arXiv subjects

Yifeng Wang

Publications and source records attributed to Yifeng Wang.

50 records · Page 3Linked to original sources

arXiv2024

Boundary-aware Contrastive Learning for Semi-supervised Nuclei Instance Segmentation

Semi-supervised segmentation methods have demonstrated promising results in natural scenarios, providing a solution to reduce dependency on manual annotation. However, these methods face significant challenges when directly applied to pathological images due to the subtle color differences between nuclei and tissues, as well as the significant morphological variations among nuclei. Consequently, the generated pseudo-labels often contain much noise, especially at the nuclei boundaries. To address the above problem, this paper proposes a boundary-aware contrastive learning network to denoise the boundary noise in a semi-supervised nuclei segmentation task. The model has two key designs: a low-resolution denoising (LRD) module and a cross-RoI contrastive learning (CRC) module. The LRD improves the smoothness of the nuclei boundary by pseudo-labels denoising, and the CRC enhances the discrimination between foreground and background by boundary feature contrastive learning. We conduct extensive experiments to demonstrate the superiority of our proposed method over existing semi-supervised instance segmentation methods.

cs.CV↗

arXiv2023

Wavelet Dynamic Selection Network for Inertial Sensor Signal Enhancement

As attitude and motion sensing components, inertial sensors are widely used in various portable devices. But the severe errors of inertial sensors restrain their function, especially the trajectory recovery and semantic recognition. As a mainstream signal processing method, wavelet is hailed as the mathematical microscope of signal due to the plentiful and diverse wavelet basis functions. However, complicated noise types and application scenarios of inertial sensors make selecting wavelet basis perplexing. To this end, we propose a wavelet dynamic selection network (WDSNet), which intelligently selects the appropriate wavelet basis for variable inertial signals. In addition, existing deep learning architectures excel at extracting features from input data but neglect to learn the characteristics of target categories, which is essential to enhance the category awareness capability, thereby improving the selection of wavelet basis. Therefore, we propose a category representation mechanism (CRM), which enables the network to extract and represent category features without increasing trainable parameters. Furthermore, CRM transforms the common fully connected network into category representations, which provide closer supervision to the feature extractor than the far and trivial one-hot classification labels. We call this process of imposing interpretability on a network and using it to supervise the feature extractor the feature supervision mechanism, and its effectiveness is demonstrated experimentally and theoretically in this paper. The enhanced inertial signal can perform impracticable tasks with regard to the original signal, such as trajectory reconstruction. Both quantitative and visual results show that WDSNet outperforms the existing methods. Remarkably, WDSNet, as a weakly-supervised method, achieves the state-of-the-art performance of all the compared fully-supervised methods.

eess.SP↗

arXiv2023

Learning Robust Medical Image Segmentation from Multi-source Annotations

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.

eess.IV↗

arXiv2023

Rapid Image Labeling via Neuro-Symbolic Learning

The success of Computer Vision (CV) relies heavily on manually annotated data. However, it is prohibitively expensive to annotate images in key domains such as healthcare, where data labeling requires significant domain expertise and cannot be easily delegated to crowd workers. To address this challenge, we propose a neuro-symbolic approach called Rapid, which infers image labeling rules from a small amount of labeled data provided by domain experts and automatically labels unannotated data using the rules. Specifically, Rapid combines pre-trained CV models and inductive logic learning to infer the logic-based labeling rules. Rapid achieves a labeling accuracy of 83.33% to 88.33% on four image labeling tasks with only 12 to 39 labeled samples. In particular, Rapid significantly outperforms finetuned CV models in two highly specialized tasks. These results demonstrate the effectiveness of Rapid in learning from small data and its capability to generalize among different tasks. Code and our dataset are publicly available at https://github.com/Neural-Symbolic-Image-Labeling/

cs.CV↗

arXiv2023

AugDiff: Diffusion based Feature Augmentation for Multiple Instance Learning in Whole Slide Image

Multiple Instance Learning (MIL), a powerful strategy for weakly supervised learning, is able to perform various prediction tasks on gigapixel Whole Slide Images (WSIs). However, the tens of thousands of patches in WSIs usually incur a vast computational burden for image augmentation, limiting the MIL model's improvement in performance. Currently, the feature augmentation-based MIL framework is a promising solution, while existing methods such as Mixup often produce unrealistic features. To explore a more efficient and practical augmentation method, we introduce the Diffusion Model (DM) into MIL for the first time and propose a feature augmentation framework called AugDiff. Specifically, we employ the generation diversity of DM to improve the quality of feature augmentation and the step-by-step generation property to control the retention of semantic information. We conduct extensive experiments over three distinct cancer datasets, two different feature extractors, and three prevalent MIL algorithms to evaluate the performance of AugDiff. Ablation study and visualization further verify the effectiveness. Moreover, we highlight AugDiff's higher-quality augmented feature over image augmentation and its superiority over self-supervised learning. The generalization over external datasets indicates its broader applications.

cs.CV↗

arXiv2022

Human Health Indicator Prediction from Gait Video

Body Mass Index (BMI), age, height and weight are important indicators of human health conditions, which can provide useful information for plenty of practical purposes, such as health care, monitoring and re-identification. Most existing methods of health indicator prediction mainly use front-view body or face images. These inputs are hard to be obtained in daily life and often lead to the lack of robustness for the models, considering their strict requirements on view and pose. In this paper, we propose to employ gait videos to predict health indicators, which are more prevalent in surveillance and home monitoring scenarios. However, the study of health indicator prediction from gait videos using deep learning was hindered due to the small amount of open-sourced data. To address this issue, we analyse the similarity and relationship between pose estimation and health indicator prediction tasks, and then propose a paradigm enabling deep learning for small health indicator datasets by pre-training on the pose estimation task. Furthermore, to better suit the health indicator prediction task, we bring forward Global-Local Aware aNd Centrosymmetric Encoder (GLANCE) module. It first extracts local and global features by progressive convolutions and then fuses multi-level features by a centrosymmetric double-path hourglass structure in two different ways. Experiments demonstrate that the proposed paradigm achieves state-of-the-art results for predicting health indicators on MoVi, and that the GLANCE module is also beneficial for pose estimation on 3DPW.

cs.CV↗

arXiv2022

Temperature effect on non-Darcian flow in low-permeability porous media

In low-permeability porous media, the velocity of a fluid flow exhibits a nonlinear dependence on the imposed pressure gradient. This non-Darcian flow behavior has important implications to geological disposal of nuclear waste, hydrocarbon extraction from shale, and flow and transport in clay-rich aquifers. Temperature has been postulated to affect the threshold pressure gradient of a non-Darcian flow; however, the supporting data is very limited. In this study we for the first time report a systematic measurement of the threshold pressure gradient under various permeabilities and temperatures. The results show that a higher temperature leads to a lower threshold pressure gradient under the same permeability and a faster reduction of the threshold pressure gradient with increasing permeability. The experimental data are fitted to a two-parameter model to determine the parameters, h0 and a, which characterize the interfacial fluid-solid interactions and the transition between the Darcy and non-Darcian regimes.

physics.geo-ph↗

arXiv2022

Multiple Instance Learning with Mixed Supervision in Gleason Grading

With the development of computational pathology, deep learning methods for Gleason grading through whole slide images (WSIs) have excellent prospects. Since the size of WSIs is extremely large, the image label usually contains only slide-level label or limited pixel-level labels. The current mainstream approach adopts multi-instance learning to predict Gleason grades. However, some methods only considering the slide-level label ignore the limited pixel-level labels containing rich local information. Furthermore, the method of additionally considering the pixel-level labels ignores the inaccuracy of pixel-level labels. To address these problems, we propose a mixed supervision Transformer based on the multiple instance learning framework. The model utilizes both slide-level label and instance-level labels to achieve more accurate Gleason grading at the slide level. The impact of inaccurate instance-level labels is further reduced by introducing an efficient random masking strategy in the mixed supervision training process. We achieve the state-of-the-art performance on the SICAPv2 dataset, and the visual analysis shows the accurate prediction results of instance level. The source code is available at https://github.com/bianhao123/Mixed_supervision.

cs.CV↗

arXiv2021

An Equation for Predicting Binding Strengths of Metal Cations to Protein of Human Serum Transferrin

Because human serum transferrin (hTF) exists freely in serum, it is a potential target for cancer treatment drugs and in curing iron-overloaded conditions in patients via long-term transfusion therapy. The understanding of the interactions between hTF and metal ions is very important for biological, pharmalogical, toxicological, and other protein engineering purposes. In this paper, a simple linear free energy correlation is proposed to predict the binding strength between hTF protein and metal cations. The stability constants for a family of metal-hTF complexes can be correlated to the non-solvation energies and the radii of cations. The binding strength is determined by both the physical properties (charge and size or ionic radius) and chemical properties (non-solvation energy) of a given cation. The binding strengths of either divalent and trivalent metals can then be predicted systematically.

q-bio.BM↗

arXiv2021

TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification

Multiple instance learning (MIL) is a powerful tool to solve the weakly supervised classification in whole slide image (WSI) based pathology diagnosis. However, the current MIL methods are usually based on independent and identical distribution hypothesis, thus neglect the correlation among different instances. To address this problem, we proposed a new framework, called correlated MIL, and provided a proof for convergence. Based on this framework, we devised a Transformer based MIL (TransMIL), which explored both morphological and spatial information. The proposed TransMIL can effectively deal with unbalanced/balanced and binary/multiple classification with great visualization and interpretability. We conducted various experiments for three different computational pathology problems and achieved better performance and faster convergence compared with state-of-the-art methods. The test AUC for the binary tumor classification can be up to 93.09% over CAMELYON16 dataset. And the AUC over the cancer subtypes classification can be up to 96.03% and 98.82% over TCGA-NSCLC dataset and TCGA-RCC dataset, respectively. Implementation is available at: https://github.com/szc19990412/TransMIL.

cs.CV↗

arXiv2019

Stabilizing effect of enhanced resistivity on peeling-ballooning instabilities on EAST

Previous stability analysis of NSTX equilibrium with lithium-conditioning demonstrates that the enhanced resistivity due to the increased effective charge number Zeff (i.e. increased impurity level) can provide a stabilizing effect on low-n edge localized modes (Banerjee et al 2017 Nucl. Fusion 24 054501). This paper extends the resistivity stabilizing effect to the intermediate-n peeling-ballooning (PB) instabilities with the linear stability analysis of EAST high-confinement mode equilibria in NIMROD two-fluid calculations. However, the resistivity stabilizing effect on PB instabilities in the EAST tokamak appears weaker than that found in NSTX. This work may give better insight into the physical mechanism behind the beneficial effects of impurity on the pedestal stability.

physics.plasm-ph↗

arXiv2017

Feasibility of Direct Disposal of Salt Waste from Electochemical Processing of Spent Nuclear Fuel

The US Department of Energy decided in 2000 to treat its sodium-bonded spent nuclear fuel, produced for experiments on breeder reactors, with an electrochemical process. The metallic waste produced is to be cast into ingots and the salt waste further processed to form a ceramic waste form for disposal in a mined repository. However, alternative disposal pathways for metallic and salt waste streams are being investigated that may reduce the processing complexity. As summarized here, performance assessments analyzing the direct disposal the salt waste demonstrate that both mined repositories in salt and deep boreholes in basement crystalline rock can easily accommodate the salt waste. Also summarized here is an analysis of the feasibility of transporting the salt waste in a proposed vessel. The vessel is viable for transport to and disposal in a generic mined repository in salt or deep borehole but a portion of the salt waste would need to be diluted for disposal in the Waste Isolation Pilot Plant. The generally positive results continue to demonstrate the feasibility of direct disposal of salt waste after electrochemical processing of spent nuclear fuel.

physics.app-ph↗

arXiv2016

A Novel Approach for Stable Selection of Informative Redundant Features from High Dimensional fMRI Data

Feature selection is among the most important components because it not only helps enhance the classification accuracy, but also or even more important provides potential biomarker discovery. However, traditional multivariate methods is likely to obtain unstable and unreliable results in case of an extremely high dimensional feature space and very limited training samples, where the features are often correlated or redundant. In order to improve the stability, generalization and interpretations of the discovered potential biomarker and enhance the robustness of the resultant classifier, the redundant but informative features need to be also selected. Therefore we introduced a novel feature selection method which combines a recent implementation of the stability selection approach and the elastic net approach. The advantage in terms of better control of false discoveries and missed discoveries of our approach, and the resulted better interpretability of the obtained potential biomarker is verified in both synthetic and real fMRI experiments. In addition, we are among the first to demonstrate the robustness of feature selection benefiting from the incorporation of stability selection and also among the first to demonstrate the possible unrobustness of the classical univariate two-sample t-test method. Specifically, we show the robustness of our feature selection results in existence of noisy (wrong) training labels, as well as the robustness of the resulted classifier based on our feature selection results in the existence of data variation, demonstrated by a multi-center attention-deficit/hyperactivity disorder (ADHD) fMRI data.

cs.CV↗

arXiv2016

The role of ionized impurity scattering on the thermoelectric performances of rock salt AgPbmSnSe2+m

We report on the successful synthesis and on the properties of polycrystalline AgPbmSnSe2+m (m = ++++, 100, 50, 25) samples with a rock salt structure. Between 160 K and 400 K, the dominant scattering process of the carriers in this system changes from acoustic phonon scattering in PbSe to ionized impurity scattering in AgPbmSnSe2+m, which synergistically optimizes electrical and thermal transport properties. Thanks to the faint amount of AgSnSe2, the Seebeck coefficient is enhanced by boosting the scattering factor, the electric conductivity is improved by the increase of the concentration of holes coupled to a limited degradation of their mobility, and the total thermal conductivity is reduced by suppressing bipolar thermal conductivity. Therefore, ZT of AgPbmSnSe2+m (m = 50) reaches 1.3 at 889 K. The mechanism suggested in this study opens new paths to improve the thermoelectric performances of other families of materials.

cond-mat.mtrl-sci↗