Cranial Defect Reconstruction Using Cascaded CNN with Alignment

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F20%3APU138873" target="_blank" >RIV/00216305:26230/20:PU138873 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-030-64327-0_7" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-030-64327-0_7</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-64327-0_7" target="_blank" >10.1007/978-3-030-64327-0_7</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Cranial Defect Reconstruction Using Cascaded CNN with Alignment

Popis výsledku v původním jazyce

Designing a patient-specific cranial implant usually requires reconstructing the defective part of the skull using computer-aided design software, which is a tedious and time-demanding task. This lead to some recent advances in the field of automatic skull reconstruction with use of methods based on shape analysis or deep learning. The AutoImplant Challenge aims at providing a public platform for benchmarking skull reconstruction methods. The BUT submission to this challenge is based on skull alignment using landmark detection followed by a cascade of low-resolution and high-resolution reconstruction convolutional neural network. We demonstrate that the proposed method successfully reconstructs every skull in the standard test dataset and outperforms the baseline method in both overlap and distance metrics, achieving 0.920 DSC and 4.137 mm HD.

Název v anglickém jazyce

Cranial Defect Reconstruction Using Cascaded CNN with Alignment

Popis výsledku anglicky

Designing a patient-specific cranial implant usually requires reconstructing the defective part of the skull using computer-aided design software, which is a tedious and time-demanding task. This lead to some recent advances in the field of automatic skull reconstruction with use of methods based on shape analysis or deep learning. The AutoImplant Challenge aims at providing a public platform for benchmarking skull reconstruction methods. The BUT submission to this challenge is based on skull alignment using landmark detection followed by a cascade of low-resolution and high-resolution reconstruction convolutional neural network. We demonstrate that the proposed method successfully reconstructs every skull in the standard test dataset and outperforms the baseline method in both overlap and distance metrics, achieving 0.920 DSC and 4.137 mm HD.

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

N - Vyzkumna aktivita podporovana z neverejnych zdroju

Rok uplatnění

2020

Kód důvěrnosti údajů

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

Název statě ve sborníku

Towards the Automatization of Cranial Implant Design in Cranioplasty

ISBN

978-3-030-64327-0

ISSN

—

e-ISSN

—

Počet stran výsledku

9

Strana od-do

56-64

Název nakladatele

Springer Nature Switzerland AG

Místo vydání

Lima

Místo konání akce

Lima

Datum konání akce

8. 10. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—