Why Use Position Features in Liver Segmentation Performed by Convolutional Neural Network
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00669806%3A_____%2F21%3A10433251" target="_blank" >RIV/00669806:_____/21:10433251 - isvavai.cz</a>
Nalezeny alternativní kódy
RIV/00216208:11140/21:10433251 RIV/49777513:23520/21:43962802
Výsledek na webu
<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=xOThCu6s1L" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=xOThCu6s1L</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.3389/fphys.2021.734217" target="_blank" >10.3389/fphys.2021.734217</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Why Use Position Features in Liver Segmentation Performed by Convolutional Neural Network
Popis výsledku v původním jazyce
The calculation of liver volume is primarily based on Computed Tomography. Unfortunately, automatic segmentation algorithms based on handcrafted features tend to leak segmented objects into surrounding tissues like the heart or the spleen. Currently, convolutional neural networks are widely used in various applications of computer vision including image segmentation, while providing very promising results. In our work, we utilize robustly segmentable structures like the spine, body surface, and sagittal plane. They are used as key points for position estimation inside the body. The signed distance fields derived from these structures are calculated and used as an additional channel on the input of our convolutional neural network, to be more specific U-Net, which is widely used in medical image segmentation tasks. Our work shows that this additional position information improves the results of the segmentation. We test our approach in two experiments on two public datasets of Computed Tomography images. To evaluate the results, we use the Accuracy, the Hausdorff distance, and the Dice coefficient. Code is publicly available.
Název v anglickém jazyce
Why Use Position Features in Liver Segmentation Performed by Convolutional Neural Network
Popis výsledku anglicky
The calculation of liver volume is primarily based on Computed Tomography. Unfortunately, automatic segmentation algorithms based on handcrafted features tend to leak segmented objects into surrounding tissues like the heart or the spleen. Currently, convolutional neural networks are widely used in various applications of computer vision including image segmentation, while providing very promising results. In our work, we utilize robustly segmentable structures like the spine, body surface, and sagittal plane. They are used as key points for position estimation inside the body. The signed distance fields derived from these structures are calculated and used as an additional channel on the input of our convolutional neural network, to be more specific U-Net, which is widely used in medical image segmentation tasks. Our work shows that this additional position information improves the results of the segmentation. We test our approach in two experiments on two public datasets of Computed Tomography images. To evaluate the results, we use the Accuracy, the Hausdorff distance, and the Dice coefficient. Code is publicly available.
Klasifikace
Druh
J<sub>imp</sub> - Článek v periodiku v databázi Web of Science
CEP obor
—
OECD FORD obor
10600 - Biological sciences
Návaznosti výsledku
Projekt
Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.
Návaznosti
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Ostatní
Rok uplatnění
2021
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název periodika
Frontiers in Physiology [online]
ISSN
1664-042X
e-ISSN
—
Svazek periodika
12
Číslo periodika v rámci svazku
October
Stát vydavatele periodika
CH - Švýcarská konfederace
Počet stran výsledku
9
Strana od-do
734217
Kód UT WoS článku
000710484200001
EID výsledku v databázi Scopus
2-s2.0-85117256040