arXiv subjects

Yuqi Ma

Publications and source records attributed to Yuqi Ma.

10 recordsLinked to original sources

arXiv2026

Radiology-Report Semantic Modelling and Host-Response Laboratory Biomarkers for Multimodal Survival Prediction in Lung Cancer

TNM staging is essential for lung cancer management, but patients within the same anatomic stage often show heterogeneous survival outcomes. We developed a multimodal adaptive risk score (AMRS) that integrates radiology-report semantics with routinely available clinical laboratory biomarkers. In a retrospective two-center cohort, 1129 patients diagnosed between December 2017 and February 2026 were screened; 574 patients were included after exclusion for short follow-up or missing imaging reports and were split into training (n = 459) and test (n = 115) cohorts. Radiology reports were encoded with a domain-adapted MC-BERT branch to capture imaging-derived semantic information, while clinical and laboratory variables were modeled after Mahalanobis-distance-based imputation using random survival forests. Weighted risk fusion generated the final patient-level score. AMRS achieved C-index values of 0.920 in training and 0.849 in testing, and separated survival trajectories across clinical subgroups and TNM-related strata. SHAP analysis identified hematologic, inflammatory, coagulation, nutritional, tumor-marker, organ-function, and age-related contributors. AMRS may complement TNM staging in imaging-centered oncology workflows, but prospective validation, calibration, ablation testing, and clinical-utility assessment are required before deployment.

physics.med-ph↗

arXiv2026

Patient-Level Diagnosis of Acute Myeloid Leukemia via Deep Learning Analysis of Bone Marrow Smear

Bone marrow smear review remains important for acute myeloid leukemia (AML) assessment, but manual single-cell interpretation is labor-intensive and patient-level diagnosis requires aggregation of many cellular observations. We present a cell-to-patient deep learning pipeline for AML-assisted diagnosis from bone marrow smear images. The study included 258 patients from six anonymized centers, including a main cohort of 169 patients from Centers 1-3 and an external validation cohort of 89 patients from Centers 4-6. A 16-category cell annotation vocabulary was used to describe the global cellular composition, including granulocytic, monocytic, erythroid, lymphoid, eosinophilic, and other cells. Rather than identifying strict AML blasts or leukemic blasts, the model targets an expert-defined composite category termed Composite Blast-like Cells (CBLC), comprising N, N1, M, M1, R, R1, J, and J1 according to the project-wide morphological standard. A fixed YOLO-based segmentation module detected cells, predicted contours were matched to expert polygon annotations by contour IoU, and standardized single-cell crops were generated. An EfficientNet-B0 classifier was trained through a two-stage GT-to-YOLO and YOLO-to-YOLO strategy with class-imbalance correction, center-border regularization, and morphology-assisted supervision. Cell-level predictions were aggregated into patient-level CBLC ratios for AML-oriented diagnostic support. The pipeline achieved stable internal validation and maintained external generalization, with ensemble weighted F1-scores of 0.9076, 0.8696, and 0.9124 on Centers 4, 5, and 6, respectively.

cs.CV↗

arXiv2025

AnatoMaskGAN: GNN-Driven Slice Feature Fusion and Noise Augmentation for Medical Semantic Image Synthesis

Medical semantic-mask synthesis boosts data augmentation and analysis, yet most GAN-based approaches still produce one-to-one images and lack spatial consistency in complex scans. To address this, we propose AnatoMaskGAN, a novel synthesis framework that embeds slice-related spatial features to precisely aggregate inter-slice contextual dependencies, introduces diverse image-augmentation strategies, and optimizes deep feature learning to improve performance on complex medical images. Specifically, we design a GNN-based strongly correlated slice-feature fusion module to model spatial relationships between slices and integrate contextual information from neighboring slices, thereby capturing anatomical details more comprehensively; we introduce a three-dimensional spatial noise-injection strategy that weights and fuses spatial features with noise to enhance modeling of structural diversity; and we incorporate a grayscale-texture classifier to optimize grayscale distribution and texture representation during generation. Extensive experiments on the public L2R-OASIS and L2R-Abdomen CT datasets show that AnatoMaskGAN raises PSNR on L2R-OASIS to 26.50 dB (0.43 dB higher than the current state of the art) and achieves an SSIM of 0.8602 on L2R-Abdomen CT--a 0.48 percentage-point gain over the best model, demonstrating its superiority in reconstruction accuracy and perceptual quality. Ablation studies that successively remove the slice-feature fusion module, spatial 3D noise-injection strategy, and grayscale-texture classifier reveal that each component contributes significantly to PSNR, SSIM, and LPIPS, further confirming the independent value of each core design in enhancing reconstruction accuracy and perceptual quality.

eess.IV↗

arXiv2024

KAE: Kolmogorov-Arnold Auto-Encoder for Representation Learning

The Kolmogorov-Arnold Network (KAN) has recently gained attention as an alternative to traditional multi-layer perceptrons (MLPs), offering improved accuracy and interpretability by employing learnable activation functions on edges. In this paper, we introduce the Kolmogorov-Arnold Auto-Encoder (KAE), which integrates KAN with autoencoders (AEs) to enhance representation learning for retrieval, classification, and denoising tasks. Leveraging the flexible polynomial functions in KAN layers, KAE captures complex data patterns and non-linear relationships. Experiments on benchmark datasets demonstrate that KAE improves latent representation quality, reduces reconstruction errors, and achieves superior performance in downstream tasks such as retrieval, classification, and denoising, compared to standard autoencoders and other KAN variants. These results suggest KAE's potential as a useful tool for representation learning. Our code is available at \url{https://github.com/SciYu/KAE/}.

cs.LG↗

arXiv2024

Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer

Existing methodologies for animating portrait images face significant challenges, particularly in handling non-frontal perspectives, rendering dynamic objects around the portrait, and generating immersive, realistic backgrounds. In this paper, we introduce the first application of a pretrained transformer-based video generative model that demonstrates strong generalization capabilities and generates highly dynamic, realistic videos for portrait animation, effectively addressing these challenges. The adoption of a new video backbone model makes previous U-Net-based methods for identity maintenance, audio conditioning, and video extrapolation inapplicable. To address this limitation, we design an identity reference network consisting of a causal 3D VAE combined with a stacked series of transformer layers, ensuring consistent facial identity across video sequences. Additionally, we investigate various speech audio conditioning and motion frame mechanisms to enable the generation of continuous video driven by speech audio. Our method is validated through experiments on benchmark and newly proposed wild datasets, demonstrating substantial improvements over prior methods in generating realistic portraits characterized by diverse orientations within dynamic and immersive scenes. Further visualizations and the source code are available at: https://fudan-generative-vision.github.io/hallo3/.

cs.CV↗

arXiv2024

Double-Strand Break Clustering: An Economical and Effective Strategy for DNA Repair

In mammalian cells, repair centers for DNA double-strand breaks (DSBs) have been identified. However, previous researches predominantly rely on methods that induce specific DSBs by cutting particular DNA sequences. The clustering and its spatiotemporal properties of non-specifically DSBs, especially those induced by environmental stresses such as irradiation, remains unclear. In this study, we used Dragonfly microscopy to induce high-precision damage in cells and discovered that DSB clustering during the early stages of DNA damage response (DDR) and repair, but not during the repair plateau phase. Early in DDR, DSB clustered into existing 53BP1 foci. The DSB clustering at different stages has different implications for DNA repair. By controlling the distance between adjacent damage points, we found that the probability of DSB clustering remains constant at distances of 0.8 - 1.4 um, while clustering does not occur beyond 1.4 um. Within the 0.8 um range, the probability of clustering significantly increases due to the phase separation effect of 53BP1. Using a Monte Carlo approach, we developed a dynamic model of 53BP1 foci formation, fission, and fusion. This model accurately predicts experimental outcomes and further demonstrates the temporal and spatial influences on DSB clustering. These results showed that, similarly to specifically induced DSBs, non-specifically induced DSBs can also cluster. The extent of DSB clustering is influenced by both temporal and spatial factors, which provide new insights into the dynamics of DSB clustering and the role of 53BP1 in DNA repair processes. Such findings could enhance our understanding of DNA damage responses and help us improve DNA repair therapies in disease.

physics.bio-ph↗

arXiv2024

HA-FGOVD: Highlighting Fine-grained Attributes via Explicit Linear Composition for Open-Vocabulary Object Detection

Open-vocabulary object detection (OVD) models are considered to be Large Multi-modal Models (LMM), due to their extensive training data and a large number of parameters. Mainstream OVD models prioritize object coarse-grained category rather than focus on their fine-grained attributes, e.g., colors or materials, thus failed to identify objects specified with certain attributes. However, OVD models are pretrained on large-scale image-text pairs with rich attribute words, whose latent feature space can represent the global text feature as a linear composition of fine-grained attribute tokens without highlighting them. Therefore, we propose in this paper a universal and explicit approach for frozen mainstream OVD models that boosts their attribute-level detection capabilities by highlighting fine-grained attributes in explicit linear space. Firstly, a LLM is leveraged to highlight attribute words within the input text as a zero-shot prompted task. Secondly, by strategically adjusting the token masks, the text encoders of OVD models extract both global text and attribute-specific features, which are then explicitly composited as two vectors in linear space to form the new attribute-highlighted feature for detection tasks, where corresponding scalars are hand-crafted or learned to reweight both two vectors. Notably, these scalars can be seamlessly transferred among different OVD models, which proves that such an explicit linear composition is universal. Empirical evaluation on the FG-OVD dataset demonstrates that our proposed method uniformly improves fine-grained attribute-level OVD of various mainstream models and achieves new state-of-the-art performance.

cs.CV↗

arXiv2024

NeuroMoCo: A Neuromorphic Momentum Contrast Learning Method for Spiking Neural Networks

Recently, brain-inspired spiking neural networks (SNNs) have attracted great research attention owing to their inherent bio-interpretability, event-triggered properties and powerful perception of spatiotemporal information, which is beneficial to handling event-based neuromorphic datasets. In contrast to conventional static image datasets, event-based neuromorphic datasets present heightened complexity in feature extraction due to their distinctive time series and sparsity characteristics, which influences their classification accuracy. To overcome this challenge, a novel approach termed Neuromorphic Momentum Contrast Learning (NeuroMoCo) for SNNs is introduced in this paper by extending the benefits of self-supervised pre-training to SNNs to effectively stimulate their potential. This is the first time that self-supervised learning (SSL) based on momentum contrastive learning is realized in SNNs. In addition, we devise a novel loss function named MixInfoNCE tailored to their temporal characteristics to further increase the classification accuracy of neuromorphic datasets, which is verified through rigorous ablation experiments. Finally, experiments on DVS-CIFAR10, DVS128Gesture and N-Caltech101 have shown that NeuroMoCo of this paper establishes new state-of-the-art (SOTA) benchmarks: 83.6% (Spikformer-2-256), 98.62% (Spikformer-2-256), and 84.4% (SEW-ResNet-18), respectively.

cs.CV↗

arXiv2024

Current Views on Mechanisms of the FLASH Effect in Cancer Radiotherapy

FLASH radiotherapy (FLASH-RT) is a new modality of radiotherapy by delivering doses with ultra-high dose rates. FLASH-RT has the ability to suppress tumor growth while sparing normal tissues, known as the FLASH effect. Although FLASH effect has proved valid in various models by different ionizing radiations, the exact underlying mechanism is still unclear. This article summarizes mainstream hypotheses of FLASH effect at physicochemical and biological levels, including oxygen depletion and free radical reactions, nuclear and mitochondria damage, as well as immune response. These hypotheses contribute reasonable explanations to the FLASH effect, and are interconnected according to the chronological order of the organism's response to ionizing radiation. By collating the existing consensus, evidence, and hypotheses, this article provides a comprehensive overview of potential mechanisms of FLASH effect and practical guidance for future investigation in the field of FLASH-RT.

physics.med-ph↗

arXiv2021

Local vaccination and systemic tumor suppression via irradiation and manganese adjuvant in mice

Presently 4T-1 luc cells were irradiated with proton under ultra-high dose rate FLASH or with gamma-ray with conventional dose rate, and then subcutaneous vaccination with or without Mn immuno-enhancing adjuvant into the mice for three times. One week later, we injected untreated 4T-1 luc cells on the other side of the vaccinated mice, and found that the untreated 4T-1 luc cells injected later nearly totally did not grow tumor (1/17) while controls without previous vaccination all grow tumors (18/18). The result is very interesting and the findings may help to explore in situ tumor vaccination as well as new combined radiotherapy strategies to effectively ablate primary and disseminated tumors. To our limited knowledge, this is the first paper reporting the high efficiency induction of systemic vaccination suppressing the metastasized/disseminated tumor progression.

physics.med-ph↗