Image-Conditioned Diffusion Models for Quality Assurance of Organ-at-Risk Segmentations in Radiotherapy
研究使用图像条件扩散模型来检测头颈部CT中器官风险分割的错误,以提高放射治疗规划的质量保证。
研究使用图像条件扩散模型来检测头颈部CT中器官风险分割的错误,以提高放射治疗规划的质量保证。
研究使用模糊精度方法提高基于PPG信号的皮肤色调分类准确性,通过三种机器学习方法实现,其中树模型在原始信号上达到最高模糊精度96%。
This study addresses the challenge of detecting subtle, age-related morphological changes in arterial pulse waveforms to facilitate early assessment of cardiovascular health risks. To this end, it introduces a novel approach that, for the first time, integrates Symmetric Projection Attractor Reconstruction (SPAR) with convolutional neural networks to transform pulse wave time series—acquired via photoplethysmography (PPG) and arterial tonometry—into image representations. These SPAR-derived images are employed to discriminate between adjacent age groups (35–40 years versus 50–55 years) within a healthy population. The method achieves F1 scores exceeding 70% on both internal and external test sets, demonstrating that SPAR effectively encodes discriminative age-related features. This work thus establishes a new paradigm for non-invasive vascular age estimation.
This work addresses the performance degradation of atrial fibrillation (AF) classification from photoplethysmography (PPG) signals collected by wearable devices under cross-domain scenarios, where distribution shifts between source and target domains adversely affect model generalization. To tackle this challenge, the authors propose a novel framework that integrates deep generative domain adaptation with decision-theoretic uncertainty quantification. Specifically, a generative model aligns target-domain features to the source domain, while— for the first time—a task-oriented uncertainty estimation mechanism is embedded within the domain adaptation pipeline to assess the reliability of generated signals for downstream AF classification. Experimental results demonstrate that the proposed approach not only significantly improves cross-domain classification accuracy but also enhances the trustworthiness of synthesized data and the overall robustness of the system.
This work proposes an online data augmentation method grounded in control theory to address the limitations of handcrafted, non-adaptive augmentation strategies commonly used in visual recognition tasks. By constructing a control-loop architecture that leverages operation-specific response curves, the approach dynamically adjusts the intensity distribution of individual augmentation operations during training—eliminating the need for preset parameters and automatically suppressing augmentations detrimental to model performance. Experimental results demonstrate that, when applied with WideResNet-28-10 on CIFAR-10, CIFAR-100, and SVHN-core, the method achieves performance on par with state-of-the-art data augmentation techniques, offering a task-adaptive and fully automated dynamic augmentation mechanism without manual intervention.
研究使用图像条件扩散模型来检测头颈部CT中器官风险分割的错误,以提高放射治疗规划的质量保证。
研究使用模糊精度方法提高基于PPG信号的皮肤色调分类准确性,通过三种机器学习方法实现,其中树模型在原始信号上达到最高模糊精度96%。
This study addresses the challenge of detecting subtle, age-related morphological changes in arterial pulse waveforms to facilitate early assessment of cardiovascular health risks. To this end, it introduces a novel approach that, for the first time, integrates Symmetric Projection Attractor Reconstruction (SPAR) with convolutional neural networks to transform pulse wave time series—acquired via photoplethysmography (PPG) and arterial tonometry—into image representations. These SPAR-derived images are employed to discriminate between adjacent age groups (35–40 years versus 50–55 years) within a healthy population. The method achieves F1 scores exceeding 70% on both internal and external test sets, demonstrating that SPAR effectively encodes discriminative age-related features. This work thus establishes a new paradigm for non-invasive vascular age estimation.
This work addresses the performance degradation of atrial fibrillation (AF) classification from photoplethysmography (PPG) signals collected by wearable devices under cross-domain scenarios, where distribution shifts between source and target domains adversely affect model generalization. To tackle this challenge, the authors propose a novel framework that integrates deep generative domain adaptation with decision-theoretic uncertainty quantification. Specifically, a generative model aligns target-domain features to the source domain, while— for the first time—a task-oriented uncertainty estimation mechanism is embedded within the domain adaptation pipeline to assess the reliability of generated signals for downstream AF classification. Experimental results demonstrate that the proposed approach not only significantly improves cross-domain classification accuracy but also enhances the trustworthiness of synthesized data and the overall robustness of the system.
This work proposes an online data augmentation method grounded in control theory to address the limitations of handcrafted, non-adaptive augmentation strategies commonly used in visual recognition tasks. By constructing a control-loop architecture that leverages operation-specific response curves, the approach dynamically adjusts the intensity distribution of individual augmentation operations during training—eliminating the need for preset parameters and automatically suppressing augmentations detrimental to model performance. Experimental results demonstrate that, when applied with WideResNet-28-10 on CIFAR-10, CIFAR-100, and SVHN-core, the method achieves performance on par with state-of-the-art data augmentation techniques, offering a task-adaptive and fully automated dynamic augmentation mechanism without manual intervention.