Search

Surgical video segmentation is a critical task in computer-assisted surgery and is vital for enhancing surgical quality and patient outcomes. Recently, the Segment Anything Model 2 (SAM2) framework has shown superior advancements in image and video segmentation. However, SAM2 struggles with efficiency due to the high computational demands of processing high-resolution images and complex and long-range temporal dynamics in surgical videos. To address these challenges, we introduce Surgical SAM 2 (SurgSAM-2), an advanced model to utilize SAM2 with an Efficient Frame Pruning (EFP) mechanism, to facilitate real-time surgical video segmentation. The EFP mechanism dynamically manages the memory bank by selectively retaining only the most informative frames, reducing memory usage and computational cost while maintaining high segmentation accuracy. Our extensive experiments demonstrate that SurgSAM-2 significantly improves both efficiency and segmentation accuracy compared to the vanilla SAM2. Remarkably, SurgSAM-2 achieves a 3$\times$ FPS compared with SAM2, while also delivering state-of-the-art performance after fine-tuning with lower-resolution data. These advancements establish SurgSAM-2 as a leading model for surgical video analysis, making real-time surgical video segmentation in resource-constrained environments a feasible reality., Comment: 16 pages, 2 figures

We introduce a novel graph-based Retrieval-Augmented Generation (RAG) framework specifically designed for the medical domain, called \textbf{MedGraphRAG}, aimed at enhancing Large Language Model (LLM) capabilities and generating evidence-based results, thereby improving safety and reliability when handling private medical data. Our comprehensive pipeline begins with a hybrid static-semantic approach to document chunking, significantly improving context capture over traditional methods. Extracted entities are used to create a three-tier hierarchical graph structure, linking entities to foundational medical knowledge sourced from medical papers and dictionaries. These entities are then interconnected to form meta-graphs, which are merged based on semantic similarities to develop a comprehensive global graph. This structure supports precise information retrieval and response generation. The retrieval process employs a U-retrieve method to balance global awareness and indexing efficiency of the LLM. Our approach is validated through a comprehensive ablation study comparing various methods for document chunking, graph construction, and information retrieval. The results not only demonstrate that our hierarchical graph construction method consistently outperforms state-of-the-art models on multiple medical Q\&A benchmarks, but also confirms that the responses generated include source documentation, significantly enhancing the reliability of medical LLMs in practical applications. Code will be at: https://github.com/MedicineToken/Medical-Graph-RAG/tree/main

Although segmenting natural images has shown impressive performance, these techniques cannot be directly applied to medical image segmentation. Medical image segmentation is particularly complicated by inherent uncertainties. For instance, the ambiguous boundaries of tissues can lead to diverse but plausible annotations from different clinicians. These uncertainties cause significant discrepancies in clinical interpretations and impact subsequent medical interventions. Therefore, achieving quantitative segmentations from uncertain medical images becomes crucial in clinical practice. To address this, we propose a novel approach that integrates an \textbf{uncertainty-aware model} with \textbf{human-in-the-loop interaction}. The uncertainty-aware model proposes several plausible segmentations to address the uncertainties inherent in medical images, while the human-in-the-loop interaction iteratively modifies the segmentation under clinician supervision. This collaborative model ensures that segmentation is not solely dependent on automated techniques but is also refined through clinician expertise. As a result, our approach represents a significant advancement in the field which enhances the safety of medical image segmentation. It not only offers a comprehensive solution to produce quantitative segmentation from inherent uncertain medical images, but also establishes a synergistic balance between algorithmic precision and clincian knowledge. We evaluated our method on various publicly available multi-clinician annotated datasets: REFUGE2, LIDC-IDRI and QUBIQ. Our method showcases superior segmentation capabilities, outperforming a wide range of deterministic and uncertainty-aware models. We also demonstrated that our model produced significantly better results with fewer interactions compared to previous interactive models. We will release the code to foster further research in this area.

In this paper, we introduce Medical SAM 2 (MedSAM-2), an advanced segmentation model that utilizes the SAM 2 framework to address both 2D and 3D medical image segmentation tasks. By adopting the philosophy of taking medical images as videos, MedSAM-2 not only applies to 3D medical images but also unlocks new One-prompt Segmentation capability. That allows users to provide a prompt for just one or a specific image targeting an object, after which the model can autonomously segment the same type of object in all subsequent images, regardless of temporal relationships between the images. We evaluated MedSAM-2 across a variety of medical imaging modalities, including abdominal organs, optic discs, brain tumors, thyroid nodules, and skin lesions, comparing it against state-of-the-art models in both traditional and interactive segmentation settings. Our findings show that MedSAM-2 not only surpasses existing models in performance but also exhibits superior generalization across a range of medical image segmentation tasks. Our code will be released at: https://github.com/MedicineToken/Medical-SAM2

Medicine is inherently a multimodal discipline. Medical images can reflect the pathological changes of cancer and tumors, while the expression of specific genes can influence their morphological characteristics. However, most deep learning models employed for these medical tasks are unimodal, making predictions using either image data or genomic data exclusively. In this paper, we propose a multimodal pre-training framework that jointly incorporates genomics and medical images for downstream tasks. To address the issues of high computational complexity and difficulty in capturing long-range dependencies in genes sequence modeling with MLP or Transformer architectures, we utilize Mamba to model these long genomic sequences. We aligns medical images and genes using a self-supervised contrastive learning approach which combines the Mamba as a genetic encoder and the Vision Transformer (ViT) as a medical image encoder. We pre-trained on the TCGA dataset using paired gene expression data and imaging data, and fine-tuned it for downstream tumor segmentation tasks. The results show that our model outperformed a wide range of related methods.

The Segment Anything Model (SAM) gained significant success in natural image segmentation, and many methods have tried to fine-tune it to medical image segmentation. An efficient way to do so is by using Adapters, specialized modules that learn just a few parameters to tailor SAM specifically for medical images. However, unlike natural images, many tissues and lesions in medical images have blurry boundaries and may be ambiguous. Previous efforts to adapt SAM ignore this challenge and can only predict distinct segmentation. It may mislead clinicians or cause misdiagnosis, especially when encountering rare variants or situations with low model confidence. In this work, we propose a novel module called the Uncertainty-aware Adapter, which efficiently fine-tuning SAM for uncertainty-aware medical image segmentation. Utilizing a conditional variational autoencoder, we encoded stochastic samples to effectively represent the inherent uncertainty in medical imaging. We designed a new module on a standard adapter that utilizes a condition-based strategy to interact with samples to help SAM integrate uncertainty. We evaluated our method on two multi-annotated datasets with different modalities: LIDC-IDRI (lung abnormalities segmentation) and REFUGE2 (optic-cup segmentation). The experimental results show that the proposed model outperforms all the previous methods and achieves the new state-of-the-art (SOTA) on both benchmarks. We also demonstrated that our method can generate diverse segmentation hypotheses that are more realistic as well as heterogeneous.

Some visual recognition tasks are more challenging then the general ones as they require professional categories of images. The previous efforts, like fine-grained vision classification, primarily introduced models tailored to specific tasks, like identifying bird species or car brands with limited scalability and generalizability. This paper aims to design a scalable and explainable model to solve Professional Visual Recognition tasks from a generic standpoint. We introduce a biologically-inspired structure named Pro-NeXt and reveal that Pro-NeXt exhibits substantial generalizability across diverse professional fields such as fashion, medicine, and art-areas previously considered disparate. Our basic-sized Pro-NeXt-B surpasses all preceding task-specific models across 12 distinct datasets within 5 diverse domains. Furthermore, we find its good scaling property that scaling up Pro-NeXt in depth and width with increasing GFlops can consistently enhances its accuracy. Beyond scalability and adaptability, the intermediate features of Pro-NeXt achieve reliable object detection and segmentation performance without extra training, highlighting its solid explainability. We will release the code to foster further research in this area., Comment: 20 pages including reference. arXiv admin note: text overlap with arXiv:2211.15672

We propose an algorithm for calculating the determinant of a square matrix, and construct the quantum circuit realizing it, using multiqubit control gates (representable in terms of Toffoli gates, CNOTs and SWAPs), Hadamard transformations and $Z$-operators. Each row of the matrix is encoded as a pure state of some quantum system. The admitted matrix is therefore arbitrary up to the normalization of quantum states of those systems. The depth of the proposed algorithm is $O(N^3\log \, N)$ for the $N\times N$ matrix., Comment: 8 pages, 3 figures, minor change in presentation

We propose protocols for calculating inner product, matrix addition and matrix multiplication based on multiqubit Toffoli-type and the simplest one-qubit operations and employ ancilla measurements to remove all garbage of calculations. The depth (runtime) of the addition protocol is $O(1)$ and that of other protocols logarithmically increases with the dimensionality of the considered matrices., Comment: 5 pages, 1 figure

The study of quantum channels is the most fundamental theoretical problem in quantum information and quantum communication theory. The link product theory of quantum channels is an important tool for studying quantum networks. In this paper, we establish the Stinespring dilation theorem of the link product of quantum channels in two different ways, discuss the discrimination of quantum channels and show that the distinguishability can be improved by self-linking each quantum channel n times as n grows. We also find that the maximum value of Uhlmann's theorem can be achieved for diagonal channels., Comment: 11 pages

In this paper, we present an efficient quantum compression method for identically prepared states with arbitrary dimentional.

In this paper, we consider two versions of the Text Assembling problem. We are given a sequence of strings $s^1,\dots,s^n$ of total length $L$ that is a dictionary, and a string $t$ of length $m$ that is texts. The first version of the problem is assembling $t$ from the dictionary. The second version is the ``Shortest Superstring Problem''(SSP) or the ``Shortest Common Superstring Problem''(SCS). In this case, $t$ is not given, and we should construct the shortest string (we call it superstring) that contains each string from the given sequence as a substring. These problems are connected with the sequence assembly method for reconstructing a long DNA sequence from small fragments. For both problems, we suggest new quantum algorithms that work better than their classical counterparts. In the first case, we present a quantum algorithm with $O(m+\log m\sqrt{nL})$ running time. In the case of SSP, we present a quantum algorithm with running time $O(n^3 1.728^n +L +\sqrt{L}n^{1.5}+\sqrt{L}n\log^2L\log^2n)$., Comment: arXiv admin note: text overlap with arXiv:2112.13319

The most simplest form of quantum network is an one dimensional quantum network with a single player in each node. In remote entanglement distribution each of the players carry out measurement at the intermediate nodes to produce an entangled state between initial and final node which are remotely separated. It is imperative to say that the flow of information as well as the percolation of entanglement in a network between the source and target node is an important area of study. This will help us to understand the limits of the resource states as well as the measurements that are carried out in the process of remote entanglement distribution. In this article we investigate how the concurrence of the final entangled state obtained is connected with the concurrences of the initial entangled states present in a 1-D chain. We extend the works done for the pure entangled states for mixed entangled states like Werner states, Bell diagonal states and for general mixed states. We did not limit ourselves to a situation where the measurements are happening perfectly. We also investigate how these relations change when we consider imperfect swapping. We obtain the limits on the number of swappings as well as the success probability measurements to ensure the final state to be entangled state after swapping. In addition to these we also investigate on how much quantum information can be sent from the initial node to the final node (by computing the teleportation fidelity) when the measurement is perfect and imperfect with the same set of examples. Here also we obtain the limits on the number of swapping and the success probability of measurement to ensure that the final state obtained is capable of transferring the information . These results have tremendous future applications in sending quantum information between two quantum processors in remote entangled distribution., Comment: 31 Pages, 52 Figures. Added additional references where similar work is done for multipartite entanglement and papers on improving length of quantum networks

Large foundation models, known for their strong zero-shot generalization, have excelled in visual and language applications. However, applying them to medical image segmentation, a domain with diverse imaging types and target labels, remains an open challenge. Current approaches, such as adapting interactive segmentation models like Segment Anything Model (SAM), require user prompts for each sample during inference. Alternatively, transfer learning methods like few/one-shot models demand labeled samples, leading to high costs. This paper introduces a new paradigm toward the universal medical image segmentation, termed 'One-Prompt Segmentation.' One-Prompt Segmentation combines the strengths of one-shot and interactive methods. In the inference stage, with just \textbf{one prompted sample}, it can adeptly handle the unseen task in a single forward pass. We train One-Prompt Model on 64 open-source medical datasets, accompanied by the collection of over 3,000 clinician-labeled prompts. Tested on 14 previously unseen datasets, the One-Prompt Model showcases superior zero-shot segmentation capabilities, outperforming a wide range of related methods. The code and data is released as https://github.com/KidsWithTokens/one-prompt., Comment: arXiv admin note: text overlap with arXiv:2304.12620

Pathologic myopia (PM) is a common blinding retinal degeneration suffered by highly myopic population. Early screening of this condition can reduce the damage caused by the associated fundus lesions and therefore prevent vision loss. Automated diagnostic tools based on artificial intelligence methods can benefit this process by aiding clinicians to identify disease signs or to screen mass populations using color fundus photographs as inputs. This paper provides insights about PALM, our open fundus imaging dataset for pathological myopia recognition and anatomical structure annotation. Our databases comprises 1200 images with associated labels for the pathologic myopia category and manual annotations of the optic disc, the position of the fovea and delineations of lesions such as patchy retinal atrophy (including peripapillary atrophy) and retinal detachment. In addition, this paper elaborates on other details such as the labeling process used to construct the database, the quality and characteristics of the samples and provides other relevant usage notes., Comment: 10 pages, 6 figures

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., Comment: Code released at: https://github.com/KidsWithTokens/Medical-SAM-Adapter

Image enhancement is a common technique used to mitigate issues such as severe noise, low brightness, low contrast, and color deviation in low-light images. However, providing an optimal high-light image as a reference for low-light image enhancement tasks is impossible, which makes the learning process more difficult than other image processing tasks. As a result, although several low-light image enhancement methods have been proposed, most of them are either too complex or insufficient in addressing all the issues in low-light images. In this paper, to make the learning easier in low-light image enhancement, we introduce FLW-Net (Fast and LightWeight Network) and two relative loss functions. Specifically, we first recognize the challenges of the need for a large receptive field to obtain global contrast and the lack of an absolute reference, which limits the simplification of network structures in this task. Then, we propose an efficient global feature information extraction component and two loss functions based on relative information to overcome these challenges. Finally, we conducted comparative experiments to demonstrate the effectiveness of the proposed method, and the results confirm that the proposed method can significantly reduce the complexity of supervised low-light image enhancement networks while improving processing effect. The code is available at \url{https://github.com/hitzhangyu/FLW-Net}., Comment: 19 pages, 11 figures

In this paper, we show that the minimal quantum discord over "cross-symmetric" state extensions is an entanglement monotone. In particular, we show that the minimal Bures distance of discord over cross-symmetric extensions is equivalent to the Bures distance of entanglement. At last, we refute a long-held but unstated convention that only contractive distances can be used to construct entanglement monotones by showing that the entanglement quantifier induced by the Hilbert-Schmidt distance, which is not contractive under quantum operations, is also an entanglement monotone., Comment: 9 pages, 1 figure. arXiv admin note: text overlap with arXiv:2012.03835

We study partial coherence and its connections with entanglement. First, we provide a sufficient and necessary condition for bipartite pure state transformation under partial incoherent operations: A bipartite pure state can be transformed to another one if and only if a majorization relationship holds between their partial coherence vectors. As a consequence, we introduce the concept of maximal partial coherent states in the sense that they can be used to construct any bipartite state of the same system via partial incoherent operations. Second, we provide a strategy to construct measures of partial coherence by the use of symmetric concave functions. Third, we establish some relationships between partial coherence and entanglement. We show that the minimal partial coherence under local unitary operations is a measure of entanglement for bipartite pure states, which can be extended to all mixed states by convex-roof. We also show that partial coherence measures are induced through maximal entanglement under partial incoherent operations for bipartite pure states. There is a one-to-one correspondence between entanglement and partial coherence measures., Comment: 12 pages, 2 figures, 1 table

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, Comment: Code will be released at https://github.com/KidsWithTokens/MedSegDiff

In medical image segmentation, it is often necessary to collect opinions from multiple experts to make the final decision. This clinical routine helps to mitigate individual bias. But when data is multiply annotated, standard deep learning models are often not applicable. In this paper, we propose a novel neural network framework, called Multi-Rater Prism (MrPrism) to learn the medical image segmentation from multiple labels. Inspired by the iterative half-quadratic optimization, the proposed MrPrism will combine the multi-rater confidences assignment task and calibrated segmentation task in a recurrent manner. In this recurrent process, MrPrism can learn inter-observer variability taking into account the image semantic properties, and finally converges to a self-calibrated segmentation result reflecting the inter-observer agreement. Specifically, we propose Converging Prism (ConP) and Diverging Prism (DivP) to process the two tasks iteratively. ConP learns calibrated segmentation based on the multi-rater confidence maps estimated by DivP. DivP generates multi-rater confidence maps based on the segmentation masks estimated by ConP. The experimental results show that by recurrently running ConP and DivP, the two tasks can achieve mutual improvement. The final converged segmentation result of MrPrism outperforms state-of-the-art (SOTA) strategies on a wide range of medical image segmentation tasks.

Different from the general visual classification, some classification tasks are more challenging as they need the professional categories of the images. In the paper, we call them expert-level classification. Previous fine-grained vision classification (FGVC) has made many efforts on some of its specific sub-tasks. However, they are difficult to expand to the general cases which rely on the comprehensive analysis of part-global correlation and the hierarchical features interaction. In this paper, we propose Expert Network (ExpNet) to address the unique challenges of expert-level classification through a unified network. In ExpNet, we hierarchically decouple the part and context features and individually process them using a novel attentive mechanism, called Gaze-Shift. In each stage, Gaze-Shift produces a focal-part feature for the subsequent abstraction and memorizes a context-related embedding. Then we fuse the final focal embedding with all memorized context-related embedding to make the prediction. Such an architecture realizes the dual-track processing of partial and global information and hierarchical feature interactions. We conduct the experiments over three representative expert-level classification tasks: FGVC, disease classification, and artwork attributes classification. In these experiments, superior performance of our ExpNet is observed comparing to the state-of-the-arts in a wide range of fields, indicating the effectiveness and generalization of our ExpNet. The code will be made publicly available.

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., Comment: Code is released at: https://github.com/WuJunde/MedSegDiff

GAMMA Challenge is organized to encourage the AI models to screen the glaucoma from a combination of 2D fundus image and 3D optical coherence tomography volume, like the ophthalmologists.

On the medical images, many of the tissues/lesions may be ambiguous. That is why the medical segmentation is typically annotated by a group of clinical experts to mitigate the personal bias. However, this clinical routine also brings new challenges to the application of machine learning algorithms. Without a definite ground-truth, it will be difficult to train and evaluate the deep learning models. When the annotations are collected from different graders, a common choice is majority vote. However such a strategy ignores the difference between the grader expertness. In this paper, we consider the task of predicting the segmentation with the calibrated inter-observer uncertainty. We note that in clinical practice, the medical image segmentation is usually used to assist the disease diagnosis. Inspired by this observation, we propose diagnosis-first principle, which is to take disease diagnosis as the criterion to calibrate the inter-observer segmentation uncertainty. Following this idea, a framework named Diagnosis First segmentation Framework (DiFF) is proposed to estimate diagnosis-first segmentation from the raw images.Specifically, DiFF will first learn to fuse the multi-rater segmentation labels to a single ground-truth which could maximize the disease diagnosis performance. We dubbed the fused ground-truth as Diagnosis First Ground-truth (DF-GT).Then, we further propose Take and Give Modelto segment DF-GT from the raw image. We verify the effectiveness of DiFF on three different medical segmentation tasks: OD/OC segmentation on fundus images, thyroid nodule segmentation on ultrasound images, and skin lesion segmentation on dermoscopic images. Experimental results show that the proposed DiFF is able to significantly facilitate the corresponding disease diagnosis, which outperforms previous state-of-the-art multi-rater learning methods., Comment: arXiv admin note: text overlap with arXiv:2202.06505

Open checkout-free grocery is the grocery store where the customers never have to wait in line to check out. Developing a system like this is not trivial since it faces challenges of recognizing the dynamic and massive flow of people. In particular, a clustering method that can efficiently assign each snapshot to the corresponding customer is essential for the system. In order to address the unique challenges in the open checkout-free grocery, we propose an efficient and effective person clustering method. Specifically, we first propose a Crowded Sub-Graph (CSG) to localize the relationship among massive and continuous data streams. CSG is constructed by the proposed Pick-Link-Weight (PLW) strategy, which \textbf{picks} the nodes based on time-space information, \textbf{links} the nodes via trajectory information, and \textbf{weighs} the links by the proposed von Mises-Fisher (vMF) similarity metric. Then, to ensure that the method adapts to the dynamic and unseen person flow, we propose Graph Convolutional Network (GCN) with a simple Nearest Neighbor (NN) strategy to accurately cluster the instances of CSG. GCN is adopted to project the features into low-dimensional separable space, and NN is able to quickly produce a result in this space upon dynamic person flow. The experimental results show that the proposed method outperforms other alternative algorithms in this scenario. In practice, the whole system has been implemented and deployed in several real-world open checkout-free groceries., Comment: European Conference on Computer Vision (ECCV) 2022

Glaucoma causes irreversible vision loss due to damage to the optic nerve, and there is no cure for glaucoma.OCT imaging modality is an essential technique for assessing glaucomatous damage since it aids in quantifying fundus structures. To promote the research of AI technology in the field of OCT-assisted diagnosis of glaucoma, we held a Glaucoma OCT Analysis and Layer Segmentation (GOALS) Challenge in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2022 to provide data and corresponding annotations for researchers studying layer segmentation from OCT images and the classification of glaucoma. This paper describes the released 300 circumpapillary OCT images, the baselines of the two sub-tasks, and the evaluation methodology. The GOALS Challenge is accessible at https://aistudio.baidu.com/aistudio/competition/detail/230., Comment: 8 pages, 3 figures, OMIA9 (MICCAI 2022) workshop

Clinically, the accurate annotation of lesions/tissues can significantly facilitate the disease diagnosis. For example, the segmentation of optic disc/cup (OD/OC) on fundus image would facilitate the glaucoma diagnosis, the segmentation of skin lesions on dermoscopic images is helpful to the melanoma diagnosis, etc. With the advancement of deep learning techniques, a wide range of methods proved the lesions/tissues segmentation can also facilitate the automated disease diagnosis models. However, existing methods are limited in the sense that they can only capture static regional correlations in the images. Inspired by the global and dynamic nature of Vision Transformer, in this paper, we propose Segmentation-Assisted diagnosis Transformer (SeATrans) to transfer the segmentation knowledge to the disease diagnosis network. Specifically, we first propose an asymmetric multi-scale interaction strategy to correlate each single low-level diagnosis feature with multi-scale segmentation features. Then, an effective strategy called SeA-block is adopted to vitalize diagnosis feature via correlated segmentation features. To model the segmentation-diagnosis interaction, SeA-block first embeds the diagnosis feature based on the segmentation information via the encoder, and then transfers the embedding back to the diagnosis feature space by a decoder. Experimental results demonstrate that SeATrans surpasses a wide range of state-of-the-art (SOTA) segmentation-assisted diagnosis methods on several disease diagnosis tasks.

The segmentation of optic disc(OD) and optic cup(OC) from fundus images is an important fundamental task for glaucoma diagnosis. In the clinical practice, it is often necessary to collect opinions from multiple experts to obtain the final OD/OC annotation. This clinical routine helps to mitigate the individual bias. But when data is multiply annotated, standard deep learning models will be inapplicable. In this paper, we propose a novel neural network framework to learn OD/OC segmentation from multi-rater annotations. The segmentation results are self-calibrated through the iterative optimization of multi-rater expertness estimation and calibrated OD/OC segmentation. In this way, the proposed method can realize a mutual improvement of both tasks and finally obtain a refined segmentation result. Specifically, we propose Diverging Model(DivM) and Converging Model(ConM) to process the two tasks respectively. ConM segments the raw image based on the multi-rater expertness map provided by DivM. DivM generates multi-rater expertness map from the segmentation mask provided by ConM. The experiment results show that by recurrently running ConM and DivM, the results can be self-calibrated so as to outperform a range of state-of-the-art(SOTA) multi-rater segmentation methods.

Pre-training is essential to deep learning model performance, especially in medical image analysis tasks where limited training data are available. However, existing pre-training methods are inflexible as the pre-trained weights of one model cannot be reused by other network architectures. In this paper, we propose an architecture-irrelevant hyper-initializer, which can initialize any given network architecture well after being pre-trained for only once. The proposed initializer is a hypernetwork which takes a downstream architecture as input graphs and outputs the initialization parameters of the respective architecture. We show the effectiveness and efficiency of the hyper-initializer through extensive experimental results on multiple medical imaging modalities, especially in data-limited fields. Moreover, we prove that the proposed algorithm can be reused as a favorable plug-and-play initializer for any downstream architecture and task (both classification and segmentation) of the same modality.

Deep learning based medical imaging classification models usually suffer from the domain shift problem, where the classification performance drops when training data and real-world data differ in imaging equipment manufacturer, image acquisition protocol, patient populations, etc. We propose Feature Centroid Contrast Learning (FCCL), which can improve target domain classification performance by extra supervision during training with contrastive loss between instance and class centroid. Compared with current unsupervised domain adaptation and domain generalization methods, FCCL performs better while only requires labeled image data from a single source domain and no target domain. We verify through extensive experiments that FCCL can achieve superior performance on at least three imaging modalities, i.e. fundus photographs, dermatoscopic images, and H & E tissue images.

With the rapid development of artificial intelligence (AI) in medical image processing, deep learning in color fundus photography (CFP) analysis is also evolving. Although there are some open-source, labeled datasets of CFPs in the ophthalmology community, large-scale datasets for screening only have labels of disease categories, and datasets with annotations of fundus structures are usually small in size. In addition, labeling standards are not uniform across datasets, and there is no clear information on the acquisition device. Here we release a multi-annotation, multi-quality, and multi-device color fundus image dataset for glaucoma analysis on an original challenge -- Retinal Fundus Glaucoma Challenge 2nd Edition (REFUGE2). The REFUGE2 dataset contains 2000 color fundus images with annotations of glaucoma classification, optic disc/cup segmentation, as well as fovea localization. Meanwhile, the REFUGE2 challenge sets three sub-tasks of automatic glaucoma diagnosis and fundus structure analysis and provides an online evaluation framework. Based on the characteristics of multi-device and multi-quality data, some methods with strong generalizations are provided in the challenge to make the predictions more robust. This shows that REFUGE2 brings attention to the characteristics of real-world multi-domain data, bridging the gap between scientific research and clinical application., Comment: 29 pages, 21 figures

Color fundus photography and Optical Coherence Tomography (OCT) are the two most cost-effective tools for glaucoma screening. Both two modalities of images have prominent biomarkers to indicate glaucoma suspected. Clinically, it is often recommended to take both of the screenings for a more accurate and reliable diagnosis. However, although numerous algorithms are proposed based on fundus images or OCT volumes in computer-aided diagnosis, there are still few methods leveraging both of the modalities for the glaucoma assessment. Inspired by the success of Retinal Fundus Glaucoma Challenge (REFUGE) we held previously, we set up the Glaucoma grAding from Multi-Modality imAges (GAMMA) Challenge to encourage the development of fundus \& OCT-based glaucoma grading. The primary task of the challenge is to grade glaucoma from both the 2D fundus images and 3D OCT scanning volumes. As part of GAMMA, we have publicly released a glaucoma annotated dataset with both 2D fundus color photography and 3D OCT volumes, which is the first multi-modality dataset for glaucoma grading. In addition, an evaluation framework is also established to evaluate the performance of the submitted methods. During the challenge, 1272 results were submitted, and finally, top-10 teams were selected to the final stage. We analysis their results and summarize their methods in the paper. Since all these teams submitted their source code in the challenge, a detailed ablation study is also conducted to verify the effectiveness of the particular modules proposed. We find many of the proposed techniques are practical for the clinical diagnosis of glaucoma. As the first in-depth study of fundus \& OCT multi-modality glaucoma grading, we believe the GAMMA Challenge will be an essential starting point for future research.

With the advancement of deep learning techniques, an increasing number of methods have been proposed for optic disc and cup (OD/OC) segmentation from the fundus images. Clinically, OD/OC segmentation is often annotated by multiple clinical experts to mitigate the personal bias. However, it is hard to train the automated deep learning models on multiple labels. A common practice to tackle the issue is majority vote, e.g., taking the average of multiple labels. However such a strategy ignores the different expertness of medical experts. Motivated by the observation that OD/OC segmentation is often used for the glaucoma diagnosis clinically, in this paper, we propose a novel strategy to fuse the multi-rater OD/OC segmentation labels via the glaucoma diagnosis performance. Specifically, we assess the expertness of each rater through an attentive glaucoma diagnosis network. For each rater, its contribution for the diagnosis will be reflected as an expertness map. To ensure the expertness maps are general for different glaucoma diagnosis models, we further propose an Expertness Generator (ExpG) to eliminate the high-frequency components in the optimization process. Based on the obtained expertness maps, the multi-rater labels can be fused as a single ground-truth which we dubbed as Diagnosis First Ground-truth (DiagFirstGT). Experimental results show that by using DiagFirstGT as ground-truth, OD/OC segmentation networks will predict the masks with superior glaucoma diagnosis performance., Comment: MICCAI 2022

Fundamental matrix operations and solving linear systems of equations are ubiquitous in scientific investigations. Using the "Sender-Receiver" model, we propose quantum algorithms for matrix operations such as matrix-vector product, matrix-matrix product, the sum of two matrices, and calculation of determinant and inverse of a matrix. We encode the matrix entries into the probability amplitudes of pure initial states of senders. After applying a proper unitary transformation to the complete quantum system, the desired result can be found in certain blocks of the receiver's density matrix. These quantum protocols can be used as subroutines in other quantum schemes. Furthermore, we present an alternative quantum algorithm for solving linear systems of equations., Comment: 9 pages, 1 figure, 1 table, revised manuscript

The optimal state-independent lower bounds for the sum of variances or deviations of observables are of significance for the growing number of experiments that reach the uncertainty limited regime. We present a framework for computing the tight uncertainty relations of variance or deviation via determining the uncertainty regions, which are formed by the tuples of two or more of quantum observables in random quantum states induced from the uniform Haar measure on the purified states. From the analytical formulae of these uncertainty regions, we present state-independent uncertainty inequalities satisfied by the sum of variances or deviations of two, three and arbitrary many observables, from which experimentally friend entanglement detection criteria are derived for bipartite and tripartite systems., Comment: 42 pages; a few typoes in the published version are corrected in this version

In object detection, multi-level prediction (e.g., FPN) and reweighting skills (e.g., focal loss) have drastically improved one-stage detector performance. However, the synergy between these two techniques is not fully explored in a unified framework. We find that, during training, the one-stage detector's optimization is not only restricted to the static hard-case mining loss (gradient drift) but also suffered from the diverse positive samples' proportions split by different pyramid levels (level discrepancy). Under this concern, we propose Hierarchical Progressive Focus (HPF) consisting of two key designs: 1) progressive focus, a more flexible hard-case mining setting calculated adaptive to the convergence progress, 2) hierarchical sampling, automatically generating a set of progressive focus for level-specific target optimization. Based on focal loss with ATSS-R50, our approach achieves 40.5 AP, surpassing the state-of-the-art QFL (Quality Focal Loss, 39.9 AP) and VFL (Varifocal Loss, 40.1 AP). Our best model achieves 55.1 AP on COCO test-dev, obtaining excellent results with only a typical training setting. Moreover, as a plug-and-play scheme, HPF can cooperate well with recent advances, providing a stable performance improvement on nine mainstream detectors.

The dilation method is a practical way to experimentally simulate non-Hermitian, especially $\cal PT$-symmetric quantum systems. However, the time-dependent dilation problem cannot be explicitly solved in general. In this paper, we present a simple yet non-trivial exactly solvable dilation problem with two dimensional time-dependent $\cal PT$-symmetric Hamiltonian. Our system is initially set in the unbroken $\cal PT$-symmetric phase and later goes across the so-called exceptional point and enters the broken $\cal PT$-symmetric phase. For this system, the dilated Hamiltonian and the evolution of $\cal PT$-symmetric system are analytically worked out. Our result clearly showed that the exceptional points do not have much physical relevance in a \textit{time-dependent} system., Comment: 9 pages, 4 figures, close to the published version

Quantum coherence, like entanglement, is a fundamental resource in quantum information. In recent years, remarkable progress has been made in formulating resource theory of coherence from a broader perspective. The notions of block-coherence and POVM-based coherence have been established. Certain challenges, however, remain to be addressed. It is difficult to define incoherent operations directly, without requiring incoherent states, which proves a major obstacle in establishing the resource theory of dynamical coherence. In this paper, we overcome this limitation by introducing an alternate definition of incoherent operations, induced via coherence measures, and quantify dynamical coherence based on this definition. Finally, we apply our proposed definition to quantify POVM-based dynamical coherence., Comment: 7 pages, 1 figure, close to published version

We propose a framework to characterize entanglement with quantum discord, both asymmetric and symmetric, over state extensions. In particular, we show that the minimal Bures distance of discord over state extensions is equivalent to Bures distance of entanglement. This equivalence places quantum discord at a more primitive position than entanglement conceptually in the sense that entanglement can be interpreted as an irreducible part of discord over all state extensions. Based on this equivalence, we also offer an operational meaning of Bures distance of entanglement by connecting it to quantum state discriminations. Moreover, for the relative entropy part, we prove that the entanglement measure introduced by Devi and Rajagopal [A. R. U. Devi and A. K. Rajagopal, Phys. Rev. Lett. 100, 140502 (2008)] is actually equivalent to the relative entropy of entanglement. We also provide several quantifications of entanglement based on discord measures., Comment: 11 pages, 2 figures, close to published version

With progress in quantum technologies, the field of quantum networks has emerged as an important area of research. In the last few years, there has been substantial progress in understanding the correlations present in quantum networks. In this article, we study cloning as a prospective method to generate three party quantum networks which can be further used to create larger networks. We analyze various quantum network topologies that can be created using cloning transformations. This would be useful in the situations wherever the availability of entangled pairs is limited. In addition to that we focus on the problem of distinguishing networks created by cloning from those which are created by distributing independently generated entangled pairs. We find that there are several states which cannot be distinguished using the Finner inequalities in the standard way. For such states, we propose an extension to the existing Finner inequality for triangle networks by further increasing the number of observers from three to four or six depending on the network topology. This takes into account the additional correlations that exist in the case of cloned networks. In the last part of the article we have used tripartite mutual information to distinguish cloned networks from networks created by independent sources and have further used squashed entanglement as a measure to quantify the amount of dependence in the cloned networks., Comment: 10 pages, 10 Figures

Quantum resource theories provide a diverse and powerful framework for extensively studying the phenomena in quantum physics. Quantum coherence, a quantum resource, is the basic ingredient in many quantum information tasks. It is a subject of broad and current interest in quantum information, and many new concepts have been introduced and generalized since its establishment. Here we show that the block coherence can be transformed into entanglement via a block incoherent operation. Moreover, we find that the POVM-based coherence associated with block coherence through the Naimark extension acts as a potential resource from the perspective of generating entanglement. Finally, we discuss avenues of creating entanglement from POVM-based coherence, present strategies that require embedding channels and auxiliary systems, give some examples, and generalize them., Comment: 10 pages, 2 figures, title changed, close to published version

To effectively realize a $\cal PT$-symmetric system, one can dilate a $\cal PT$-symmetric Hamiltonian to some global Hermitian one and simulate its evolution in the dilated Hermitian system. However, with only a global Hermitian Hamiltonian, how do we know whether it is a dilation and is useful for simulation? To answer this question, we consider the problem of how to extract the internal nonlocality in the Hermitian dilation. We unveil that the internal nonlocality brings nontrivial correlations between the subsystems. By evaluating the correlations with local measurements in three different pictures, the resulting different expectations of the Bell operator reveal the distinction of the internal nonlocality. When the simulated $\cal PT$-symmetric Hamiltonian approaches its exceptional point, such a distinction tends to be most significant. Our results clearly make a difference between the Hermitian dilation and other global Hamiltonians without internal nonlocality. They also provide the figure of merit to test the reliability of the simulation, as well as to verify a $\cal PT$-symmetric (sub)system.

Retinal artery/vein (A/V) classification lays the foundation for the quantitative analysis of retinal vessels, which is associated with potential risks of various cardiovascular and cerebral diseases. The topological connection relationship, which has been proved effective in improving the A/V classification performance for the conventional graph based method, has not been exploited by the deep learning based method. In this paper, we propose a Topology Ranking Generative Adversarial Network (TR-GAN) to improve the topology connectivity of the segmented arteries and veins, and further to boost the A/V classification performance. A topology ranking discriminator based on ordinal regression is proposed to rank the topological connectivity level of the ground-truth, the generated A/V mask and the intentionally shuffled mask. The ranking loss is further back-propagated to the generator to generate better connected A/V masks. In addition, a topology preserving module with triplet loss is also proposed to extract the high-level topological features and further to narrow the feature distance between the predicted A/V mask and the ground-truth. The proposed framework effectively increases the topological connectivity of the predicted A/V masks and achieves state-of-the-art A/V classification performance on the publicly available AV-DRIVE dataset.

Recently, deep learning has been adopted to the glaucoma classification task with performance comparable to that of human experts. However, a well trained deep learning model demands a large quantity of properly labeled data, which is relatively expensive since the accurate labeling of glaucoma requires years of specialist training. In order to alleviate this problem, we propose a glaucoma classification framework which takes advantage of not only the properly labeled images, but also undiagnosed images without glaucoma labels. To be more specific, the proposed framework is adapted from the teacher-student-learning paradigm. The teacher model encodes the wrapped information of undiagnosed images to a latent feature space, meanwhile the student model learns from the teacher through knowledge transfer to improve the glaucoma classification. For the model training procedure, we propose a novel training strategy that simulates the real-world teaching practice named as 'Learning To Teach with Knowledge Transfer (L2T-KT)', and establish a 'Quiz Pool' as the teacher's optimization target. Experiments show that the proposed framework is able to utilize the undiagnosed data effectively to improve the glaucoma prediction performance.

Space and time are crucial twins in physics. In quantum mechanics, spatial correlations already reveal nonclassical features, such as entanglement, and have bred many quantum technologies. However, the nature of quantum temporal correlations still remains in vague. In this Letter, based on the entangled-history formalism, we prove rigorously that temporal correlations are equivalent to spatial correlations. The effect of temporal correlations corresponds to a quantum channel. The resulting quantifications and classifications of quantum temporal correlations are illustrated in a natural way. Our proposed procedures also show how to determine temporal correlations completely.

We propose a new measure of relative incompatibility for a quantum system with respect to two non-commuting observables, and call it quantumness of relative incompatibility. In case of a classical state, order of observation is inconsequential, hence probability distribution of outcomes of any observable remains undisturbed. We define relative entropy of the two marginal probability distributions as a measure of quantumness in the state, which is revealed only in presence of two non-commuting observables. Like all other measures, we show that the proposed measure satisfies some basic axioms. Also, we find that this measure depicts complementarity with quantum coherence. The relation is more vivid when we choose one of the observables in such a way that its eigen basis matches with the basis in which the coherence is measured. Our result indicates that the quantumness in a single system is still an interesting question to explore and there can be an inherent feature of the state which manifests beyond the idea of quantum coherence., Comment: 7 pages, 4 figures