Glioblastoma Surgery Imaging–Reporting and Data System: Validation and Performance of the Automated Segmentation Task

Bouget, David; Eijgelaar, Roelant S; Pedersen, André; Kommers, Ivar; Ardon, Hilko; Barkhof, Frederik; Bello, Lorenzo; Berger, Mitchel S.; Nibali, Marco Conti; Furtner, Julia; Fyllingen, Even Hovig; Hervey-Jumper, Shawn L.; Idema, Albert J. S.; Kiesel, Barbara; Kloet, Alfred; Mandonnet, Emmanuel; Müller, Domenique M J; Robe, Pierre A.; Rossi, Marco; Sagberg, Lisa Millgård; Sciortino, Tommaso; Brink, W. A. van den; Wagemakers, Michiel; Widhalm, Georg; Witte, Marnix G.; Zwinderman, Aeilko H.; Reinertsen, Ingerid; Hamer, Philip C. De Witt; Solheim, Ole

doi:10.3390/cancers13184674

Cited by 13 publications

(14 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The architecture selected to train segmentation models for each brain tumor type is AGU-Net, which has shown to perform well on glioblastoma and meningioma segmentation ( 32 , 44 ). In the following, the different training blocks are presented with some inner variations specified by roman numbers inside brackets.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Preoperative Brain Tumor Imaging: Models and Software for Segmentation and Standardized Reporting

et al. 2022

Self Cite

View full text Add to dashboard Cite

For patients suffering from brain tumor, prognosis estimation and treatment decisions are made by a multidisciplinary team based on a set of preoperative MR scans. Currently, the lack of standardized and automatic methods for tumor detection and generation of clinical reports, incorporating a wide range of tumor characteristics, represents a major hurdle. In this study, we investigate the most occurring brain tumor types: glioblastomas, lower grade gliomas, meningiomas, and metastases, through four cohorts of up to 4,000 patients. Tumor segmentation models were trained using the AGU-Net architecture with different preprocessing steps and protocols. Segmentation performances were assessed in-depth using a wide-range of voxel and patient-wise metrics covering volume, distance, and probabilistic aspects. Finally, two software solutions have been developed, enabling an easy use of the trained models and standardized generation of clinical reports: Raidionics and Raidionics-Slicer. Segmentation performances were quite homogeneous across the four different brain tumor types, with an average true positive Dice ranging between 80 and 90%, patient-wise recall between 88 and 98%, and patient-wise precision around 95%. In conjunction to Dice, the identified most relevant other metrics were the relative absolute volume difference, the variation of information, and the Hausdorff, Mahalanobis, and object average symmetric surface distances. With our Raidionics software, running on a desktop computer with CPU support, tumor segmentation can be performed in 16–54 s depending on the dimensions of the MRI volume. For the generation of a standardized clinical report, including the tumor segmentation and features computation, 5–15 min are necessary. All trained models have been made open-access together with the source code for both software solutions and validation metrics computation. In the future, a method to convert results from a set of metrics into a final single score would be highly desirable for easier ranking across trained models. In addition, an automatic classification of the brain tumor type would be necessary to replace manual user input. Finally, the inclusion of post-operative segmentation in both software solutions will be key for generating complete post-operative standardized clinical reports.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The architecture selected to train segmentation models for each brain tumor type is AGU-Net, which has shown to perform well on glioblastoma and meningioma segmentation (32,44).…”

Section: Tumor Segmentationmentioning

confidence: 99%

Preoperative Brain Tumor Imaging: Models and Software for Segmentation and Standardized Reporting

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Similar to our previous work on pre-operative glioblastoma segmentation 27 , the following two competitive CNN architectures were selected for the task of voxel-wise segmentation of residual tumor tissue: patch-wise nnU-Net 14 and full-volume AGU-Net 28 .…”

Section: Segmentation Processmentioning

confidence: 99%

“…The selected architectures are the nnU-Net, state-of-the-art for pre-operative glioblastoma segmentation, and AGU-Net, an architecture developed for pre-operative segmentation of brain tumors. These architectures have both demonstrated excellent performance on pre-operative segmentation in previous studies on pre-operative brain tumor segmentation [27][28][29] , and they exhibit different strengths and weaknesses. The automatic results are compared with manual segmentations, using different combinations of MRI scans in a large dataset consisting of paired pre-and early post-operative MRI scans from 956 patients in 12 medical centers in Europe and the United States.…”

Section: Introductionmentioning

confidence: 96%

Segmentation of glioblastomas in early post-operative multi-modal MRI with deep neural networks

Helland

Ferles

Pedersen

et al. 2023

Preprint

View full text Add to dashboard Cite

Extent of resection after surgery is one of the main prognostic factors for patients diagnosed with glioblastoma. To achieve this, accurate segmentation and classification of residual tumor from post-operative MR images is essential. The current standard method for estimating it is subject to high inter-and intra-rater variability, and an automated method for segmentation of residual tumor in early post-operative MRI could lead to a more accurate estimation of extent of resection. In this study, two state-of-the-art neural network architectures for pre-operative segmentation were trained for the task. The models were extensively validated on a multicenter dataset with nearly 1000 patients, from 12 hospitals in Europe and the United States. The best performance achieved was a 61% Dice score, and the best classification performance was about 80% balanced accuracy, with a demonstrated ability to generalize across hospitals. In addition, the segmentation performance of the best models was on par with human expert raters. The predicted segmentations can be used to accurately classify the patients into those with residual tumor, and those with gross total resection.

show abstract

“…The architecture selected to train segmentation models for each brain tumor type is AGU-Net, which has shown to perform well on glioblastoma and meningioma segmentation [40,32]. In the following, the different training blocks are presented with some inner variations specified by roman numbers inside brackets.…”

Section: Tumor Segmentationmentioning

confidence: 99%

Preoperative brain tumor imaging: models and software for segmentation and standardized reporting

Bouget¹,

Pedersen²,

Jakola³

et al. 2022

Preprint

View full text Add to dashboard Cite

For patients suffering from brain tumor, prognosis estimation and treatment decisions are made by a multidisciplinary team based on a set of preoperative MR scans. Currently, the lack of standardized and automatic methods for tumor detection and generation of clinical reports, incorporating a wide range of tumor characteristics, represents a major hurdle. In this study, we investigate the most occurring brain tumor types: glioblastomas, lower grade gliomas, meningiomas, and metastases, through four cohorts of up to 4 000 patients. Tumor segmentation models were trained using the AGU-Net architecture with different preprocessing steps and protocols. Segmentation performances were assessed in-depth using a wide-range of voxel and patient-wise metrics covering volume, distance, and probabilistic aspects. Finally, two software solutions have been developed, enabling an easy use of the trained models and standardized generation of clinical reports: Raidionics and Raidionics-Slicer. Segmentation performances were quite homogeneous across the four different brain tumor types, with an average true positive Dice ranging between 80% and 90%, patient-wise recall between 88% and 98%, and patient-wise precision around 95%. In conjunction to Dice, the identified most relevant other metrics were the relative absolute volume difference, the variation of information, and the Hausdorff, Mahalanobis, and object average symmetric surface distances. With our Raidionics software, running on a desktop computer with CPU support, tumor segmentation can be performed in 16 to 54 seconds depending on the dimensions of the MRI volume. For the generation of a standardized clinical report, including the tumor segmentation and features computation, 5 to 15 minutes are necessary. All trained models have been made open-access together with the source code for both software solutions and validation metrics computation. In the future, a method to convert results from a set of metrics into a final single score would be highly desirable for easier ranking across trained models. In addition, an automatic classification of the brain tumor type would be necessary to replace manual user input. Finally, the inclusion of post-operative segmentation in both software solutions will be key for generating complete post-operative standardized clinical reports.

show abstract

Glioblastoma Surgery Imaging–Reporting and Data System: Validation and Performance of the Automated Segmentation Task

Cited by 13 publications

References 52 publications

Preoperative Brain Tumor Imaging: Models and Software for Segmentation and Standardized Reporting

Preoperative Brain Tumor Imaging: Models and Software for Segmentation and Standardized Reporting

Segmentation of glioblastomas in early post-operative multi-modal MRI with deep neural networks

Preoperative brain tumor imaging: models and software for segmentation and standardized reporting

Contact Info

Product

Resources

About