1
|
Ranjbar S, Singleton KW, Curtin L, Paulson L, Clark-Swanson K, Hawkins-Daarud A, Mitchell JR, Jackson PR, Swanson AKR. Towards Longitudinal Glioma Segmentation: Evaluating combined pre- and post-treatment MRI training data for automated tumor segmentation using nnU-Net. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.05.31.23290537. [PMID: 37333148 PMCID: PMC10274985 DOI: 10.1101/2023.05.31.23290537] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/20/2023]
Abstract
Identification of key phenotypic regions such as necrosis, contrast enhancement, and edema on magnetic resonance imaging (MRI) is important for understanding disease evolution and treatment response in patients with glioma. Manual delineation is time intensive and not feasible for a clinical workflow. Automating phenotypic region segmentation overcomes many issues with manual segmentation, however, current glioma segmentation datasets focus on pre-treatment, diagnostic scans, where treatment effects and surgical cavities are not present. Thus, existing automatic segmentation models are not applicable to post-treatment imaging that is used for longitudinal evaluation of care. Here, we present a comparison of three-dimensional convolutional neural networks (nnU-Net architecture) trained on large temporally defined pre-treatment, post-treatment, and mixed cohorts. We used a total of 1563 imaging timepoints from 854 patients curated from 13 different institutions as well as diverse public data sets to understand the capabilities and limitations of automatic segmentation on glioma images with different phenotypic and treatment appearance. We assessed the performance of models using Dice coefficients on test cases from each group comparing predictions with manual segmentations generated by trained technicians. We demonstrate that training a combined model can be as effective as models trained on just one temporal group. The results highlight the importance of a diverse training set, that includes images from the course of disease and with effects from treatment, in the creation of a model that can accurately segment glioma MRIs at multiple treatment time points.
Collapse
Affiliation(s)
- Sara Ranjbar
- Mathematical NeuroOncology Lab, Department of Neurological Surgery, Mayo Clinic, Phoenix AZ 85054, USA
| | - Kyle W Singleton
- Mathematical NeuroOncology Lab, Department of Neurological Surgery, Mayo Clinic, Phoenix AZ 85054, USA
| | - Lee Curtin
- Mathematical NeuroOncology Lab, Department of Neurological Surgery, Mayo Clinic, Phoenix AZ 85054, USA
| | - Lisa Paulson
- Mathematical NeuroOncology Lab, Department of Neurological Surgery, Mayo Clinic, Phoenix AZ 85054, USA
| | - Kamala Clark-Swanson
- Mathematical NeuroOncology Lab, Department of Neurological Surgery, Mayo Clinic, Phoenix AZ 85054, USA
| | - Andrea Hawkins-Daarud
- Mathematical NeuroOncology Lab, Department of Neurological Surgery, Mayo Clinic, Phoenix AZ 85054, USA
| | | | - Pamela R Jackson
- Mathematical NeuroOncology Lab, Department of Neurological Surgery, Mayo Clinic, Phoenix AZ 85054, USA
| | - And Kristin R Swanson
- Mathematical NeuroOncology Lab, Department of Neurological Surgery, Mayo Clinic, Phoenix AZ 85054, USA
| |
Collapse
|