Junde Wu

The Diffusion Probabilistic Model (DPM) has recently gained popularity in the field of computer vision, thanks to its image generation applications, such as Imagen, Latent Diffusion Models, and Stable Diffusion, which have demonstrated impressive capabilities and sparked much discussion within the community. Recent investigations have further unveiled the utility of DPM in the domain of medical image analysis, as underscored by the commendable performance exhibited by the medical image segmentation model across various tasks. Although these models were originally underpinned by a UNet architecture, there exists a potential avenue for enhancing their performance through the integration of vision transformer mechanisms. However, we discovered that simply combining these two models resulted in subpar performance. To effectively integrate these two cutting-edge techniques for the Medical image segmentation, we propose a novel Transformer-based Diffusion framework, called MedSegDiff-V2. We verify its effectiveness on 20 medical image segmentation tasks with different image modalities. Through comprehensive evaluation, our approach demonstrates superiority over prior state-of-the-art (SOTA) methodologies. Code is released at https://github.com/KidsWithTokens/MedSegDiff.

The Segment Anything Model (SAM) has recently gained popularity in the field of image segmentation due to its impressive capabilities in various segmentation tasks and its prompt-based interface. However, recent studies and individual experiments have shown that SAM underperforms in medical image segmentation, since the lack of the medical specific knowledge. This raises the question of how to enhance SAM's segmentation capability for medical images. In this paper, instead of fine-tuning the SAM model, we propose the Medical SAM Adapter (Med-SA), which incorporates domain-specific medical knowledge into the segmentation model using a light yet effective adaptation technique. In Med-SA, we propose Space-Depth Transpose (SD-Trans) to adapt 2D SAM to 3D medical images and Hyper-Prompting Adapter (HyP-Adpt) to achieve prompt-conditioned adaptation. We conduct comprehensive evaluation experiments on 17 medical image segmentation tasks across various image modalities. Med-SA outperforms several state-of-the-art (SOTA) medical image segmentation methods, while updating only 2\% of the parameters. Our code is released at https://github.com/KidsWithTokens/Medical-SAM-Adapter.

The operational characterization of quantum coherence is the cornerstone in the development of the resource theory of coherence. We introduce a new coherence quantifier based on maximum relative entropy. We prove that the maximum relative entropy of coherence is directly related to the maximum overlap with maximally coherent states under a particular class of operations, which provides an operational interpretation of the maximum relative entropy of coherence. Moreover, we show that, for any coherent state, there are examples of subchannel discrimination problems such that this coherent state allows for a higher probability of successfully discriminating subchannels than that of all incoherent states. This advantage of coherent states in subchannel discrimination can be exactly characterized by the maximum relative entropy of coherence. By introducing a suitable smooth maximum relative entropy of coherence, we prove that the smooth maximum relative entropy of coherence provides a lower bound of one-shot coherence cost, and the maximum relative entropy of coherence is equivalent to the relative entropy of coherence in the asymptotic limit. Similar to the maximum relative entropy of coherence, the minimum relative entropy of coherence has also been investigated. We show that the minimum relative entropy of coherence provides an upper bound of one-shot coherence distillation, and in the asymptotic limit the minimum relative entropy of coherence is equivalent to the relative entropy of coherence.

Diffusion probabilistic model (DPM) recently becomes one of the hottest topic in computer vision. Its image generation application such as Imagen, Latent Diffusion Models and Stable Diffusion have shown impressive generation capabilities, which aroused extensive discussion in the community. Many recent studies also found it is useful in many other vision tasks, like image deblurring, super-resolution and anomaly detection. Inspired by the success of DPM, we propose the first DPM based model toward general medical image segmentation tasks, which we named MedSegDiff. In order to enhance the step-wise regional attention in DPM for the medical image segmentation, we propose dynamic conditional encoding, which establishes the state-adaptive conditions for each sampling step. We further propose Feature Frequency Parser (FF-Parser), to eliminate the negative effect of high-frequency noise component in this process. We verify MedSegDiff on three medical segmentation tasks with different image modalities, which are optic cup segmentation over fundus images, brain tumor segmentation over MRI images and thyroid nodule segmentation over ultrasound images. The experimental results show that MedSegDiff outperforms state-of-the-art (SOTA) methods with considerable performance gap, indicating the generalization and effectiveness of the proposed model. Our code is released at https://github.com/WuJunde/MedSegDiff.

We define two ways of quantifying the quantum correlations based on quantum Fisher information (QFI) in order to study the quantum correlations as a resource in quantum metrology. By investigating the hierarchy of measurement-induced Fisher information introduced in Lu et al. [X. M. Lu, S. Luo, and C. H. Oh, Phys. Rev. A 86, 022342 (2012)], we show that the presence of quantum correlation can be confirmed by the difference of the Fisher information induced by the measurements of two hierarchies. In particular, the quantitative quantum correlations based on QFI coincide with the geometric discord for pure quantum states.