Search

Diffusion Probabilistic Models have recently attracted significant attention in the community of computer vision due to their outstanding performance. However, while a substantial amount of diffusion-based research has focused on generative tasks, no work introduces diffusion models to advance the results of polyp segmentation in videos, which is frequently challenged by polyps' high camouflage and redundant temporal cues.In this paper, we present a novel diffusion-based network for video polyp segmentation task, dubbed as Diff-VPS. We incorporate multi-task supervision into diffusion models to promote the discrimination of diffusion models on pixel-by-pixel segmentation. This integrates the contextual high-level information achieved by the joint classification and detection tasks. To explore the temporal dependency, Temporal Reasoning Module (TRM) is devised via reasoning and reconstructing the target frame from the previous frames. We further equip TRM with a generative adversarial self-supervised strategy to produce more realistic frames and thus capture better dynamic cues. Extensive experiments are conducted on SUN-SEG, and the results indicate that our proposed Diff-VPS significantly achieves state-of-the-art performance. Code is available at https://github.com/lydia-yllu/Diff-VPS.

Video Shadow Detection (VSD) aims to detect the shadow masks with frame sequence. Existing works suffer from inefficient temporal learning. Moreover, few works address the VSD problem by considering the characteristic (i.e., boundary) of shadow. Motivated by this, we propose a Timeline and Boundary Guided Diffusion (TBGDiff) network for VSD where we take account of the past-future temporal guidance and boundary information jointly. In detail, we design a Dual Scale Aggregation (DSA) module for better temporal understanding by rethinking the affinity of the long-term and short-term frames for the clipped video. Next, we introduce Shadow Boundary Aware Attention (SBAA) to utilize the edge contexts for capturing the characteristics of shadows. Moreover, we are the first to introduce the Diffusion model for VSD in which we explore a Space-Time Encoded Embedding (STEE) to inject the temporal guidance for Diffusion to conduct shadow detection. Benefiting from these designs, our model can not only capture the temporal information but also the shadow property. Extensive experiments show that the performance of our approach overtakes the state-of-the-art methods, verifying the effectiveness of our components. We release the codes, weights, and results at \url{https://github.com/haipengzhou856/TBGDiff}., Comment: ACM MM2024

Breast magnetic resonance imaging (MRI) is the imaging technique with the highest sensitivity for detecting breast cancer and is routinely used for women at high risk. Despite the comprehensive multiparametric protocol of breast MRI, existing artificial intelligence-based studies predominantly rely on single sequences and have limited validation. Here we report a large mixture-of-modality-experts model (MOME) that integrates multiparametric MRI information within a unified structure, offering a noninvasive method for personalized breast cancer management. We have curated the largest multiparametric breast MRI dataset, involving 5,205 patients from three hospitals in the north, southeast, and southwest of China, for the development and extensive evaluation of our model. MOME demonstrated accurate and robust identification of breast cancer. It achieved comparable performance for malignancy recognition to that of four senior radiologists and significantly outperformed a junior radiologist, with 0.913 AUROC, 0.948 AUPRC, 0.905 F1 score, and 0.723 MCC. Our findings suggest that MOME could reduce the need for biopsies in BI-RADS 4 patients with a ratio of 7.3%, classify triple-negative breast cancer with an AUROC of 0.709, and predict pathological complete response to neoadjuvant chemotherapy with an AUROC of 0.694. The model further supports scalable and interpretable inference, adapting to missing modalities and providing decision explanations by highlighting lesions and measuring modality contributions. MOME exemplifies a discriminative, robust, scalable, and interpretable multimodal model, paving the way for noninvasive, personalized management of breast cancer patients based on multiparametric breast imaging data., Comment: 27 pages, 8 figures, 10 tables

Existing state-of-the-art methods for surgical phase recognition either rely on the extraction of spatial-temporal features at a short-range temporal resolution or adopt the sequential extraction of the spatial and temporal features across the entire temporal resolution. However, these methods have limitations in modeling spatial-temporal dependency and addressing spatial-temporal redundancy: 1) These methods fail to effectively model spatial-temporal dependency, due to the lack of long-range information or joint spatial-temporal modeling. 2) These methods utilize dense spatial features across the entire temporal resolution, resulting in significant spatial-temporal redundancy. In this paper, we propose the Surgical Transformer (Surgformer) to address the issues of spatial-temporal modeling and redundancy in an end-to-end manner, which employs divided spatial-temporal attention and takes a limited set of sparse frames as input. Moreover, we propose a novel Hierarchical Temporal Attention (HTA) to capture both global and local information within varied temporal resolutions from a target frame-centric perspective. Distinct from conventional temporal attention that primarily emphasizes dense long-range similarity, HTA not only captures long-term information but also considers local latent consistency among informative frames. HTA then employs pyramid feature aggregation to effectively utilize temporal information across diverse temporal resolutions, thereby enhancing the overall temporal representation. Extensive experiments on two challenging benchmark datasets verify that our proposed Surgformer performs favorably against the state-of-the-art methods. The code is released at https://github.com/isyangshu/Surgformer.

We demonstrate a compact ion beam device capable of accelerating H$^+$ and D$^+$ ions up to 75keV energy, on to a solid target, with sufficient beam current to study fusion reactions. The ion beam system uses a microwave driven plasma source to generate ions that are accelerated to high energy with a direct current (DC) acceleration structure. The plasma source is driven by pulsed microwaves from a solid-state radiofrequency (RF) amplifier, which is impedance matched to the plasma source chamber at the ISM band frequency (2.4-2.5GHz). The plasma chamber is held at high positive DC potential and is isolated from the impedance matching structure (at ground potential) by a dielectric-filled gap. To facilitate the use of high-energy-particle detectors near the target, the plasma chamber is biased to a high positive voltage, while the target remains grounded. A target loaded with deuterium is used to study D-D fusion and a B$_4$C or LaB$_6$ target is used to study p-$^{11}$B fusion. Detectors include solid-state charged particle detector and a scintillation fast neutron detector. The complete ion beam system can fit on a laboratory table and is a useful tool for teaching undergraduate and graduate students about the physics of fusion., Comment: 21 pages, 13 figures, accepted manuscript in Physics Open (ISSN: 2666-0326)

Accurate vessel segmentation in Ultra-Wide-Field Scanning Laser Ophthalmoscopy (UWF-SLO) images is crucial for diagnosing retinal diseases. Although recent techniques have shown encouraging outcomes in vessel segmentation, models trained on one medical dataset often underperform on others due to domain shifts. Meanwhile, manually labeling high-resolution UWF-SLO images is an extremely challenging, time-consuming and expensive task. In response, this study introduces a pioneering framework that leverages a patch-based active domain adaptation approach. By actively recommending a few valuable image patches by the devised Cascade Uncertainty-Predominance (CUP) selection strategy for labeling and model-finetuning, our method significantly improves the accuracy of UWF-SLO vessel segmentation across diverse medical centers. In addition, we annotate and construct the first Multi-center UWF-SLO Vessel Segmentation (MU-VS) dataset to promote this topic research, comprising data from multiple institutions. This dataset serves as a valuable resource for cross-center evaluation, verifying the effectiveness and robustness of our approach. Experimental results demonstrate that our approach surpasses existing domain adaptation and active learning methods, considerably reducing the gap between the Upper and Lower bounds with minimal annotations, highlighting our method's practical clinical value. We will release our dataset and code to facilitate relevant research: https://github.com/whq-xxh/SFADA-UWF-SLO., Comment: MICCAI 2024 Early Accept

Automatic report generation has arisen as a significant research area in computer-aided diagnosis, aiming to alleviate the burden on clinicians by generating reports automatically based on medical images. In this work, we propose a novel framework for automatic ultrasound report generation, leveraging a combination of unsupervised and supervised learning methods to aid the report generation process. Our framework incorporates unsupervised learning methods to extract potential knowledge from ultrasound text reports, serving as the prior information to guide the model in aligning visual and textual features, thereby addressing the challenge of feature discrepancy. Additionally, we design a global semantic comparison mechanism to enhance the performance of generating more comprehensive and accurate medical reports. To enable the implementation of ultrasound report generation, we constructed three large-scale ultrasound image-text datasets from different organs for training and validation purposes. Extensive evaluations with other state-of-the-art approaches exhibit its superior performance across all three datasets. Code and dataset are valuable at this link.

Unsupervised semantic segmentation (USS) aims to achieve high-quality segmentation without manual pixel-level annotations. Existing USS models provide coarse category classification for regions, but the results often have blurry and imprecise edges. Recently, a robust framework called the segment anything model (SAM) has been proven to deliver precise boundary object masks. Therefore, this paper proposes a universal organizer based on SAM, termed as UO-SAM, to enhance the mask quality of USS models. Specifically, using only the original image and the masks generated by the USS model, we extract visual features to obtain positional prompts for target objects. Then, we activate a local region optimizer that performs segmentation using SAM on a per-object basis. Finally, we employ a global region optimizer to incorporate global image information and refine the masks to obtain the final fine-grained masks. Compared to existing methods, our UO-SAM achieves state-of-the-art performance., Comment: accepted by IEEE International Conference on Multimedia & Expo

The Vision Transformer (ViT) has demonstrated remarkable performance in Self-Supervised Learning (SSL) for 3D medical image analysis. Mask AutoEncoder (MAE) for feature pre-training can further unleash the potential of ViT on various medical vision tasks. However, due to large spatial sizes with much higher dimensions of 3D medical images, the lack of hierarchical design for MAE may hinder the performance of downstream tasks. In this paper, we propose a novel \textit{Mask in Mask (MiM)} pre-training framework for 3D medical images, which aims to advance MAE by learning discriminative representation from hierarchical visual tokens across varying scales. We introduce multiple levels of granularity for masked inputs from the volume, which are then reconstructed simultaneously ranging at both fine and coarse levels. Additionally, a cross-level alignment mechanism is applied to adjacent level volumes to enforce anatomical similarity hierarchically. Furthermore, we adopt a hybrid backbone to enhance the hierarchical representation learning efficiently during the pre-training. MiM was pre-trained on a large scale of available 3D volumetric images, \textit{i.e.,} Computed Tomography (CT) images containing various body parts. Extensive experiments on thirteen public datasets demonstrate the superiority of MiM over other SSL methods in organ/lesion/tumor segmentation and disease classification. We further scale up the MiM to large pre-training datasets with more than 10k volumes, showing that large-scale pre-training can further enhance the performance of downstream tasks. The improvement also concluded that the research community should pay more attention to the scale of the pre-training dataset towards the healthcare foundation model for 3D medical images., Comment: submitted to journal

Twisted and coiled polymer actuators (TCPAs) generate large contractile mechanical work mimicking natural muscles, which makes them suitable for robotics and health-assistive devices. Understanding the mechanism of nylon TCPA remains challenging due to the interplay between their intricate geometry, chirality, residual stresses, and material microstructure. This study integrates a material microstructure model with rod theory to analytically predict the equilibrium helical shape of the nylon TCPA after fabrication and to explain the observed contraction mechanism upon stimulation. The first ingredient of the model is to treat nylon as a two-phase thermomechanical microstructure system capable of storing strain energy and exchanging it among the two phases. This is validated by characterizing the torsional actuation response of twisted and annealed nylon fibers. The second ingredient of the model is to use the classic Kirchhoff Rod Theory and add a necessary term that couples the bending and twisting energy. Validation with experiments shows that the model captures the equilibrium and longitudinal stiffness of the TCPA in both active and passive states, and the stimulated contraction under external load. Importantly, the model quantifies the influence of the stored energy level on the actuation performance. These concepts can be extended to other types of TCPAs and could enable new material design.

Multimodal pre-training demonstrates its potential in the medical domain, which learns medical visual representations from paired medical reports. However, many pre-training tasks require extra annotations from clinicians, and most of them fail to explicitly guide the model to learn the desired features of different pathologies. To the best of our knowledge, we are the first to utilize Visual Question Answering (VQA) for multimodal pre-training to guide the framework focusing on targeted pathological features. In this work, we leverage descriptions in medical reports to design multi-granular question-answer pairs associated with different diseases, which assist the framework in pre-training without requiring extra annotations from experts. We also propose a novel pre-training framework with a quasi-textual feature transformer, a module designed to transform visual features into a quasi-textual space closer to the textual domain via a contrastive learning strategy. This narrows the vision-language gap and facilitates modality alignment. Our framework is applied to four downstream tasks: report generation, classification, segmentation, and detection across five datasets. Extensive experiments demonstrate the superiority of our framework compared to other state-of-the-art methods. Our code will be released upon acceptance.

Solar cells based on inorganic perovskite CsPbI3 are promising candidates to resolve the challenge of operational stability in the field of perovskite photovoltaics. For stable operation, however, it is crucial to thoroughly understand the extractive and recombinative processes occurring at the interfaces of perovskite and the charge-selective layers. In this study, we focus on the electronic properties of (doped) TiO2 as an electron-selective contact. We show via KPFM that co-doping of TiO2 with Nb(V) and Sn(IV) reduces the materials work function by 270 meV, giving it stronger n-type characteristics compared to Nb(V) mono-doped TiO2. The altered electronic alignment with CsPbI3 translates to enhanced electron extraction, as demonstrated with ssPL, trPL and trSPV in triad. Importantly, we extract crucial parameters, such as the concentration of extracted electrons and the interface hole recombination velocity, from the SPV transients via 2D drift-diffusion simulations. When implementing the co-doped TiO2 into full n-i-p solar cells, the operational stability is enhanced to 32000 h of projected TS80 lifetime. This study provides fundamental understanding of interfacial charge extraction and its correlation with operational stability of perovskite solar cells, which can be transferred to other charge-selective contacts., Comment: 20 pages, 2 figures

A snap-through bifurcation occurs when a bistable structure loses one of its stable states and moves rapidly to the remaining state. For example, a buckled arch with symmetrically clamped ends can snap between an inverted and a natural state as the ends are released. A standard linear stability analysis suggests that the arch becomes unstable to asymmetric perturbations. Surprisingly, our experiments show that this is not always the case: symmetric transitions are also observed. Using experiments, numerics, and a toy model, we show that the symmetry of the transition depends on the rate at which the ends are released with sufficiently fast loading leading to symmetric snap-through. Our toy model reveals that this behavior is caused by a region of the system's state space in which any initial asymmetry is amplified. The system may not enter this region when loaded fast (hence remaining symmetric) but will traverse it for some interval of time when loaded slowly, causing a transient amplification of asymmetry. Our toy model suggests that this behavior is not unique to snapping arches, but rather can be observed in dynamical systems where both a saddle-node and a pitchfork bifurcation occur in close proximity., Comment: 6 pages main text + 19 pages of supplementary material

Laparoscopic surgery offers minimally invasive procedures with better patient outcomes, but smoke presence challenges visibility and safety. Existing learning-based methods demand large datasets and high computational resources. We propose the Progressive Frequency-Aware Network (PFAN), a lightweight GAN framework for laparoscopic image desmoking, combining the strengths of CNN and Transformer for progressive information extraction in the frequency domain. PFAN features CNN-based Multi-scale Bottleneck-Inverting (MBI) Blocks for capturing local high-frequency information and Locally-Enhanced Axial Attention Transformers (LAT) for efficiently handling global low-frequency information. PFAN efficiently desmokes laparoscopic images even with limited training data. Our method outperforms state-of-the-art approaches in PSNR, SSIM, CIEDE2000, and visual quality on the Cholec80 dataset and retains only 629K parameters. Our code and models are made publicly available at: https://github.com/jlzcode/PFAN.

Breast lesion segmentation in ultrasound (US) videos is essential for diagnosing and treating axillary lymph node metastasis. However, the lack of a well-established and large-scale ultrasound video dataset with high-quality annotations has posed a persistent challenge for the research community. To overcome this issue, we meticulously curated a US video breast lesion segmentation dataset comprising 572 videos and 34,300 annotated frames, covering a wide range of realistic clinical scenarios. Furthermore, we propose a novel frequency and localization feature aggregation network (FLA-Net) that learns temporal features from the frequency domain and predicts additional lesion location positions to assist with breast lesion segmentation. We also devise a localization-based contrastive loss to reduce the lesion location distance between neighboring video frames within the same video and enlarge the location distances between frames from different ultrasound videos. Our experiments on our annotated dataset and two public video polyp segmentation datasets demonstrate that our proposed FLA-Net achieves state-of-the-art performance in breast lesion segmentation in US videos and video polyp segmentation while significantly reducing time and space complexity. Our model and dataset are available at https://github.com/jhl-Det/FLA-Net., Comment: 10 pages

Tin perovskites are the most promising environmentally friendly alternative to lead perovskites. Among tin perovskites, FASnI3 (CH4N2SnI3) shows optimum band gap, and easy processability. However, the performance of FASnI3 based solar cells is incomparable to lead perovskites for several reasons, including energy band mismatch between the perovskite absorber film and the charge transporting layers (CTLs) for both types of carriers, i.e., for electrons (ETLs) and holes (HTLs). However, the band diagrams in the literature are inconsistent, and the charge extraction dynamics are poorly understood. In this paper, we study the energy band positions of FASnI3 based perovskites using Kelvin probe (KP) and photoelectron yield spectroscopy (PYS) to provide a precise band diagram of the most used device stack. In addition, we analyze the defects within the current energetic landscape of tin perovskites. We uncover the role of bathocuproine (BCP) in enhancing the electron extraction at the fullerene C60/BCP interface. Furthermore, we used transient surface photovoltage (tr-SPV) for the first time for tin perovskites to understand the charge extraction dynamics of the most reported HTLs such as NiOx and PEDOT, and ETLs such as C60, ICBA, and PCBM. Finally, we used Hall effect, KP, and time-resolved photoluminescence (TRPL) to estimate an accurate value of the p-doping concentration in FASnI3 and showed a consistent result of 1.5 * 1017 cm-3. Our findings prove that the energetic system of tin halide perovskites is deformed and should be redesigned independently from lead perovskites to unlock the full potential of tin perovskites., Comment: 22 pages, 5 figures

Large-scale well-annotated datasets are of great importance for training an effective object detector. However, obtaining accurate bounding box annotations is laborious and demanding. Unfortunately, the resultant noisy bounding boxes could cause corrupt supervision signals and thus diminish detection performance. Motivated by the observation that the real ground-truth is usually situated in the aggregation region of the proposals assigned to a noisy ground-truth, we propose DIStribution-aware CalibratiOn (DISCO) to model the spatial distribution of proposals for calibrating supervision signals. In DISCO, spatial distribution modeling is performed to statistically extract the potential locations of objects. Based on the modeled distribution, three distribution-aware techniques, i.e., distribution-aware proposal augmentation (DA-Aug), distribution-aware box refinement (DA-Ref), and distribution-aware confidence estimation (DA-Est), are developed to improve classification, localization, and interpretability, respectively. Extensive experiments on large-scale noisy image datasets (i.e., Pascal VOC and MS-COCO) demonstrate that DISCO can achieve state-of-the-art detection performance, especially at high noise levels. Code is available at https://github.com/Correr-Zhou/DISCO., Comment: Accepted by BMVC2024

In perovskite solar cells (PSCs) energy levels alignment and charge extraction at the interfaces are the essential factors directly affecting the device performance. In this work, we present a modified interface between all-inorganic CsPbI$_3$ perovskite and its hole selective contact (Spiro-OMeTAD), realized by a dipole molecule trioctylphosphine oxide (TOPO), to align the energy levels. On a passivated perovskite film, by n-Octyl ammonium Iodide (OAI), we created an upward surface band-bending at the interface by TOPO treatment. This improved interface by the dipole molecule induces a better energy level alignment and enhances the charge extraction of holes from the perovskite layer to the hole transport material. Consequently, a Voc of 1.2 V and high-power conversion efficiency (PCE) of over 19% were achieved for inorganic CsPbI$_3$ perovskite solar cells. Further, to demonstrate the effect of the TOPO dipole molecule, we present a layer-by-layer charge extraction study by transient surface photovoltage technique (trSPV) accomplished by charge transport simulation., Comment: 20 pages, 4 Figures

Semi-supervised semantic segmentation aims to learn from a small amount of labeled data and plenty of unlabeled ones for the segmentation task. The most common approach is to generate pseudo-labels for unlabeled images to augment the training data. However, the noisy pseudo-labels will lead to cumulative classification errors and aggravate the local inconsistency in prediction. This paper proposes a Region Relevance Network (RRN) to alleviate the problem mentioned above. Specifically, we first introduce a local pseudo-label filtering module that leverages discriminator networks to assess the accuracy of the pseudo-label at the region level. A local selection loss is proposed to mitigate the negative impact of wrong pseudo-labels in consistency regularization training. In addition, we propose a dynamic region-loss correction module, which takes the merit of network diversity to further rate the reliability of pseudo-labels and correct the convergence direction of the segmentation network with a dynamic region loss. Extensive experiments are conducted on PASCAL VOC 2012 and Cityscapes datasets with varying amounts of labeled data, demonstrating that our proposed approach achieves state-of-the-art performance compared to current counterparts., Comment: accepted by IEEE International Conference on Multimedia and Expo 2023

Collecting annotations from multiple independent sources could mitigate the impact of potential noises and biases from a single source, which is a common practice in medical image segmentation. Learning segmentation networks from multi-source annotations remains a challenge due to the uncertainties brought by the variance of annotations and the quality of images. In this paper, we propose an Uncertainty-guided Multi-source Annotation Network (UMA-Net), which guides the training process by uncertainty estimation at both the pixel and the image levels. First, we developed the annotation uncertainty estimation module (AUEM) to learn the pixel-wise uncertainty of each annotation, which then guided the network to learn from reliable pixels by weighted segmentation loss. Second, a quality assessment module (QAM) was proposed to assess the image-level quality of the input samples based on the former assessed annotation uncertainties. Importantly, we introduced an auxiliary predictor to learn from the low-quality samples instead of discarding them, which ensured the preservation of their representation knowledge in the backbone without directly accumulating errors within the primary predictor. Extensive experiments demonstrated the effectiveness and feasibility of our proposed UMA-Net on various datasets, including 2D chest X-ray segmentation, fundus image segmentation, and 3D breast DCE-MRI segmentation.