Deep learning-based algorithm for postoperative glioblastoma MRI segmentation : a promising new tool for tumor burden assessment
© 2023. Springer-Verlag GmbH Germany, part of Springer Nature..
OBJECTIVE: Clinical and surgical decisions for glioblastoma patients depend on a tumor imaging-based evaluation. Artificial Intelligence (AI) can be applied to magnetic resonance imaging (MRI) assessment to support clinical practice, surgery planning and prognostic predictions. In a real-world context, the current obstacles for AI are low-quality imaging and postoperative reliability. The aim of this study is to train an automatic algorithm for glioblastoma segmentation on a clinical MRI dataset and to obtain reliable results both pre- and post-operatively.
METHODS: The dataset used for this study comprises 237 (71 preoperative and 166 postoperative) MRIs from 71 patients affected by a histologically confirmed Grade IV Glioma. The implemented U-Net architecture was trained by transfer learning to perform the segmentation task on postoperative MRIs. The training was carried out first on BraTS2021 dataset for preoperative segmentation. Performance is evaluated using DICE score (DS) and Hausdorff 95% (H95).
RESULTS: In preoperative scenario, overall DS is 91.09 (± 0.60) and H95 is 8.35 (± 1.12), considering tumor core, enhancing tumor and whole tumor (ET and edema). In postoperative context, overall DS is 72.31 (± 2.88) and H95 is 23.43 (± 7.24), considering resection cavity (RC), gross tumor volume (GTV) and whole tumor (WT). Remarkably, the RC segmentation obtained a mean DS of 63.52 (± 8.90) in postoperative MRIs.
CONCLUSIONS: The performances achieved by the algorithm are consistent with previous literature for both pre-operative and post-operative glioblastoma's MRI evaluation. Through the proposed algorithm, it is possible to reduce the impact of low-quality images and missing sequences.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:10 |
|---|---|
| Enthalten in: |
Brain informatics - 10(2023), 1 vom: 06. Okt., Seite 26 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Bianconi, Andrea [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Deep learning |
|---|
| Anmerkungen: |
Date Revised 21.11.2023 published: Electronic Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1186/s40708-023-00207-6 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM362947414 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM362947414 | ||
| 003 | DE-627 | ||
| 005 | 20231226092313.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1186/s40708-023-00207-6 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1209.xml |
| 035 | |a (DE-627)NLM362947414 | ||
| 035 | |a (NLM)37801128 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Bianconi, Andrea |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Deep learning-based algorithm for postoperative glioblastoma MRI segmentation |b a promising new tool for tumor burden assessment |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 21.11.2023 | ||
| 500 | |a published: Electronic | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a © 2023. Springer-Verlag GmbH Germany, part of Springer Nature. | ||
| 520 | |a OBJECTIVE: Clinical and surgical decisions for glioblastoma patients depend on a tumor imaging-based evaluation. Artificial Intelligence (AI) can be applied to magnetic resonance imaging (MRI) assessment to support clinical practice, surgery planning and prognostic predictions. In a real-world context, the current obstacles for AI are low-quality imaging and postoperative reliability. The aim of this study is to train an automatic algorithm for glioblastoma segmentation on a clinical MRI dataset and to obtain reliable results both pre- and post-operatively | ||
| 520 | |a METHODS: The dataset used for this study comprises 237 (71 preoperative and 166 postoperative) MRIs from 71 patients affected by a histologically confirmed Grade IV Glioma. The implemented U-Net architecture was trained by transfer learning to perform the segmentation task on postoperative MRIs. The training was carried out first on BraTS2021 dataset for preoperative segmentation. Performance is evaluated using DICE score (DS) and Hausdorff 95% (H95) | ||
| 520 | |a RESULTS: In preoperative scenario, overall DS is 91.09 (± 0.60) and H95 is 8.35 (± 1.12), considering tumor core, enhancing tumor and whole tumor (ET and edema). In postoperative context, overall DS is 72.31 (± 2.88) and H95 is 23.43 (± 7.24), considering resection cavity (RC), gross tumor volume (GTV) and whole tumor (WT). Remarkably, the RC segmentation obtained a mean DS of 63.52 (± 8.90) in postoperative MRIs | ||
| 520 | |a CONCLUSIONS: The performances achieved by the algorithm are consistent with previous literature for both pre-operative and post-operative glioblastoma's MRI evaluation. Through the proposed algorithm, it is possible to reduce the impact of low-quality images and missing sequences | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a Glioblastoma | |
| 650 | 4 | |a Glioma | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Magnetic resonance imaging | |
| 650 | 4 | |a Segmentation | |
| 700 | 1 | |a Rossi, Luca Francesco |e verfasserin |4 aut | |
| 700 | 1 | |a Bonada, Marta |e verfasserin |4 aut | |
| 700 | 1 | |a Zeppa, Pietro |e verfasserin |4 aut | |
| 700 | 1 | |a Nico, Elsa |e verfasserin |4 aut | |
| 700 | 1 | |a De Marco, Raffaele |e verfasserin |4 aut | |
| 700 | 1 | |a Lacroce, Paola |e verfasserin |4 aut | |
| 700 | 1 | |a Cofano, Fabio |e verfasserin |4 aut | |
| 700 | 1 | |a Bruno, Francesco |e verfasserin |4 aut | |
| 700 | 1 | |a Morana, Giovanni |e verfasserin |4 aut | |
| 700 | 1 | |a Melcarne, Antonio |e verfasserin |4 aut | |
| 700 | 1 | |a Ruda, Roberta |e verfasserin |4 aut | |
| 700 | 1 | |a Mainardi, Luca |e verfasserin |4 aut | |
| 700 | 1 | |a Fiaschi, Pietro |e verfasserin |4 aut | |
| 700 | 1 | |a Garbossa, Diego |e verfasserin |4 aut | |
| 700 | 1 | |a Morra, Lia |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Brain informatics |d 2014 |g 10(2023), 1 vom: 06. Okt., Seite 26 |w (DE-627)NLM258981288 |x 2198-4018 |7 nnns |
| 773 | 1 | 8 | |g volume:10 |g year:2023 |g number:1 |g day:06 |g month:10 |g pages:26 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1186/s40708-023-00207-6 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 10 |j 2023 |e 1 |b 06 |c 10 |h 26 | ||