Robust Boundary Segmentation in Medical Images Using a Consecutive Deep Encoder-Decoder Network

Abstract

Image segmentation is typically used to locate objects and boundaries. It is essential in many clinical applications, such as the pathological diagnosis of hepatic diseases, surgical planning, and postoperative assessment. The segmentation task is hampered by fuzzy boundaries, complex backgrounds, and appearances of objects of interest, which vary considerably. The success of the procedure is still highly dependent on the operator's skills and the level of hand-eye coordination. Thus, this paper was strongly motivated by the necessity to obtain an early and accurate diagnosis of a detected object in medical images. In this paper, we propose a new polyp segmentation method based on the architecture of a multiple deep encoder-decoder networks combination called CDED-net. The architecture can not only hold multi-level contextual information by extracting discriminative features at different effective fields-of-view and multiple image scales but also learn rich information features from missing pixels in the training phase. Moreover, the network is also able to capture object boundaries by using multiscale effective decoders. We also propose a novel strategy for improving the method's segmentation performance based on a combination of a boundary-emphasization data augmentation method and a new effective dice loss function. The goal of this strategy is to make our deep learning network available with poorly defined object boundaries, which are caused by the non-specular transition zone between the background and foreground regions. To provide a general view of the proposed method, our network was trained and evaluated on three well-known polyp datasets, CVC-ColonDB, CVC-ClinicDB, and ETIS-Larib PolypDB. Furthermore, we also used the Pedro Hispano Hospital (PH 2 ), ISBI 2016 skin lesion segmentation dataset, and CT healthy abdominal organ segmentation dataset to depict our network's ability. Our results reveal that the CDED-net significantly surpasses the state-of-the-art methods.

Notice of Violation of IEEE Publication Principles: Deep Learning Assisted Image Interactive Framework for Brain Image Segmentation

“…In medical images, the author introduced a way for an earlier time and effective diagnosis of an identified object. In this paper, they present a new polyp-segment approach based on the architecture of deep CDED-net decoder combinations [22]. In addition, the architecture can learn rich information from missing pixels throughout the training phase by extracting multi-level background information from discrimination features from various effective fields and numerous image scales.…”

“…As shown in algorithm 1, equations (20) and (21) are used to calculate the input and to generate output as nonlinear activation for all neurons in the convolutional and interconnected layers. In eq (22) Ԅ is the total number of training samples, is the ‫ݐ‬ sample with the and the chance of classification is the ‫ݐ‬ sample in the training set.. Note that Ԅ displays the weights in iteration for convolutional layer reflects the expense of miniatures.…”

Contour-Aware Polyp Segmentation in Colonoscopy Images Using Detailed Upsampling Encoder-Decoder Networks

“…In other words, by integrating DUpsampling mehtod we can make the component DEDN avoid overly reducing the overall strides of the encoder and it also significantly reduces the computation time and memory footprint of the semantic segmentation method. Unlike in our previous research studies [38], in which we fully applied the architecture of Chen et al [14], we created a new DEDN by merging two state-of-the-art approaches in segmentation. In addition, instead of using pre-trained deep learning models to extract discriminative features, in our study we could train every single component DEDN using its pre-trained model and our augmented training dataset.…”

“…It consists of a cascade architecture of dilated convolutions and includes an effective decoder module. This network architecture was inspired by a previous deep encoder-decoder network [16], the DeepLabv3+ [14] network and our previous work [38] with the advantage of upsampling method by Tian et al [54] for segmenting objects. First, the cascade architecture of dilated convolutions is used at the end of our network to extract multi-scale context information in local regions without requiring an increased the number of training parameters [67].…”

Skin Lesion Segmentation Using Local Binary Convolution-Deconvolution Architecture

“…In the past few years, with the advantages in technology, various computer aided techniques have evolved for the analysis and segmentation of medical images. Automatic medical image analysis methods have been successful in medical image analysis over the past two decades (Nguyen and Lee, 2019). Automated analysis of skin lesion has assisted clinicians in making quick and accurate decisions in melanoma detection.…”