Flash-Radiomics: A Scalable Hybrid CPU-CUDA Engine for Standardized Scalar Radiomics and Accelerated Spatial…

Abstract

Background and Objectives: Spatial mapping retains the spatial distribution of radiomic features, but computational cost and fragmented software limit its use. We developed Flash-Radiomics with scalar extraction and spatial mapping, a central processing unit (CPU) backend, a hybrid Compute Unified Device Architecture (CUDA) backend, consistent feature names, and Hierarchical Data Format version 5 (HDF5) storage. Methods: We evaluated Image Biomarker Standardisation Initiative (IBSI) compliance, CPU-CUDA concordance, and end-to-end processing time. Compliance testing included 825 chapter 1 (IBSI-1) tests covering 165 high-consensus features and 323 chapter 2 (IBSI-2) tests with numerical references. Concordance testing included 1,148 scalar pairs and 93 spatial-map pairs. End-to-end processing time was measured five times per input volume of interest (VOI) size. Comparisons included the Medical Image Radiomics Processor (MIRP) and PyRadiomics for 102 shared scalar features and PyRadiomics for 93 shared spatial maps. Results: Both backends passed all 1,148 IBSI tests, and all paired results were concordant. At the largest scalar input, CPU required 76.343 s and hybrid CUDA 81.915 s; CPU was 4.7 times faster than MIRP and 190.7 times faster than PyRadiomics. At the largest spatial input completed by both backends, hybrid CUDA reduced processing time by 68.6% relative to CPU (79.280 versus 252.791 s). At PyRadiomics' largest completed spatial input, hybrid CUDA was 84.9 times faster. Conclusions: Flash-Radiomics unified standardized scalar extraction, spatial mapping, concordant CPU-CUDA results, and HDF5 storage. CPU processing time was similar or shorter for scalar extraction, whereas hybrid CUDA was faster for spatial mapping under the tested conditions.

PhenoMapR: scalable mapping of sample phenotypes to single-cell, spatial, and bulk transcriptomics data
B. A. Benard, C. K. Lalgudi, A. Azizi +1
bioRxiv8 Sep 2026PreprintCC BY-NCFull text1 citedBioinformatics & computational biologybioRxiv
Nine minutes is enough: An accelerated fMRI protocol for reliable connectivity mapping in healthy young adults.
Adrian Falkowski, Krzysztof Szwed
Dialogues in clinical neuroscience14 Oct 2026Peer-reviewedCC BYFull textNeuroscienceEurope PMC
HESTIA: Scalable Multimodal Integration of Histology and High-Resolution Spatial Transcriptomics for Robust Spatial Domain Identification
Z. Zhong, X. Zhu, J. Guo +2
bioRxiv14 May 2026PreprintCC BY-NCFull textBioinformatics & computational biologybioRxiv
SpCAST enables scalable and interpretable integration of single-cell RNA sequencing and single-cell-resolved spatial transcriptomics
Yiyang Zhang, Bokai Zhao, Xiaoru Zhang +4
arXiv10 Sep 2026PreprintCC BY-NC-SA 4.0Full textCell biologyarXiv
Accurate and scalable decontamination of imaging-based spatial transcriptomics via optimal transport
Y. Chen, Y. Liu, Z. Chao +9
bioRxiv9 Sep 2026PreprintCC BY-NC-NDFull textBioinformatics & computational biologybioRxiv

Cite

BibTeX RIS

BibTeX

@misc{ding2026flashradiomics,
  title = {{Flash-Radiomics: A Scalable Hybrid CPU-CUDA Engine for Standardized Scalar Radiomics and Accelerated Spatial Mapping}},
  author = {Shanli Ding and Yiyi Hu and Ziyu Fu and Chia-Hsin Lin and Ruihan Luo and Jaehee Chun and Xinyue Zhang and Osama Mawlawi},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.19190},
  eprint = {2609.19190},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.19190},
  note = {CC BY-NC-ND 4.0},
}

RIS

TY  - UNPB
TI  - Flash-Radiomics: A Scalable Hybrid CPU-CUDA Engine for Standardized Scalar Radiomics and Accelerated Spatial Mapping
AU  - Shanli Ding
AU  - Yiyi Hu
AU  - Ziyu Fu
AU  - Chia-Hsin Lin
AU  - Ruihan Luo
AU  - Jaehee Chun
AU  - Xinyue Zhang
AU  - Osama Mawlawi
PY  - 2026
DA  - 2026/09/15
PB  - arXiv
DO  - 10.48550/arxiv.2609.19190
UR  - https://arxiv.org/abs/2609.19190
AB  - Background and Objectives: Spatial mapping retains the spatial distribution of radiomic features, but computational cost and fragmented software limit its use. We developed Flash-Radiomics with scalar extraction and spatial mapping, a central processing unit (CPU) backend, a hybrid Compute Unified Device Architecture (CUDA) backend, consistent feature names, and Hierarchical Data Format version 5 (HDF5) storage. Methods: We evaluated Image Biomarker Standardisation Initiative (IBSI) compliance, CPU-CUDA concordance, and end-to-end processing time. Compliance testing included 825 chapter 1 (IBSI-1) tests covering 165 high-consensus features and 323 chapter 2 (IBSI-2) tests with numerical references. Concordance testing included 1,148 scalar pairs and 93 spatial-map pairs. End-to-end processing time was measured five times per input volume of interest (VOI) size. Comparisons included the Medical Image Radiomics Processor (MIRP) and PyRadiomics for 102 shared scalar features and PyRadiomics for 93 shared spatial maps. Results: Both backends passed all 1,148 IBSI tests, and all paired results were concordant. At the largest scalar input, CPU required 76.343 s and hybrid CUDA 81.915 s; CPU was 4.7 times faster than MIRP and 190.7 times faster than PyRadiomics. At the largest spatial input completed by both backends, hybrid CUDA reduced processing time by 68.6% relative to CPU (79.280 versus 252.791 s). At PyRadiomics' largest completed spatial input, hybrid CUDA was 84.9 times faster. Conclusions: Flash-Radiomics unified standardized scalar extraction, spatial mapping, concordant CPU-CUDA results, and HDF5 storage. CPU processing time was similar or shorter for scalar extraction, whereas hybrid CUDA was faster for spatial mapping under the tested conditions.
ER  -

Abstract

Related

Cite