Auscultation of the chest is a fundamental diagnostic tool for cardiovascular and pulmonary diseases. However, the two main chest sound parts, heart sound (HS) and lung sound (LS), are often mixed, limiting diagnostic accuracy. This paper presents a novel Phase-Enhanced Neural Network (PENN) for HS and LS separation. To address the under-utilization of phase information, PENN integrates a feedforward connection that feeds the input spectrum into the Restorer, enabling phase recovery based on the local inference feature of phase. A time-frequency Dual-Path Transformer (DPT) is employed to expand the network's receptive field and enhance performance. To interpret the effectiveness of PENN, two new metrics, mSI-SDRi and pSI-SDRi, are proposed to separately evaluate the contributions of magnitude and phase. Experiments show that PENN achieves pSI-SDRi improvements of 1.44 dB for HS and 2.25 dB for LS under a LS cutoff frequency ($f_{c\text{lung}}$) of 60Hz. Extensive experimental results demonstrate the effectiveness and robustness of PENN, offering a promising solution to improve the accuracy of auscultation.

The rapid advancement of diffusion models has increased the need for customized image generation. However, current customization methods face several limitations: 1) typically accept either image or text conditions alone; 2) customization in complex visual scenarios often leads to subject leakage or confusion; 3) image-conditioned outputs tend to suffer from inconsistent backgrounds; and 4) high computational costs. To address these issues, this paper introduces Multi-party Collaborative Attention Control (MCA-Ctrl), a tuning-free method that enables high-quality image customization using both text and complex visual conditions. Specifically, MCA-Ctrl leverages two key operations within the self-attention layer to coordinate multiple parallel diffusion processes and guide the target image generation. This approach allows MCA-Ctrl to capture the content and appearance of specific subjects while maintaining semantic consistency with the conditional input. Additionally, to mitigate subject leakage and confusion issues common in complex visual scenarios, we introduce a Subject Localization Module that extracts precise subject and editable image layers based on user instructions. Extensive quantitative and human evaluation experiments show that MCA-Ctrl outperforms existing methods in zero-shot image customization, effectively resolving the mentioned issues.

In safety-critical domains such as medical diagnostics and autonomous driving, single-image evidence is sometimes insufficient to reflect the inherent ambiguity of vision problems. Therefore, multiple plausible assumptions that match the image semantics may be needed to reflect the actual distribution of targets and support downstream tasks. However, balancing and improving the diversity and consistency of segmentation predictions under the high-dimensional output spaces and potential multimodal distributions is still challenging. This paper presents Hierarchical Self-Regulation Diffusion (HSRDiff), a unified framework that simulates joint probability distribution over entire labels. Our model self-regulates the balance between the two modes of predicting the label and noise in a novel ``differentiation to unification" pipeline and dynamically fits the optimal path to model the aleatoric uncertainty rooted in observations. In addition, we preserve the high-fidelity reconstruction of the delicate structure in images by leveraging the hierarchical multi-scale condition priors. We validate HSRDiff in three different semantic scenarios. Experimental results show that HSRDiff is superior to the comparison method with a considerable performance gap.

Multi-teacher Knowledge Distillation (KD) transfers diverse knowledge from a teacher pool to a student network. The core problem of multi-teacher KD is how to balance distillation strengths among various teachers. Most existing methods often develop weighting strategies from an individual perspective of teacher performance or teacher-student gaps, lacking comprehensive information for guidance. This paper proposes Multi-Teacher Knowledge Distillation with Reinforcement Learning (MTKD-RL) to optimize multi-teacher weights. In this framework, we construct both teacher performance and teacher-student gaps as state information to an agent. The agent outputs the teacher weight and can be updated by the return reward from the student. MTKD-RL reinforces the interaction between the student and teacher using an agent in an RL-based decision mechanism, achieving better matching capability with more meaningful weights. Experimental results on visual recognition tasks, including image classification, object detection, and semantic segmentation tasks, demonstrate that MTKD-RL achieves state-of-the-art performance compared to the existing multi-teacher KD works.

Diffusion transformers have emerged as the mainstream paradigm for video generation models. However, the use of up to billions of parameters incurs significant computational costs. Quantization offers a promising solution by reducing memory usage and accelerating inference. Nonetheless, we observe that the joint modeling of spatial and temporal information in video diffusion models (V-DMs) leads to extremely long token sequences, which introduces high calibration variance and learning challenges. To address these issues, we propose **$S^2$Q-VDiT**, a post-training quantization framework for V-DMs that leverages **S**alient data and **S**parse token distillation. During the calibration phase, we identify that quantization performance is highly sensitive to the choice of calibration data. To mitigate this, we introduce *Hessian-aware Salient Data Selection*, which constructs high-quality calibration datasets by considering both diffusion and quantization characteristics unique to V-DMs. To tackle the learning challenges, we further analyze the sparse attention patterns inherent in V-DMs. Based on this observation, we propose *Attention-guided Sparse Token Distillation*, which exploits token-wise attention distributions to emphasize tokens that are more influential to the model's output. Under W4A6 quantization, $S^2$Q-VDiT achieves lossless performance while delivering $3.9\times$ model compression and $1.3\times$ inference acceleration. Code will be available at https://github.com/wlfeng0509/s2q-vdit.

PurposeAccurate differentiation between glioma recurrence and radiation necrosis is critical for the management of patients suspected of glioma recurrence following radiation therapy. This study aims to develop a deep learning-based methodology for automated discrimination between glioma recurrence and radiation necrosis using routine magnetic resonance imaging (MRI) scans.MethodWe retrospectively investigated 234 patients who underwent radiotherapy after glioma resection and presented with suspected recurrent lesions during follow-up MRI examinations. Routine 3D-MRI scans, including T1-weighted, T2-weighted, and contrast-enhanced T1 (T1ce) sequences, were acquired for each patient. Among the analyzed cases, 192 (82.1%) were pathologically confirmed as glioma recurrence, while 42 (17.9%) were diagnosed as radiation necrosis. Various Convolutional Neural Network (CNN) models were employed to learn radiological features indicative of glioma recurrence and radiation necrosis from the MRI scans. Performance evaluation metrics, such as sensitivity, specificity, accuracy, and area under the curve (AUC), were used to assess the models’ performance.ResultAmong the evaluated CNN models, ResNet10 demonstrated the highest sensitivity (0.78), specificity (0.94), accuracy (0.91), and an AUC value of 0.83. Additionally, the MresNet model achieved the highest specificity (0.980) but exhibited a relatively lower sensitivity (0.56). Another evaluated CNN model, Vgg16, showed a sensitivity of 0.56, specificity of 0.94, accuracy of 0.88, and an AUC value of 0.70.ConclusionThe proposed ResNet10 CNN model demonstrates promising performance on routine MRI scans, rendering it highly applicable in clinical settings. These findings contribute to enhancing the diagnostic accuracy for distinguishing between glioma recurrence and radiation necrosis using routine MRI.

Contrastive Language-Image Pre-training (CLIP) has become a promising language-supervised visual pre-training framework. This paper aims to distill small CLIP models supervised by a large teacher CLIP model. We propose several distillation strategies, including relation, feature, gradient and contrastive paradigms, to examine the effectiveness of CLIP-Knowledge Distillation (KD). We show that a simple feature mimicry with Mean Squared Error loss works surprisingly well. Moreover, interactive contrastive learning across teacher and student encoders is also effective in performance improvement. We explain that the success of CLIP-KD can be attributed to maximizing the feature similarity between teacher and student. The unified method is applied to distill several student models trained on CC3M+12M. CLIP-KD improves student CLIP models consistently over zero-shot ImageNet classification and cross-modal retrieval benchmarks. When using ViT-L/14 pretrained on Laion-400M as the teacher, CLIP-KD achieves 57.5% and 55.4% zero-shot top-1 ImageNet accuracy over ViT-B/16 and ResNet-50, surpassing the original CLIP without KD by 20.5% and 20.1% margins, respectively. Our code is released on https://github.com/winycg/CLIP-KD.

Radiologists possess diverse training and clinical experiences, leading to variations in the segmentation annotations of lung nodules and resulting in segmentation uncertainty. Conventional methods typically select a single annotation as the learning target or attempt to learn a latent space comprising multiple annotations. However, these approaches fail to leverage the valuable information inherent in the consensus and disagreements among the multiple annotations. In this paper, we propose an Uncertainty-Aware Attention Mechanism (UAAM) that utilizes consensus and disagreements among multiple annotations to facilitate better segmentation. To this end, we introduce the Multi-Confidence Mask (MCM), which combines a Low-Confidence (LC) Mask and a High-Confidence (HC) Mask. The LC mask indicates regions with low segmentation confidence, where radiologists may have different segmentation choices. Following UAAM, we further design an Uncertainty-Guide Multi-Confidence Segmentation Network (UGMCS-Net), which contains three modules: a Feature Extracting Module that captures a general feature of a lung nodule, an Uncertainty-Aware Module that produces three features for the annotations' union, intersection, and annotation set, and an Intersection-Union Constraining Module that uses distances between the three features to balance the predictions of final segmentation and MCM. To comprehensively demonstrate the performance of our method, we propose a Complex-Nodule Validation on LIDC-IDRI, which tests UGMCS-Net's segmentation performance on lung nodules that are difficult to segment using common methods. Experimental results demonstrate that our method can significantly improve the segmentation performance on nodules that are difficult to segment using conventional methods.

Medical image data are often limited due to expensive acquisition and annotation processes. Directly using such limited annotated samples can easily lead to the deep learning models overfitting on the training dataset. An alternative way is to leverage the unlabeled dataset which is free to obtain in most cases. Semi-supervised methods using a small set of labeled data and large amounts of unlabeled data have received much attention. In this paper, we propose a novel semi-supervised method for medical image segmentation that uses partial class supervision. Specifically, for a given multi-class label, we extend it to generate several labeled images with partial classes annotated while others remain unannotated. The unlabeled part in the partially annotated label is supervised by a pseudo-labels approach. In addition, we project the labeled pixel values into pseudo-labels to achieve rectified pixel-level pseudo-labels. In this way, our method can effectively increase the number of training samples. The experimental results on two public medical datasets of heart and prostate anatomy demonstrate that our method outperforms the state-of-the-art semi-supervised methods. Additional experiments also show that the proposed method gives better results compared to fully supervised segmentation methods.

—Radiologists have different training and clinical experiences, so they may provide various segmentation annotations for a lung nodule, which causes segmentation uncertainty among multiple annotations. Conventional methods usually chose a single annotation as the learning target or tried to learn a latent space of various annotations. Still, they wasted the valuable information of consensus or disagreements ingrained in the multiple annotations. This paper proposes an Uncertainty-Aware Attention Mechanism (UAAM), which utilizes consensus or disagreements among annotations to produce a better segmentation. In UAAM, we propose a Multi-Confidence Mask (MCM), which is a combination of a Low-Confidence (LC) Mask and a High-Confidence (HC) Mask. LC mask indicates regions with low segmentation confidence, which may cause different segmentation options among radiologists. Following UAAM, we further design an Uncertainty-Guide Segmentation Network (UGS-Net), which contains three modules: Feature Extracting Module captures a general feature of a lung nodule. Uncertainty-Aware Module produce three features for the annotations’ union, intersection, and annotation set. Finally, Intersection-Union Constraining Module use distances between three features to balance the predictions of final segmentation, LC mask, and HC mask. To fully demonstrate the performance of our method, we propose a Complex Nodule Challenge on LIDC-IDRI, which tests UGS-Net’s segmentation performance on the lung nodules that are difficult to segment by U-Net. Experimental results demonstrate that our method can significantly improve the segmentation performance on nodules with poor segmentation by U-Net.