Deep Learning for Cranioplasty in Clinical Practice: Going from Synthetic to Real Patient Data

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F21%3APU142904" target="_blank" >RIV/00216305:26230/21:PU142904 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/abs/pii/S0010482521005606?via%3Dihub" target="_blank" >https://www.sciencedirect.com/science/article/abs/pii/S0010482521005606?via%3Dihub</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.compbiomed.2021.104766" target="_blank" >10.1016/j.compbiomed.2021.104766</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Deep Learning for Cranioplasty in Clinical Practice: Going from Synthetic to Real Patient Data

Popis výsledku v původním jazyce

Correct virtual reconstruction of a de- fective skull is a prerequisite for successful cranioplasty and its automatization has the potential for accelerat- ing and standardizing the clinical workflow. This work provides a deep learning-based method for the recon- struction of a skull shape and cranial implant design on clinical data of patients indicated for cranioplasty. The method is based on a cascade of multi-branch vol- umetric CNNs that enables simultaneous training on two different types of cranioplasty ground-truth data: the skull patch, which represents the exact shape of the missing part of the original skull, and which can be eas- ily created artificially from healthy skulls, and expert- designed cranial implant shapes that are much harder to acquire. The proposed method reaches an average surface distance of the reconstructed skull patches of 0.67 mm on a clinical test set of 75 defective skulls. It also achieves a 12% reduction of a newly proposed de- fect border Gaussian curvature error metric, compared to a baseline model trained on synthetic data only. Ad- ditionally, it produces directly 3D printable cranial im- plant shapes with a Dice coefficient 0.88 and a surface error of 0.65 mm. The outputs of the proposed skull reconstruction method reach good quality and can be considered for use in semi- or fully automatic clinical cranial implant design workflows.

Název v anglickém jazyce

Deep Learning for Cranioplasty in Clinical Practice: Going from Synthetic to Real Patient Data

Popis výsledku anglicky

Correct virtual reconstruction of a de- fective skull is a prerequisite for successful cranioplasty and its automatization has the potential for accelerat- ing and standardizing the clinical workflow. This work provides a deep learning-based method for the recon- struction of a skull shape and cranial implant design on clinical data of patients indicated for cranioplasty. The method is based on a cascade of multi-branch vol- umetric CNNs that enables simultaneous training on two different types of cranioplasty ground-truth data: the skull patch, which represents the exact shape of the missing part of the original skull, and which can be eas- ily created artificially from healthy skulls, and expert- designed cranial implant shapes that are much harder to acquire. The proposed method reaches an average surface distance of the reconstructed skull patches of 0.67 mm on a clinical test set of 75 defective skulls. It also achieves a 12% reduction of a newly proposed de- fect border Gaussian curvature error metric, compared to a baseline model trained on synthetic data only. Ad- ditionally, it produces directly 3D printable cranial im- plant shapes with a Dice coefficient 0.88 and a surface error of 0.65 mm. The outputs of the proposed skull reconstruction method reach good quality and can be considered for use in semi- or fully automatic clinical cranial implant design workflows.

Druh

J_imp - Článek v periodiku v databázi Web of Science

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

2021

Kód důvěrnosti údajů

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

Název periodika

COMPUTERS IN BIOLOGY AND MEDICINE

ISSN

0010-4825

e-ISSN

1879-0534

Svazek periodika

137

Číslo periodika v rámci svazku

104766

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

10

Strana od-do

1-10

Kód UT WoS článku

000704338500006

EID výsledku v databázi Scopus

2-s2.0-85113276148