2020/05/08 by Mehmet Yamaç, Yamac, Mehmet, Mete Ahishali +9 · 2 citations
Computer Science · Medicine · #AI in cancer detection #Anomaly Detection Techniques and Applications #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2005.04014
openalex publication_date 2020/05/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/04/28
Coronavirus disease (Covid-19) has been the main agenda of the whole world\nsince it came in sight in December 2019. It has already caused thousands of\ncausalities and infected several millions worldwide. Any technological tool\nthat can be provided to healthcare practitioners to save time, effort, and\npossibly lives has crucial importance. The main tools practitioners currently\nuse to diagnose Covid-19 are Reverse Transcription-Polymerase Chain reaction\n(RT-PCR) and Computed Tomography (CT), which require significant time,\nresources and acknowledged experts. X-ray imaging is a common and easily\naccessible tool that has great potential for Covid-19 diagnosis. In this study,\nwe propose a novel approach for Covid-19 recognition from chest X-ray images.\nDespite the importance of the problem, recent studies in this domain produced\nnot so satisfactory results due to the limited datasets available for training.\nRecall that Deep Learning techniques can generally provide state-of-the-art\nperformance in many classification tasks when trained properly over large\ndatasets, such data scarcity can be a crucial obstacle when using them for\nCovid-19 detection. Alternative approaches such as representation-based\nclassification (collaborative or sparse representation) might provide\nsatisfactory performance with limited size datasets, but they generally fall\nshort in performance or speed compared to Machine Learning methods. To address\nthis deficiency, Convolution Support Estimation Network (CSEN) has recently\nbeen proposed as a bridge between model-based and Deep Learning approaches by\nproviding a non-iterative real-time mapping from query sample to ideally sparse\nrepresentation coefficient' support, which is critical information for class\ndecision in representation based techniques.\n