Colonoscopy For Detection Of Polyps Research Articles

Colonoscopy Polyp Detection Using Bi-Directional Conv-LSTM U-Net with Densely Connected Convolution

Colonoscopy Polyp Detection Using Bi-Directional Conv-LSTM U-Net with Densely Connected Convolution

Two-stage deep-learning-based colonoscopy polyp detection incorporating fisheye and reflection correction.

Colonoscopy is a useful method for the diagnosis and management of colorectal diseases. Many computer-aided systems have been developed to assist clinicians in detecting colorectal lesions by analyzing colonoscopy images. However, fisheye-lens distortion and light reflection in colonoscopy images can substantially affect the clarity of these images and their utility in detecting polyps. This study proposed a two-stage deep-learning model to correct distortion and reflections in colonoscopy images and thus facilitate polyp detection. Images were collected from the PolypSet dataset, the Kvasir-SEG dataset, and one medical center's patient archiving and communication system. The training, validation, and testing datasets comprised 808, 202, and 1100 images, respectively. The first stage involved the correction of fisheye-related distortion in colonoscopy images and polyp detection, which was performed using a convolutional neural network. The second stage involved the use of generative and adversarial networks for correcting reflective colonoscopy images before the convolutional neural network was used for polyp detection. The model had higher accuracy when it was validated using corrected images than when it was validated using uncorrected images (96.8% vs 90.8%, P<0.001). The model's accuracy in detecting polyps in the Kvasir-SEG dataset reached 96%, and the area under the receiver operating characteristic curve was 0.94. The proposed model can facilitate the clinical diagnosis of colorectal polyps and improve the quality of colonoscopy.

Artificial Intelligence in Colonoscopic Polyp Detection and Characterization: Merging Computer Technology and Endoscopic Skill for Better Patient Care

AbstractArtificial intelligence (AI) is a computer technology for mathematical modeling that uses nonlinear statistical analysis. While multilayer perceptron network is used for prediction of clinical outcome, convolutional neural network is used for detection of lesion in an image and its classification. In this issue of the journal, an article reviewed the impact of AI in colorectal polyp detection and characterization. This is an upcoming area of gastroenterology, which has already reached the doorstep of practicing clinicians and in the near future, it may bring a paradigm shift in clinical practice. It is expected that this thought-provoking review will stimulate endoscopists to take up research in this important field of application of an AI-based computer technology for endoscopic detection of gastrointestinal lesions.

Effect of selection bias on Automatic Colonoscopy Polyp Detection

Despite the successful demonstration of the deep learning architectures for Automatic Colonoscopy Polyp Detection (ACPD), studies have argued upon human bias, and lack of interpretability in the existing architectures which hampers its routine clinical and real-time use. To investigate the presence of selection bias, the present work develops a proof-of-concept model with the help of reverse psychology. The model comprises a fine-tuned, interpretable ACPD architecture (VGG-16) and its real-time application (app) called the polyp testing app (link) without consideration of selection bias in the existing open-source colonoscopy datasets. To check the robustness of the developed architecture, it has been trained, validated, and tested on six independent datasets. Evaluation methods in the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) criteria have been used to check the effectiveness of the architecture. Specificity and precision up to 97.3% and 92.0% respectively have been achieved on the validation dataset. A new test set called ‘Gastrolab-Polyp’ has been developed for fair external testing of the developed architecture (link). In comparison to the reference app, the developed app achieved a percentage improvement of 15%, 30.5%, and 14.5% in an overall test dataset accuracy, precision, and recall respectively for the developed Gastrolab-Polyp test dataset. Interpretability methods such as class activation maps, Shapley plots, LIME, and detection analysis of the developed and reference app indicate a bias towards polyp frames. The present work concludes that there is a selection bias of non-polyp frames in five open-source colonoscopy datasets used for polyp detection. Careful dataset collection is needed for its use.

Specific Targeting and Labeling of Colonic Polyps in CPC-APC Mice with Mucin 5AC Fluorescent Antibodies: A Model for Detection of Early Colon Cancer.

Poor visualization of polyps can limit colorectal cancer screening. Fluorescent antibodies to mucin5AC (MUC5AC), a glycoprotein upregulated in adenomas and colorectal cancer, could improve screening colonoscopy polyp detection rate. Adenomatous polyposis coli flox mice with a Cdx2-Cre transgene (CPC-APC) develop colonic polyps that contain both dysplastic and malignant tissue. Mice received MUC5AC-IR800 or IRdye800 as a control IV and were sacrificed after 48 h for near-infrared imaging of their colons. A polyp-to-background ratio (PBR) was calculated for each polyp by dividing the mean fluorescence intensity of the polyp by the mean fluorescence intensity of the background tissue. The mean 25 μg PBR was 1.70 (±0.56); the mean 50 μg PBR was 2.64 (±0.97); the mean 100 μg PBR was 3.32 (±1.33); and the mean 150 μg PBR was 3.38 (±0.87). The mean PBR of the dye-only control was 2.22 (±1.02), significantly less than the 150 μg arm (p-value 0.008). The present study demonstrates the ability of fluorescent anti-MUC5AC antibodies to specifically target and label colonic polyps containing high-grade dysplasia and intramucosal adenocarcinoma in CPC-APC mice. This technology can potentially improve the detection rate and decrease the miss rate of advanced colonic neoplasia and early cancer at colonoscopy.

Cost-effectiveness of Artificial Intelligence-Aided Colonoscopy for Adenoma Detection in Colon Cancer Screening.

Artificial intelligence-aided colonoscopy significantly improves adenoma detection. We assessed the cost-effectiveness of the GI Genius technology, an artificial intelligence-aided computer diagnosis for polyp detection (CADe), in improving colorectal cancer outcomes, adopting a Canadian health care perspective. A Markov model with 1-year cycles and a lifetime horizon was used to estimate incremental cost-effectiveness ratio comparing CADe to conventional colonoscopy polyp detection amongst patients with a positive faecal immunochemical test. Outcomes were life years (LYs) and quality-adjusted life years (QALY) gained. The analysis applied costs associated with health care resource utilization, including procedures and follow-ups, from a provincial payer's perspective using 2022 Canadian dollars. Effectiveness and cost data were sourced from the literature and publicly available databases. Extensive probabilistic and deterministic sensitivity analyses were performed, assessing model robustness. Life years and QALY gains for the CADe and conventional colonoscopy groups were 19.144 versus 19.125 and 17.137 versus 17.113, respectively. CADe and conventional colonoscopies' overall per-case costs were $2990.74 and $3004.59, respectively. With a willingness-to-pay pre-set at $50,000/QALY, the incremental cost-effectiveness ratio was dominant for both outcomes, showing that CADe colonoscopy is cost-effective. Deterministic sensitivity analysis confirmed that the model was sensitive to the incidence risk ratio of adenoma per colonoscopy for large adenomas. Probabilistic sensitivity analysis showed that the CADe strategy was cost-effective in up to 73.4% of scenarios. The addition of CADe solution to colonoscopy is a dominant, cost-effective strategy when used in faecal immunochemical test-positive patients in a Canadian health care setting.

Computer-aided automated diminutive colonic polyp detection in colonoscopy by using deep machine learning system; first indigenous algorithm developed in India.

Colonic polyps can be detected and resected during a colonoscopy before cancer development. However, about 1/4th of the polyps could be misseddue to their small size, location or human errors. An artificial intelligence (AI) system can improve polyp detection and reduce colorectal cancer incidence. We are developing an indigenous AI systemto detect diminutive polyps in real-life scenarios that can be compatible with any high-definition colonoscopy and endoscopic video-capture software. We trained a masked region-based convolutional neural network model to detect and localize colonic polyps. Three independent datasets of colonoscopy videos comprising 1,039 image frames were used and divided into a training dataset of 688 frames and a testing dataset of 351 frames. Of 1,039 image frames, 231 were from real-life colonoscopy videos from our centre. The rest were from publicly available image frames already modified to be directly utilizable for developing the AI system. The image frames of the testing dataset were also augmented by rotating and zooming the images to replicate real-life distortions of images seen during colonoscopy. The AI system was trained to localize the polyp by creating a 'bounding box'. It was then applied to the testing dataset to test its accuracy in detecting polyps automatically. The AI system achieved a mean average precision (equivalent to specificity) of 88.63% for automatic polyp detection. All polyps in the testing were identified by AI, i.e., nofalse-negativeresult in the testing dataset (sensitivity of 100%). The mean polyp size in the study was 5 (± 4) mm. The mean processing time per image frame was 96.4minutes. This AI system, when applied to real-life colonoscopy images, having wide variations in bowel preparation and small polyp size, can detect colonic polyps with a high degree of accuracy.

Endoscopist Characteristics and Polyp Detection in Colonoscopy: Cross-Sectional Analyses of Screening of Swedish Colons

Endoscopist Characteristics and Polyp Detection in Colonoscopy: Cross-Sectional Analyses of Screening of Swedish Colons

Frame-by-Frame Analysis of a Commercially Available Artificial Intelligence Polyp Detection System in Full-Length Colonoscopies

Introduction: Computer-aided detection (CADe) helps increase colonoscopic polyp detection. However, little is known about other performance metrics like the number and duration of false-positive (FP) activations or how stable the detection of a polyp is. Methods: 111 colonoscopy videos with total 1,793,371 frames were analyzed on a frame-by-frame basis using a commercially available CADe system (GI-Genius, Medtronic Inc.). Primary endpoint was the number and duration of FP activations per colonoscopy. Additionally, we analyzed other CADe performance parameters, including per-polyp sensitivity, per-frame sensitivity, and first detection time of a polyp. We additionally investigated whether a threshold for withholding CADe activations can be set to suppress short FP activations and how this threshold alters the CADe performance parameters. Results: A mean of 101 ± 88 FPs per colonoscopy were found. Most of the FPs consisted of less than three frames with a maximal 66-ms duration. The CADe system detected all 118 polyps and achieved a mean per-frame sensitivity of 46.6 ± 26.6%, with the lowest value for flat polyps (37.6 ± 24.8%). Withholding CADe detections up to 6 frames length would reduce the number of FPs by 87.97% (p < 0.001) without a significant impact on CADe performance metrics. Conclusions: The CADe system works reliable but generates many FPs as a side effect. Since most FPs are very short, withholding short-term CADe activations could substantially reduce the number of FPs without impact on other performance metrics. Clinical practice would benefit from the implementation of customizable CADe thresholds.

The study on artificial intelligence (AI) colonoscopy in affecting the rate of polyp detection in colonoscopy: A single centre retrospective study

AbstractAimThe aim of this study was to evaluate if the application of Artificial Intelligence (AI) Colonoscopy CLN (ENDO‐AID) could increase the polyp detection rate (PDR).Methods and MaterialsA single center retrospective study was performed in Tin Shui Wai Hospital. PDR in CLN from 11/2020 to 03/2021 after the application of ENDO‐AID (AI group) was compared to the cases from 12/2019 to 11/2020 before the application of the practice (non‐AI group). Procedures were performed by a single endoscopist with experience in performing &gt; 3,000 CLN. Variables, such as patients' demographic data, indications, incidence of PDR, Boston Bowel Preparation Scale BBPS, withdrawal time, post CLN complication rate between the 2 groups, were compared. Categorical and continuous variables were analyzed by using the Chi‐Square test (Fisher exact test if appropriate) and Mann‐Whitney test respectively. Results were considered to be significant if p‐value &lt; 0.05.ResultsTotal 234 patients were recruited. 115 patients (49.1%) were in the non‐AI group while 119 patients (50.9%) were in the AI group. The mean age of the non‐AI was higher than the AI group (65.3 vs 59.2, p&lt; 0.001*), otherwise, there was no significant difference in sex (p = 0.05), percentage of smokers (20.8% vs 27.7%, p = 0.22), past medical history of IBD (0 vs 0, p = 1.0), family history of colorectal cancer (9 vs 9, p = 0.94), indications for CLN (e.g. follow up CLN for polyp/ cancer, per‐rectal bleeding, altered bowel habit etc. p &gt; 0.05), BBPS (7.88 vs 8.04, p = 0.217), withdrawal time (7.65 min vs 7.48 min, p = 0.935), completion rate (95.6% vs 98.3%, p = 0.27) and complication rate (0% in both groups,p=1.0) between groups. In the contrary, PDR was significantly higher in the AI group than the non‐AI group (64.7% vs 46.0%, p = 0.003*). Besides, adenoma detection rate was also found significantly higher in the AI group than the non‐AI group (52.9% vs 37.4%, p = 0.017*).ConclusionsAI CLN can improve the PDR.

Colonoscopic image synthesis with generative adversarial network for enhanced detection of sessile serrated lesions using convolutional neural network

Computer-aided detection (CADe) systems have been actively researched for polyp detection in colonoscopy. To be an effective system, it is important to detect additional polyps that may be easily missed by endoscopists. Sessile serrated lesions (SSLs) are a precursor to colorectal cancer with a relatively higher miss rate, owing to their flat and subtle morphology. Colonoscopy CADe systems could help endoscopists; however, the current systems exhibit a very low performance for detecting SSLs. We propose a polyp detection system that reflects the morphological characteristics of SSLs to detect unrecognized or easily missed polyps. To develop a well-trained system with imbalanced polyp data, a generative adversarial network (GAN) was used to synthesize high-resolution whole endoscopic images, including SSL. Quantitative and qualitative evaluations on GAN-synthesized images ensure that synthetic images are realistic and include SSL endoscopic features. Moreover, traditional augmentation methods were used to compare the efficacy of the GAN augmentation method. The CADe system augmented with GAN synthesized images showed a 17.5% improvement in sensitivity on SSLs. Consequently, we verified the potential of the GAN to synthesize high-resolution images with endoscopic features and the proposed system was found to be effective in detecting easily missed polyps during a colonoscopy.

Deep reconstruction-recoding network for unsupervised domain adaptation and multi-center generalization in colonoscopy polyp detection

Background and objective: Currently, the best performing methods in colonoscopy polyp detection are primarily based on deep neural networks (DNNs), which are usually trained on large amounts of labeled data. However, different hospitals use different endoscope models and set different imaging parameters, which causes the collected endoscopic images and videos to vary greatly in style. There may be variations in the color space, brightness, contrast, and resolution, and there are also differences between white light endoscopy (WLE) and narrow band image endoscopy (NBIE). We call these variations the domain shift. The DNN performance may decrease when the training data and the testing data come from different hospitals or different endoscope models. Additionally, it is quite difficult to collect enough new labeled data and retrain a new DNN model before deploying that DNN to a new hospital or endoscope model.Methods: To solve this problem, we propose a domain adaptation model called Deep Reconstruction-Recoding Network (DRRN), which jointly learns a shared encoding representation for two tasks: i) a supervised object detection network for labeled source data, and ii) an unsupervised reconstruction-recoding network for unlabeled target data. Through the DRRN, the object detection network's encoder not only learns the features from the labeled source domain, but also encodes useful information from the unlabeled target domain. Therefore, the distribution difference of the two domains’ feature spaces can be reduced.Results: We evaluate the performance of the DRRN on a series of cross-domain datasets. Compared with training the polyp detection network using only source data, the performance of the DRRN on the target domain is improved. Through feature statistics and visualization, it is demonstrated that the DRRN can learn the common distribution and feature invariance of the two domains. The distribution difference between the feature spaces of the two domains can be reduced.Conclusion: The DRRN can improve cross-domain polyp detection. With the DRRN, the generalization performance of the DNN-based polyp detection model can be improved without additional labeled data. This improvement allows the polyp detection model to be easily transferred to datasets from different hospitals or different endoscope models.

Artificial intelligence-assisted colonoscopy: A prospective, multicenter, randomized controlled trial of polyp detection.

BackgroundArtificial intelligence (AI) assistance has been considered as a promising way to improve colonoscopic polyp detection, but there are limited prospective studies on real‐time use of AI systems.MethodsWe conducted a prospective, multicenter, randomized controlled trial of patients undergoing colonoscopy at six centers. Eligible patients were randomly assigned to conventional colonoscopy (control group) or AI‐assisted colonoscopy (AI group). AI assistance was our newly developed AI system for real‐time colonoscopic polyp detection. Primary outcome is polyp detection rate (PDR). Secondary outcomes include polyps per positive patient (PPP), polyps per colonoscopy (PPC), and non‐first polyps per colonoscopy (PPC‐Plus).ResultsA total of 2352 patients were included in the final analysis. Compared with the control, AI group did not show significant increment in PDR (38.8% vs. 36.2%, p = 0.183), but its PPC‐Plus was significantly higher (0.5 vs. 0.4, p < 0.05). In addition, AI group detected more diminutive polyps (76.0% vs. 68.8%, p < 0.01) and flat polyps (5.9% vs. 3.3%, p < 0.05). The effects varied somewhat between centers. In further logistic regression analysis, AI assistance independently contributed to the increment of PDR, and the impact was more pronounced for male endoscopists, shorter insertion time but longer withdrawal time, and elderly patients with larger waist circumference.ConclusionThe intervention of AI plays a limited role in overall polyp detection, but increases detection of easily missed polyps; ChiCTR.org.cn number, ChiCTR1800015607.

Author commentary on Erik A. Holzwanger et al.

Erik A. Holzwanger et al. Benchmarking definitions of false-positive alerts during computer-aided polyp detection in colonoscopy

Colonoscopy polyp detection and classification: Dataset creation and comparative evaluations.

Colorectal cancer (CRC) is one of the most common types of cancer with a high mortality rate. Colonoscopy is the preferred procedure for CRC screening and has proven to be effective in reducing CRC mortality. Thus, a reliable computer-aided polyp detection and classification system can significantly increase the effectiveness of colonoscopy. In this paper, we create an endoscopic dataset collected from various sources and annotate the ground truth of polyp location and classification results with the help of experienced gastroenterologists. The dataset can serve as a benchmark platform to train and evaluate the machine learning models for polyp classification. We have also compared the performance of eight state-of-the-art deep learning-based object detection models. The results demonstrate that deep CNN models are promising in CRC screening. This work can serve as a baseline for future research in polyp detection and classification.

Artificial intelligence and polyp detection in colonoscopy: Use of a single neural network to achieve rapid polyp localization for clinical use.

Artificial intelligence has been extensively studied to assist clinicians in polyp detection, but such systems usually require expansive processing power, making them prohibitively expensive and hindering wide adaption. The current study used a fast object detection algorithm, known as the YOLOv3 algorithm, to achieve real-time polyp detection on a laptop. In addition, we evaluated and classified the causes of false detections to further improve accuracy. The YOLOv3 algorithm was trained and validated with 6038 and 2571 polyp images, respectively. Videos from live colonoscopies in a tertiary center and those obtained from public databases were used for the training and validation sets. The algorithm was tested on 10 unseen videos from the CVC-Video ClinicDB dataset. Only bounding boxes with an intersection over union area of >0.3 were considered positive predictions. Polyp detection rate in our study was 100%, with the algorithm able to detect every polyp in each video. Sensitivity, specificity, and F1 score were 74.1%, 85.1%, and 83.3, respectively. The algorithm achieved a speed of 61.2frames per second (fps) on a desktop RTX2070 GPU and 27.2fps on a laptop GTX2060 GPU. Nearly a quarter of false negatives happened when the polyps were at the corner of an image. Image blurriness accounted for approximately 3% and 9% of false positive and false negative detections, respectively. The YOLOv3 algorithm can achieve real-time poly detection with high accuracy and speed on a desktop GPU, making it low cost and accessible to most endoscopy centers worldwide.

Current Status and Future Perspective of Artificial Intelligence in the Management of Peptic Ulcer Bleeding: A Review of Recent Literature.

With the decreasing incidence of peptic ulcer bleeding (PUB) over the past two decades, the clinician experience of managing patients with PUB has also declined, especially for young endoscopists. A patient with PUB management requires collaborative care involving the emergency department, gastroenterologist, radiologist, and surgeon, from initial assessment to hospital discharge. The application of artificial intelligence (AI) methods has remarkably improved people’s lives. In particular, AI systems have shown great potential in many areas of gastroenterology to increase human performance. Colonoscopy polyp detection or diagnosis by an AI system was recently introduced for commercial use to improve endoscopist performance. Although PUB is a longstanding health problem, these newly introduced AI technologies may soon impact endoscopists’ clinical practice by improving the quality of care for these patients. To update the current status of AI application in PUB, we reviewed recent relevant literature and provided future perspectives that are required to integrate such AI tools into real-world practice.

Initial experiments of eye-tracking during AIassisted polyp-detection in colonoscopy

Abstract Currently, various AI-based systems for computerassisted adenoma- and polyp-detection during colonoscopy have been brought to the market and are under clinical investigation. With these systems available to be used during routine screening colonoscopy and first results published about experiments and findings, it has become of interest how and to which extend such systems are used during the examination. Specifically, similarly to automotive navigation, it is of interest of how much visual focus is put onto the augmented image of the above-mentioned devices, signalling possible hypothesis of adenomas or polyps, and how much time-of-attention remains on the original colonoscopic video data. Thus, within a study, N = 36 participants using a prototype of a polypdetection system have been observed with an eye-tracker-system, to capture and evaluate the relative time of attention with respect to the original and augmented video data and differentiate these values between various sub-groups based on experience, education and gender. T-tests were conducted to identify potential significant differences. Based on the obtained data, the augmented video data is used with a very high attention (up to 75%) depending on the regarded sub-group. Experienced as well as less-experienced users (with &gt; 500 colonoscopies) both preferred looking at the original data. In contrast, gastroenterologists (in contrast to nurses, students, engineers) were more interested in the outcome of the novel AIsystem. The female group preferred looking at the unobstructed data, while the male group was highly interested in the AI-based data.

A robust real-time deep learning based automatic polyp detection system

Colorectal cancer (CRC) is globally the third most common type of cancer. Colonoscopy is considered the gold standard in colorectal cancer screening and allows for the removal of polyps before they become cancerous. Computer-aided detection systems (CADs) have been developed to detect polyps. Unfortunately, these systems have limited sensitivity and specificity. In contrast, deep learning architectures provide better detection by extracting the different properties of polyps. However, the desired success has not yet been achieved in real-time polyp detection. Here, we propose a new structure for real-time polyp detection by scaling the YOLOv4 algorithm to overcome these obstacles. For this, we first replace the whole structure with Cross Stage Partial Networks (CSPNet), then substitute the Mish activation function for the Leaky ReLu activation function and also substituted the Distance Intersection over Union (DIoU) loss for the Complete Intersection over Union (CIoU) loss. We improved performance of YOLOv3 and YOLOv4 architectures using different structures such as ResNet, VGG, DarkNet53, and Transformers. To increase success of the proposed method, we utilized a variety of data augmentation approaches for preprocessing, an ensemble learning model, and NVIDIA TensorRT for post processing. In order to compare our study with other studies more objectively, we only employed public data sets and followed MICCAI Sub-Challenge on Automatic Polyp Detection in Colonoscopy. The proposed method differs from other methods with its real-time performance and state-of-the-art detection accuracy. The proposed method (without ensemble learning) achieved higher results than those found in the literature, precision: 91.62%, recall: 82.55%, F1-score: 86.85% on public ETIS-LARIB data set and precision: 96.04%, recall: 96.68%, F1-score: 96.36% on public CVC-ColonDB data set, respectively.

Impact of Artifical Intelligence in Colonoscopic Polyp Detection and Classification

Background: Despite screening colonoscopy the relative risk for incidence and mortality of colorectal cancer accounts still for 50 to 60% probably due to missed adenomas. Artificial intelligence is a new development to rise detection of colorectal lesions and additionally to classify them.