Chest X-ray Image Analysis using Convolutional Vision Transformer

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F23%3APU148419" target="_blank" >RIV/00216305:26220/23:PU148419 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2023_sbornik_2_v2.pdf" target="_blank" >https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2023_sbornik_2_v2.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.13164/eeict.2023.161" target="_blank" >10.13164/eeict.2023.161</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Chest X-ray Image Analysis using Convolutional Vision Transformer

Popis výsledku v původním jazyce

In recent years, computer techniques for clinical image analysis have been improved significantly, especially because of the pandemic situation. Most recent approaches are focused on the detection of viral pneumonia or COVID-19 diseases. However, there is less attention to common pulmonary diseases, such as fibrosis, infiltration and others. This paper introduces the neural network, which is aimed to detect 14 pulmonary diseases. This model is composed of two branches: global, which is the InceptionNetV3, and local, which consists of Inception modules and a modified Vision Transformer. Additionally, the Asymmetric Loss function was utilized to deal with the problem of multilabel classification. The proposed model has achieved an AUC of 0.8012 and an accuracy of 0.7429, which outperforms the well-known classification models.

Název v anglickém jazyce

Chest X-ray Image Analysis using Convolutional Vision Transformer

Popis výsledku anglicky

In recent years, computer techniques for clinical image analysis have been improved significantly, especially because of the pandemic situation. Most recent approaches are focused on the detection of viral pneumonia or COVID-19 diseases. However, there is less attention to common pulmonary diseases, such as fibrosis, infiltration and others. This paper introduces the neural network, which is aimed to detect 14 pulmonary diseases. This model is composed of two branches: global, which is the InceptionNetV3, and local, which consists of Inception modules and a modified Vision Transformer. Additionally, the Asymmetric Loss function was utilized to deal with the problem of multilabel classification. The proposed model has achieved an AUC of 0.8012 and an accuracy of 0.7429, which outperforms the well-known classification models.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20203 - Telecommunications

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings II of the 29th Conference STUDENT EEICT 2023 Selected papers

ISBN

978-80-214-6154-3

ISSN

2788-1334

e-ISSN

—

Počet stran výsledku

5

Strana od-do

161-165

Název nakladatele

Brno University of Technology, Faculty of Electrical Engineering and Communication

Místo vydání

Brno

Místo konání akce

Brno

Datum konání akce

25. 4. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—