Value of Micro Flow Imaging in the Prediction of Adenomatous Polyps.

OBJECTIVE: The aim of this study was to assess the value of micro flow imaging (MFI) in distinguishing adenomatous polyps from cholesterol polyps. METHODS: A total of 143 patients who underwent cholecystectomy for gallbladder polyps were retrospectively analyzed. B-mode ultrasound (BUS), color Doppler flow imaging (CDFI), MFI and contrast-enhanced ultrasound (CEUS) were performed before cholecystectomy. The weighted kappa consistency test was used to evaluate the agreement of vascular morphology among CDFI, MFI and CEUS. Ultrasound image characteristics, including BUS, CDFI and MFI images, were compared between adenomatous polyps and cholesterol polyps. The independent risk factors for adenomatous polyps were selected. The diagnostic performance of MFI combined with BUS in determining adenomatous polyps was compared with CDFI combined with BUS. RESULTS: Of the 143 patients, 113 cases were cholesterol polyps, and 30 cases were adenomatous polyps. The vascular morphology of gallbladder polyps was more clearly depicted by MFI than CDFI, and it had better agreement with CEUS. Differences in maximum size, height/width ratio, hyperechoic spot and vascular intensity on CDFI and MFI images were significant between adenomatous polyps and cholesterol polyps (p < 0.05). The maximum size, height/width ratio, and vascular intensity on MFI images were independent risk factors for adenomatous polyps. For MFI combined with BUS, sensitivity, specificity and accuracy were 90.00%, 94.69% and 93.70%, respectively. Area under the receiver operating characteristic curve (AUC) of MFI combined with BUS was significantly higher than that of CDFI combined with BUS (AUC = 0.923 vs. 0.784). CONCLUSION: Compared with CDFI combined with BUS, MFI combined with BUS had higher diagnostic performance in determining adenomatous polyps.

Conventional Ultrasound Combined With Contrast-Enhanced Ultrasound in Differential Diagnosis of Gallbladder Cholesterol and Adenomatous Polyps (1-2 cm).

OBJECTIVES: This study aimed to determine ultrasonic image characteristics that enable differentiation between cholesterol and adenomatous polyps and to assess the diagnostic efficacy of combining conventional ultrasound (CUS) with contrast-enhanced ultrasound (CEUS). METHODS: Eighty-nine patients with gallbladder polyps of 1-2 cm in diameter were enrolled and examined by CUS and CEUS before cholecystectomy. The appearances on CUS and CEUS were recorded and analyzed. The receiver operating characteristic (ROC) curve was used to calculate the optimal size threshold for distinguishing cholesterol from adenomatous polyps. A logistic regression analysis was performed to identify diagnostic variables. ROC analysis was performed to evaluate the diagnostic efficacy of the size, the independent variables, and the combined factors. RESULTS: There were differences in size, number, vascularity on CUS and intralesional vascular shape, wash-out, and area under the curve on CEUS between the two groups (P < .05). ROC analysis indicated that a maximum diameter of 1.45 cm was the optimal threshold for the prediction of adenomatous polyps. The logistic regression analysis proved that the single polyp, presence of vascularity, and intralesional linear vessels were associated with adenomatous polyps (P < .05). ROC analysis showed that the area under the ROC curve, sensitivity, and specificity for the combination of the three independent variables were 0.858, 87.3%, and 67.6%. The number combined with intralesional vascular shape had the highest diagnostic sensitivity of 91.2%. CONCLUSIONS: The combination of CUS and CEUS demonstrated great significance in the differential diagnosis of cholesterol and adenomatous polyps.

Value of Conventional Ultrasound-based Scoring System in Distinguishing Adenomatous Polyps From Cholesterol Polyps.

BACKGROUND AND AIM: Ultrasound has increased the detection of gallbladder polyps, but it has limitations in evaluating the nature of gallbladder polyps, especially the maximum size of 1.0 to 1.5 cm. We assessed the value of ultrasound scoring system based on independent predictive parameters in distinguishing adenomatous polyps from cholesterol polyps with the maximum size of 1.0 to 1.5 cm. MATERIALS AND METHODS: We enrolled 163 patients with gallbladder polyps (1.0 to 1.5 cm) who underwent ultrasonography and cholecystectomy. Ultrasound image characteristics were compared between cholesterol polyps and adenomatous polyps in the training cohort from April 2018 to January 2020. An ultrasound scoring system was constructed in the training cohort, and its diagnostic performance was evaluated in the validation cohort from February 2020 to February 2021. RESULTS: Maximum size, height/width ratio, stone or sludge, vascularity, and hyperechoic spot were significantly different between cholesterol polyps and adenomatous polyps in the training cohort ( P <0.05). The independent predictive parameters for adenomatous polyps were lower height/width ratio, presence of vascularity and absence of hyperechoic spot. The total score was as follows: (height/width ratio, <0.9=4, ≥0.9=0) + (vascularity, present=3, absent=0) + (hyperechoic spot, absent=2, present=0). The sensitivity, specificity and accuracy of ultrasound scoring system ≥5 for diagnosis of adenomatous polyps in the validation cohort were 73.33%, 80.49%, and 78.57%, respectively. CONCLUSIONS: The ultrasound scoring system aids in distinguishing adenomatous polyps from cholesterol polyps, and effectively decreasing unnecessary cholecystectomy.

First experience in clinical application of hyperspectral endoscopy for evaluation of colonic polyps.

Early detection and resection of adenomatous polyps prevents their progression to colorectal cancer (CRC), significantly improving patient outcomes. Polyps are typically identified and removed during white-light colonoscopy. Unfortunately, the rate of interval cancers that arise between CRC screening events remains high, linked to poor visualization of polyps during screening and incomplete polyp removal. Here, we sought to evaluate the potential of a hyperspectral endoscope (HySE) to enhance polyp discrimination for detection and resection. We designed, built and tested a new compact HySE in a proof-of-concept clinical study. We successfully collected spectra from three tissue types in seven patients undergoing routine colonoscopy screening. The acquired spectral data from normal tissue and polyps, both pre- and post- resection, were subjected to quantitative analysis using spectral angle mapping and machine learning, which discriminated the data by tissue type, meriting further investigation of HySE as a clinical tool.

External validation of blue light imaging (BLI) criteria for the optical characterization of colorectal polyps by endoscopy experts.

BACKGROUND AND AIM: Recently, the BLI Adenoma Serrated International Classification (BASIC) system was developed by European experts to differentiate colorectal polyps. Our aim was to validate the BASIC classification system among the US-based endoscopy experts. METHODS: Participants utilized a web-based interactive learning system where the group was asked to characterize polyps using the BASIC criteria: polyp surface (presence of mucus, regular/irregular and [pseudo]depressed), pit appearance (featureless, round/non-round with/without dark spots; homogeneous/heterogeneous distribution with/without focal loss), and vessels (present/absent, lacy, peri-cryptal, irregular). The final testing consisted of reviewing BLI images/videos to determine whether the criteria accurately predicted the histology results. Confidence in adenoma identification (rated "1" to "5") and agreement in polyp (adenoma vs non-adenoma) identification and characterization per BASIC criteria were derived. Strength of interobserver agreement with kappa (k) value was reported for adenoma identification. RESULTS: Ten endoscopy experts from the United States identified conventional adenoma (vs non-adenoma) with 94.4% accuracy, 95.0% sensitivity, 93.8% specificity, 93.8% positive predictive value, and 94.9% negative predictive value using BASIC criteria. Overall strength of interobserver agreement was high: kappa 0.89 (0.82-0.96). Agreement for the individual criteria was as follows: surface mucus (93.8%), regularity (65.6%), type of pit (40.6%), pit visibility (66.9%), pit distribution (57%), vessel visibility (73%), and being lacy (46%) and peri-cryptal (61%). The confidence in diagnosis was rated at high ≥4 in 67% of the cases. CONCLUSIONS: A group of US-based endoscopy experts have validated a simple and easily reproducible BLI classification system to characterize colorectal polyps with >90% accuracy and a high level of interobserver agreement.

New polyp image classification technique using transfer learning of network-in-network structure in endoscopic images.

While colorectal cancer is known to occur in the gastrointestinal tract. It is the third most common form of cancer of 27 major types of cancer in South Korea and worldwide. Colorectal polyps are known to increase the potential of developing colorectal cancer. Detected polyps need to be resected to reduce the risk of developing cancer. This research improved the performance of polyp classification through the fine-tuning of Network-in-Network (NIN) after applying a pre-trained model of the ImageNet database. Random shuffling is performed 20 times on 1000 colonoscopy images. Each set of data are divided into 800 images of training data and 200 images of test data. An accuracy evaluation is performed on 200 images of test data in 20 experiments. Three compared methods were constructed from AlexNet by transferring the weights trained by three different state-of-the-art databases. A normal AlexNet based method without transfer learning was also compared. The accuracy of the proposed method was higher in statistical significance than the accuracy of four other state-of-the-art methods, and showed an 18.9% improvement over the normal AlexNet based method. The area under the curve was approximately 0.930 ± 0.020, and the recall rate was 0.929 ± 0.029. An automatic algorithm can assist endoscopists in identifying polyps that are adenomatous by considering a high recall rate and accuracy. This system can enable the timely resection of polyps at an early stage.

Dual-energy CT to differentiate gallbladder polyps: cholesterol versus adenomatous.

BACKGROUND: Dual-energy computed tomography (DE-CT) scans were acquired to identify cholesterol and adenomatous gallbladder (GB) polyps, which have not been well evaluated before surgery. PURPOSE: To evaluate the DE-CT findings of GB polyps 1.0-2.0 cm in size and differentiate between cholesterol and adenomatous polyps. MATERIAL AND METHODS: Forty-six patients with GB polyps were surgically treated from December 2017 to December 2019 and divided into two groups according to their postoperative pathologic results: a cholesterol group with 26 patients and an adenomatous group with 20 patients. All of these patients underwent DE-CT imaging with tube voltages of 80 kVp and 140 kVp within two weeks before surgery. Mean attenuation values were measured for every GB polyp at 80/140 kVp and at 40/140 keV. The mean attenuation value changes between 140 kVp and 80 kVp (MAVC140-80 kVp) and mean attenuation value changes between 100 keV and 40 keV (MAVC100-40 keV) were calculated. RESULTS: The CT image parameters of all 46 patients with GB polyps were analyzed. There were significant differences in MAVC140-80 kVp and MAVC100-40 keV between cholesterol and adenomatous polyps (P <0.05); these values were positive for cholesterol polyps and negative for adenomatous polyps. CONCLUSION: The unique energy spectrum information provided by DE-CT scans is helpful in differentiating between cholesterol and adenomatous polyps 1.0-2.0 cm in size.

Polyp detection algorithm can detect small polyps: Ex vivo reading test compared with endoscopists.

BACKGROUND AND STUDY AIMS: Small polyps are occasionally missed during colonoscopy. This study was conducted to validate the diagnostic performance of a polyp-detection algorithm to alert endoscopists to unrecognized lesions. METHODS: A computer-aided detection (CADe) algorithm was developed based on convolutional neural networks using training data from 1991 still colonoscopy images from 283 subjects with adenomatous polyps. The CADe algorithm was evaluated on a validation dataset including 50 short videos with 1-2 polyps (3.5 ± 1.5 mm, range 2-8 mm) and 50 videos without polyps. Two expert colonoscopists and two physicians in training separately read the same videos, blinded to the presence of polyps. The CADe algorithm was also evaluated using eight full videos with polyps and seven full videos without a polyp. RESULTS: The per-video sensitivity of CADe for polyp detection was 88% and the per-frame false-positive rate was 2.8%, with a confidence level of ≥30%. The per-video sensitivity of both experts was 88%, and the sensitivities of the two physicians in training were 84% and 76%. For each reader, the frames with missed polyps appearing on short videos were significantly less than the frames with detected polyps, but no trends were observed regarding polyp size, morphology or color. For full video readings, per-polyp sensitivity was 100% with a per-frame false-positive rate of 1.7%, and per-frame specificity of 98.3%. CONCLUSIONS: The sensitivity of CADe to detect small polyps was almost equivalent to experts and superior to physicians in training. A clinical trial using CADe is warranted.

Longer Withdrawal Time Is More Important than Excellent Bowel Preparation in Colonoscopy of Adequate Bowel Preparation.

BACKGROUND: Adequate bowel preparation is crucial for effective screening colonoscopy. However, it is unclear whether higher bowel preparation scores correspond to beneficial effects on the adenoma and polyp detection rate (ADR and PDR) in the adequate bowel preparation group. AIMS: This study aimed to evaluate the effects of bowel preparation, according to the Boston Bowel Preparation Scale (BBPS), and colonoscopy withdrawal time (CWT) on ADR and PDR in the adequate bowel preparation group. METHODS: Healthy examinees between 50 and 75 years old who underwent colonoscopy between September 2015 and August 2016 were included. BBPS scores, CWT, ADR, and PDR were reviewed retrospectively. Predictors of ADR and PDR were analyzed with a generalized linear mixed model. RESULTS: A total of 5073 cases with adequate bowel preparation (BBPS ≥ 6) were analyzed. Examinees with good (BBPS = 6, 7) and excellent (BBPS = 8, 9) bowel preparation were 1898 (37.4%) and 3175 (62.6%), respectively. Both ADR and PDR were higher in the good bowel preparation group than in the excellent bowel preparation group (ADR 47.3% vs. 45.0%, P = 0.035; PDR 73.7% vs. 69.5%, P = 0.004, respectively). In the multivariate analysis, CWT, rather than BBPS, was significantly associated with both ADR (OR 1.04; 95% CI 1.02-1.06; P < 0.001) and PDR (OR 1.05; 95% CI 1.02-1.07; P = 0.002). CONCLUSIONS: Both ADR and PDR were lower when bowel preparation was excellent rather than good. However, CWT, not BBPS, was significantly associated with ADR and PDR in the adequate bowel preparation group. Therefore, meticulous inspection is important for high-quality colonoscopy regardless of the BBPS score in examinees with adequate bowel preparation.

Evaluation of the satisfaction of the patient undergoing screening colonoscopy and quality of the procedure.

BACKGROUND: Screening colonoscopy requires quality parameters to determine its efficacy to detect cancerous or precancerous lesions. Limitations of the procedure are the patient's rejection, difficulty for its preparation or lack of preparation. OBJECTIVE: To assess whether patient satisfaction correlates with the quality of the procedure. METHOD: 100 consecutive patients for a screening colonoscopy were included, they were randomized to use a preparation with polyethylene glycol (PEG) or sodium picosulfate (P). In addition, a second parameter evaluated was related to a follow-up phone call performed to half of the patients prior to the study, during the preparation time. RESULTS: P was better tolerated and qualified, however, there was no difference with the quality of preparation, adenomatous polyps detection rate, cecum insertion rate and patient satisfaction. A difference was found in whom had a follow-up phone call. DISCUSSION: A good colon preparation is a key factor to have a quality colonoscopy, and it has been shown important that a good relationship for explain the doubts and follow the preparation. CONCLUSION: It was found that the type of preparation and patient follow-up during the study correlate with the quality of the study and patient satisfaction.

ANTECEDENTES: La colonoscopia de escrutinio requiere parámetros de calificación para determinar su eficiencia en la detección de lesiones cancerosas o precancerosas. Sus limitantes son su rechazo, la dificultad durante su preparación o la falta de preparación. OBJETIVO: Evaluar la satisfacción del paciente y los criterios de calidad del estudio. MÉTODO: Se incluyeron 100 pacientes enviados para colonoscopia de escrutinio asignados aleatoriamente a uno de dos grupos de preparación colónica: polietilenglicol (PEG) o picosulfato de sodio (P), para evaluar la satisfacción y la limpieza colónica. Otra evaluación fue por medio de llamada de refuerzo al momento de la preparación. RESULTADOS: Con P se tuvieron mejores tolerabilidad y calificaciones de satisfacción, en comparación con PEG. No hubo diferencia para la calidad de la limpieza, la tasa de detección de pólipos adenomatosos ni la intubación cecal. La llamada telefónica de reforzamiento incrementó la satisfacción, la limpieza colónica y la tasa de detección de adenomas. DISCUSIÓN: Una relación estrecha con el paciente durante su proceso de limpieza y explicación del procedimiento se ha visto como uno de los factores más importantes para lograr una colonoscopia de alta calidad. CONCLUSIÓN: El tipo de preparación colónica y la intervención durante la preparación se relacionaron con una mejor calidad del estudio y una mayor satisfacción del paciente.

Helicobacter pylori Eradication Regressed Gastric Hyperplastic Polyp: A Randomized Controlled Trial.

BACKGROUND: Helicobacter pylori infection and hyperplastic polyp are known to have strong connections, but there are not enough randomized controlled trial data. AIMS: To evaluate the effect of H. pylori eradication on gastric hyperplastic polyp. METHOD: This is an open-labeled, single-center, randomized controlled trial. Patients with hyperplastic polyp and current infection of H. pylori were randomly assigned to eradication or non-eradication groups. All participants underwent follow-up endoscopy to investigate the regression of gastric polyps. Gastric polyp regression was defined as the disappearance of polyps or a reduction of more than 50% in size. RESULTS: Thirty-two patients were randomized to eradication (n = 17) and non-eradication groups (n = 15). Final included patients were 14 in eradication group and 13 in non-eradication group. All patients showed polyp regression in eradication group, whereas no regression was observed in non-eradication group (P < 0.001). Disappearance of polyp (n = 7) and decrease in size (n = 7) were observed in eradication group. In non-eradication group, no change (n = 5), increase of size (n = 5), and increase of number (n = 3) were observed. Mean regression time was 6.8 months, and disappearance time was 9.8 months. In non-eradication group, hyperglycemia was noted in 50% of progression group but not noted in no change group (P = 0.057). CONCLUSIONS: H. pylori eradication induced regression of hyperplastic polyp, and persistent H. pylori infection was related to progression of gastric polyp. CLINICAL TRIAL REGISTRATION: ClinicalTrials.gov ID: NCT03065868.

Predictive rules for optical diagnosis of < 10-mm colorectal polyps based on a dedicated software.

BACKGROUND: The BASIC classification for predicting in vivo colorectal polyp histology incorporates both surface and pit/vessel descriptor domains. This study aimed to define new BASIC classes for adenomatous and hyperplastic polyps. METHODS: A video library (102 still images/videos of < 10-mm polyps using white-light [WLI] and blue-light imaging [BLI]) was reviewed by seven expert endoscopists. Polyps were rated according to the individual descriptors of the three BASIC domains (surface/pit/vessel). A model to predict polyp histology (adenomatous or hyperplastic) was developed using multivariable logistic regression and subsequent "leave-one-out" cross-validation. New BASIC rules were then defined by Delphi agreement. The overall accuracy of these rules when used by experts was evaluated according to the level of confidence and light type. RESULTS: The strength of prediction for adenomatous histology from 2175 observations assessed by area under the curve (AUC; 95 % confidence interval) was poor-to-fair for the surface descriptors (0.50 [0.33 - 0.69] for mucus; 0.68 [0.57 - 0.79] for irregular surface), but stronger for pits (0.87 [0.80 - 0.96] for featureless/round/not round) and vessels (0.80 [0.65 - 0.87] for not present/lacy/pericryptal). By combining the domains, a good-to-excellent prediction was shown (AUC 0.89 [0.81 - 0.96]). After the definition of new BASIC rules for adenomatous and hyperplastic polyps, accuracy for high confidence BLI predictions was 90.3 % (86.3 % - 93.2 %), which was superior to high confidence WLI (83.7 % [77.3 % - 87.7 %]) and low confidence BLI predictions (77.7 % [61.1 % - 88.6 %]). CONCLUSIONS: Based on the strength of prediction, the new BASIC classes for adenomatous and hyperplastic histology show favorable results for accuracy and confidence levels.

Pancreatoblastoma: Cytologic and histologic analysis of 12 adult cases reveals helpful criteria in their diagnosis and distinction from common mimics.

BACKGROUND: Pancreatoblastoma (PBL) is a rare malignant pancreatic tumor seen predominantly in childhood, and its cytologic diagnosis remains challenging. METHODS: Twelve fine-needle-aspirations from 11 adults were analyzed. RESULTS: In total, 6 men and 5 women (median age, 45 years; age range, 32-60 years) had tumors measuring a median 5.6 cm (range, 2.5-12 cm) located in the pancreatic head (n = 7) or tail (n = 4), including 3 with familial adenomatous polyposis (FAP)/FAP-related syndromes and 4 with metastasis at diagnosis. The median follow-up was 39.8 months (range, 0.8-348 months), and 5 patients died of disease. The original cytology diagnoses were: PBL (n = 2), neuroendocrine neoplasm (n = 2), poorly differentiated neuroendocrine carcinoma (n = 2), well differentiated neuroendocrine tumor (n = 1), poorly differentiated carcinoma (n = 2), "positive for malignancy" (n = 1), acinar cell carcinoma (n = 1), and epithelioid neoplasm with endocrine and acinar differentiation versus PBL (n = 1). Universal cytopathologic findings included hypercellularity; 3-dimensional clusters; and single, monotonous, blast-like cells that were from 1.5 to 2.0 times the size of red blood cells with high nuclear-to-cytoplasmic ratio, fine chromatin, small, distinct nucleoli, and a resemblance to well differentiated neuroendocrine tumor and poorly differentiated neuroendocrine carcinoma. Branching pseudopapillae (n = 7) and grooved nuclei (n = 3) raised the differential diagnosis of solid-pseudopapillary neoplasm, but with more atypia. Uncommon features included pleomorphism (n = 4) and numerous mitoses (n = 1). Squamoid morules were seen on smears (n = 5) or cell blocks (n = 6) in 70% of patients and were characterized by epithelioid cells with elongated, streaming nuclei, fine chromatin, absent nucleoli, and positive nuclear ß-catenin (n = 6 of 8). The median Ki-67 index was 21% (range, 2%-70%), and neuroendocrine marker expression was common (100%), but acinar markers were variable (63%). CONCLUSIONS: A combination of cytologic findings in PBL, including a predominant population of primitive blast-like cells, subtle squamoid morules, frequent neuroendocrine and variable acinar phenotype, should facilitate accurate cytologic diagnosis and distinction from common mimics.

Dynamic bioenergetic alterations in colorectal adenomatous polyps and adenocarcinomas.

BACKGROUND: Energy metabolism in carcinogenesis is poorly understood. It is widely accepted the majority of colorectal cancers (CRCs) arise from adenomatous polyps (APs). We aimed to characterize the bioenergetic alterations in APs and CRCs. METHODS: Fifty-six APs, 93 CRCs and adjacent normal mucosae were tested. Oxygen consumption rate (OCR) was measured representing mitochondrial oxidative phosphorylation (OxPhos), and extracellular acidification rate (ECAR)was measured representing glycolysis. Mitochondrial DNA (mtDNA) variants and mutations were studied. Over-expressed metabolic genes in APs were identified by microarray and validated by qRT-PCR, Western blots and immunohistochemistry. Identified genes were knocked down in WiDr and colo205 CRC cell lines, and their expression was analyzed in APs/CRCs with enhanced glycolysis. FINDINGS: ECAR, not OCR, was significantly increased in APs. While no difference of ECAR was found between CRCs and normal mucosae, OCR was significantly reduced in CRCs. OCR/ECAR ratio was decreased in APs over 1 cm, APs with a villous component and CRCs, indicating their glycolytic tendencies. The number of mtDNA mutations was increased in APs and CRCs, but not correlated with metabolic profiles. Two metabolic genes ALDOB and SLC16A4 were up-regulated in APs. Both ALDOB-knockdown and SLC16A4-knockdown CRC cell lines showed increased basal motichondrial OxPhos and decreased basal glycolysis. Moreover, the increase of mitochondrial ATP-linked respiration and the decrease of glycolytic capacity were showed in SLC16A4-knockdown cells. Finally, APs/CRCs with enhanced glycolysis had increased SLC16A4 expression. INTERPRETATION: ATP production shifts from OxPhos to glycolysis in the process of AP enlargement and villous transformation. OxPhos defects are present in CRCs but not in APs. APs and CRCs tend to accumulate mtDNA mutations, but these are not correlated with bioenergetic profiles. Finally, the ALDOB and SLC16A4 may contribute to the glycolytic shift in APs/CRCs.

Real-time gastric polyp detection using convolutional neural networks.

Computer-aided polyp detection in gastric gastroscopy has been the subject of research over the past few decades. However, despite significant advances, automatic polyp detection in real time is still an unsolved problem. In this paper, we report on a convolutional neural network (CNN) for polyp detection that is constructed based on Single Shot MultiBox Detector (SSD) architecture and which we call SSD for Gastric Polyps (SSD-GPNet). To take full advantages of feature maps' information from the feature pyramid and to acquire higher accuracy, we re-use information that is abandoned by Max-Pooling layers. In other words, we reuse the lost data from the pooling layers and concatenate that data as extra feature maps to contribute to classification and detection. Meanwhile, in the feature pyramid, we concatenate feature maps of the lower layers and feature maps that are deconvolved from upper layers to make explicit relationships between layers and to effectively increase the number of channels. The results show that our enhanced SSD for gastric polyp detection can realize real-time polyp detection with 50 frames per second (FPS) and can improve the mean average precision (mAP) from 88.5% to 90.4%, with only a little loss in time-performance. And the further experiment shows that SSD-GPNet has excellent performance in improving polyp detection recalls over 10% (p = 0.00053), especially in small polyp detection. This can help endoscopic physicians more easily find missed polyps and decrease the gastric polyp miss rate. It may be applicable in daily clinical practice to reduce the burden on physicians.

Optical Technologies for Endoscopic Real-Time Histologic Assessment of Colorectal Polyps: A Meta-Analysis.

OBJECTIVES: Accurate, real-time, endoscopic risk stratification of colorectal polyps would improve decision-making and optimize clinical efficiency. Technologies to manipulate endoscopic optical outputs can be used to predict polyp histology in vivo; however, it remains unclear how accuracy has progressed and whether it is sufficient for routine clinical implementation. METHODS: A meta-analysis was conducted by searching MEDLINE, Embase, and the Cochrane Library. Studies were included if they prospectively deployed an endoscopic optical technology for real-time in vivo prediction of adenomatous colorectal polyps. Polyposis and inflammatory bowel diseases were excluded. Bayesian bivariate meta-analysis was performed, presenting 95% confidence intervals (CI). RESULTS: One hundred two studies using optical technologies on 33,123 colorectal polyps were included. Digital chromoendoscopy differentiated neoplasia (adenoma and adenocarcinoma) from benign polyps with sensitivity of 92.2% (90.6%-93.9% CI) and specificity of 84.0% (81.5%-86.3% CI), with no difference between constituent technologies (narrow-band imaging, Fuji intelligent Chromo Endoscopy, iSCAN) or with only diminutive polyps. Dye chromoendoscopy had sensitivity of 92.7% (90.1%-94.9% CI) and specificity of 86.6% (82.9%-89.9% CI), similarly unchanged for diminutive polyps. Spectral analysis of autofluorescence had sensitivity of 94.4% (84.0%-99.1% CI) and specificity of 50.9% (13.2%-88.8% CI). Endomicroscopy had sensitivity of 93.6% (85.3%-98.3% CI) and specificity of 92.5% (81.8%-98.1% CI). Computer-aided diagnosis had sensitivity of 88.9% (74.2%-96.7% CI) and specificity of 80.4% (52.6%-95.7% CI). Prediction confidence and endoscopist experience alone did not significantly improve any technology. The only subgroup to demonstrate a negative predictive value for adenoma above 90% was digital chromoendoscopy, making high confidence predictions of diminutive recto-sigmoid polyps. Chronologic meta-analyses show a falling negative predictive value over time. A significant publication bias exists. DISCUSSION: This novel approach to meta-analysis demonstrates that existing optical technologies are increasingly unlikely to allow safe "resect and discard" strategies and that step-change innovation may be required. A "diagnose and leave" strategy may be supported for diminutive recto-sigmoid polyps diagnosed with high confidence; however, limitations exist in the evidence base for this cohort.

Endoscopic features of sessile serrated adenoma/polyps under narrowband imaging: A retrospective study.

OBJECTIVE: Sessile serrated adenoma/polyps (SSA/P) are recognized as precancerous lesions in the colon and resemble hyperplastic polyps (HP). Definite endoscopic features under narrow band imaging (NBI) with or without magnification may help differentiate these two lesions. Our study aimed to identify specific endoscopic features of SSA/P by NBI. METHODS: A total of 199 patients with histopathologically proven colorectal SSA/P or HP after a polypectomy were enrolled. Magnifying and non-magnifying NBI pictures of 206 matching lesions were evaluated by one expert and two non-expert endoscopists using various endoscopic characteristics retrospectively. RESULTS: Multivariate analysis indicated that a clouded surface (odds ratio [OR] 6.48, 95% confidence interval [CI] 2.72-15.44, P = 0.000) and dilated and branching vessels (DBV) (OR 7.95, 95% CI 3.71-17.02, P = 0.000) were significant endoscopic features for diagnosing SSA/P compared with HP. The combination of these two features could improve diagnostic specificity to 96%, and the area under the receiver operating characteristic curve was 0.749. However, it seemed that the presence of dark spots (OR 1.93, 95% CI 0.94-4.00, P = 0.075) was not a definite feature in differentiating these two lesions. Neither a mucus cap nor CP-II meshed capillary vessels showed statistical significance in differentiating SSA/P from HP (P = 0.590 and 0.293, respectively). CONCLUSIONS: A clouded surface and DBV were two indicators for diagnosing SSA/P. Combining these two factors together under NBI with or without magnification achieved better diagnostic performance than when they were used alone.

The value of oral contrast ultrasonography in the diagnosis of gastric cancer in elderly patients.

BACKGROUND: This study aims to investigate the value of oral contrast ultrasonography (OCUS) in the diagnosis of gastric cancer in elderly patients. METHODS: OCUS data obtained from patients ≥ 60 years old were retrospectively analyzed and compared with gastroscopy results. RESULTS: Among the 12,716 subjects examined by OCUS, 5021 subjects were ≥ 60 years old, which accounted for 39.48% (5021/12,716). Gastritis, gastric polyp, benign ulcer, and gastric cancer were detected by OCUS in 1099 patients. Among them, 196 patients underwent gastroscopy. Furthermore, ulcerative lesions were detected in 32 patients by OCUS and in 51 patients by gastroscopy, and the coincidence rate was 62.74%. Among these patients, gastric cancer was diagnosed in 18 patients by OCUS with a detection rate of 1.64% (18/1099) and detected in 19 patients by gastroscopy with a diagnostic coincidence rate of 94.73% (18/19). Furthermore, benign ulcer was detected in 14 patients by OCUS and in 32 patients by gastroscopy, and the diagnostic coincidence rate was 43.75% (14/32). CONCLUSION: OCUS helps to timely detect senile gastric cancer and can be used as a suitable technique for the detection of gastric diseases.

FANCA D1359Y mutation in a patient with gastric polyposis and cancer susceptibility: A case report and review of literature.

Gastric polyposis is a rare disease. Not all polyps progress to cancer. Monoallelic mutation in Fanconi anemia (FA) genes, unlike biallelic gene mutations that causes typical FA phenotype, can increase risks of cancers in a sporadic manner. Aberrations in the FA pathway were reported in all molecular subtypes of gastric cancer. We studied a patient with synchronous gastric cancer from gastric polyposis by conducting a 13-year long-term follow up. Via pathway-driven massive parallel genomic sequencing, a germline mutation at FANCA D1359Y was identified. We identified several recurrent mutations in DNA methylation (TET1, V873I), the ß-catenin pathway (CTNNB1, S45F) and RHO signaling pathway (PLEKHG5, R203C) by comparing the genetic events between benign and malignant gastric polyps. Furthermore, we revealed gastric polyposis susceptible genes and genetic events promoting malignant transformation using pathway-driven targeted gene sequencing.