Planar 3D Transfer Learning for End to End Unimodal MRI Unbalanced Data Segmentation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F21%3APU141428" target="_blank" >RIV/00216305:26220/21:PU141428 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-030-76423-4_10" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-030-76423-4_10</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICPR48806.2021.9412150" target="_blank" >10.1109/ICPR48806.2021.9412150</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Planar 3D Transfer Learning for End to End Unimodal MRI Unbalanced Data Segmentation

Popis výsledku v původním jazyce

We present a novel approach of 2D to 3D transfer learning based on mapping pre-trained 2D convolutional neural network weights into planar 3D kernels. The method is validated by the proposed planar 3D res-u-net network with encoder transferred from the 2D VGG-16, which is applied for a single-stage unbalanced 3D image data segmentation. In particular, we evaluate the method on the MICCAI 2016 MS lesion segmentation challenge dataset utilizing solely fluid-attenuated inversion recovery (FLAIR) sequence without brain extraction for training and inference to simulate real medical praxis. The planar 3D res-u-net network performed the best both in sensitivity and Dice score amongst end to end methods processing raw MRI scans and achieved comparable Dice score to a state-of-the-art unimodal not end to end approach. Complete source code was released under the open-source license, and this paper complies with the Machine learning reproducibility checklist. By implementing practical transfer learning for 3D data representation, we could segment heavily unbalanced data without selective sampling and achieved more reliable results using less training data in a single modality. From a medical perspective, the unimodal approach gives an advantage in real praxis as it does not require co-registration nor additional scanning time during an examination. Although modern medical imaging methods capture high-resolution 3D anatomy scans suitable for computer-aided detection system processing, deployment of automatic systems for interpretation of radiology imaging is still rather theoretical in many medical areas. Our work aims to bridge the gap by offering a solution for partial research questions.

Název v anglickém jazyce

Planar 3D Transfer Learning for End to End Unimodal MRI Unbalanced Data Segmentation

Popis výsledku anglicky

We present a novel approach of 2D to 3D transfer learning based on mapping pre-trained 2D convolutional neural network weights into planar 3D kernels. The method is validated by the proposed planar 3D res-u-net network with encoder transferred from the 2D VGG-16, which is applied for a single-stage unbalanced 3D image data segmentation. In particular, we evaluate the method on the MICCAI 2016 MS lesion segmentation challenge dataset utilizing solely fluid-attenuated inversion recovery (FLAIR) sequence without brain extraction for training and inference to simulate real medical praxis. The planar 3D res-u-net network performed the best both in sensitivity and Dice score amongst end to end methods processing raw MRI scans and achieved comparable Dice score to a state-of-the-art unimodal not end to end approach. Complete source code was released under the open-source license, and this paper complies with the Machine learning reproducibility checklist. By implementing practical transfer learning for 3D data representation, we could segment heavily unbalanced data without selective sampling and achieved more reliable results using less training data in a single modality. From a medical perspective, the unimodal approach gives an advantage in real praxis as it does not require co-registration nor additional scanning time during an examination. Although modern medical imaging methods capture high-resolution 3D anatomy scans suitable for computer-aided detection system processing, deployment of automatic systems for interpretation of radiology imaging is still rather theoretical in many medical areas. Our work aims to bridge the gap by offering a solution for partial research questions.

Druh

D - Stať ve sborníku

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

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

2020 25th International Conference on Pattern Recognition (ICPR)

ISBN

978-1-7281-8808-9

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

1-8

Název nakladatele

IEEE

Místo vydání

Online

Místo konání akce

Milano

Datum konání akce

10. 1. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000678409206025