Naslov
Using Convolutional Neural Network for Chest X-ray Image classification

Autori
Sorić, Matija : Pongrac, Danijela : Inza, Iñaki

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
43rd International Convention on Information, Communication and Electronic Technology (MIPRO) / Karolj Skala - Rijeka : Hrvatska udruga za informacijsku i komunikacijsku tehnologiju, elektroniku i mikroelektroniku - MIPRO, 2020, 2101-2106

Skup
43rd International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO 2020)

Mjesto i datum
Opatija, Hrvatska, 28.09.2020. - 02.10.2020

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
convolutional neural network, classification, deep learning, X-ray imaging

Sažetak
Chest X-ray is an imaging technique that plays an important role in pneumonia diagnosis. Owing to the high availability of medically-oriented image datasets, great success can be achieved using convolutional neural networks (CNNs) in the recognition and classification of these images. Since previous research has shown CNNs to perform as well as the best clinicians in diagnostic tasks, they caused great excitement among researchers. In this paper, convolutional neural network (CNN) machine learning (ML) model was built using a supervised dataset. The dataset used contained both pneumonia and nonpneumonia images, which the model had to classify correctly. In the end, the model is demonstrated to have achieved satisfactory results, with the high accuracy of 90.38%, 98.21% recall and 87.84% precision.

Izvorni jezik
Engleski

Znanstvena područja
Informacijske i komunikacijske znanosti

POVEZANOST RADA