Towards automatic polyp detection with a polyp appearance model

By Jorge Bernal, F. Sánchez, F. Vilariño. Pattern Recognition, 2012

690 citations recorded by the source corpus.

This work aims at automatic polyp detection by using a model of polyp appearance in the context of the analysis of colonoscopy videos. Our method consists of three stages: region segmentation, region description and region classification. The performance of our region segmentation method guarantees that if a polyp is present in the image, it will be exclusively and totally contained in a single region. The output of the algorithm also defines which regions can be considered as non-informative. We define as our region descriptor the novel Sector Accumulation-Depth of Valleys Accumulation (SA-DOVA), which provides a necessary but not sufficient condition for the polyp presence. Finally, we classify our segmented regions according to the maximal values of the SA-DOVA descriptor. Our preliminary classification results are promising, especially when classifying those parts of the image that do not contain a polyp inside.

Subfields: Computer Vision and Pattern Recognition, Oncology

View Paper: https://www.semanticscholar.org/paper/9d32259f16ac76089c39e84063296f697a76460f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Oncology

Citations in the corpus

Shallow Attention Network for Polyp Segmentation (2021, methodology): “To evaluate the performance of the proposed SANet, five polyp segmentation datasets are adopted, including Kvasir [10], CVC-ClinicDB [2], CVC-ColonDB [3], EndoScene [18] and ETIS [16].”
Toward embedded detection of polyps in WCE images for early diagnosis of colorectal cancer (2014, methodology): “10 Comparison between the method exposed by Bernal [9] and the attentional boosting based classification method proposed: from left to right: sensitivity, specificity, and FPR”
Deep Learning Localizes and Identifies Polyps in Real Time with 96% Accuracy in Screening Colonoscopy (2018, methodology): “An early application of computer-assisted polyp detection, utilized traditional non-learning-based computer-vision engineering methods and achieved an AUC of 0.98 for detecting a limited class of polyp types 43 , but could not work in real-time requiring 19 seconds to process a single frame.”
UNCERTAINTY MODELING AND INTERPRETABILITY IN CONVOLUTIONAL NEURAL NETWORKS FOR POLYP SEGMENTATION (2018, methodology): “Database Training Validation Test Resolution CVC-Colon [5] [1-76], [98-148], [221-273].”
UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation (2021, methodology): “We validate our method with five famous polyp segmentation benchmarks, Kvasir, CVC-ClinicDB, ETIS, CVC-ColonDB and CVC-300 and achieve state-of-the-art performance among previous methods. ar X iv :2 10 7.”
Comparative Validation of Polyp Detection Methods in Video Colonoscopy: Results From the MICCAI 2015 Endoscopic Vision Challenge (2017, neutral): “protruding elements in the scene and, as a consequence of this, specularities appear in their surface as their reflect light back to the camera [52].”
Kvasir-SEG: A Segmented Polyp Dataset (2019, methodology): “. 2 Related Work There are only few available polyp datasets that consist of ground truth and corresponding segmentation mask. These are CVC-ColonDB [24], ASU-Mayo Clinic Colonoscopy Video c Database [3], ETIS-Larib Polyp DB [23], and CVCClinic DB [2]. CVC-ColonDB [24] is the second largest database”
Automated Polyp Detection in Colonoscopy Videos Using Shape and Context Information (2016, methodology): “5Note that the operating point shown for [17] was not available in their published manuscript—it was kindly provided by the corresponding author.”
Cross-level Feature Aggregation Network for Polyp Segmentation (2023, background): “Colorectal cancer (CRC) is the third most frequently diagnosed cancer around the world [1,2] .”
Distribution-Free, Risk-Controlling Prediction Sets (2021, methodology): “We evaluated our method with an experiment combining several open-source polyp segmentation datasets: Kvasir [45], Hyper-Kvasir [46], CVC-ColonDB and CVC-ClinicDB [47], and ETIS-Larib [48].”
A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images (2016, background): “…to overcome this limitation and introduce an extended benchmark of colonoscopy images by combining the two largest datasets of colonoscopy images [5,4] and incorporating additional annotations to segment lumen and specular highlights, with the hope of establishing a new strong benchmark for…”
A Comprehensive Study on Colorectal Polyp Segmentation With ResUNet++, Conditional Random Field and Test-Time Augmentation (2021, neutral): “2) We validate the extended architecture on a large range of datasets, i.e., Kvasir-SEG [4], CVC-ClinicDB [11], CVC-ColonDB [12], EITS-Larib [13], ASU-Mayo Clinic Colonoscopy Video Database [14] and CVC-VideoClinicDB [15], [16], and we compare our proposed approaches with the recent State-of-the-art”