Diffusion-Refined Segmentation and Vision-Language Interpretation for Pediatric Brain Tumor MRI

• URL: http://arxiv.org/abs/2606.14072v1
• Date: Fri, 12 Jun 2026 03:38:40 GMT
• Title: Diffusion-Refined Segmentation and Vision-Language Interpretation for Pediatric Brain Tumor MRI
• Abstract summary: We present a two-stage deep learning framework for improving pediatric brain MRI segmentation.<n>First, we evaluate 3D Res U-Net and Swin-UNETR baselines on BraTS-PEDs MRI scans.<n>Second, we introduce diffusion-based refinement models conditioned on coarse Swin-UNETR predictions.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Accurate pediatric brain tumor segmentation remains challenging due to limited annotated data, heterogeneous imaging phenotypes, diffuse tumor boundaries, and class imbalance across tumor subregions. Here, we present a two-stage deep learning framework for improving multi-modal pediatric brain MRI segmentation and clinical interpretation. First, we evaluate 3D Res U-Net and Swin-UNETR baselines on BraTS-PEDs MRI scans, using four co-registered modalities to predict tumor core, whole tumor, and enhancing tumor regions. Second, we introduce diffusion-based refinement models conditioned on coarse Swin-UNETR predictions, including a 3D DDPM refiner and MedSegDiff. Conditioning substantially improves diffusion stability and performance, particularly for enhancing tumor boundary segmentation. Conditioned MedSegDiff achieves the strongest boundary agreement with the lowest HD95. Finally, predicted tumor volumes and representative segmentation overlays are integrated with a multimodal language model to generate structured radiology-style reports. Together, our results suggest that coarse-to-refined diffusion segmentation can improve pediatric tumor boundary delineation and support end-to-end interpretable AI-assisted neuro-oncology workflows.

Related papers

• AnaDiffusion: Anatomically CompositionalLatent Diffusion for Controllable 3D Brain MRI Generation [58.56402940400457]
  3D brain MRI generation has made significant advances in medical imaging, simulation, and controllable anatomical analysis.<n>We introduce AnaDiffusion, an anatomically compositional latent diffusion framework that factorizes the generation process into distinct, anatomically meaningful regions.<n>AnaDiffusion produces both explicit part assets and a globally coherent volume, enabling controllable part editing.
  arXiv  Detail & Related papers  (2026-08-24T09:16:42Z)
• D3Seg: Dependency-Aware Diffusion for Brain Tumor Segmentation with Missing Modalities [54.87947751720332]
  We propose a novel segmentation model D3Seg to maintain stable performance under missing-modality settings.<n>The proposed model achieves approximately 1.5-2.0% Dice improvement on enhancing tumor (ET) and around 1.0% on tumor core (TC) across multiple missing modality configurations.
  arXiv  Detail & Related papers  (2026-05-21T09:55:42Z)
• DRBD-Mamba for Robust and Efficient Brain Tumor Segmentation with Analytical Insights [54.87947751720332]
  Accurate brain tumor segmentation is significant for clinical diagnosis and treatment.<n>Mamba-based State Space Models have demonstrated promising performance.<n>We propose a dual-resolution bi-directional Mamba that captures multi-scale long-range dependencies with minimal computational overhead.
  arXiv  Detail & Related papers  (2025-10-16T07:31:21Z)
• VGDM: Vision-Guided Diffusion Model for Brain Tumor Detection and Segmentation [2.538209532048867]
  VGDM is a vision-guided diffusion framework for brain tumor detection and segmentation.<n>It embeds a vision transformer at the core of the diffusion process.<n>Transformer backbone enables more effective modeling of spatial relationships across entire MRI volumes.<n>It mitigates voxel-level errors and recovers fine-grained tumor details.
  arXiv  Detail & Related papers  (2025-10-02T14:52:08Z)
• SynBT: High-quality Tumor Synthesis for Breast Tumor Segmentation by 3D Diffusion Model [0.15833270109954134]
  We propose a 3D medical diffusion model, called SynBT, to generate high-quality breast tumor in contrast-enhanced MRI images.<n>The proposed model consists of a patch-to-volume autoencoder, which is able to compress the high-resolution MRIs into compact latent space.<n>We evaluate the proposed method for a tumor segmentation task, which demonstrated the proposed high-quality tumor synthesis method can facilitate the common segmentation models.
  arXiv  Detail & Related papers  (2025-09-03T12:33:54Z)
• MAST-Pro: Dynamic Mixture-of-Experts for Adaptive Segmentation of Pan-Tumors with Knowledge-Driven Prompts [54.915060471994686]
  We propose MAST-Pro, a novel framework that integrates dynamic Mixture-of-Experts (D-MoE) and knowledge-driven prompts for pan-tumor segmentation.<n>Specifically, text and anatomical prompts provide domain-specific priors guiding tumor representation learning, while D-MoE dynamically selects experts to balance generic and tumor-specific feature learning.<n>Experiments on multi-anatomical tumor datasets demonstrate that MAST-Pro outperforms state-of-the-art approaches, achieving up to a 5.20% improvement in average improvement while reducing trainable parameters by 91.04%, without compromising accuracy.
  arXiv  Detail & Related papers  (2025-03-18T15:39:44Z)
• Unified HT-CNNs Architecture: Transfer Learning for Segmenting Diverse Brain Tumors in MRI from Gliomas to Pediatric Tumors [2.104687387907779]
  We introduce HT-CNNs, an ensemble of Hybrid Transformers and Convolutional Neural Networks optimized through transfer learning for varied brain tumor segmentation.<n>This method captures spatial and contextual details from MRI data, fine-tuned on diverse datasets representing common tumor types.<n>Our findings underscore the potential of transfer learning and ensemble approaches in medical image segmentation, indicating a substantial enhancement in clinical decision-making and patient care.
  arXiv  Detail & Related papers  (2024-12-11T09:52:01Z)
• Mask-Enhanced Segment Anything Model for Tumor Lesion Semantic Segmentation [48.107348956719775]
  We introduce Mask-Enhanced SAM (M-SAM), an innovative architecture tailored for 3D tumor lesion segmentation. We propose a novel Mask-Enhanced Adapter (MEA) within M-SAM that enriches the semantic information of medical images with positional data from coarse segmentation masks. Our M-SAM achieves high segmentation accuracy and also exhibits robust generalization.
  arXiv  Detail & Related papers  (2024-03-09T13:37:02Z)
• A unified 3D framework for Organs at Risk Localization and Segmentation for Radiation Therapy Planning [56.52933974838905]
  Current medical workflow requires manual delineation of organs-at-risk (OAR) In this work, we aim to introduce a unified 3D pipeline for OAR localization-segmentation. Our proposed framework fully enables the exploitation of 3D context information inherent in medical imaging.
  arXiv  Detail & Related papers  (2022-03-01T17:08:41Z)
• Cross-Modality Deep Feature Learning for Brain Tumor Segmentation [158.8192041981564]
  This paper proposes a novel cross-modality deep feature learning framework to segment brain tumors from the multi-modality MRI data. The core idea is to mine rich patterns across the multi-modality data to make up for the insufficient data scale. Comprehensive experiments are conducted on the BraTS benchmarks, which show that the proposed cross-modality deep feature learning framework can effectively improve the brain tumor segmentation performance.
  arXiv  Detail & Related papers  (2022-01-07T07:46:01Z)
• Dilated Inception U-Net (DIU-Net) for Brain Tumor Segmentation [0.9176056742068814]
  We propose a new end-to-end brain tumor segmentation architecture based on U-Net. Our proposed model performed significantly better than the state-of-the-art U-Net-based model for tumor core and whole tumor segmentation.
  arXiv  Detail & Related papers  (2021-08-15T16:04:09Z)
• Expectation-Maximization Regularized Deep Learning for Weakly Supervised Tumor Segmentation for Glioblastoma [8.24450401153384]
  We present an Expectation-Maximization (EM) Regularized Deep Learning (EMReDL) model for the weakly supervised tumor segmentation. The proposed framework was tailored to glioblastoma, a type of malignant tumor characterized by its diffuse infiltration into the surrounding brain tissue.
  arXiv  Detail & Related papers  (2021-01-21T18:14:43Z)

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.