Improving CT Image Tumor Segmentation Through Deep Supervision and Attentional Gates

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F70883521%3A28140%2F20%3A63525359" target="_blank" >RIV/70883521:28140/20:63525359 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.frontiersin.org/articles/10.3389/frobt.2020.00106/full" target="_blank" >https://www.frontiersin.org/articles/10.3389/frobt.2020.00106/full</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3389/frobt.2020.00106" target="_blank" >10.3389/frobt.2020.00106</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Improving CT Image Tumor Segmentation Through Deep Supervision and Attentional Gates

Popis výsledku v původním jazyce

Computer Tomography (CT) is an imaging procedure that combines many X-ray measurements taken from different angles. The segmentation of areas in the CT images provides a valuable aid to physicians and radiologists in order to better provide a patient diagnose. The CT scans of a body torso usually include different neighboring internal body organs. Deep learning has become the state-of-the-art in medical image segmentation. For such techniques, in order to perform a successful segmentation, it is of great importance that the network learns to focus on the organ of interest and surrounding structures and also that the network can detect target regions of different sizes. In this paper, we propose the extension of a popular deep learning methodology, Convolutional Neural Networks (CNN), by including deep supervision and attention gates. Our experimental evaluation shows that the inclusion of attention and deep supervision results in consistent improvement of the tumor prediction accuracy across the different datasets and training sizes while adding minimal computational overhead.

Název v anglickém jazyce

Improving CT Image Tumor Segmentation Through Deep Supervision and Attentional Gates

Popis výsledku anglicky

Computer Tomography (CT) is an imaging procedure that combines many X-ray measurements taken from different angles. The segmentation of areas in the CT images provides a valuable aid to physicians and radiologists in order to better provide a patient diagnose. The CT scans of a body torso usually include different neighboring internal body organs. Deep learning has become the state-of-the-art in medical image segmentation. For such techniques, in order to perform a successful segmentation, it is of great importance that the network learns to focus on the organ of interest and surrounding structures and also that the network can detect target regions of different sizes. In this paper, we propose the extension of a popular deep learning methodology, Convolutional Neural Networks (CNN), by including deep supervision and attention gates. Our experimental evaluation shows that the inclusion of attention and deep supervision results in consistent improvement of the tumor prediction accuracy across the different datasets and training sizes while adding minimal computational overhead.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2020

Kód důvěrnosti údajů

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

Název periodika

Frontiers Robotics AI

ISSN

2296-9144

e-ISSN

—

Svazek periodika

7

Číslo periodika v rámci svazku

Neuveden

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

14

Strana od-do

1-14

Kód UT WoS článku

000570414900001

EID výsledku v databázi Scopus

2-s2.0-85090765676