Esophageal cancer is categorized as a type of disease with a high mortality rate. Early detection of esophageal abnormalities (i.e. precancerous and early cancerous) can improve the survival rate of the patients. Recent deep learning-based methods for selected types of esophageal abnormality detection from endoscopic images have been proposed. However, no methods have been introduced in the literature to cover the detection from endoscopic videos, detection from challenging frames and detection of more than one esophageal abnormality type. In this paper, we present an efficient method to automatically detect different types of esophageal abnormalities from endoscopic videos. We propose a novel 3D Sequential DenseConvLstm network that extracts spatiotemporal features from the input video. Our network incorporates 3D Convolutional Neural Network (3DCNN) and Convolutional Lstm (ConvLstm) to efficiently learn short and long term spatiotemporal features. The generated feature map is utilized by a region proposal network and ROI pooling layer to produce a bounding box that detects abnormality regions in each frame throughout the video. Finally, we investigate a post-processing method named Frame Search Conditional Random Field (FS-CRF) that improves the overall performance of the model by recovering the missing regions in neighborhood frames within the same clip. We extensively validate our model on an endoscopic video dataset that includes a variety of esophageal abnormalities. Our model achieved high performance using different evaluation metrics showing 93.7% recall, 92.7% precision, and 93.2% F-measure. Moreover, as no results have been reported in the literature for the esophageal abnormality detection from endoscopic videos, to validate the robustness of our model, we have tested the model on a publicly available colonoscopy video dataset, achieving the polyp detection performance in a recall of 81.18%, precision of 96.45% and F-measure 88.16%, compared to the state-of-the-art results of 78.84% recall, 90.51% precision and 84.27% F-measure using the same dataset. This demonstrates that the proposed method can be adapted to different gastrointestinal endoscopic video applications with a promising performance.
Segmentation of echocardiographic images is an essential step for assessing the cardiac functionality and providing indicative clinical measures, and all further heart analysis relies on the accuracy of this process. However, the fuzzy nature of echocardiographic images degraded by distortion and speckle noise poses some challenges on the manual segmentation task. In this paper, we propose a fully automated left ventricle segmentation method that can overcome those challenges. Our method performs accurate delineation for the ventricle boundaries despite the ill-defined borders and shape variability of the left ventricle. The well-known deep learning segmentation model, known as the U-net, has addressed some of these challenges with outstanding performance. However, it still ignores the contribution of all semantic information through the segmentation process. Here we propose a novel deep learning segmentation method based on U-net, named ResDUnet. It incorporates feature extraction at different scales through the integration of cascaded dilated convolution. To ease the training process, residual blocks are deployed instead of the basic U-net blocks. Each residual block is enriched with a squeeze and excitation unit for channel-wise attention and adaptive feature re-calibration. The performance of the method is evaluated on a dataset of 2000 images acquired from 500 patients with large variability in quality and patient pathology. ResDUnet outperforms state-of-the-art methods with a Dice similarity increase of 8.4% and 1.2% compared to deeplabv3 and U-net, respectively. Furthermore, to demonstrate the impact of each proposed sub-module, several experiments have been carried out with different designs and variations of the integrated submodules. We also describe and discuss all technical elements of a deep-learning model via a step-by-step explanation of parameters and methods, while using our left ventricle segmentation as a case study, to explain the application of AI to echocardiographic imaging.
Matching occluded and noisy shapes is a prob- inside the shape; but they ignore the boundary information. 15We describe a method that combines the boundary signature 16 of a shape obtained from II and structural information from 17 the Ecc to yield results that improve on them separately.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.