations. Pretreated spectra were matched against normal, malignant and benign standard sets to obtain a match/mismatch status, which in turn was correlated with histopathology. Among 69 samples analyzed, 61 could be unambiguously diagnosed as 29 normal, 17 malignant and 15 benign, as their spectra matched with only one standard set and mismatched against the others. In the cases of the remaining tissue samples, matching them against pathological sets was the determining criteria. These samples were diagnosed as pathological since at least one of the spectra of these tissues had matched with pathological sets. Thus, we demonstrate a good correlation between histopathology and Raman spectroscopic diagnosis. Therefore, findings of the study further support the efficacy of Raman spectroscopic models that were developed by us. Prospectively, by developing models for as many pathological conditions as possible followed by rigorous validation, objective/unambiguous Raman spectroscopic diagnosis of breast pathologies can be realized.

Background and Objectives Raman spectroscopy (RS) provides information about molecular structure and is a potential tool for non-invasive tissue diagnosis. To determine if Raman spectra could be obtained rapidly from laryngeal tissue in vitro, and compare Raman spectra from normal, benign, and cancerous laryngeal tissue. Study Design/Materials and Methods Forty-seven laryngeal specimens were studied using RS with signal acquisition times (SAT) between 1 and 30 second(s). Multivariate analysis was used to determine the diagnostic ability of RS compared to standard histology (n = 18, 13, and 16 respectively for normal tissue, carcinoma, and squamous papilloma). Results Good quality spectra were obtained with 5-second SAT. Spectral peak analysis showed prediction sensitivities of 89%, 69%, and 88%, and specificities of 86%, 94%, and 94% for normal tissue, carcinoma, and papilloma. Conclusions In the larynx, spectral differences appear to exist between normal tissue, carcinoma, and papilloma. The ability to obtain spectra rapidly supports potential for future in vivo studies. © 2005 Wiley-Liss, Inc.

Gastric intestinal metaplasia (GIM) is a high risk for intestinal type gastric cancer; however, there is a limitation for detection of GIM using white light imaging (WLI). Image-enhanced endoscopy (IEE) is more advantageous than WLI for optical diagnosis of GIM (1). Linked color imaging (LCI) (FUJIFILM Co., Tokyo, Japan) was newly developed for advanced IEE and enables visualization of red lesions that appear redder and whitish red lesions that appear whiter during routine endoscopy (2). GIM is observed as a lavender color that is distinguishable from the circumferential mucosa without GIM by using LCI (Figure 1). We speculate that the lavender color is the same as the bluish−whitish patchy areas including a light blue crest or a marginal turbid band in narrow band imaging (3, 4). On the other hand, gastric cancer is observed as lesions of various degrees of redness depending on the quantity of blood vessels. This article is protected by copyright. All rights reserved.

Background and Objectives Raman spectroscopy (RS), which can detect molecular changes associated with cancer, was explored as a means of distinguishing normal and cancerous nasopharyngeal tissue. Study Design/Patients and Methods Tissue from six patients with normal and cancerous biopsies was studied using a rapid acquisition Raman spectrometer. Results Spectra were obtainable within 5 seconds. Consistent differences were noted between normal and cancer tissue in three bands 1,290–1,320 cm−1 (P = 0.005), 1,420–1,470 cm−1 (P = 0.006), and 1,530–1,580 cm−1 (P = 0.002). Conclusions Spectral differences appear to exist between normal and cancerous nasopharyngeal tissue. The ability to obtain spectra rapidly supports the potential for future in vivo application. Lasers Surg. Med. 32:210–214, 2003. © 2003 Wiley-Liss, Inc.