Coordinate-Unet 3D for segmentation of lung parenchyma
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| hal.structure.identifier | BoRdeaux Institute in onCology [Inserm U1312 - BRIC] | |
| hal.structure.identifier | Institut Bergonié [Bordeaux] | |
| hal.structure.identifier | Modélisation Mathématique pour l'Oncologie [MONC] | |
| dc.contributor.author | LE, Van-Linh | |
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| hal.structure.identifier | Modélisation Mathématique pour l'Oncologie [MONC] | |
| dc.contributor.author | SAUT, Olivier | |
| dc.date.accessioned | 2024-04-04T02:32:03Z | |
| dc.date.available | 2024-04-04T02:32:03Z | |
| dc.date.created | 2023-07-19 | |
| dc.date.conference | 2023-05-15 | |
| dc.identifier.isbn | 2464-4617 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/190352 | |
| dc.description.abstractEn | Lung segmentation is an initial step to provide accurate lung parenchyma in many studies on lung diseases based on analyzing the Computed Tomography (CT) scan, especially in Non-Small Cell Lung Cancer (NSCLC) detection. In this work, Coordinate-UNet 3D, a model inspired by UNet, is proposed to improve the accuracy of lung segmentation in the CT scan. Like UNet, the proposed model consists of a contracting/encoder path to extract the high-level information and an expansive/decoder path to recover the features to provide the segmentation. However, we have considered modifying the structure inside each level of the model and using the Coordinate Convolutional layer as the final layer to provide the segmentation. This network was trained end-to-end from a small set of CT scans of NSCLC patients. The experimental results show the proposed network can provide a highly accurate segmentation for the validation set with a Dice Coefficient index of 0.991, an F1 score of 0.976, and a Jaccard index (IOU) of 0.9535. | |
| dc.language.iso | en | |
| dc.rights.uri | http://creativecommons.org/licenses/by/ | |
| dc.subject.en | Lung segmentation | |
| dc.subject.en | NSCLC | |
| dc.subject.en | Unet | |
| dc.subject.en | Coordinate Convolutional | |
| dc.subject.en | Deep Learning | |
| dc.title.en | Coordinate-Unet 3D for segmentation of lung parenchyma | |
| dc.type | Communication dans un congrès | |
| dc.identifier.doi | 10.24132/CSRN.3301.6 | |
| dc.subject.hal | Informatique [cs] | |
| bordeaux.page | 36-42 | |
| bordeaux.hal.laboratories | Institut de Mathématiques de Bordeaux (IMB) - UMR 5251 | * |
| bordeaux.institution | Université de Bordeaux | |
| bordeaux.institution | Bordeaux INP | |
| bordeaux.institution | CNRS | |
| bordeaux.conference.title | WSCG 2023 – 31th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision | |
| bordeaux.country | CZ | |
| bordeaux.conference.city | Pilsen | |
| bordeaux.peerReviewed | oui | |
| hal.identifier | hal-04222468 | |
| hal.version | 1 | |
| hal.invited | non | |
| hal.proceedings | oui | |
| hal.conference.end | 2023-05-19 | |
| hal.popular | non | |
| hal.audience | Internationale | |
| hal.origin.link | https://hal.archives-ouvertes.fr//hal-04222468v1 | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.spage=36-42&rft.epage=36-42&rft.au=LE,%20Van-Linh&SAUT,%20Olivier&rft.isbn=2464-4617&rft.genre=unknown |
Fichier(s) constituant ce document
| Fichiers | Taille | Format | Vue |
|---|---|---|---|
|
Il n'y a pas de fichiers associés à ce document. |
|||