HaN-Seg: The head and neck organ-at-risk CT and MR segmentation challenge

Radiotherapy and Oncology, Journal Year: 2024, Volume and Issue: 198, P. 110410 - 110410

Published: June 24, 2024

To promote the development of auto-segmentation methods for head and neck (HaN) radiation treatment (RT) planning that exploit information computed tomography (CT) magnetic resonance (MR) imaging modalities, we organized HaN-Seg: The Head Neck Organ-at-Risk CT MR Segmentation Challenge. challenge task was to automatically segment 30 organs-at-risk (OARs) HaN region in 14 withheld test cases given availability 42 publicly available training cases. Each case consisted one contrast-enhanced T1-weighted image same patient, with up corresponding reference OAR delineation masks. performance evaluated terms Dice similarity coefficient (DSC) 95-percentile Hausdorff distance (HD95), statistical ranking applied each metric by pairwise comparison submitted using Wilcoxon signed-rank test. While 23 teams registered challenge, only seven their final phase. top-performing team achieved a DSC 76.9 % HD95 3.5 mm. All participating utilized architectures based on U-Net, winning leveraging rigid registration combined network entry-level concatenation both modalities. This simulated real-world clinical scenario providing non-registered images varying fields-of-view voxel sizes. Remarkably, segmentation surpassing inter-observer agreement dataset. These results set benchmark future research this dataset paired multi-modal general.

Language: Английский

---

Development of an MR-only radiotherapy treatment planning workflow using a commercial synthetic CT generator for brain and head & neck tumor patients

Zeitschrift für Medizinische Physik, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 1, 2025

In magnetic resonance (MR)-only radiotherapy (RT) workflows, synthetic computed tomography images (sCT) are needed as a surrogate for dose calculation. Commercial and certified sCT algorithms became recently available, but many have not been evaluated in clinical setting, especially the head neck tumor (HN) region. this study, an MRI-only workflow using commercial generator photon beam therapy brain HN body sites was terms of calculation accuracy, modelling immobilization devices, well usability autosegmentation. For 13 10 cancer patients, MR scans T1W mDIXON sequences were retrospectively collected. Four all patients scanned RT treatment position with devices. All MRIs converted to MRCAT algorithm (Philips, Eindhoven, The Netherlands). underwent standard planning CT (pCT) segmentation VMAT planning. rigidly registered pCT contours transferred sCT. dosimetric evaluation based calculation, plans recalculated on D1% Dmean compared structures between sCT, D95%, D98% targets only. MR-invisible device modelling, MR-visible markers placed into geometric robustness analysis performed same target dose-volume parameters. organs-at-risk (OARs) autosegmentation, both autosegmented clinically established CT-based autocontouring software. agreement analyzed by similar parameters dice similarity (DSC) Hausforff distance (HD). overall median deviation (± interquartile range) including model 1.1 ± 0.4% volumes, 1.3 1.2% OAR, 0.4 0.7% volumes 0.9% OAR. over autocontours resulted DSC = 0.82 OAR 0.79 MR-only software package feasible tumors, acceptable accuracy. devices could be modelled system autosegmentation sCTs tool feasible.

Language: Английский

---

AI in MRI: Computational Frameworks for a Faster, Optimized, and Automated Imaging Workflow

Bioengineering, Journal Year: 2023, Volume and Issue: 10(4), P. 492 - 492

Published: April 20, 2023

Over the last decade, artificial intelligence (AI) has made an enormous impact on a wide range of fields, including science, engineering, informatics, finance, and transportation [...].

Language: Английский

---

The future of MRI in radiation therapy: Challenges and opportunities for the MR community

Magnetic Resonance in Medicine, Journal Year: 2022, Volume and Issue: 88(6), P. 2592 - 2608

Published: Sept. 21, 2022

Abstract Radiation therapy is a major component of cancer treatment pathways worldwide. The main aim this to achieve tumor control through the delivery ionizing radiation while preserving healthy tissues for minimal toxicity. Because relies on accurate localization target and surrounding tissues, imaging plays crucial role throughout chain. In planning phase, radiological images are essential defining volumes organs‐at‐risk, as well providing elemental composition (e.g., electron density) information dose calculations. At treatment, onboard informs patient setup could be used guide placement sites affected by motion. Imaging also an important tool response assessment plan adaptation. MRI, with its excellent soft tissue contrast capacity probe functional properties, holds great untapped potential transforming paradigms in therapy. MR Therapy ISMRM Study Group was established provide forum within community discuss unmet needs fuel opportunities further advancement MRI applications. During summer 2021, study group organized first virtual workshop, attended diverse international clinicians, scientists, clinical physicists, explore our predictions future next 25 years. This article reviews findings from event considers challenges reaching vision expanding field.

Language: Английский

---

Stereotactic body radiotherapy of central lung tumours using a 1.5 T MR-linac: First clinical experiences

Clinical and Translational Radiation Oncology, Journal Year: 2024, Volume and Issue: 45, P. 100744 - 100744

Published: Feb. 15, 2024

MRI-guidance may aid better discrimination between Organs at Risk (OARs) and target volumes in proximity of the mediastinum. We report first clinical experiences with Stereotactic Body Radiotherapy (SBRT) (ultra)central lung tumours on a 1.5 T MR-linac.

Language: Английский

---

How Imaging Advances Are Defining the Future of Precision Radiation Therapy

Radiographics, Journal Year: 2024, Volume and Issue: 44(2)

Published: Jan. 11, 2024

Radiation therapy is fundamental in the treatment of cancer. Imaging has always played a central role radiation oncology. Integrating imaging technology into irradiation devices increased precision and accuracy dose delivery decreased toxic effects treatment. Although CT become standard modality therapy, development recently introduced next-generation techniques improved diagnostic therapeutic decision making Functional molecular techniques, as well other advanced modalities such SPECT, yield information about anatomic biologic characteristics tumors for workflow. In clinical practice, they can be useful characterizing tumor phenotypes, delineating volumes, planning treatment, determining patients' prognoses, predicting effects, assessing responses to detecting relapse. Next-generation enable personalization based on greater understanding factors. It used map characteristics, metabolic pathways, vascularity, cellular proliferation, hypoxia, that are known define phenotype. also consider heterogeneity by highlighting areas at risk resistance focused escalation, which impact process patient outcomes. The authors review possible contributions patients undergoing therapy. addition, roles radio(geno)mics limitations these hurdles introducing them practice discussed.

Language: Английский

---

Clinical feasibility of deep learning-based synthetic CT images from T2-weighted MR images for cervical cancer patients compared to MRCAT

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: April 12, 2024

Abstract This work aims to investigate the clinical feasibility of deep learning-based synthetic CT images for cervix cancer, comparing them MR calculating attenuation (MRCAT). Patient cohort with 50 pairs T2-weighted and from cervical cancer patients was split into 40 training 10 testing phases. We conducted deformable image registration Nyul intensity normalization maximize similarity between as a preprocessing step. The processed were plugged learning model, generative adversarial network. To prove feasibility, we assessed accuracy in using structural (SSIM) mean-absolute-error (MAE) dosimetry gamma passing rate (GPR). Dose calculation performed on true commercial Monte Carlo algorithm. Synthetic generated by outperformed MRCAT 1.5% SSIM, 18.5 HU MAE. In dosimetry, DL-based achieved 98.71% 96.39% GPR at 1% 1 mm criterion 10% 60% cut-off values prescription dose, which 0.9% 5.1% greater GPRs over images.

Language: Английский

---

Live‐view 4D GRASP MRI: A framework for robust real‐time respiratory motion tracking with a sub‐second imaging latency

Magnetic Resonance in Medicine, Journal Year: 2023, Volume and Issue: 90(3), P. 1053 - 1068

Published: May 19, 2023

To propose a framework called live-view golden-angle radial sparse parallel (GRASP) MRI for low-latency and high-fidelity real-time volumetric MRI.

Language: Английский

---

Magnetic Resonance Imaging Sequences and Technologies in Adaptive Radiation Therapy

International Journal of Radiation Oncology*Biology*Physics, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

---

MRI motion artifact reduction using a conditional diffusion probabilistic model (MAR‐CDPM)

Medical Physics, Journal Year: 2023, Volume and Issue: 51(4), P. 2598 - 2610

Published: Nov. 27, 2023

Abstract Background High‐resolution magnetic resonance imaging (MRI) with excellent soft‐tissue contrast is a valuable tool utilized for diagnosis and prognosis. However, MRI sequences long acquisition time are susceptible to motion artifacts, which can adversely affect the accuracy of post‐processing algorithms. Purpose This study proposes novel retrospective correction method named “motion artifact reduction using conditional diffusion probabilistic model” (MAR‐CDPM). The MAR‐CDPM aimed remove artifacts from multicenter three‐dimensional contrast‐enhanced T1 magnetization‐prepared rapid gradient echo (3D ceT1 MPRAGE) brain dataset different tumor types. Materials methods employed two publicly accessible datasets: one containing 3D MPRAGE 2D T2‐fluid attenuated inversion recovery (FLAIR) images 230 patients diverse tumors, other comprising T1‐weighted (T1W) 148 healthy volunteers, included real artifacts. former was used train evaluate model in silico data, latter performance A simulation performed k ‐space domain generate an minor, moderate, heavy distortion levels. process then implemented convert structure data into Gaussian noise by gradually increasing network Unet backbone trained reverse distorted structured data. scenarios: conditioning on step process, both T2‐FLAIR images. quantitatively qualitatively compared supervised Unet, conditioned T2‐FLAIR, CycleGAN, Pix2pix, Pix2pix models. To quantify spatial distortions level remaining after applying models, quantitative metrics were reported including normalized mean squared error (NMSE), structural similarity index (SSIM), multiscale (MS‐SSIM), peak signal‐to‐noise ratio (PSNR), visual information fidelity (VIF), magnitude deviation (MS‐GMSD). Tukey's Honestly Significant Difference multiple comparison test difference between models where p ‐value considered statistically significant. Results Qualitatively, outperformed these preserving regions. It also successfully preserved boundaries like method. Our recovered motion‐free highest PSNR VIF all levels differences significant ( ‐values ). In addition, our t ) terms NMSE, MS‐SSIM, SSIM, MS‐GMSD. Moreover, only generative had comparable performances Conclusions could MPRAGE. particularly beneficial elderly who may experience involuntary movements during high‐resolution times.

Language: Английский

---