Single Shot Multibox Detector Automatic Polyp Detection Network Based on Gastrointestinal Endoscopic Images.

PURPOSE: In order to resolve the situation of high missed diagnosis rate and high misdiagnosis rate of the pathological analysis of the gastrointestinal endoscopic images by experts, we propose an automatic polyp detection algorithm based on Single Shot Multibox Detector (SSD). METHOD: In the paper, SSD is based on VGG-16, the fully connected layer is changed to a convolutional layer, and four convolutional layers with successively decreasing scales are added as a new network structure. In order to verify the practicability, it is not only compared with manual polyp detection but also with Mask R-CNN. RESULTS: Multiple experimental results show that the mean Average Precision (mAP) of the SSD network is 95.74%, which is 12.4% higher than the manual detection and 5.7% higher than the Mask R-CNN. When detecting a single frame of image, the detection speed of SSD is 8.41 times that of manual detection. CONCLUSION: Based on the traditional pattern recognition algorithm and the target detection algorithm using deep learning, we select a variety of algorithms to identify and classify polyps to achieve efficient detection results. Our research demonstrates that deep learning has a lot of room for development in the field of gastrointestinal image recognition.

The Workgroup Serrated Polyps and Polyposis (WASP) classification for optical diagnosis of colorectal diminutive polyps with iScan and the impact of the revised World Health Organization (WHO) criteria.

BACKGROUND AND AIMS: The Workgroup Serrated Polyps and Polyposis (WASP) developed criteria for optical diagnosis of colorectal polyps. The aims of this study were: (1) to improve optical diagnosis of diminutive colorectal polyps, especially SSLs, after training endoscopists in applying WASP criteria on videos of polyps obtained with iScan and (2) to evaluate if the WASP criteria are still useful when polyps are pathologically revised according to the World Health Organization (WHO) 2019 criteria. METHODS: Twenty-one endoscopists participated in a training session and predicted polyp histology on 30 videos of diminutive polyps, before and after training (T0 and T1 ). After three months, they scored another 30 videos (T2 ). Primary outcome was overall diagnostic accuracy (DA) at T0 , T1 and T2 . Polyps were histopathologically classified according to the WHO 2010 and 2019 criteria. RESULTS: Overall DA (both diminutive adenomas and SSLs) significantly improved from 0.58 (95% CI 0.55-0.62) at T0 to 0.63 (95% CI 0.60-0.66, p = 0.004) at T1 . For SSLs, DA did not change with 0.51 (95% CI 0.46-0.56) at T0 and 0.55 (95% CI 0.49-0.60, p = 0.119) at T1 . After three months, overall DA was 0.58 (95% CI 0.54-0.62, p = 0.787, relative to T0 ) while DA for SSLs was 0.48 (95% CI 0.42-0.55, p = 0.520) at T2 . After pathological revision according to the WHO 2019 criteria, DA of all polyps significantly changed at all time points. CONCLUSION: A training session in applying WASP criteria on endoscopic videos made with iScan did not improve endoscopists' long-term ability to optically diagnose diminutive polyps. The change of DA following polyp revision according to the revised WHO 2019 criteria suggests that the WASP classification may need revision.

Advanced endoscopy technologies to improve the detection and characterisation of colorrectal polyps. / Tecnologías de endoscopia avanzada para mejorar la detección y caracterización de los pólipos colorrectales.

Colorectal cancer is a major health problem. An improvement to its survival has been demonstrated by performing colonoscopy screenings and removing its precursor lesions: polyps. However, colonoscopy is not infallible and multiple strategies have been proposed aimed at improving the quality thereof. This report describes the endoscopic systems available to improve the detection and characterization of polyps, the different classifications for histological prediction and the current indications of advanced endoscopic diagnostic techniques.

[Clinicopathological features of non-neoplastic colorectal polyps].

Objective: To characterize clinicopathological characteristics of the non-neoplastic colorectal polyps for accurate diagnosis. Methods: 1 190 cases were collected from the Second Affiliated Hospital of Harbin Medical University from January 2012 to December 2016 and their clinicopathological characteristics were reviewed. Results: There were 746 males and 444 females patients with male/female ratio of 1.7∶1.0. The average age was 52 and 85.4% (1 016/1 190) of cases were over 40 years old. A total of 1 289 polyps were found in the study cohort including 1 238 inflammatory polyps (96.0%), 47 harmartomatous polyps (3.7%) and 4 other types of polypoid lesions (0.3%). Among 1 249 inflammatory polyps, 1 212 were inflammatory pseudopolyps (97.9%), 15 post-inflammatory polyps (1.2%), 8 inflammatory myoglandular polyps (0.6%), and 3 prolapse-type inflammatory polyps (colitis cystica profunda). Among 47 hamartomatous polyps, there were 39 juvenile polyps (83.0%), 8 Peutz-Jegher polyps (17.0%). Four polypoid lesions of endometriosis. Among 1 289 polyps, 751 polyps were located in sigmoid and rectum (58.3%). 168 polyps were pedunculated (12.9%) and 1 132 polyps were sessile (87.1%). Conclusions: For non-neoplastic colorectal polyps, the average age of patients is 40 years. The polyps generally involve the sigmoid colon and rectum. The most common pathological type is inflammatory pseudopolyp and the most common pathological type of hamartomatous polyp is juvenile subtype.

Validation of serrated polyps (SPs) in Swedish pathology registers.

BACKGROUND: Little is known about the natural history of serrated polyps (SPs), partly due to the lack of large-scale epidemiologic data. In this study, we examined the validity of SP identification according to SNOMED (Systematised Nomenclature of Medicine) codes and free text from colorectal histopathology reports. METHODS: Through the ESPRESSO (Epidemiology Strengthened by histoPathology Reports in Sweden) study, we retrieved data on SPs from all pathology departments in Sweden in 2015-2017 by using SNOMED codes and free-text search in colorectal histopathology reports. Randomly selected individuals with a histopathology report of SPs were validated against patient charts using a structured, retrospective review. RESULTS: SPs were confirmed in 101/106 individuals with a histopathology report of SPs, yielding a positive predictive value (PPV) of 95% (95%CI = 89-98%). By year of diagnosis, the PPV was 89% (95%CI = 69-97%), 96% (95%CI = 81-99%) and 97% (95%CI = 89-99%) for individuals diagnosed before 2001 (n = 19), between 2001 and 2010 (n = 26) and after 2010 (n = 61), respectively. According to search method, the PPV for individuals identified by SNOMED codes was 100% (95%CI = 93-100%), and 93% (95%CI = 86-97%) using free-text search. Recorded location (colon vs. rectum) was correct in 94% of all SP histopathology reports (95%CI = 84-98%) identified by SNOMED codes. Individuals with SPs were classified into hyperplastic polyps (n = 34; 32%), traditional serrated adenomas (n = 3; 3%), sessile serrated adenomas/polyps (SSA/Ps) (n = 70; 66%), unspecified SPs (n = 3, 3%), and false positive SPs (n = 5, 5%). For individuals identified by SNOMED codes, SSA/Ps were confirmed in 49/52 individuals, resulting in a PPV of 94% (95%CI: 84-98%). In total, 57% had ≥2 polyps (1: n = 44, 2-3: n = 33 and ≥ 4: n = 27). Some 46% of SPs (n = 71) originated from the proximal colon and 24% were ≥ 10 mm in size (n = 37). Heredity for colorectal cancer, intestinal polyposis syndromes, or both was reported in seven individuals (7%). Common comorbidities included diverticulosis (n = 45, 42%), colorectal cancer (n = 19, 18%), and inflammatory bowel disease (n = 10, 9%). CONCLUSION: Colorectal histopathology reports are a reliable data source to identify individuals with SPs.

Duodenal Epithelial Polyps: A Clinicopathologic Review.

CONTEXT.­: Duodenal epithelial polyps are reported in 1.5% to 3% of individuals referred for upper endoscopy. Most duodenal epithelial polyps are asymptomatic and nonneoplastic; however, a small subset is neoplastic and may progress to adenocarcinoma. Recent advances in immunohistochemical and molecular techniques have helped further characterize these polyps, shedding light on their origin, classification, and risk of progression to adenocarcinoma. OBJECTIVE.­: To provide a comprehensive clinicopathologic review of nonneoplastic and neoplastic duodenal epithelial polyps, with particular emphasis on recent developments in classification schemes and risk stratification based upon immunohistochemical and molecular profiles. DATA SOURCES.­: This review is based on peer-reviewed literature and the authors' experiences. CONCLUSIONS.­: In this review we provide an update on the clinicopathologic, immunohistochemical, and molecular features of duodenal epithelial polyps and discuss the surveillance recommendations and treatment options available. Particular attention should be placed on recognizing duodenal adenomas with intestinal, gastric, and serrated phenotype, as they have an increased risk of malignant transformation if not completely excised.

Histological and molecular classification of gastrointestinal polyps.

Endoscopic diagnosis and treatment for gastrointestinal polyps became widely available within the last decades. Exact terminology is important for further therapeutic steps, follow up or treatment. Gastroenterologists, Oncologists, Surgeons and Pathologists need to be aware of the most recent terminology to ensure proper risk assessment and subsequent treatment if necessary. This manuscript aims to list the variety of gastrointestinal polyps and the molecular background where appropriate.

High resolution microendoscopy for classification of colorectal polyps.

BACKGROUND AND STUDY AIMS: It can be difficult to distinguish adenomas from benign polyps during routine colonoscopy. High resolution microendoscopy (HRME) is a novel method for imaging colorectal mucosa with subcellular detail. HRME criteria for the classification of colorectal neoplasia have not been previously described. Study goals were to develop criteria to characterize HRME images of colorectal mucosa (normal, hyperplastic polyps, adenomas, cancer) and to determine the accuracy and interobserver variability for the discrimination of neoplastic from non-neoplastic polyps when these criteria were applied by novice and expert microendoscopists. METHODS: Two expert pathologists created consensus HRME image criteria using images from 68 patients with polyps who had undergone colonoscopy plus HRME. Using these criteria, HRME expert and novice microendoscopists were shown a set of training images and then tested to determine accuracy and interobserver variability. RESULTS: Expert microendoscopists identified neoplasia with sensitivity, specificity, and accuracy of 67 % (95 % confidence interval [CI] 58 % - 75 %), 97 % (94 % - 100 %), and 87 %, respectively. Nonexperts achieved sensitivity, specificity, and accuracy of 73 % (66 % - 80 %), 91 % (80 % - 100 %), and 85 %, respectively. Overall, neoplasia were identified with sensitivity 70 % (65 % - 76 %), specificity 94 % (87 % - 100 %), and accuracy 85 %. Kappa values were: experts 0.86; nonexperts 0.72; and overall 0.78. CONCLUSIONS: Using the new criteria, observers achieved high specificity and substantial interobserver agreement for distinguishing benign polyps from neoplasia. Increased expertise in HRME imaging improves accuracy. This low-cost microendoscopic platform may be an alternative to confocal microendoscopy in lower-resource or community-based settings.

Interobserver agreement in the reporting of colorectal polyp pathology among bowel cancer screening pathologists in Wales.

AIMS: To assess the interobserver agreement in the reporting of colorectal polyps among histopathologists participating in the Welsh Bowel Cancer Screening (BCS) programme. METHODS AND RESULTS: Twelve benign polyps representative of BCS cases were identified from pathology files and reported by 28 BCS histopathologists using proforma sheets. The level of agreement between the participants and a gold standard was determined using kappa (κ) statistics. A moderate level of agreement was achieved in the reporting of polyp type [κ = 0.45; 95% confidence interval (CI) 0.34-0.59] and adenomatous lesions were distinguished from non-adenomatous lesions in 96% of cases. Substantial agreement was obtained in distinguishing low- and high-grade dysplasias (κ = 0.67; 95% CI 0.50-0.86), but there was only fair agreement in reporting excision margin status (κ = 0.24; 95% CI 0.07-0.43) with frequent use of the 'uncertain' category. Significant issues included categorizing serrated lesions, recognizing focal high-grade dysplasia and epithelial misplacement, and apparent overdiagnosis of villous change in adenomas. CONCLUSIONS: Interobserver variability in some aspects of reporting colorectal polyps by BCS pathologists is suboptimal, with a potential impact upon patient management and the efficient running of the screening service. Approaches to addressing this are discussed.

Composite intestinal adenoma-microcarcinoid clues to diagnosing an under-recognised mimic of invasive adenocarcinoma.

AIMS: Microcarcinoids refer to microscopic nests of monotonous cells with endocrine and squamoid features. Their peculiar morphology can appear infiltrative with a desmoplastic-like background, raising concerns for an infiltrating adenocarcinoma. To further characterise microcarcinoids, we undertook a prospective clinicopathological study. METHODS: 11 specimens originating from five men and six women (average age=58.9 years) were prospectively collected from December 2004 to December 2011. RESULTS: Microcarcinoids were most commonly identified in high-risk adenomas (size ≥10 mm (n=10), villous components (n=8) and/or high-grade dysplasia (n=4)). All polyps had mucosal prolapse and four displayed background fibrosis reminiscent of desmoplasia. The microcarcinoid component was most often multifocal (n=7) within the individual polyp and extended over an average length of 3.9 mm. The individual microcarcinoid cells were cuboidal with abundant eosinophilic cytoplasm. All cases had monotonous nuclei which lacked pleomorphism, hyperchromasia and mitotic activity. All available microcarcinoids were ß-catenin and synaptophysin reactive and non-reactive for chromogranin and p53 with a negligible Ki-67 proliferation index (<2%). In addition, the microcarcinoids were variably reactive for p63 and/or CK 5/6, thereby demonstrating focal squamoid features. Two of the study cases were submitted with a concern for invasive carcinoma. Clinical information was available in 10 patients with up to 24 months of follow-up: all patients are alive and well and no subsequent malignancy has been reported. CONCLUSIONS: Awareness of this unique morphology is important to avoid overdiagnosing microcarcinoids as invasive adenocarcinoma. Moreover, this immunohistochemical panel can be helpful in discriminating microcarcinoids from its malignant mimic in challenging cases.

Correlation between location, size and histologic type of colorectal polyps at the presence of dysplasia and adenocarcinoma

Adenocarcinoma represents 96-98% of colorectal neoplasms, and neoplastic polyps (adenomas) are their precursors. The aim of this study is to correlate size, location and histologic type of colorectal polyps at the presence of dysplasia and adenocarcinoma. Methods: Colonoscopies from January/2007 to December/2008 were retrospectively studied, in order to evaluate the characteristics of the polyps. Results and Discussion: Out of the 2,401 analyzed colonoscopies, 583 (24.3%) presented polyps. Due to the lack of histopathologic data, 139 exams were excluded. Mean age of the patients was 58±12 years, and 60% were females. Polyps were prevalent in the left colon (38.5%) and rectum (32.5%). Out of the 850 polyps which were histologically examined, 55.17% were tubular adenomas; 21.88%, hyperplastic; 17.05%, serrated; 5.4%, tubulovillous; and 0.47%, villous. As to polyps ≤1.0 cm, dysplasia was observed in 16.0% and adenocarcinoma in 1.9%. Those >1.0 cm, 72.0% (p<0.001) presented dysplasia, and 25.3% (p<0.001) presented adenocarcinoma. Polyps in the right and transverse colon were strongly associated with dysplasia (17.8% and 16.7%). Adenocarcinomas were prevalent in the left colon (2.5%) and rectum (2.1%). Conclusion: Polyps were more frequent in the left colon and rectum. The right and transverse colons were strongly correlated with dysplasia. Those of the left colon and rectum were associated with adenocarcinoma. Lesions >1.0 cm were positively related to dysplasia and neoplasm. (AU)

O adenocarcinoma representa 96-98% do câncer colorretal, sendo os pólipos neoplásicos (adenomas) seus precursores. O objetivo desse estudo é correlacionar tamanho, localização e tipo histológico de pólipos colorretais com a presença de displasia e adenocarcinoma. Métodos: Estudou-se retrospectivamente colonoscopias realizadas entre janeiro/2007 e dezembro/2008, avaliando-se as características dos pólipos. Resultados e Discussão: Das 2401 colonoscopias analisadas, 583 (24,3%) apresentaram pólipos. Por falta de dados histopatológicos, excluiu-se 139 exames. A média de idade foi 58±12 anos, sendo 60% mulheres. Houve predomínio no cólon esquerdo (38,5%) e reto (32,5%). Quanto ao tamanho, 86,58% eram ≤1 cm. Dos 850 pólipos analisados histologicamente, 55,17% eram adenomas tubulares, 21,88% hiperplásicos, 17,05% serrilhados, 5,4% tubulovilosos e 0,47% vilosos. Dos pólipos ≤1,0 cm, 16,0% apresentaram displasia e 1,9% adenocarcinoma; dos >1,0 cm houve displasia em 72,0% (p<0,001) e adenocarcinoma em 25,3% (p<0,001). Pólipos do cólon direito e transverso associaram-se mais à displasia (17,8% e 16,7%, respectivamente). Adenocarcinoma predominou no cólon esquerdo (2,5%) e reto (2,1%). Conclusão: Os pólipos predominaram em cólon esquerdo e reto. Os do cólon direito e transverso correlacionam-se fortemente à displasia, e os do reto e cólon esquerdo ao adenocarcinoma. Lesões maiores que 1,0 cm associaram-se positivamente com a presença de displasia e neoplasia. (AU)

[Standardized and structured histopathological evaluation of colorectal polyps: a practical checklist against the background of the new WHO classification]. / Standardisierte und strukturierte histopathologische Befundung kolorektaler Polypen: Eine Checkliste für die Praxis vor dem Hintergrund der neuen WHO-Klassifikation.

Gastroenterologists removing colorectal polyps expect standardized and well-structured pathological reports, providing them with all relevant data for the further clinical management of the patient. Over the last year, a task force of clinicians and pathologists has developed a checklist to improve and harmonize endoscopic and pathological reporting of colorectal polyps. This checklist concentrates more on concrete recommendations from evidence-based guidelines and established international classifications for daily practice rather than detailed molecular pathological pathways of carcinogenesis. These recommendations are based on the current S3 guidelines for colorectal cancer (the chapter entitled "Management of colorectal polyps"), the histomorphological consensus manuscript of the GI working group of the German Society for Pathology, as well as the current WHO classification for tumors of the digestive system.

Knowledge of the anatomical polyp location might bias the pathological classification of histologically equivocal colorectal serrated polyps - a consensus study performed by pathology trainees.

Colorectal serrated polyps (CSPs) comprise hyperplastic polyps (HPs), traditional (TSAs) and sessile (SSAs) serrated adenomas, as well as inflammatory cloacogenic polyps (ICPs). These lesions have typical anatomical locations and share a histomorphological overlap. In this study, we assessed the so far neglected issue as to what extent the histological classification of these lesions performed by pathology trainees is biased by the pathologists' knowledge of the polyp location in dependency on the duration of their training. To reach this aim, 49 CSPs were classified by three pathology trainees blinded to clinical data. In a second round of examination, the same raters were provided with the polyp location. A third round was conducted after a consensus conference. Intra- and inter-rater analyses were performed using Kappa (K) statistics and Spearman correlations. Our data suggest that the histological classification of CSPs performed by pathology trainees might be influenced in a clinically significant fashion by knowledge of the anatomical polyp location depending on the duration of their pathology training.

Sporadic duodenal polyps: classification, investigation, and management.

Sporadic duodenal polyps are uncommon, being found in up to 5% of patients referred for upper gastrointestinal endoscopy. They are often discovered incidentally and are usually asymptomatic. The histological subtype of polyps cannot always be determined on endoscopic appearance alone, and biopsy is advocated. The need for further imaging, endoscopic procedures, surgical resection, and surveillance is determined by the histological features, neoplastic potential and associated symptoms. This review describes the different subtypes of sporadic duodenal polyp: adenomas, hamartomas, gastric metaplasia, inflammatory fibroids, lipomas, leiomyomas, carcinoids, stromal tumors, solitary Peutz-Jeghers polyps, lymphomas, and other rare benign and malignant lesions. It describes the epidemiology, clinical presentation, investigation, management options, and screening and surveillance strategies for each, based on current evidence.