Resection of Diminutive and Small Colorectal Polyps: What Is the Optimal Technique?

Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning

Computer-aided detection, localisation, and segmentation methods can help improve colonoscopy procedures. Even though many methods have been built to tackle automatic detection and segmentation of polyps, benchmarking of state-of-the-art methods still remains an open problem. This is due to the increasing number of researched computer vision methods that can be applied to polyp datasets. Benchmarking of novel methods can provide a direction to the development of automated polyp detection and segmentation tasks. Furthermore, it ensures that the produced results in the community are reproducible and provide a fair comparison of developed methods. In this paper, we benchmark several recent state-of-the-art methods using Kvasir-SEG, an open-access dataset of colonoscopy images for polyp detection, localisation, and segmentation evaluating both method accuracy and speed. Whilst, most methods in literature have competitive performance over accuracy, we show that the proposed ColonSegNet achieved a better trade-off between an average precision of 0.8000 and mean IoU of 0.8100, and the fastest speed of 180 frames per second for the detection and localisation task. Likewise, the proposed ColonSegNet achieved a competitive dice coefficient of 0.8206 and the best average speed of 182.38 frames per second for the segmentation task. Our comprehensive comparison with various state-of-the-art methods reveals the importance of benchmarking the deep learning methods for automated real-time polyp identification and delineations that can potentially transform current clinical practices and minimise miss-detection rates.

Prediction of Polyp Pathology Using Convolutional Neural Networks Achieves "Resect and Discard" Thresholds

OBJECTIVES

Reliable in situ diagnosis of diminutive (≤5 mm) colorectal polyps could allow for "resect and discard" and "diagnose and leave" strategies, resulting in $1 billion cost savings per year in the United States alone. Current methodologies have failed to consistently meet the Preservation and Incorporation of Valuable endoscopic Innovations (PIVIs) initiative thresholds. Convolutional neural networks (CNNs) have the potential to predict polyp pathology and achieve PIVI thresholds in real time.

METHODS

We developed a CNN-based optical pathology (OP) model using Tensorflow and pretrained on ImageNet, capable of operating at 77 frames per second. A total of 6,223 images of unique colorectal polyps of known pathology, location, size, and light source (white light or narrow band imaging [NBI]) underwent 5-fold cross-training (80%) and validation (20%). Separate fresh validation was performed on 634 polyp images. Surveillance intervals were calculated, comparing OP with true pathology.

RESULTS

In the original validation set, the negative predictive value for adenomas was 97% among diminutive rectum/rectosigmoid polyps. Results were independent of use of NBI or white light. Surveillance interval concordance comparing OP and true pathology was 93%. In the fresh validation set, the negative predictive value was 97% among diminutive polyps in the rectum and rectosigmoid and surveillance concordance was 94%.

DISCUSSION

This study demonstrates the feasibility of in situ diagnosis of colorectal polyps using CNN. Our model exceeds PIVI thresholds for both "resect and discard" and "diagnose and leave" strategies independent of NBI use. Point-of-care adenoma detection rate and surveillance recommendations are potential added benefits.

Prediction of Polyp Pathology Using Convolutional Neural Networks Achieves "Resect and Discard" Thresholds

OBJECTIVES

Reliable in situ diagnosis of diminutive (≤5 mm) colorectal polyps could allow for "resect and discard" and "diagnose and leave" strategies, resulting in $1 billion cost savings per year in the United States alone. Current methodologies have failed to consistently meet the Preservation and Incorporation of Valuable endoscopic Innovations (PIVIs) initiative thresholds. Convolutional neural networks (CNNs) have the potential to predict polyp pathology and achieve PIVI thresholds in real time.

METHODS

We developed a CNN-based optical pathology (OP) model using Tensorflow and pretrained on ImageNet, capable of operating at 77 frames per second. A total of 6,223 images of unique colorectal polyps of known pathology, location, size, and light source (white light or narrow band imaging [NBI]) underwent 5-fold cross-training (80%) and validation (20%). Separate fresh validation was performed on 634 polyp images. Surveillance intervals were calculated, comparing OP with true pathology.

RESULTS

In the original validation set, the negative predictive value for adenomas was 97% among diminutive rectum/rectosigmoid polyps. Results were independent of use of NBI or white light. Surveillance interval concordance comparing OP and true pathology was 93%. In the fresh validation set, the negative predictive value was 97% among diminutive polyps in the rectum and rectosigmoid and surveillance concordance was 94%.

DISCUSSION

This study demonstrates the feasibility of in situ diagnosis of colorectal polyps using CNN. Our model exceeds PIVI thresholds for both "resect and discard" and "diagnose and leave" strategies independent of NBI use. Point-of-care adenoma detection rate and surveillance recommendations are potential added benefits.

Comparative efficacy of cold polypectomy techniques for diminutive colorectal polyps: a systematic review and network meta-analysis

BACKGROUND

Although cold polypectomy techniques are preferred over polypectomy with electrocautery in the management of diminutive polyps, comprehensive comparisons among various cold polypectomy techniques have not yet been fully performed.

METHODS

We searched for all relevant randomized controlled trials published up until October 2016 examining the efficacy of cold polypectomy techniques for diminutive polyps. Cold polypectomy techniques were classified as cold forceps polypectomy (CFP), jumbo forceps polypectomy (JFP), traditional cold snare polypectomy (CSP), and dedicated CSP, according to the type of device. A network meta-analysis was performed to calculate the direct and indirect estimates of efficacy among the cold polypectomy techniques.

RESULTS

Seven studies with 703 patients and 968 polyps were included in the meta-analysis. Regarding comparative efficacy for complete histological eradication, there was no inconsistency in the network (Cochran's Q test, df = 4, P = 0.22; I ² = 30%). In terms of complete histological eradication, both dedicated and traditional CSP were superior to CFP (odds ratio [OR] [95% confidence interval [CI]] 4.31 [1.92-9.66] and 2.45 [1.30-4.63], respectively); dedicated CSP was superior to traditional CSP (OR [95% CI] 1.76 [1.07-2.89]); and there was no difference between JFP versus CFP (OR [95% CI] 1.36 [0.40-4.61]). Regarding tissue retrieval rate, there was no difference between dedicated versus traditional CSP (OR [95% CI] 1.03 [0.44-2.38]). The procedure time for CSP was comparable to that of CFP.

CONCLUSIONS

Dedicated CSP was shown to be superior to other cold polypectomy techniques in terms of complete histological eradication. Cold polypectomy using a dedicated snare can be recommended for the removal of diminutive colorectal polyps.