Abstract
To use artificial intelligence to assist in diagnoses applications, a model to utilize quality data is required, which results in massive time and cost. In medical data, data imbalance occurs because the amount of data with lesions is less than that without lesions. To overcome this limitation, this study proposes a progressive growth of generative adversarial networks (PGGAN)-based anomaly classification on chest X-rays using weighted multi-scale similarity. An anomaly detection method is applied to learn the distribution of normal images to solve the problem of data imbalance. The use of PGGAN, which is a model that generates high-resolution images by gradually adding layers, enables to find image characteristics on a multi-scale and define the similarity between an original image and a generated image. The anomaly score is calculated by applying the weighted arithmetic mean to a resolution-by-resolution similarity. The threshold is defined after the analysis of the F1-score, and then the classification performance is evaluated. The accuracy of the proposed model was assessed using a confusion matrix and compared with that of a conventional classification model, and the efficiency was demonstrated through ablation studies. The classification accuracy of the test dataset was 0.8525. Compared to a U-net-based disease classifier with low-resolution which accuracy was 0.8410, the performance of the proposed model was 0.8507, exhibited an improvement.
Highlights
Artificial intelligence (AI), one of the main technologies of the 4th Industrial Revolution, has been studied and applied in several industries
Data imbalance is a common problem in medical images, caused by the quantity difference between normal data and abnormal data, and requires excess resource consumption due to annotation
To overcome these problems with chest X-ray images and classify anomalies, this study proposed a chest X-ray anomaly classification model using progressive growth of generative adversarial networks (PGGAN)-based weighted multi-scale similarity
Summary
Artificial intelligence (AI), one of the main technologies of the 4th Industrial Revolution, has been studied and applied in several industries. The attention-based model enabled to detect diseases despite inefficient information of data (position, label, etc.). Chung: PGGAN-based Anomaly classification on Chest X-ray using Weighted Multi-Scale Similarity was changed, and the multiple-label deep CNN (DCNN) model was trained [10]-[12]. In terms of a GAN-based model for learning the distribution of normal data and discerning the distribution of abnormal data, this study proposes the use of progressive growth of GANs (PGGANs) as a base model This model shows better performance for high-resolution image generation than the deep convolutional GAN (DCGAN) [23], [24]. - A segmented high-resolution image generation model overcomes information loss and failures in the detection of small lesions, which are common in conventional unsupervised learning-based models;.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
