16 research outputs found
Sine Wave Normalization for Deep Learning-Based Tumor Segmentation in CT/PET Imaging
Get PDFThis report presents a normalization block for automated tumor segmentation in CT/PET scans, developed for the autoPET III Challenge. The key innovation is the introduction of the SineNormal, which applies periodic sine transformations to PET data to enhance lesion detection. By highlighting intensity variations and producing concentric ring patterns in PET highlighted regions, the model aims to improve segmentation accuracy, particularly for challenging multitracer PET datasets. The code for this project is available on GitHub (https://github.com/BBQtime/Sine-Wave-Normalization-for-Deep-Learning-Based-Tumor-Segmentation-in-CT-PET).Report for Team WukongRT in the AutoPET III Challeng
Continuous sPatial-Temporal Deformable Image Registration (CPT-DIR) for motion modelling in radiotherapy: beyond classic voxel-based methods
Get PDFBackground and purpose: Deformable image registration (DIR) is a crucial tool
in radiotherapy for extracting and modelling organ motion. However, when
significant changes and sliding boundaries are present, it faces compromised
accuracy and uncertainty, determining the subsequential contour propagation and
dose accumulation procedures. Materials and methods: We propose an implicit
neural representation (INR)-based approach modelling motion continuously in
both space and time, named Continues-sPatial-Temporal DIR (CPT-DIR). This
method uses a multilayer perception (MLP) network to map 3D coordinate (x,y,z)
to its corresponding velocity vector (vx,vy,vz). The displacement vectors
(dx,dy,dz) are then calculated by integrating velocity vectors over time. The
MLP's parameters can rapidly adapt to new cases without pre-training, enhancing
optimisation. The DIR's performance was tested on the DIR-Lab dataset of 10
lung 4DCT cases, using metrics of landmark accuracy (TRE), contour conformity
(Dice) and image similarity (MAE). Results: The proposed CPT-DIR can reduce
landmark TRE from 2.79mm to 0.99mm, outperforming B-splines' results for all
cases. The MAE of the whole-body region improves from 35.46HU to 28.99HU.
Furthermore, CPT-DIR surpasses B-splines for accuracy in the sliding boundary
region, lowering MAE and increasing Dice coefficients for the ribcage from
65.65HU and 90.41% to 42.04HU and 90.56%, versus 75.40HU and 89.30% without
registration. Meanwhile, CPT-DIR offers significant speed advantages,
completing in under 15 seconds compared to a few minutes with the conventional
B-splines method. Conclusion: Leveraging the continuous representations, the
CPT-DIR method significantly enhances registration accuracy, automation and
speed, outperforming traditional B-splines in landmark and contour precision,
particularly in the challenging areas
A Bio‐Inspired Structurally‐Responsive and Polysulfides‐Mobilizable Carbon/Sulfur Composite as Long‐Cycling Life Li−S Battery Cathode
No full textDiffusion-SDF: Text-to-Shape via Voxelized Diffusion
Get PDFWith the rising industrial attention to 3D virtual modeling technology,
generating novel 3D content based on specified conditions (e.g. text) has
become a hot issue. In this paper, we propose a new generative 3D modeling
framework called Diffusion-SDF for the challenging task of text-to-shape
synthesis. Previous approaches lack flexibility in both 3D data representation
and shape generation, thereby failing to generate highly diversified 3D shapes
conforming to the given text descriptions. To address this, we propose a SDF
autoencoder together with the Voxelized Diffusion model to learn and generate
representations for voxelized signed distance fields (SDFs) of 3D shapes.
Specifically, we design a novel UinU-Net architecture that implants a
local-focused inner network inside the standard U-Net architecture, which
enables better reconstruction of patch-independent SDF representations. We
extend our approach to further text-to-shape tasks including text-conditioned
shape completion and manipulation. Experimental results show that Diffusion-SDF
generates both higher quality and more diversified 3D shapes that conform well
to given text descriptions when compared to previous approaches. Code is
available at: https://github.com/ttlmh/Diffusion-SDFComment: Accepted to CVPR 2023, project page:
https://ttlmh.github.io/DiffusionSDF
Amorphous CoFeBO nanoparticles as highly active electrocatalysts for efficient water oxidation reaction
No full textA proof-of-concept study of direct magnetic resonance imaging-based proton dose calculation for brain tumors via neural networks with Monte Carlo-comparable accuracy
No full textISSN:2405-631
Learning Dual-Level Deformable Implicit Representation for Real-World Scale Arbitrary Super-Resolution
No full textScale arbitrary super-resolution based on implicit image function gains increasing popularity since it can better represent the visual world in a continuous manner. However, existing scale arbitrary works are trained and evaluated on simulated datasets, where low-resolution images are generated from their ground truths by the simplest bicubic downsampling. These models exhibit limited generalization to real-world scenarios due to the greater complexity of real-world degradations. To address this issue, we build a RealArbiSR dataset, a new real-world super-resolution benchmark with both integer and non-integer scaling factors fo the training and evaluation of real-world scale arbitrary super-resolution. Moreover, we propose a Dual-level Deformable Implicit Representation (DDIR) to solve real-world scale arbitrary super-resolution. Specifically, we design the appearance embedding and deformation field to handle both image-level and pixel-level deformations caused by real-world degradations. The appearance embedding models the characteristics of low-resolution inputs to deal with photometric variations at different scales, and the pixel-based deformation field learns RGB differences which result from the deviations between the real-world and simulated degradations at arbitrary coordinates. Extensive experiments show our trained model achieves state-of-the-art performance on the RealArbiSR and RealSR benchmarks for real-world scale arbitrary super-resolution. The dataset and code are available at \url{https://github.com/nonozhizhiovo/RealArbiSR}
A proof-of-concept study of direct magnetic resonance imaging-based proton dose calculation for brain tumors via neural networks with Monte Carlo-comparable accuracy
No full textBackground and purpose: Proton therapy currently relies on computed tomography (CT) imaging despite magnetic resonance imaging’s (MRI) superior soft-tissue contrast. While synthetic CTs can be generated from magnetic resonance (MR) images, this introduces additional complexity. We present a deep learning-based dose engine enabling direct proton dose calculation from MR images to streamline workflows while maintaining Monte Carlo (MC)-level accuracy. Materials and methods: Using paired MR-CT scans from 39 brain tumor patients (29/3/7 for training/validation/testing), we developed a deep learning framework using various sequence models for individual proton pencil beam dose prediction. The framework processes beam-eye-view patches from 2000 random beam configurations per patient, varying in angles and energy, with corresponding MC dose distributions pre-calculated on CT. Models using CT images were trained for comparison. Results: The xLSTM architecture performed best for both MR and CT-based scenarios among the evaluated sequence models. For full treatment plans, our model achieved gamma pass rates with median 99.8 % (range: 98.6 %–99.9 %, 1 mm/1%), and median percentage dose errors of 0.2 % (range: 0.1 %–0.4 %) within patient bodies and 1.3 % (range: 0.8 %–3.7 %) in high-dose regions (>90 % prescription dose). The model required only 3 ms per beam prediction compared to 2 s for MC simulation. Conclusion: This study demonstrated the feasibility of MC-quality proton dose calculations directly from MR images for brain tumor patients, achieving comparable accuracy with faster computation and simplified implementation
Activism via attention: interpretable spatiotemporal learning to forecast protest activities
Get PDFAbstract The diffusion of new information and communication technologies—social media in particular—has played a key role in social and political activism in recent decades. In this paper, we propose a theory-motivated, spatiotemporal learning approach, ActAttn, that leverages social movement theories and a deep learning framework to examine the relationship between protest events and their social and geographical contexts as reflected in social media discussions. To do so, we introduce a novel predictive framework that incorporates a new design of attentional networks, and which effectively learns the spatiotemporal structure of features. Our approach is not only capable of forecasting the occurrence of future protests, but also provides theory-relevant interpretations—it allows for interpreting what features, from which places, have significant contributions on the protest forecasting model, as well as how they make those contributions. Our experiment results from three movement events indicate that ActAttn achieves superior forecasting performance, with interesting comparisons across the three events that provide insights into these recent movements
