Detecting, Localising and Classifying Polyps from Colonoscopy Videos using Deep Learning

• URL: http://arxiv.org/abs/2101.03285v1
• Date: Sat, 9 Jan 2021 04:25:34 GMT
• Title: Detecting, Localising and Classifying Polyps from Colonoscopy Videos using Deep Learning
• Authors: Yu Tian, Leonardo Zorron Cheng Tao Pu, Yuyuan Liu, Gabriel Maicas, Johan W. Verjans, Alastair D. Burt, Seon Ho Shin, Rajvinder Singh, Gustavo Carneiro
• Abstract summary: We propose and analyse a system that can automatically detect, localise and classify polyps from colonoscopy videos. The detection of frames with polyps is formulated as a few-shot anomaly classification problem. We use uncertainty estimation and classification calibration to improve the reliability and interpretability of the classification result.
• Score: 17.441138604295364
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose and analyse a system that can automatically detect, localise and classify polyps from colonoscopy videos. The detection of frames with polyps is formulated as a few-shot anomaly classification problem, where the training set is highly imbalanced with the large majority of frames consisting of normal images and a small minority comprising frames with polyps. Colonoscopy videos may contain blurry images and frames displaying feces and water jet sprays to clean the colon -- such frames can mistakenly be detected as anomalies, so we have implemented a classifier to reject these two types of frames before polyp detection takes place. Next, given a frame containing a polyp, our method localises (with a bounding box around the polyp) and classifies it into five different classes. Furthermore, we study a method to improve the reliability and interpretability of the classification result using uncertainty estimation and classification calibration. Classification uncertainty and calibration not only help improve classification accuracy by rejecting low-confidence and high-uncertain results, but can be used by doctors to decide how to decide on the classification of a polyp. All the proposed detection, localisation and classification methods are tested using large data sets and compared with relevant baseline approaches.

Related papers

• EndoFinder: Online Image Retrieval for Explainable Colorectal Polyp Diagnosis [10.83700068295662]
  EndoFinder is a content-based image retrieval framework. It finds the 'digital twin' polyp in the reference database given a newly detected polyp. The clinical semantics of the new polyp can be inferred referring to the matched ones.
  arXiv  Detail & Related papers  (2024-07-16T05:40:17Z)
• Benchmarking common uncertainty estimation methods with histopathological images under domain shift and label noise [62.997667081978825]
  In high-risk environments, deep learning models need to be able to judge their uncertainty and reject inputs when there is a significant chance of misclassification. We conduct a rigorous evaluation of the most commonly used uncertainty and robustness methods for the classification of Whole Slide Images. We observe that ensembles of methods generally lead to better uncertainty estimates as well as an increased robustness towards domain shifts and label noise.
  arXiv  Detail & Related papers  (2023-01-03T11:34:36Z)
• Contrastive Transformer-based Multiple Instance Learning for Weakly Supervised Polyp Frame Detection [30.51410140271929]
  Current polyp detection methods from colonoscopy videos use exclusively normal (i.e., healthy) training images. We formulate polyp detection as a weakly-supervised anomaly detection task that uses video-level labelled training data to detect frame-level polyps.
  arXiv  Detail & Related papers  (2022-03-23T01:30:48Z)
• Colonoscopy polyp detection with massive endoscopic images [4.458670612147842]
  We improved an existing end-to-end polyp detection model with better average precision validated by different data sets. Our model can achieve state-of-the-art polyp detection performance while still maintain real-time detection speed.
  arXiv  Detail & Related papers  (2022-02-17T16:07:59Z)
• Calibrating Histopathology Image Classifiers using Label Smoothing [42.38682782211358]
  We propose label smoothing methods that utilize per-image annotator agreement. We find that our proposed agreement-aware label smoothing methods reduce calibration error by almost 70%. Our methods merit further exploration and potential implementation in other histopathology image classification tasks.
  arXiv  Detail & Related papers  (2022-01-28T00:13:09Z)
• Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection [97.93062818228015]
  We propose to integrate the reconstruction-based functionality into a novel self-supervised predictive architectural building block. Our block is equipped with a loss that minimizes the reconstruction error with respect to the masked area in the receptive field. We demonstrate the generality of our block by integrating it into several state-of-the-art frameworks for anomaly detection on image and video.
  arXiv  Detail & Related papers  (2021-11-17T13:30:31Z)
• Colorectal Polyp Classification from White-light Colonoscopy Images via Domain Alignment [57.419727894848485]
  A computer-aided diagnosis system is required to assist accurate diagnosis from colonoscopy images. Most previous studies at-tempt to develop models for polyp differentiation using Narrow-Band Imaging (NBI) or other enhanced images. We propose a novel framework based on a teacher-student architecture for the accurate colorectal polyp classification.
  arXiv  Detail & Related papers  (2021-08-05T09:31:46Z)
• Malignancy Prediction and Lesion Identification from Clinical Dermatological Images [65.1629311281062]
  We consider machine-learning-based malignancy prediction and lesion identification from clinical dermatological images. We first identify all lesions present in the image regardless of sub-type or likelihood of malignancy, then it estimates their likelihood of malignancy, and through aggregation, it also generates an image-level likelihood of malignancy.
  arXiv  Detail & Related papers  (2021-04-02T20:52:05Z)
• Classification with Rejection Based on Cost-sensitive Classification [83.50402803131412]
  We propose a novel method of classification with rejection by ensemble of learning. Experimental results demonstrate the usefulness of our proposed approach in clean, noisy, and positive-unlabeled classification.
  arXiv  Detail & Related papers  (2020-10-22T14:05:05Z)
• Few-Shot Anomaly Detection for Polyp Frames from Colonoscopy [20.23118616722365]
  We propose a new few-shot anomaly detection method based on an encoder trained to maximise the mutual information between feature embeddings and normal images. We evaluate our proposed method on the clinical problem of detecting frames containing polyps from colonoscopy video sequences.
  arXiv  Detail & Related papers  (2020-06-26T06:08:46Z)
• Semi-supervised Medical Image Classification with Relation-driven Self-ensembling Model [71.80319052891817]
  We present a relation-driven semi-supervised framework for medical image classification. It exploits the unlabeled data by encouraging the prediction consistency of given input under perturbations. Our method outperforms many state-of-the-art semi-supervised learning methods on both single-label and multi-label image classification scenarios.
  arXiv  Detail & Related papers  (2020-05-15T06:57:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.