Haoqing Li

Deep learning methods face dual challenges of limited clinical samples and low inter-class differentiation among Diffuse Cystic Lung Diseases (DCLDs) in advancing Birt-Hogg-Dube syndrome (BHD) diagnosis via Computed Tomography (CT) imaging. While Multimodal Large Language Models (MLLMs) demonstrate diagnostic potential fo such rare diseases, the absence of domain-specific knowledge and referable radiological features intensify hallucination risks. To address this problem, we propose BHD-RAG, a multimodal retrieval-augmented generation framework that integrates DCLD-specific expertise and clinical precedents with MLLMs to improve BHD diagnostic accuracy. BHDRAG employs: (1) a specialized agent generating imaging manifestation descriptions of CT images to construct a multimodal corpus of DCLDs cases. (2) a cosine similarity-based retriever pinpointing relevant imagedescription pairs for query images, and (3) an MLLM synthesizing retrieved evidence with imaging data for diagnosis. BHD-RAG is validated on the dataset involving four types of DCLDs, achieving superior accuracy and generating evidence-based descriptions closely aligned with expert insights.

Infrared small target detection is a technique for finding small targets from infrared clutter background. Previous deep-learning-based approaches have achieved promising results. However, the lack of high-level semantic information leads to a degradation of small infrared target features in the deeper layers of the neural network, resulting in suboptimal representation capabilities. To address this issue, we propose an Infrared Low-level Network (ILNet) that conceptualizes infrared small targets as salient regions characterized by limited semantic information. In contrast to other state-of-the-art methods, ILNet emphasizes low-level information more significantly, rather than treating it uniformly with high-level information. A lightweight feature fusion module, named Interactive Polarized Orthogonal Fusion module (IPOF), is proposed, which integrates more important low-level features from the shallow layers into the deep layers. A Dynamic One-Dimensional Aggregation layers (DODA) are inserted into the IPOF, to dynamically adjust the aggregation of low dimensional information according to the number of input channels. In addition, the idea of ensemble learning is used to design a Representative Block (RB) to dynamically allocate weights for shallow and deep layers. Experimental results on the challenging NUAA-SIRST (78.22% nIoU and $1.33 \times 10^{-6}$ Fa) and IRSTD-1k (68.91% nIoU and $3.23 \times 10^{-6}$Fa) dataset demonstrate that the proposed ILNet can get better performances than other SOTA methods. Moreover, ILNet can obtain a greater improvement with the increasement of data volume. Training code are available at https://github.com/Li-Haoqing/ILNet.

Infrared Small Target Detection (IRSTD) aims to segment small targets from infrared clutter background. Existing methods mainly focus on discriminative approaches, i.e., a pixel-level front-background binary segmentation. Since infrared small targets are small and low signal-to-clutter ratio, empirical risk has few disturbances when a certain false alarm and missed detection exist, which seriously affect the further improvement of such methods. Motivated by the dense prediction generative methods, in this paper, we compensate pixel-level discriminant with mask posterior distribution modeling. Specifically, we propose a diffusion model framework for Infrared Small Target Detection. This generative framework maximizes the posterior distribution of the small target mask to surmount the performance bottleneck associated with minimizing discriminative empirical risk. This transition from the discriminative paradigm to generative one enables us to bypass the target-level insensitivity. Furthermore, we design a Low-frequency Isolation in wavelet domain to suppress the interference of intrinsic infrared noise on the diffusion noise estimation. The low-frequency component of the infrared image in the wavelet domain is processed by a neural network, and the high-frequency component is utilized to restore the targets information, to estimate the residuals of the enhanced features. Experiments show that the proposed method achieves competitive performance gains over state-of-the-art methods on NUAA-SIRST, NUDT-SIRST, and IRSTD-1 k datasets. Code are available at https://github.com/Li-Haoqing/IRSTD-Diff .

Infrared Small Target Detection (IRSTD) aims to segment small targets from infrared clutter background. Existing methods mainly focus on discriminative approaches, i.e., a pixel-level front-background binary segmentation. Since infrared small targets are small and low signal-to-clutter ratio, empirical risk has few disturbances when a certain false alarm and missed detection exist, which seriously affect the further improvement of such methods. Motivated by the dense prediction generative methods, in this paper, we propose a diffusion model framework for Infrared Small Target Detection which compensates pixel-level discriminant with mask posterior distribution modeling. Furthermore, we design a Low-frequency Isolation in the wavelet domain to suppress the interference of intrinsic infrared noise on the diffusion noise estimation. This transition from the discriminative paradigm to generative one enables us to bypass the target-level insensitivity. Experiments show that the proposed method achieves competitive performance gains over state-of-the-art methods on NUAA-SIRST, IRSTD-1k, and NUDT-SIRST datasets. Code are available at https://github.com/Li-Haoqing/IRSTD-Diff.

Infrared Small Target Detection is a challenging task to separate small targets from infrared clutter background. Recently, deep learning paradigms have achieved promising results. However, these data-driven methods need plenty of manual annotations. Due to the small size of infrared targets, manual annotation consumes more resources and restricts the development of this field. This letter proposed a labor-efficient annotation framework with level set, which obtains a high-quality pseudo mask with only one cursory click. A variational level set formulation with an expectation difference energy functional is designed, in which the zero level contour is intrinsically maintained during the level set evolution. It solves the issue that zero level contour disappearing due to small target size and excessive regularization. Experiments on the NUAA-SIRST and IRSTD-1k datasets demonstrate that our approach achieves superior performance. Code is available at https://github.com/Li-Haoqing/COM.

Infrared Small Target Detection is a challenging task to separate small targets from infrared clutter background. Recently, deep learning paradigms have achieved promising results. However, these data-driven methods need plenty of manual annotation. Due to the small size of infrared targets, manual annotation consumes more resources and restricts the development of this field. This letter proposed a labor-efficient and cursory annotation framework with level set, which obtains a high-quality pseudo mask with only one cursory click. A variational level set formulation with an expectation difference energy functional is designed, in which the zero level contour is intrinsically maintained during the level set evolution. It solves the issue that zero level contour disappearing due to small target size and excessive regularization. Experiments on the NUAA-SIRST and IRSTD-1k datasets reveal that our approach achieves superior performance. Code is available at https://github.com/Li-Haoqing/COM.