scholarly journals PICCOLO White-Light and Narrow-Band Imaging Colonoscopic Dataset: A Performance Comparative of Models and Datasets

2020 ◽  
Vol 10 (23) ◽  
pp. 8501
Author(s):  
Luisa F. Sánchez-Peralta ◽  
J. Blas Pagador ◽  
Artzai Picón ◽  
Ángel José Calderón ◽  
Francisco Polo ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Deep Learning ◽  
White Light ◽  
Narrow Band ◽  
Narrow Band Imaging ◽  
Polyp Detection ◽  
Test Set ◽  
Learning Techniques ◽  
Adenoma Detection ◽  
Comparison Results

Colorectal cancer is one of the world leading death causes. Fortunately, an early diagnosis allows for effective treatment, increasing the survival rate. Deep learning techniques have shown their utility for increasing the adenoma detection rate at colonoscopy, but a dataset is usually required so the model can automatically learn features that characterize the polyps. In this work, we present the PICCOLO dataset, that comprises 3433 manually annotated images (2131 white-light images 1302 narrow-band images), originated from 76 lesions from 40 patients, which are distributed into training (2203), validation (897) and test (333) sets assuring patient independence between sets. Furthermore, clinical metadata are also provided for each lesion. Four different models, obtained by combining two backbones and two encoder–decoder architectures, are trained with the PICCOLO dataset and other two publicly available datasets for comparison. Results are provided for the test set of each dataset. Models trained with the PICCOLO dataset have a better generalization capacity, as they perform more uniformly along test sets of all datasets, rather than obtaining the best results for its own test set. This dataset is available at the website of the Basque Biobank, so it is expected that it will contribute to the further development of deep learning methods for polyp detection, localisation and classification, which would eventually result in a better and earlier diagnosis of colorectal cancer, hence improving patient outcomes.

scholarly journals TOWARDS AN UNIFIED FRAMEWORK FOR VALIDATING DEEP LEARNING METHODS FOR COLORECTAL POLYPS: FIRST STEPS

2021 ◽  
Vol 108 (Supplement_3) ◽  
Author(s):  
L F Sánchez Peralta ◽  
J F Ortega Morán ◽  
Cr L Saratxaga ◽  
J B Pagador ◽  
A Picón ◽  
...  
Keyword(s):  
Deep Learning ◽  
Colorectal Polyps ◽  
Polyp Detection ◽  
Unified Framework ◽  
Endoscopic Image ◽  
Learning Techniques ◽  
Great Utility ◽  
Adenoma Detection ◽  
Definition Of ◽  
Basic Features

Abstract INTRODUCTION Deep learning techniques have significantly contributed to the field of medical imaging analysis. In case of colorectal cancer, they have shown a great utility for increasing the adenoma detection rate at colonoscopy, but a common validation methodology is still missing. In this study, we present preliminary efforts towards the definition of a validation framework. MATERIAL AND METHODS Different models based on different backbones and encoder-decoder architectures have been trained with a publicly available dataset that contains white light and NBI colonoscopy videos, with 76 different lesions from colonoscopy procedures in 48 human patients. A computer aided detection (CADe) demonstrator has been implemented to show the performance of the models. RESULTS This CADe demonstrator shows the areas detected as polyp by overlapping the predicted mask on the endoscopic image. It allows selecting the video to be used, among those from the test set. Although it only present basic features such as play, pause and moving to the next video, it easily loads the model and allows for visualization of results. The demonstrator is accompanied by a set of metrics to be used depending on the aimed task: polyp detection, localization and segmentation. CONCLUSIONS The use of this CADe demonstrator, together with a publicly available dataset and predefined metrics will allow for an easier and more fair comparison of methods. Further work is still required to validate the proposed framework.

scholarly journals Deep Learning Applied to White Light and Narrow Band Imaging Videolaryngoscopy: Toward Real‐Time Laryngeal Cancer Detection

2021 ◽  
Author(s):  
Muhammad Adeel Azam ◽  
Claudio Sampieri ◽  
Alessandro Ioppi ◽  
Stefano Africano ◽  
Alberto Vallin ◽  
...  
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Laryngeal Cancer ◽  
Cancer Detection ◽  
White Light ◽  
Narrow Band ◽  
Narrow Band Imaging

Multicentre prospective evaluation of real-time optical diagnosis of T1 colorectal cancer in large non-pedunculated colorectal polyps using narrow band imaging (the OPTICAL study)

Gut ◽  
2018 ◽  
Vol 68 (2) ◽  
pp. 271-279 ◽  
Author(s):  
Yara Backes ◽  
Matthijs P Schwartz ◽  
Frank ter Borg ◽  
Frank H J Wolfhagen ◽  
John N Groen ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Risk Score ◽  
White Light ◽  
Clinical Decision Making ◽  
Narrow Band ◽  
Narrow Band Imaging ◽  
Colorectal Polyps ◽  
Optical Diagnosis ◽  
Temporal Validation ◽  
T1 Colorectal Cancer

ObjectiveThis study evaluated the preresection accuracy of optical diagnosis of T1 colorectal cancer (CRC) in large non-pedunculated colorectal polyps (LNPCPs).DesignIn this multicentre prospective study, endoscopists predicted the histology during colonoscopy in consecutive patients with LNPCPs using a standardised procedure for optical assessment. The presence of morphological features assessed with white light, and vascular and surface pattern with narrow-band imaging (NBI) were recorded, together with the optical diagnosis, the confidence level of prediction and the recommended treatment. A risk score chart was developed and validated using a multivariable mixed effects binary logistic least absolute shrinkage and selection (LASSO) model.ResultsAmong 343 LNPCPs, 47 cancers were found (36 T1 CRCs and 11 ≥T2 CRCs), of which 11 T1 CRCs were superficial invasive T1 CRCs (23.4% of all malignant polyps). Sensitivity and specificity for optical diagnosis of T1 CRC were 78.7% (95% CI 64.3 to 89.3) and 94.2% (95% CI 90.9 to 96.6), and 63.3% (95% CI 43.9 to 80.1) and 99.0% (95% CI 97.1 to 100.0) for optical diagnosis of endoscopically unresectable lesions (ie, ≥T1 CRC with deep invasion), respectively. A LASSO-derived model using white light and NBI features discriminated T1 CRCs from non-invasive polyps with a cross-validation area under the curve (AUC) of 0.85 (95% CI 0.80 to 0.90). This model was validated in a temporal validation set of 100 LNPCPs (AUC of 0.81; 95% CI 0.66 to 0.96).ConclusionOur study provides insights in the preresection accuracy of optical diagnosis of T1 CRC. Sensitivity is still limited, so further studies will show how the risk score chart could be improved and finally used for clinical decision making with regard to the type of endoresection to be used and whether to proceed to surgery instead of endoscopy.Trial registration numberNTR5561.

scholarly journals Colorectal Polyp Image Detection and Classification through Grayscale Images and Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 5995
Author(s):  
Chen-Ming Hsu ◽  
Chien-Chang Hsu ◽  
Zhe-Ming Hsu ◽  
Feng-Yu Shih ◽  
Meng-Lin Chang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Narrow Band ◽  
Colorectal Polyp ◽  
Computer Assisted ◽  
Polyp Detection ◽  
Image Detection ◽  
Adenoma Detection ◽  
Incidence And Mortality ◽  
Rgb Images ◽  
Grayscale Images

Colonoscopy screening and colonoscopic polypectomy can decrease the incidence and mortality rate of colorectal cancer (CRC). The adenoma detection rate and accuracy of diagnosis of colorectal polyp which vary in different experienced endoscopists have impact on the colonoscopy protection effect of CRC. The work proposed a colorectal polyp image detection and classification system through grayscale images and deep learning. The system collected the data of CVC-Clinic and 1000 colorectal polyp images of Linkou Chang Gung Medical Hospital. The red-green-blue (RGB) images were transformed to 0 to 255 grayscale images. Polyp detection and classification were performed by convolutional neural network (CNN) model. Data for polyp detection was divided into five groups and tested by 5-fold validation. The accuracy of polyp detection was 95.1% for grayscale images which is higher than 94.1% for RGB and narrow-band images. The diagnostic accuracy, precision and recall rates were 82.8%, 82.5% and 95.2% for narrow-band images, respectively. The experimental results show that grayscale images achieve an equivalent or even higher accuracy of polyp detection than RGB images for lightweight computation. It is also found that the accuracy of polyp detection and classification is dramatically decrease when the size of polyp images small than 1600 pixels. It is recommended that clinicians could adjust the distance between the lens and polyps appropriately to enhance the system performance when conducting computer-assisted colorectal polyp analysis.

scholarly journals Polyp detection rates using magnification with narrow band imaging and white light

2015 ◽  
Vol 7 (5) ◽  
pp. 555 ◽  
Author(s):  
Nooman Gilani ◽  
Sally Stipho ◽  
James D Panetta ◽  
Sorin Petre ◽  
Michele A Young ◽  
...  
Keyword(s):  
White Light ◽  
Narrow Band ◽  
Narrow Band Imaging ◽  
Polyp Detection ◽  
Detection Rates
Sign in / Sign up

Export Citation Format

Share Document