Automatic detection of colonic polyps is still an unsolved problem due to the large variation of polyps in terms of shape, texture, size and color, and the existence of various polyp-like mimics during colonoscopy. In this study, we apply a recent region based convolutional neural network (CNN) approach for the automatic detection of polyps in images and videos obtained from colonoscopy examinations. We use a deep-CNN model (Inception Resnet) as a transfer learning scheme in the detection system. To overcome the polyp detection obstacles and the small number of polyp images, we examine image augmentation strategies for training deep networks. We further propose two efficient post-learning methods such as, automatic false positive learning and off-line learning, both of which can be incorporated with the region based detection system for reliable polyp detection. Using the large size of colonoscopy databases, experimental results demonstrate that the suggested detection systems show better performance compared to other systems in the literature. Furthermore, we show improved detection performance using the proposed post-learning schemes for colonoscopy videos.

Automatic polyp detection has been shown to be difficult due to various polyp-like structures in the colon and high interclass variations in polyp size, color, shape, and texture. An efficient method should not only have a high correct detection rate (high sensitivity) but also a low false detection rate (high precision and specificity). The state-of-the-art detection methods include convolutional neural net-works (CNN). However, CNNs have shown to be vulnerable to small perturbations and noise; they sometimes miss the same polyp appearing in neighboring frames and produce a high number of false positives. We aim to tackle this prob-lem and improve the overall performance of the CNN-based object detectors for polyp detection in colonoscopy videos. Our method consists of two stages: a region of interest (RoI) proposal by CNN-based object detector networks and a false positive (FP) reduction unit. The FP reduction unit exploits the temporal dependencies among image frames in video by integrating the bidirectional temporal informa-tion obtained by RoIs in a set of consecutive frames. This information is used to make the final decision. The exper-imental results show that the bidirectional temporal infor-mation has been helpful in estimating polyp positions and accurately predict the FPs. This provides an overall perfor-mance improvement in terms of sensitivity, precision, and This work was supported by Research Council of Norway through the industrial Ph.D. project under the contract num-ber 271542/O30 and through the MELODY project under the contract number 225885/O70.

One of the major obstacles in automatic polyp detection during colonoscopy is the lack of labeled polyp training images. In this study, we propose a framework of conditional adversarial networks to increase the number of training samples by generating synthetic polyp images. Using a normal binary form of polyp mask which represents only the polyp position as an input conditioned image, realistic polyp image generation is a difficult task in generative adversarial networks approach. Therefore, we propose an edge filtering based combined input conditioned image. More importantly, our proposed framework generates synthetic polyp images from normal colonoscopy images which have the advantage of being relatively easy to obtain. This means realistic polyp images can be generated while maintaining the original structures of the colonoscopy image frames. The network architecture is based on the use of multiple dilated convolutions in each encoding part of our generator network to consider large receptive fields and avoid much contractions of feature map size. An image resizing with convolution for up sampling in the decoding layers is considered to prevent artifacts on generated images. We show that the generated polyp images are not only qualitatively look realistic but also help to improve polyp detection performance.INDEX TERMS Colonoscopy, convolutional neural network, dilated convolution, generative adversarial networks, polyp detection.

Automatic polyp detection and segmentation are highly desirable for colon screening due to polyp miss rate by physicians during colonoscopy, which is about 25%. However, this computerization is still an unsolved problem due to various polyplike structures in the colon and high interclass polyp variations in terms of size, color, shape and texture. In this paper, we adapt Mask R-CNN and evaluate its performance with different modern convolutional neural networks (CNN) as its feature extractor for polyp detection and segmentation. We investigate the performance improvement of each feature extractor by adding extra polyp images to the training dataset to answer whether we need deeper and more complex CNNs, or better dataset for training in automatic polyp detection and segmentation. Finally, we propose an ensemble method for further performance improvement. We evaluate the performance on the 2015 MICCAI polyp detection dataset. The best results achieved are 72.59% recall, 80% precision, 70.42% dice, and 61.24% jaccard. The model achieved state-of-the-art segmentation performance.

No abstract