Abstract
PurposeThis study aims to adapt and evaluate the performance of different state-of-the-art deep learning object detection methods to automatically identify esophageal adenocarcinoma (EAC) regions from high-definition white light endoscopy (HD-WLE) images.MethodSeveral state-of-the-art object detection methods using Convolutional Neural Networks (CNNs) were adapted to automatically detect abnormal regions in the esophagus HD-WLE images, utilizing VGG’16 as the backbone architecture for feature extraction. Those methods are Regional-based Convolutional Neural Network (R-CNN), Fast R-CNN, Faster R-CNN and Single-Shot Multibox Detector (SSD). For the evaluation of the different methods, 100 images from 39 patients that have been manually annotated by five experienced clinicians as ground truth have been tested.ResultsExperimental results illustrate that the SSD and Faster R-CNN networks show promising results, and the SSD outperforms other methods achieving a sensitivity of 0.96, specificity of 0.92 and F-measure of 0.94. Additionally, the Average Recall Rate of the Faster R-CNN in locating the EAC region accurately is 0.83.ConclusionIn this paper, recent deep learning object detection methods are adapted to detect esophageal abnormalities automatically. The evaluation of the methods proved its ability to locate abnormal regions in the esophagus from endoscopic images. The automatic detection is a crucial step that may help early detection and treatment of EAC and also can improve automatic tumor segmentation to monitor its growth and treatment outcome.
Highlights
A major health problem that has been emerging is esophageal adenocarcinoma (EAC) which is considered the early stage of esophageal cancer
The process of detection is done through endoscopic examination, high-definition white light endoscopy (HDWLE) is the primary tool used [6], and the cell deformation stages are confirmed by taking biopsy samples from the surface of the esophagus lining [7]
We evaluate the performance of the described deep learning object detection methods using the VGG’16 as the backbone network to identify the EAC abnormalities in the high-definition white light endoscopy (HD-WLE) images automatically
Summary
A major health problem that has been emerging is esophageal adenocarcinoma (EAC) which is considered the early stage of esophageal cancer. Studies show that esophageal cancer patients hold a 5-year survival rate of only 18.8% [1]. The early detection and treatment of EAC may help in increasing the survival chance of the patient [5]. The process of detection is done through endoscopic examination, high-definition white light endoscopy (HDWLE) is the primary tool used [6], and the cell deformation stages are confirmed by taking biopsy samples from the surface of the esophagus lining [7]. Patients are required to have regular follow-ups through endoscopy examination to control the development of abnormalities into later stages. There exists an amount of research available in the literature for automatic detec-
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have