Automated brain tumor segmentation methods have become well-established and
reached performance levels offering clear clinical utility. These methods
typically rely on four input magnetic resonance ...imaging (MRI) modalities:
T1-weighted images with and without contrast enhancement, T2-weighted images,
and FLAIR images. However, some sequences are often missing in clinical
practice due to time constraints or image artifacts, such as patient motion.
Consequently, the ability to substitute missing modalities and gain
segmentation performance is highly desirable and necessary for the broader
adoption of these algorithms in the clinical routine. In this work, we present
the establishment of the Brain MR Image Synthesis Benchmark (BraSyn) in
conjunction with the Medical Image Computing and Computer-Assisted Intervention
(MICCAI) 2023. The primary objective of this challenge is to evaluate image
synthesis methods that can realistically generate missing MRI modalities when
multiple available images are provided. The ultimate aim is to facilitate
automated brain tumor segmentation pipelines. The image dataset used in the
benchmark is diverse and multi-modal, created through collaboration with
various hospitals and research institutions.
This manuscript describes the first challenge on Federated Learning, namely the Federated Tumor Segmentation (FeTS) challenge 2021. International challenges have become the standard for validation of ...biomedical image analysis methods. However, the actual performance of participating (even the winning) algorithms on "real-world" clinical data often remains unclear, as the data included in challenges are usually acquired in very controlled settings at few institutions. The seemingly obvious solution of just collecting increasingly more data from more institutions in such challenges does not scale well due to privacy and ownership hurdles. Towards alleviating these concerns, we are proposing the FeTS challenge 2021 to cater towards both the development and the evaluation of models for the segmentation of intrinsically heterogeneous (in appearance, shape, and histology) brain tumors, namely gliomas. Specifically, the FeTS 2021 challenge uses clinically acquired, multi-institutional magnetic resonance imaging (MRI) scans from the BraTS 2020 challenge, as well as from various remote independent institutions included in the collaborative network of a real-world federation (https://www.fets.ai/). The goals of the FeTS challenge are directly represented by the two included tasks: 1) the identification of the optimal weight aggregation approach towards the training of a consensus model that has gained knowledge via federated learning from multiple geographically distinct institutions, while their data are always retained within each institution, and 2) the federated evaluation of the generalizability of brain tumor segmentation models "in the wild", i.e. on data from institutional distributions that were not part of the training datasets.
Abstract
BACKGROUND:
Advanced imaging methods have the potential to serve as quantitative biomarkers in neuro-oncology research. However, a lack of standardization of image acquisition, processing, ...and analysis limits their application in clinical research. Standardization of these methods and an organized archival platform are required to better validate and apply these markers in research settings and, ultimately, in clinical practice.
OBJECTIVE:
The primary objective of the Comprehensive Neuro-oncology Data Repository (CONDR) is to develop a data set for assessing and validating advanced imaging methods in patients diagnosed with brain tumors. As a secondary objective, informatics resources will be developed to facilitate the integrated collection, processing, and analysis of imaging, tissue, and clinical data in multicenter clinical trials. Finally, CONDR data and informatics resources will be shared with the research community for further analysis.
METHODS:
CONDR will enroll 200 patients diagnosed with primary brain tumors. Clinical, imaging, and tissue-based data are obtained from patients serially, beginning with diagnosis and continuing over the course of their treatment. The CONDR imaging protocol includes structural and functional sequences, including diffusion- and perfusion-weighted imaging. All data are managed within an XNAT-based informatics platform. Imaging markers are assessed by correlating image and spatially aligned pathological markers and a variety of clinical markers.
EXPECTED OUTCOMES:
CONDR will generate data for developing and validating imaging markers of primary brain tumors, including multispectral and probabilistic maps.
DISCUSSION:
CONDR implements a novel, open-research model that will provide the research community with both open-access data and open-source informatics resources.
In the recent years, the demand for automated processing techniques for digital medical image volumes has increased substantially. Existing algorithms, however, still often require manual ...interaction, and newly developed automated techniques are often intended for a narrow segment of processing needs. The goal of this research was to develop algorithms suitable for fast and effective correction and advanced visualization of digital MR image volumes with minimal human operator interaction. This research has resulted in a number of techniques for automated processing of MR image volumes, including a novel MR inhomogeneity correction algorithm derivative surface fitting (dsf), automatic tissue detection algorithm (atd), and a new fast technique for interactive 3D visualization of segmented volumes called gravitational shading (gs). These newly developed algorithms provided a foundation for the automated MR processing pipeline incorporated into the UniViewer medical imaging software developed in our group and available to the public. This allowed the extensive testing and evaluation of the proposed techniques. Dsf was compared with two previously published methods on 17 digital image volumes. Dsf demonstrated faster correction speeds and uniform image quality improvement in this comparison. Dsf was the only algorithm that did not remove anatomic detail. Gs was compared with the previously published algorithm fsvr and produced rendering quality improvement while preserving real-time frame-rates. These results show that the automated pipeline design principles used in this dissertation provide necessary tools for development of a fast and effective system for the automated correction and visualization of digital MR image volumes.
In the recent years, the demand for automated processing techniques for digital medical image volumes has increased substantially. Existing algorithms, however, still often require manual ...interaction, and newly developed automated techniques are often intended for a narrow segment of processing needs.The goal of this research was to develop algorithms suitable for fast and effective correction and advanced visualization of digital MR image volumes with minimal human operator interaction. This research has resulted in a number of techniques for automated processing of MR image volumes, including a novel MR inhomogeneity correction algorithm derivative surface fitting (dsf), automatic tissue detection algorithm (atd), and a new fast technique for interactive 3D visualization of segmented volumes called gravitational shading (gs).These newly developed algorithms provided a foundation for the automated MR processing pipeline incorporated into the UniViewer medical imaging software developed in our group and available to the public. This allowed the extensive testing and evaluation of the proposed techniques.Dsf was compared with two previously published methods on 17 digital image volumes. Dsf demonstrated faster correction speeds and uniform image quality improvement in this comparison. Dsf was the only algorithm that did not remove anatomic detail. Gs was compared with the previously published algorithm fsvr and produced rendering quality improvement while preserving real-time frame-rates.These results show that the automated pipeline design principles used in this dissertation provide necessary tools for development of a fast and effective system for the automated correction and visualization of digital MR image volumes.
The BraTS 2021 challenge celebrates its 10th anniversary and is jointly organized by the Radiological Society of North America (RSNA), the American Society of Neuroradiology (ASNR), and the Medical ...Image Computing and Computer Assisted Interventions (MICCAI) society. Since its inception, BraTS has been focusing on being a common benchmarking venue for brain glioma segmentation algorithms, with well-curated multi-institutional multi-parametric magnetic resonance imaging (mpMRI) data. Gliomas are the most common primary malignancies of the central nervous system, with varying degrees of aggressiveness and prognosis. The RSNA-ASNR-MICCAI BraTS 2021 challenge targets the evaluation of computational algorithms assessing the same tumor compartmentalization, as well as the underlying tumor's molecular characterization, in pre-operative baseline mpMRI data from 2,040 patients. Specifically, the two tasks that BraTS 2021 focuses on are: a) the segmentation of the histologically distinct brain tumor sub-regions, and b) the classification of the tumor's O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation status. The performance evaluation of all participating algorithms in BraTS 2021 will be conducted through the Sage Bionetworks Synapse platform (Task 1) and Kaggle (Task 2), concluding in distributing to the top ranked participants monetary awards of $60,000 collectively.
In the recent years, the demand for automated processing techniques for digital medical image volumes has increased substantially. Existing algorithms, however, still often require manual ...interaction, and newly developed automated techniques are often intended for a narrow segment of processing needs.
The goal of this research was to develop algorithms suitable for fast and effective correction and advanced visualization of digital MR image volumes with minimal human operator interaction. This research has resulted in a number of techniques for automated processing of MR image volumes, including a novel MR inhomogeneity correction algorithm derivative surface fitting (dsf), automatic tissue detection algorithm (atd), and a new fast technique for interactive 3D visualization of segmented volumes called gravitational shading (gs).
These newly developed algorithms provided a foundation for the automated MR processing pipeline incorporated into the UniViewer medical imaging software developed in our group and available to the public. This allowed the extensive testing and evaluation of the proposed techniques.
Dsf was compared with two previously published methods on 17 digital image volumes. Dsf demonstrated faster correction speeds and uniform image quality improvement in this comparison. Dsf was the only algorithm that did not remove anatomic detail. Gs was compared with the previously published algorithm fsvr and produced rendering quality improvement while preserving real-time frame-rates.
These results show that the automated pipeline design principles used in this dissertation provide necessary tools for development of a fast and effective system for the automated correction and visualization of digital MR image volumes.
Glioblastoma Mulitforme is highly infiltrative, making precise delineation of tumor margin difficult. Multimodality or multi-parametric MR imaging sequences promise an advantage over anatomic ...sequences such as post contrast enhancement as methods for determining the spatial extent of tumor involvement. In considering multi-parametric imaging sequences however, manual image segmentation and classification is time-consuming and prone to error. As a preliminary step toward integration of multi-parametric imaging into clinical assessments of primary brain tumors, we propose a machine-learning based multi-parametric approach that uses radiologist generated labels to train a classifier that is able to classify tissue on a voxel-wise basis and automatically generate a tumor segmentation. A random forests classifier was trained using a leave-one-out experimental paradigm. A simple linear classifier was also trained for comparison. The random forests classifier accurately predicted radiologist generated segmentations and tumor extent.