aiqbench analysis
This research presents a novel two-stage deep learning framework for segmenting multiple myeloma lesions on whole-body diffusion-weighted imaging, addressing challenges in anatomical delineation and marrow specificity. By generating bone regions of interest from ADC images without manual labels and utilizing an Anatomy-guided Multimodal U-Net, the method achieves a mean Dice score of 76.2%, outperforming existing approaches that rely on costly annotations or simple channel fusion. The study highlights significant advancements in medical image analysis where AI serves as the central mechanism for improving diagnostic precision in oncology.
Multiple Myeloma Lesion Segmentation on Whole-Body Diffusion-Weighted Imaging via Efficient Anatomical Anticipation and Multimodal Confirmation
arXiv:2609.06165v1 Announce Type: cross Abstract: Whole-body diffusion-weighted imaging (WB-DWI) is widely used for multiple myeloma (MM) assessment, yet automated lesion segmentation remains challenging due to limited anatomical delineation and the low specificity of marrow hyperintensity. Existing studies have introduced bone region-of-interest (ROI) information and apparent diffusion coefficient (ADC) maps to mitigate these ambiguities, but practical limitations remain. Bone ROI construction often relies on costly manual annotation, image registration, or dedicated bone models, while ADC is usually incorporated only through simple channel fusion, limiting its ability to provide complementary structural and lesion-discriminative cues. To address these limitations, we propose a two-stage framework for MM lesion segmentation on WB-DWI. In the first stage, we train a bone ROI generation model from ADC images without dedicated bone labels, providing an efficient and practical anatomical prior for lesion analysis. In the second stage, we propose Anatomy-guided Multimodal U-Net (AMU-Net), which leverages ADC in a manner consistent with clinical lesion assessment rather than treating it as a generic auxiliary modality. Extensive experiments demonstrate the effectiveness and practicality of the proposed method. It achieves the best overall performance among the evaluated methods, with a mean Dice score of 76.2%.
Abstract:Whole-body diffusion-weighted imaging (WB-DWI) is widely used for multiple myeloma (MM) assessment, yet automated lesion segmentation remains challenging due to limited anatomical delineation and the low specificity of marrow hyperintensity. Existing studies have introduced bone region-of-interest (ROI) information and apparent diffusion coefficient (ADC) maps to mitigate these ambiguities, but practical limitations remain. Bone ROI construction often relies on costly manual annotation, image registration, or dedicated bone models, while ADC is usually incorporated only through simple channel fusion, limiting its ability to provide complementary structural and lesion-discriminative cues. To address these limitations, we propose a two-stage framework for MM lesion segmentation on WB-DWI. In the first stage, we train a bone ROI generation model from ADC images without dedicated bone labels, providing an efficient and practical anatomical prior for lesion analysis. In the second stage, we propose Anatomy-guided Multimodal U-Net (AMU-Net), which leverages ADC in a manner consistent with clinical lesion assessment rather than treating it as a generic auxiliary modality. Extensive experiments demonstrate the effectiveness and practicality of the proposed method. It achieves the best overall performance among the evaluated methods, with a mean Dice score of 76.2%.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2609.06165 [cs.CV]
(or arXiv:2609.06165v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.06165 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 288 words
Related coverage
Synthesize Realistic 3D Medical Images at Scale to Ship Pre‑Trained Models
NVIDIA · May 22, 2026
The Entangled Dimensions of Decision Theory
LessWrong · Jul 30, 2026
OpenRouter: from Seed to Stripe — with OpenRouter’s Alex Atallah & AMP’s Anjney Midha
Latent Space · Sep 25, 2026
Lesion-DDPM: Lesion-Enhanced 3D Diffusion for MS MRI Synthesis
arXiv · Jun 16, 2026