arXiv subjects

Lixin Lin

Publications and source records attributed to Lixin Lin.

6 recordsLinked to original sources

arXiv2026

MorVess: Morphology-Aware Pulmonary Vessel Segmentation Network

Accurate pulmonary vessel segmentation remains challenging due to the sparse, tortuous, and multi-scale nature of vascular structures, where small branches are easily lost and topology integrity is difficult to preserve under voxel-wise supervision. Existing deep segmentation models primarily optimize binary masks, lacking explicit geometric constraints, thus struggling to recover continuous tubular morphology and fine vascular connectivity. In this study, we introduce MorVess, a morphology-aware segmentation framework that integrates differentiable geometric priors with large-scale foundation model adaptation to achieve fine-grained vascular parsing. MorVess jointly predicts vessel masks, distance maps, and thickness maps, providing explicit supervision for vascular boundaries, centerline consistency, and smooth diameter transitions. A lightweight 2.5D adapter bridges 3D spatial context and 2D SAM representations, while a global-local fusion block aggregates multi-level semantics and geometric cues for high-fidelity topology reconstruction. Across two challenging pulmonary CT benchmarks, MorVess delivers superior Dice, clDice, and HD95 scores, substantially improving small-vessel recovery and global connectivity. These results demonstrate that embedding geometric intelligence into pretrained vision models offers a principled and scalable pathway toward precise vessel analysis and clinically reliable structural quantification. Our source code is available at https://github.com/MaoFuyou/MorVess.

cs.CV↗

arXiv2026

Mutual Distillation of Dual-Foundation Models for Semi-Supervised PET/CT Segmentation

Organ segmentation from PET/CT is critical for quantitative analysis and radiotherapy planning in oncology. To ease the high annotation cost of PET/CT segmentation, semi-supervised learning (SSL) provides a practical and effective solution for developing deep models with limited labeled data. Recent developments in visual foundation models have demonstrated remarkable adaptability with improved efficiency. In this work, we propose a mutual distillation framework that seamlessly exploits both structural and functional foundation models, which act as modality-specific generalists for distilling knowledge from structural CT and metabolic PET imaging. By bridging the gap between the task-specific precision of student models and the segmentation priors of generalist foundation models, we propose \textbf{MuDuo}, a mutual distillation framework that synergistically leverages SAM-Med3D for CT and SegAnyPET for PET to distill their knowledge into a lightweight student network. Our approach eliminates the need for manual prompts while maximizing the utility of unlabeled data for automatic segmentation, achieving state-of-the-art performance on the AutoPET dataset with only 5 labeled cases. Our source code is available at https://github.com/Wu-beining/MuDuo.

cs.CV↗

arXiv2025

Quantifying the direct and indirect impact of COVID-19 vaccination: evidence from Victoria, Australia

Vaccines not only directly protect vaccinated individuals but also contribute to protect the entire population via indirect herd-immunity benefits. However, researchers have long struggled to quantify these indirect effects at the population level, hindering assessment of vaccination program effectiveness. We developed a new method to estimate these effects, thereby markedly improving measures of the number of infections, hospitalizations, and deaths averted by vaccination. Our population-based analysis of 6,440,000 residents of Victoria, Australia reveal strong indirect effects during the Delta outbreak (September-November 2021). By modelling a non-vaccination counterfactual, we conservatively estimate 316,000 infections were averted (95\% BCI: 232k-406k), as well as 33,500 hospitalizations (95\% BCI: 22.2k-46.2k), and 4,900 deaths (95\% BCI: 2.9k-7.3k). These are 4.0, 7.5, and 8.0 times higher, respectively, than observed. Half of the averted infections and around one-quarter of hospitalizations and deaths were attributable to indirect protection. Homogeneous vaccination across LGAs could have reduced outcomes by approximately 25\%.

q-bio.PE↗

arXiv2024

Cross-modal Medical Image Generation Based on Pyramid Convolutional Attention Network

The integration of multimodal medical imaging can provide complementary and comprehensive information for the diagnosis of Alzheimer's disease (AD). However, in clinical practice, since positron emission tomography (PET) is often missing, multimodal images might be incomplete. To address this problem, we propose a method that can efficiently utilize structural magnetic resonance imaging (sMRI) image information to generate high-quality PET images. Our generation model efficiently utilizes pyramid convolution combined with channel attention mechanism to extract multi-scale local features in sMRI, and injects global correlation information into these features using self-attention mechanism to ensure the restoration of the generated PET image on local texture and global structure. Additionally, we introduce additional loss functions to guide the generation model in producing higher-quality PET images. Through experiments conducted on publicly available ADNI databases, the generated images outperform previous research methods in various performance indicators (average absolute error: 0.0194, peak signal-to-noise ratio: 29.65, structural similarity: 0.9486) and are close to real images. In promoting AD diagnosis, the generated images combined with their corresponding sMRI also showed excellent performance in AD diagnosis tasks (classification accuracy: 94.21 %), and outperformed previous research methods of the same type. The experimental results demonstrate that our method outperforms other competing methods in quantitative metrics, qualitative visualization, and evaluation criteria.

cs.CE↗

arXiv2024

Quantifying indirect and direct vaccination effects arising in the SIR model

Vaccination campaigns have both direct and indirect effects that act to control an infectious disease as it spreads through a population. Indirect effects arise when vaccinated individuals block disease transmission in any infection chains they are part of, and this in turn can benefit both vaccinated and unvaccinated individuals. Indirect effects are difficult to quantify in practice, but here, working with the Susceptible-Infected-Recovered (SIR) model, they are analytically calculated in important cases, through pivoting on the Final Size formula for epidemics. Their relationship to herd immunity is also clarified. Furthermore, we identify the important distinction between quantifying indirect effects of vaccination at the "population level" versus the "per capita" individual level, which often results in radically different conclusions. As an important example, the analysis unpacks why population-level indirect effect can appear significantly larger than its per capita analogue. In addition, we consider a recently proposed epidemiological non-pharamaceutical intervention used over COVID-19, referred to as "shielding", and study its impact in our mathematical analysis. The shielding scheme is extended by inclusion of limited vaccination.

q-bio.PE↗

arXiv2016

n-Lie bialgebras

The $n$-Lie bialgebras are studied. In Section 2, the $n$-Lie coalgebra with rank $r$ is defined, and the structure of it is discussed. In Section 3, the $n$-Lie bialgebra is introduced. A triple $(L, \mu, \Delta)$ is an $n$-Lie bialgebra if and only if $\Delta$ is a conformal $1$-cocycle on the $n$-Lie algebra $L$ associated to $L$-modules $(L^{\otimes n}, \rho_s^{\mu})$, $1\leq s\leq n$, and the structure of $n$-Lie bialgebras is investigated by the structural constants. In Section 4, two-dimensional extension of finite dimensional $n$-Lie bialgebras are studied. For an $m$ dimensional $n$-Lie bialgebra $(L, \mu, \Delta)$, and an $ad_{\mu}$-invariant symmetric bilinear form on $L$, the $m+2$ dimensional $(n+1)$-Lie bialgebra is constructed. In the last section, the bialgebra structure on the finite dimensional simple $n$-Lie algebra $A_n$ is discussed. It is proved that only bialgebra structures on the simple $n$-Lie algebra $A_n$ are rank zero, and rank two.

math.RA↗