scispace - formally typeset
Search or ask a question
Author

Ellen J. Hong

Bio: Ellen J. Hong is an academic researcher from Yonsei University. The author has contributed to research in topics: Cancer & Edge detection. The author has an hindex of 2, co-authored 3 publications receiving 6 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: In this paper, a chest X-ray outlier detection model using dimension reduction and edge detection is proposed to solve the problem of high computation in learning and recognition of medical images.
Abstract: With the advancement of Artificial Intelligence technology, the development of various applied software and studies are actively conducted on detection, classification, and prediction through interdisciplinary convergence and integration. Among them, medical AI has been drawing huge interest and popularity in Computer-Aided Diagnosis, which collects human body signals to predict abnormal symptoms of health, and diagnoses diseases through medical images such as X-ray and CT. Since X-ray and CT in medicine use high-resolution images, they require high specification equipment and huge energy consumption due to high computation in learning and recognition, incurring huge costs to create an environment for operation. Thus, this paper proposes a chest X-ray outlier detection model using dimension reduction and edge detection to solve these issues. The proposed method scans an X-ray image using a window of a certain size, conducts difference imaging of adjacent segment-images, and extracts the edge information in a binary format through the AND operation. To convert the extracted edge, which is visual information, into a series of lines, it is computed in convolution with the detection filter that has a coefficient of 2n and the lines are divided into 16 types. By counting the converted data, a one-dimensional 16-size array per one segment-image is produced, and this reduced data is used as an input to the RNN-based learning model. In addition, the study conducted various experiments based on the COVID-chest X-ray dataset to evaluate the performance of the proposed model. According to the experiment results, the LFA-RNN showed the highest accuracy at 97.5% in the learning calculated through learning, followed by CRNN 96.1%, VGG 96.6%, AlexNet 94.1%, Conv1D 79.4%, and DNN 78.9%. In addition, LFA-RNN showed the lowest loss at about 0.0357.

10 citations

Journal ArticleDOI
TL;DR: Based on testing results for the suggested risk prediction model, a system was developed to guide not only accident-prone regions predicted using statistical data but to also guide a risk level for the road, which can change even for the same road.
Abstract: Traditional accident prediction models have been mostly designed with statistical analysis that finds and analyzes the causal relationships between traffic accidents and a variety of human, road geometry, and environmental factors. However, these statistical methods have limitations in that they are based on assumptions about data distribution and function type. Therefore, this study suggests an accident prediction model using deep learning. This newly suggested risk prediction model is for predicting risk by reflecting static features of the road, such its length and the speed limit on it, and dynamic features of the road, such as traffic volume when driving on it, and the altitude and azimuth of the sun. For this purpose, 4470 accident cases, collected over 5 months from August to December 2018 in Seoul—the most complex, high-traffic, and accident-prone city in Korea—were analyzed. As a result of testing the model using such data, it was found to have an accuracy of 75% and recall of 81%. Based on testing results for the suggested risk prediction model, a system was developed to guide not only accident-prone regions predicted using statistical data but to also guide a risk level for the road. This level of risk is estimated based upon each given situation, so it can change even for the same road. This guide system can be used to provide a level of risk for each road segment and region but also to improve roads with recommendations, such as installation of safety features. In addition, it could support a mobile system that provides a driver with the optimized driving path for safety.

6 citations

Journal ArticleDOI
TL;DR: An edge extraction algorithm and a modified convolutional recurrent neural network (CRNN) model are proposed to accurately assess breast cancer based on medical imaging and results show that the proposed model had the highest accuracy and lowest loss.
Abstract: Breast cancer is known to be common in many developed countries. It is reported as the most common type of cancer in the US, affecting one in eight women. In Korea, thyroid cancer is the most common type of cancer, followed by breast cancer in women. Considering this, early detection and accurate diagnosis of breast cancer are crucial for reducing the associated death rate. Recently, cancer diagnosis systems using medical images have attracted significant attention. Medical imaging methods, such as computed tomography and magnetic resonance imaging, can reveal the overall shape, heterogeneity, and growth speed of carcinoma and are, thus, more commonly employed for diagnoses. Medical imaging has gained popularity since a recent study identified that it could reflect the gene phenotype of a patient. However, an aided diagnosis system based on medical images requires high-specification equipment to analyze high-resolution data. Therefore, this article proposes an edge extraction algorithm and a modified convolutional recurrent neural network (CRNN) model to accurately assess breast cancer based on medical imaging. The proposed algorithm extracts line-segment information from a breast mass image. The extracted line segments were classified into 16 types. Each type was uniquely labeled and compressed. The image compressed in this process was used as the input for the modified CRNN model. Traditional deep learning models were used to evaluate the performance of the proposed algorithm. The results show that the proposed model had the highest accuracy and lowest loss (99.75% and 0.0257, respectively).

4 citations


Cited by
More filters
Posted Content
TL;DR: In this paper, the authors used a semi-exhaustive literature review of relevant anomaly detection papers in medical imaging to cluster into applications, highlight important results, establish lessons learned and give further advice on how to approach anomaly detection.
Abstract: The increasing digitization of medical imaging enables machine learning based improvements in detecting, visualizing and segmenting lesions, easing the workload for medical experts. However, supervised machine learning requires reliable labelled data, which is is often difficult or impossible to collect or at least time consuming and thereby costly. Therefore methods requiring only partly labeled data (semi-supervised) or no labeling at all (unsupervised methods) have been applied more regularly. Anomaly detection is one possible methodology that is able to leverage semi-supervised and unsupervised methods to handle medical imaging tasks like classification and segmentation. This paper uses a semi-exhaustive literature review of relevant anomaly detection papers in medical imaging to cluster into applications, highlight important results, establish lessons learned and give further advice on how to approach anomaly detection in medical imaging. The qualitative analysis is based on google scholar and 4 different search terms, resulting in 120 different analysed papers. The main results showed that the current research is mostly motivated by reducing the need for labelled data. Also, the successful and substantial amount of research in the brain MRI domain shows the potential for applications in further domains like OCT and chest X-ray.

12 citations

Book ChapterDOI
01 Jan 2022
TL;DR: In this article , the authors used a semi-exhaustive literature review of relevant anomaly detection papers in medical imaging to cluster into applications, highlight important results, establish lessons learned and give further advice on how to approach anomaly detection.
Abstract: The increasing digitization of medical imaging enables machine learning based improvements in detecting, visualizing and segmenting lesions, easing the workload for medical experts. However, supervised machine learning requires reliable labelled data, which is is often difficult or impossible to collect or at least time consuming and thereby costly. Therefore methods requiring only partly labeled data (semi-supervised) or no labeling at all (unsupervised methods) have been applied more regularly. Anomaly detection is one possible methodology that is able to leverage semi-supervised and unsupervised methods to handle medical imaging tasks like classification and segmentation. This paper uses a semi-exhaustive literature review of relevant anomaly detection papers in medical imaging to cluster into applications, highlight important results, establish lessons learned and give further advice on how to approach anomaly detection in medical imaging. The qualitative analysis is based on google scholar and 4 different search terms, resulting in 120 different analysed papers. The main results showed that the current research is mostly motivated by reducing the need for labelled data. Also, the successful and substantial amount of research in the brain MRI domain shows the potential for applications in further domains like OCT and chest X-ray.

11 citations

Journal ArticleDOI
TL;DR: In this paper, a chest X-ray outlier detection model using dimension reduction and edge detection is proposed to solve the problem of high computation in learning and recognition of medical images.
Abstract: With the advancement of Artificial Intelligence technology, the development of various applied software and studies are actively conducted on detection, classification, and prediction through interdisciplinary convergence and integration. Among them, medical AI has been drawing huge interest and popularity in Computer-Aided Diagnosis, which collects human body signals to predict abnormal symptoms of health, and diagnoses diseases through medical images such as X-ray and CT. Since X-ray and CT in medicine use high-resolution images, they require high specification equipment and huge energy consumption due to high computation in learning and recognition, incurring huge costs to create an environment for operation. Thus, this paper proposes a chest X-ray outlier detection model using dimension reduction and edge detection to solve these issues. The proposed method scans an X-ray image using a window of a certain size, conducts difference imaging of adjacent segment-images, and extracts the edge information in a binary format through the AND operation. To convert the extracted edge, which is visual information, into a series of lines, it is computed in convolution with the detection filter that has a coefficient of 2n and the lines are divided into 16 types. By counting the converted data, a one-dimensional 16-size array per one segment-image is produced, and this reduced data is used as an input to the RNN-based learning model. In addition, the study conducted various experiments based on the COVID-chest X-ray dataset to evaluate the performance of the proposed model. According to the experiment results, the LFA-RNN showed the highest accuracy at 97.5% in the learning calculated through learning, followed by CRNN 96.1%, VGG 96.6%, AlexNet 94.1%, Conv1D 79.4%, and DNN 78.9%. In addition, LFA-RNN showed the lowest loss at about 0.0357.

10 citations

Journal ArticleDOI
TL;DR: In this article, the authors proposed a new edge detection algorithm using a combination of the wavelet transform, Shannon entropy and thresholding, which is based on the concept that each Wavelet decomposition level has an assumed level of structure that enables the use of Shannon entropy as a measure of global image structure.
Abstract: Fast edge detection of images can be useful for many real-world applications. Edge detection is not an end application but often the first step of a computer vision application. Therefore, fast and simple edge detection techniques are important for efficient image processing. In this work, we propose a new edge detection algorithm using a combination of the wavelet transform, Shannon entropy and thresholding. The new algorithm is based on the concept that each Wavelet decomposition level has an assumed level of structure that enables the use of Shannon entropy as a measure of global image structure. The proposed algorithm is developed mathematically and compared to five popular edge detection algorithms. The results show that our solution is low redundancy, noise resilient, and well suited to real-time image processing applications.

4 citations

Journal ArticleDOI
TL;DR: This paper proposed an anomaly detection model of mammography using a YOLOv4-based histogram, which had the highest accuracy and was compared with ResNet18, ResNet50, GoogleNet, and VGG16.
Abstract: Breast cancer is the second leading cause of death in females. As such, women have high incidence and mortality rates of breast cancer. The incidence rate has been on the rise over time. The earlier breast cancer is caught, the better it shows prognosis and the lower the mortality rate is. For this reason, many researchers and medical doctors have heeded a lot of attention to the CAD systems to detect and classify breast cancer. They have proposed a myriad of methods and techniques. Among them, the CAD system based on artificial intelligence (AI) can process plenty of information fast, and its performance is evaluated to be high. As an AI algorithm, YOLO has excellent detection performance and can detect objects effectively in real time. In this paper, we proposed an anomaly detection model of mammography using a YOLOv4-based histogram. In terms of breast cancer diagnosis, mammography features a fast diagnosis time and an inexpensive cost. For this reason, it is often applied to breast cancer diagnosis. Mammography, however, generates an image only with brightness values, so that a mammogram image has a lot of noise and image edges are dim. To enhance these image edges, we create a difference through histogram and brightness range control and threshold-based region removal methods and expand the single channel of mammogram images using the generated images. Through the expansion, the image edges are enhanced and converted into a single channel again and are learned through YOLO. For performance evaluation, the method proposed in this study is compared with ResNet18, ResNet50, GoogleNet, and VGG16. According to an experiment, the proposed method had the highest accuracy, or 95.74%, followed by GoogleNet (89.9%), VGG16 (88.93%), ResNet50 (87.77%), and ResNet18 (87.67%) in order.

4 citations