arXiv subjects

Piotr Radojewski

Publications and source records attributed to Piotr Radojewski.

4 recordsLinked to original sources

arXiv2025

Learning from spatially inhomogenous data: resolution-adaptive convolutions for multiple sclerosis lesion segmentation

In the setting of clinical imaging, differences in between vendors, hospitals and sequences can yield highly inhomogeneous imaging data. In MRI in particular, voxel dimension, slice spacing and acquisition plane can vary substantially. For clinical applications, therefore, algorithms must be trained to handle data with various voxel resolutions. The usual strategy to deal with heterogeneity of resolution is harmonization: resampling imaging data to a common (usually isovoxel) resolution. This can lead to loss of fidelity arising from interpolation artifacts out-of-plane and downsampling in-plane. We present in this paper a network architecture designed to be able to learn directly from spatially heterogeneous data, without resampling: a segmentation network based on the e3nn framework that leverages a spherical harmonic, rather than voxel-grid, parameterization of convolutional kernels, with a fixed physical radius. Networks based on these kernels can be resampled to their input voxel dimensions. We trained and tested our network on a publicly available dataset assembled from three centres, and on an in-house dataset of Multiple Sclerosis cases with a high degree of spatial inhomogeneity. We compared our approach to a standard U-Net with two strategies for handling inhomogeneous data: training directly on the data without resampling, and resampling to a common resolution of 1mm isovoxels. We show that our network is able to learn from various combinations of voxel sizes and outperforms classical U-Nets on 2D testing cases and most 3D testing cases. This shows an ability to generalize well when tested on image resolutions not seen during training. Our code can be found at: http://github.com/SCAN-NRAD/e3nn\_U-Net.

eess.IV↗

arXiv2025

CHEmical-shift selective Adiabatic Pulse (CHEAP): Fast and High Resolution Downfield 3D 1H-MRSI at 7T

The key molecules such as triphosphate (ATP), glutathione (GSH), and homocarnosine (hCs) - central to metabolic processes in the human brain remain elusive or challenging to detect with upfield 1H-MRSI. Traditional 3D 1H-MRSI in vivo faces challenges, including a low signal-to-noise ratio and magnetization transfer effects with water, leading to prolonged measurement times and reduced resolution. To address these limitations, we propose a downfield 3D-MRSI method aimed at measuring downfield metabolites with enhanced spatial resolution, and speed acceptable for clinical practice at 7T. The CHEmical-shift selective Adiabatic Pulse (CHEAP) technique was integrated into echo-planar spectroscopic imaging (EPSI) readout sequence for downfield metabolite and water reference 3D-MRSI. Five healthy subjects and two glioma patients were scanned to test the feasibility. In this work, CHEAP-EPSI technique is shown to significantly enhance spatial the resolution to 0.37 ml while simultaneously reducing the scan time to 10.5 minutes. Its distinct advantages include low specific absorption rate, effective suppression of water and lipid signals, and minimal baseline distortions, making it a valuable tool for research or potentially diagnostic purposes. CHEAP-EPSI improves the detection sensitivity of downfield metabolites like N-acetyl-aspartate (NAA+) and DF8.18 (ATP&GSH+), and offers new possibilities for the study of metabolism in healthy and diseased brain.

physics.med-ph↗

arXiv2021

QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results

Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder translating DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties could enable clinical review of the most uncertain regions, thereby building trust and paving the way toward clinical translation. Several uncertainty estimation methods have recently been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019 and BraTS 2020 task on uncertainty quantification (QU-BraTS) and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentage of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, highlighting the need for uncertainty quantification in medical image analyses. Finally, in favor of transparency and reproducibility, our evaluation code is made publicly available at: https://github.com/RagMeh11/QU-BraTS.

eess.IV↗

arXiv2020

Uncertainty-driven refinement of tumor-core segmentation using 3D-to-2D networks with label uncertainty

The BraTS dataset contains a mixture of high-grade and low-grade gliomas, which have a rather different appearance: previous studies have shown that performance can be improved by separated training on low-grade gliomas (LGGs) and high-grade gliomas (HGGs), but in practice this information is not available at test time to decide which model to use. By contrast with HGGs, LGGs often present no sharp boundary between the tumor core and the surrounding edema, but rather a gradual reduction of tumor-cell density. Utilizing our 3D-to-2D fully convolutional architecture, DeepSCAN, which ranked highly in the 2019 BraTS challenge and was trained using an uncertainty-aware loss, we separate cases into those with a confidently segmented core, and those with a vaguely segmented or missing core. Since by assumption every tumor has a core, we reduce the threshold for classification of core tissue in those cases where the core, as segmented by the classifier, is vaguely defined or missing. We then predict survival of high-grade glioma patients using a fusion of linear regression and random forest classification, based on age, number of distinct tumor components, and number of distinct tumor cores. We present results on the validation dataset of the Multimodal Brain Tumor Segmentation Challenge 2020 (segmentation and uncertainty challenge), and on the testing set, where the method achieved 4th place in Segmentation, 1st place in uncertainty estimation, and 1st place in Survival prediction.

eess.IV↗