A Systematic Benchmark of Intraoperative Ultrasound-to-MR Synthesis for Brain Tumour Surgery

• URL: http://arxiv.org/abs/2606.00630v1
• Date: Sat, 30 May 2026 09:05:24 GMT
• Title: A Systematic Benchmark of Intraoperative Ultrasound-to-MR Synthesis for Brain Tumour Surgery
• Abstract summary: Intraoperative ultrasound (ioUS) is a versatile, cost-effective modality in brain tumour surgery.<n>Most prior work evaluates a single architecture in isolation.<n>No benchmark has spanned architectural paradigms, inference regimes and downstream-task endpoints.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Intraoperative ultrasound (ioUS) is a versatile, cost-effective modality in brain tumour surgery, but its interpretation is difficult: acquisition planes are non-standard, artefacts are modality-specific, and its appearance differs markedly from the preoperative MRI on which surgical-planning tools, segmentation models and the surgeon's experience rely. Synthesising MRI-like images from ioUS could let this MRI-based infrastructure be reused intraoperatively without an extra scan. Most prior work evaluates a single architecture in isolation; to our knowledge, no benchmark has spanned architectural paradigms, inference regimes and downstream-task endpoints under a common protocol. We address this gap on the public ReMIND data set (76 patients; 153 paired ioUS/T2w and 104 paired ioUS/FLAIR studies; 60/16 patient-level train/held-out split). Six generators (four GAN baselines: Pix2Pix, SwinPix2Pix, CycleGAN, CUT; the transformer-augmented ResViT; and the few-step diffusion model SynDiff) were each trained under four inference regimes (2D, 2.5D, 2D + 3D-refinement, full-3D) and two targets (T2w only; T2w + FLAIR multi-task), yielding 48 experiments. Image-fidelity metrics (SSIM, PSNR, MAE, LPIPS) were complemented by an nnU-Net v2 downstream segmentation evaluation (tumour and resection cavity) and by subgroup analyses by histological grade and reoperation. No architecture dominated every axis, and, critically, perceptual quality tracked downstream utility most closely (LPIPS, r=-0.66, p<0.001), whereas higher SSIM was associated with worse utility (r=-0.64, p<0.001); SynDiff-2.5D best preserved downstream segmentation (U_Dice=0.55). Perceptual and downstream-task metrics should therefore be reported alongside or in preference to global SSIM, and architecture choice conditioned on surgical phase, patient history and clinical objective.

Related papers

• What neurosurgeons need to see: synthetic intra-operative MRI from ultrasound for brain-shift compensation in brain tumour surgery [0.0]
  We propose an end-to-end pipeline that generates a new whole-brain MRI volume in the preoperative imaging space.<n>In 14 subjects with 215 expert landmarks, the synthesis-anchored registration reduced the mean target registration error.<n>This provides an MRI-like update of the operative field with potential for integration into surgical-navigation.
  arXiv  Detail & Related papers  (2026-06-03T11:17:47Z)
• Cross Modality Image Translation In Medical Imaging Using Generative Frameworks [5.785096712074492]
  This work is a reproducible, standardized comparative evaluation of 3D I2I translation methods in oncological imaging.<n>We compare seven generative models, three Generative Adrial Networks (GANs: Pix2Pix, CycleGAN, SRGAN) and four latent generative models (Latent Diffusion Model, Latent Diffusion Model+ControlNet, Brownian Bridge, Flow Matching)<n>The results show that GANs outperform latent generative models across all tasks, with SRGAN achieving statistically significant superiority.
  arXiv  Detail & Related papers  (2026-05-13T15:41:44Z)
• A Systematic Benchmark of GAN Architectures for MRI-to-CT Synthesis [38.31064949197421]
  Generative Adversarial Network (GAN) architectures have been proposed for MRI-to-CT translation.<n>We present a benchmark of ten GAN evaluated on the SynthRAD2025 dataset across three anatomical districts.
  arXiv  Detail & Related papers  (2026-03-13T18:54:20Z)
• MRI Cross-Modal Synthesis: A Comparative Study of Generative Models for T1-to-T2 Reconstruction [0.42970700836450487]
  Cross-modal MRI synthesis involves generating images from one acquisition protocol using another.<n>This paper presents a comparison of three state-of-the-art generative models for T1-to-T2 MRI reconstruction: Pix2Pix GAN, CycleGAN, and Variational Autoencoder (VAE)
  arXiv  Detail & Related papers  (2026-02-05T19:07:58Z)
• MOIS-SAM2: Exemplar-based Segment Anything Model 2 for multilesion interactive segmentation of neurofibromas in whole-body MRI [0.0]
  Neurofibromatosis type 1 is a genetic disorder characterized by the development of numerous neurofibromas (NFs) throughout the body.<n>This study proposes a novel interactive segmentation model tailored to this challenge.
  arXiv  Detail & Related papers  (2025-09-23T17:42:24Z)
• The Brain Resection Multimodal Image Registration (ReMIND2Reg) 2025 Challenge [42.51640997446028]
  The ReMIND2Reg 2025 Challenge provides the largest public benchmark for this task, built upon the ReMIND dataset.<n>It offers 99 training cases, 5 validation cases, and 10 private test cases comprising paired 3D ceT1 MRI, T2 MRI, and post-resection 3D iUS volumes.<n>Data are provided without annotations for training, while validation and test performance are evaluated on manually annotated anatomical landmarks.
  arXiv  Detail & Related papers  (2025-08-13T09:31:06Z)
• ViCTr: Vital Consistency Transfer for Pathology Aware Image Synthesis [0.715632820500919]
  Existing methods struggle to maintain anatomical fidelity while accurately modeling pathological features.<n>ViCTr is a novel two-stage framework that combines a rectified flow trajectory with a Tweedie-corrected diffusion process to achieve high-fidelity, pathology-aware image synthesis.<n>To our knowledge, ViCTr is the first method to provide fine-grained, pathology-aware MRI synthesis with graded severity control.
  arXiv  Detail & Related papers  (2025-05-08T05:44:16Z)
• Analysis of the BraTS 2023 Intracranial Meningioma Segmentation Challenge [44.76736949127792]
  We describe the design and results from the BraTS 2023 Intracranial Meningioma Challenge.<n>The BraTS Meningioma Challenge differed from prior BraTS Glioma challenges in that it focused on meningiomas.<n>The top ranked team had a lesion-wise median dice similarity coefficient (DSC) of 0.976, 0.976, and 0.964 for enhancing tumor, tumor core, and whole tumor.
  arXiv  Detail & Related papers  (2024-05-16T03:23:57Z)
• CathFlow: Self-Supervised Segmentation of Catheters in Interventional Ultrasound Using Optical Flow and Transformers [66.15847237150909]
  We introduce a self-supervised deep learning architecture to segment catheters in longitudinal ultrasound images. The network architecture builds upon AiAReSeg, a segmentation transformer built with the Attention in Attention mechanism. We validated our model on a test dataset, consisting of unseen synthetic data and images collected from silicon aorta phantoms.
  arXiv  Detail & Related papers  (2024-03-21T15:13:36Z)
• Learned Local Attention Maps for Synthesising Vessel Segmentations [43.314353195417326]
  We present an encoder-decoder model for synthesising segmentations of the main cerebral arteries in the circle of Willis (CoW) from only T2 MRI. It uses learned local attention maps generated by dilating the segmentation labels, which forces the network to only extract information from the T2 MRI relevant to synthesising the CoW.
  arXiv  Detail & Related papers  (2023-08-24T15:32:27Z)
• Towards Autonomous Atlas-based Ultrasound Acquisitions in Presence of Articulated Motion [48.52403516006036]
  This paper proposes a vision-based approach allowing autonomous robotic US limb scanning. To this end, an atlas MRI template of a human arm with annotated vascular structures is used to generate trajectories. In all cases, the system can successfully acquire the planned vascular structure on volunteers' limbs.
  arXiv  Detail & Related papers  (2022-08-10T15:39:20Z)
• Segmentation of the Myocardium on Late-Gadolinium Enhanced MRI based on 2.5 D Residual Squeeze and Excitation Deep Learning Model [55.09533240649176]
  The aim of this work is to develop an accurate automatic segmentation method based on deep learning models for the myocardial borders on LGE-MRI. A total number of 320 exams (with a mean number of 6 slices per exam) were used for training and 28 exams used for testing. The performance analysis of the proposed ensemble model in the basal and middle slices was similar as compared to intra-observer study and slightly lower at apical slices.
  arXiv  Detail & Related papers  (2020-05-27T20:44:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.