arXiv subjects

Pengfei Song

Publications and source records attributed to Pengfei Song.

11 recordsLinked to original sources

arXiv2026

GMENet: Generative Mixture of Experts Network for Multi-Center Glioma Diagnosis with Incomplete Imaging Sequences

Contemporary glioma diagnosis integrates molecular features with histopathology to guide clinical decision-making. However, in clinical settings, divergent imaging protocols result in incomplete MRI sequences, leading to two primary challenges: forcing existing frameworks to discard a large portion of clinical data during training and consequently limiting their clinical applicability. To address these limitations, we propose GMENet, a Generative Mixture of Experts Network for multi-center glioma diagnosis with incomplete imaging sequences. Firstly, we design a Cross-attention-based Gated Generation Module that synthesizes missing sequence features from available sequences via cross-attention and dynamic gating mechanisms, incorporating a cycle-consistency loss to preserve semantic integrity. Secondly, we introduce a Dynamically Weighted Experts Fusion Module that performs mixture-of-experts interaction and confidence-aware fusion over original and synthesized dual-sequence features for multi-task prediction. We evaluate GMENet on a multi-center cohort of 1,241 subjects from four in-house datasets and two public repositories. Experiments show that GMENet expands clinically usable training data by 97\%, relative to complete-sequence-only data. Furthermore, it consistently outperforms state-of-the-art methods trained on complete data, demonstrating improved robustness under cross-center distribution shifts.

eess.IV↗

arXiv2026

DiCLIP: Diffusion Model Enhances CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically leverages Class Activation Maps (CAMs) to achieve pixel-level predictions. Recently, Contrastive Language-Image Pre-training (CLIP) has been introduced to generate CAMs in WSSS. However, previous WSSS methods solely adopt CLIP's vision-language paired property for dense localization, neglecting its inherently limited dense knowledge across both visual and text modalities, which renders CAM generation suboptimal. In this work, we propose DiCLIP, a novel WSSS framework that leverages the generative diffusion model to enhance CLIP's dense knowledge across two modalities. Specifically, Visual Correlation Enhancement (VCE) and Text Semantic Augmentation (TSA) modules are proposed for dense prediction enhancement. To improve the spatial awareness of visual features, our VCE module utilizes diffusion's reliable spatial consistency to mitigate the over-smoothing issue in CLIP's attention. It designs the Attention Clustering Refinement (ACR) module to reliably extract diverse correlation maps from the diffusion model. The correlation maps act as a diversity bias for CLIP's self-attention, recursively pushing its visual features towards a more discriminative dense distribution. To augment the semantics of text embeddings, our TSA module argues that a single text modality is insufficient to encompass the variability of visual categories. Thus, we leverage diffusion's generative power to maintain a dynamic key-value cache model, shifting CAM generation from a patch-text matching mechanism to a novel visual knowledge retrieval paradigm. With these enhancements, DiCLIP not only outperforms state-of-the-art methods on PASCAL VOC and MS COCO but also significantly reduces training costs. Code is publicly available at https://github.com/zwyang6/DiCLIP.

cs.CV↗

arXiv2023

Non-invasive Deep-Brain Imaging with 3D Integrated Photoacoustic Tomography and Ultrasound Localization Microscopy (3D-PAULM)

Photoacoustic computed tomography (PACT) is a proven technology for imaging hemodynamics in deep brain of small animal models. PACT is inherently compatible with ultrasound (US) imaging, providing complementary contrast mechanisms. While PACT can quantify the brain's oxygen saturation of hemoglobin (sO$_2$), US imaging can probe the blood flow based on the Doppler effect. Further, by tracking gas-filled microbubbles, ultrasound localization microscopy (ULM) can map the blood flow velocity with sub-diffraction spatial resolution. In this work, we present a 3D deep-brain imaging system that seamlessly integrates PACT and ULM into a single device, 3D-PAULM. Using a low ultrasound frequency of 4 MHz, 3D-PAULM is capable of imaging the whole-brain hemodynamic functions with intact scalp and skull in a totally non-invasive manner. Using 3D-PAULM, we studied the mouse brain functions with ischemic stroke. Multi-spectral PACT, US B-mode imaging, microbubble-enhanced power Doppler (PD), and ULM were performed on the same mouse brain with intrinsic image co-registration. From the multi-modality measurements, we future quantified blood perfusion, sO$_2$, vessel density, and flow velocity of the mouse brain, showing stroke-induced ischemia, hypoxia, and reduced blood flow. We expect that 3D-PAULM can find broad applications in studying deep brain functions on small animal models.

physics.ins-det↗

arXiv2023

Human Semantic Segmentation using Millimeter-Wave Radar Sparse Point Clouds

This paper presents a framework for semantic segmentation on sparse sequential point clouds of millimeter-wave radar. Compared with cameras and lidars, millimeter-wave radars have the advantage of not revealing privacy, having a strong anti-interference ability, and having long detection distance. The sparsity and capturing temporal-topological features of mmWave data is still a problem. However, the issue of capturing the temporal-topological coupling features under the human semantic segmentation task prevents previous advanced segmentation methods (e.g PointNet, PointCNN, Point Transformer) from being well utilized in practical scenarios. To address the challenge caused by the sparsity and temporal-topological feature of the data, we (i) introduce graph structure and topological features to the point cloud, (ii) propose a semantic segmentation framework including a global feature-extracting module and a sequential feature-extracting module. In addition, we design an efficient and more fitting loss function for a better training process and segmentation results based on graph clustering. Experimentally, we deploy representative semantic segmentation algorithms (Transformer, GCNN, etc.) on a custom dataset. Experimental results indicate that our model achieves mean accuracy on the custom dataset by $\mathbf{82.31}\%$ and outperforms the state-of-the-art algorithms. Moreover, to validate the model's robustness, we deploy our model on the well-known S3DIS dataset. On the S3DIS dataset, our model achieves mean accuracy by $\mathbf{92.6}\%$, outperforming baseline algorithms.

cs.CV↗

arXiv2023

High-resolution Power Doppler Using Null Subtraction Imaging

To improve the spatial resolution of power Doppler (PD) imaging, we explored null subtraction imaging (NSI) as an alternative beamforming technique to delay-and-sum (DAS). NSI is a nonlinear beamforming approach that uses three different apodizations on receive and incoherently sums the beamformed envelopes. NSI uses a null in the beam pattern to improve the lateral resolution, which we apply here for improving PD spatial resolution both with and without contrast microbubbles. In this study, we used NSI with three types of singular value decomposition (SVD)-based clutter filters and noise equalization to generate high-resolution PD images. An element sensitivity correction scheme was also proposed as a crucial component of NSI-based PD imaging. First, a microbubble trace experiment was performed to evaluate the resolution improvement of NSI-based PD over traditional DAS-based PD. Then, both contrast-enhanced and contrast free ultrasound PD images were generated from the scan of a rat brain. The cross-sectional profile of the microbubble traces and microvessels were plotted. FWHM was also estimated to provide a quantitative metric. Furthermore, iso-frequency curves were calculated to provide a resolution evaluation metric over the global field of view. Up to six-fold resolution improvement was demonstrated by the FWHM estimate and four-fold resolution improvement was demonstrated by the iso-frequency curve from the NSI-based PD microvessel images compared to microvessel images generated by traditional DAS-based beamforming. A resolvability of 39 um was measured from the NSI-based PD microvessel image. The computational cost of NSI-based PD was only increased by 40 percent over the DAS-based PD.

eess.SP↗

arXiv2022

Joint localization and classification of breast tumors on ultrasound images using a novel auxiliary attention-based framework

Automatic breast lesion detection and classification is an important task in computer-aided diagnosis, in which breast ultrasound (BUS) imaging is a common and frequently used screening tool. Recently, a number of deep learning-based methods have been proposed for joint localization and classification of breast lesions using BUS images. In these methods, features extracted by a shared network trunk are appended by two independent network branches to achieve classification and localization. Improper information sharing might cause conflicts in feature optimization in the two branches and leads to performance degradation. Also, these methods generally require large amounts of pixel-level annotated data for model training. To overcome these limitations, we proposed a novel joint localization and classification model based on the attention mechanism and disentangled semi-supervised learning strategy. The model used in this study is composed of a classification network and an auxiliary lesion-aware network. By use of the attention mechanism, the auxiliary lesion-aware network can optimize multi-scale intermediate feature maps and extract rich semantic information to improve classification and localization performance. The disentangled semi-supervised learning strategy only requires incomplete training datasets for model training. The proposed modularized framework allows flexible network replacement to be generalized for various applications. Experimental results on two different breast ultrasound image datasets demonstrate the effectiveness of the proposed method. The impacts of various network factors on model performance are also investigated to gain deep insights into the designed framework.

eess.IV↗

arXiv2022

High-level synthesis design of scalable ultrafast ultrasound beamformer with single FPGA

Ultrafast ultrasound imaging is essential for advanced ultrasound imaging techniques such as ultrasound localization microscopy (ULM) and functional ultrasound (fUS). Current ultrafast ultrasound imaging is challenged by the ultrahigh data bandwidth associated with the radio frequency (RF) signal, and by the latency of the computationally expensive beamforming process. As such, continuous ultrafast data acquisition and beamforming remain elusive with existing software beamformers based on CPUs or GPUs. To address these challenges, the proposed work introduces a novel method of implementing an ultrafast ultrasound beamformer specifically for ultrafast plane wave imaging (PWI) on a field programmable gate array (FPGA) by using high-level synthesis. A parallelized implementation of the beamformer on a single FPGA was proposed by 1) utilizing a delay compression technique to reduce the delay profile size, which enables both run-time pre-calculated delay profile loading from external memory and delay reuse 2) vectorizing channel data fetching which is enabled by delay reuse, and 3) using fixed summing networks to reduce consumption of logic resources. Our proposed method presents two unique advantages over current FPGA beamformers: 1) high scalability that allows fast adaptation to different FPGA resources and beamforming speed demands by using Xilinx High-Level Synthesis as the development tool, and 2) allow a compact form factor design by using a single FPGA to complete the beamforming instead of multiple FPGAs. With the proposed method, a sustainable average beamforming rate of 4.83 G samples/second in terms of input raw RF sample was achieved. The resulting image quality of the proposed beamformer was compared with the software beamformer on the Verasonics Vantage system for both phantom imaging and in vivo imaging of a mouse brain.

eess.SP↗

arXiv2022

A novel adversarial learning strategy for medical image classification

Deep learning (DL) techniques have been extensively utilized for medical image classification. Most DL-based classification networks are generally structured hierarchically and optimized through the minimization of a single loss function measured at the end of the networks. However, such a single loss design could potentially lead to optimization of one specific value of interest but fail to leverage informative features from intermediate layers that might benefit classification performance and reduce the risk of overfitting. Recently, auxiliary convolutional neural networks (AuxCNNs) have been employed on top of traditional classification networks to facilitate the training of intermediate layers to improve classification performance and robustness. In this study, we proposed an adversarial learning-based AuxCNN to support the training of deep neural networks for medical image classification. Two main innovations were adopted in our AuxCNN classification framework. First, the proposed AuxCNN architecture includes an image generator and an image discriminator for extracting more informative image features for medical image classification, motivated by the concept of generative adversarial network (GAN) and its impressive ability in approximating target data distribution. Second, a hybrid loss function is designed to guide the model training by incorporating different objectives of the classification network and AuxCNN to reduce overfitting. Comprehensive experimental studies demonstrated the superior classification performance of the proposed model. The effect of the network-related factors on classification performance was investigated.

eess.IV↗

arXiv2020

Super-Resolution Ultrasound Localization Microscopy Based on a High Frame-rate Clinical Ultrasound Scanner: An In-human Feasibility Study

Non-invasive detection of microvascular alterations in deep tissues in vivo provides critical information for clinical diagnosis and evaluation of a broad-spectrum of pathologies. Recently, the emergence of super-resolution ultrasound localization microscopy (ULM) offers new possibilities for clinical imaging of microvasculature at capillary level. Currently, the clinical utility of ULM on clinical ultrasound scanners is hindered by the technical limitations, such as long data acquisition time, and compromised tracking performance associated with low imaging frame-rate. Here we present an in-human ULM on a high frame-rate (HFR) clinical ultrasound scanner to achieve super-resolution microvessel imaging using a short acquisition time (<10s). Ultrasound MB data were acquired from different human tissues, (liver, kidney, pancreatic, and breast tumor) using an HFR clinical scanner. By leveraging the HFR and advanced processing techniques including sub-pixel motion registration, MB signal separation, and Kalman filter-based tracking, MBs can be robustly localized and tracked for successful ULM under the circumstances of relatively high MB concentration and limited data acquisition time in humans. Subtle morphological and hemodynamic information were demonstrated on data acquired with single breath-hold and free-hand scanning. Compared with contrast-enhanced power Doppler generated based on the same MB dataset, ULM showed a 5.7-fold resolution improvement in a vessel, and provided a wide-range flow speed measurement that is Doppler angle-independent. This study demonstrated the feasibility of ultrafast in-human ULM in various human tissues based on a clinical scanner that supports HFR imaging, and showed a great potential for the implementation of super-resolution ultrasound microvessel imaging in a myriad of clinical applications involving microvascular abnormalities and pathologies.

physics.med-ph↗

arXiv2019

Efficient Electrocatalytic Reduction of CO2 by Nitrogen-Doped Nanoporous Carbon-Carbon Nanotube Membranes - A Step Towards the Electrochemical CO2 Refinery

The search for earth abundant, efficient and stable electrocatalysts that can enable the chemical reduction of CO2 to value-added chemicals and fuels at an industrially relevant scale, is a high priority for the development of a global network of renewable energy conversion and storage systems that can meaningfully impact greenhouse gas induced climate change. Here we introduce a straightforward, low cost, scalable and technologically relevant method to manufacture an all-carbon, electroactive, nitrogen-doped nanoporous carbon-carbon nanotube composite membrane, dubbed "HNCM-CNT". The membrane is demonstrated to function as a binder-free, high-performance electrode for the electrocatalytic reduction of CO2 to formate. The Faradaic efficiency for the production of formate is 81%. Furthermore, the robust structural and electrochemical properties of the membrane endow it with excellent long-term stability.

physics.chem-ph↗

arXiv2019

Ambient Electro-Synthesis of Ammonia - Electrode Porosity and Composition Engineering

Ammonia, key precursor for fertilizer production, convenient hydrogen carrier and emerging clean fuel, plays a pivotal role in sustaining life on earth. Currently, the main route for NH3 synthesis is via the heterogeneous catalytic Haber-Bosch process (N2+3H2 - 2NH3), which proceeds under extreme conditions of temperature and pressure with a very large carbon footprint. Herein we report that a pristine nitrogen-doped nanoporous graphitic carbon membrane (NCM) can electrochemically convert N2 into NH3 in an aqueous acidic solution under ambient conditions. The Faradaic efficiency and rate of production of NH3 on the NCM electrode reach 5.2% and 0.08 g m-2 h-1, respectively. After functionalization of the NCM with Au nanoparticles (Au NPs) these performance metrics are dramatically enhanced to 22% and 0.36 g m-2 h-1, respectively. These efficiencies and rates for the production of NH3 at room temperature and atmospheric pressure are unprecedented. As this system offers the potential to be scaled to industrial proportions there is a high likelihood it might displace the century old Haber-Bosch process.

physics.chem-ph↗