arXiv subjects

Abduz Zami

Publications and source records attributed to Abduz Zami.

3 recordsLinked to original sources

arXiv2026

PromptForSegCXR: Prompt-Driven Multi-Organ and Multi-Disease Segmentation in Chest X-rays using a Multi-stage Fusion Mechanism

Image segmentation is central to automated medical image analysis, enabling precise identification of anatomical structures and pathological regions. Conventional segmentation models typically target a single organ or disease, limiting their adaptability across clinical scenarios. While multi-organ and multi-disease segmentation has been explored, building such datasets requires extensive manual annotation by medical experts. Prompt-driven segmentation offers a flexible, user-guided alternative that speeds up annotation, yet no prior work has addressed prompt-based interactive segmentation across multiple organs and diseases in chest X-rays. This study makes two main contributions. First, we introduce a novel dataset of expert-designed doodle prompts spanning 23 classes (six organs and seventeen diseases), curated from multiple public chest X-ray datasets for prompt-driven segmentation. Second, we propose PromptForSegCXR, a lightweight dual-input segmentation framework that combines the chest X-ray with user-provided doodle prompts to accurately segment diverse anatomical and pathological regions. The model uses a multi-stage feature fusion strategy to integrate spatial and semantic representations, along with a depthwise-pointwise-residual convolution block with squeeze-and-excitation attention for efficient hierarchical feature extraction and adaptive recalibration. Experimental results show the model achieves a Dice score of 81.62 percent on the full dataset, outperforming SAM-based prompt segmentation models by up to 10 percent and conventional segmentation architectures by up to 23 percent, while remaining lightweight. These results demonstrate the effectiveness of the proposed approach for accurate, flexible, prompt-driven chest X-ray segmentation.

eess.IV↗

arXiv2026

SMFD-UNet: Semantic Face Mask Is The Only Thing You Need To Deblur Faces

For applications including facial identification, forensic analysis, photographic improvement, and medical imaging diagnostics, facial image deblurring is an essential chore in computer vision allowing the restoration of high-quality images from blurry inputs. Often based on general picture priors, traditional deblurring techniques find it difficult to capture the particular structural and identity-specific features of human faces. We present SMFD-UNet (Semantic Mask Fusion Deblurring UNet), a new lightweight framework using semantic face masks to drive the deblurring process, therefore removing the need for high-quality reference photos in order to solve these difficulties. First, our dual-step method uses a UNet-based semantic mask generator to directly extract detailed facial component masks (e.g., eyes, nose, mouth) straight from blurry photos. Sharp, high-fidelity facial images are subsequently produced by integrating these masks with the blurry input using a multi-stage feature fusion technique within a computationally efficient UNet framework. We created a randomized blurring pipeline that roughly replicates real-world situations by simulating around 1.74 trillion deterioration scenarios, hence guaranteeing resilience. Examined on the CelebA dataset, SMFD-UNet shows better performance than state-of-the-art models, attaining higher Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) while preserving satisfactory naturalness measures, including NIQE, LPIPS, and FID. Powered by Residual Dense Convolution Blocks (RDC), a multi-stage feature fusion strategy, efficient and effective upsampling techniques, attention techniques like CBAM, post-processing techniques, and the lightweight design guarantees scalability and efficiency, enabling SMFD-UNet to be a flexible solution for developing facial image restoration research and useful applications.

cs.CV↗

arXiv2025

MedPrompt: LLM-CNN Fusion with Weight Routing for Medical Image Segmentation and Classification

Current medical image analysis systems are typically task-specific, requiring separate models for classification and segmentation, and lack the flexibility to support user-defined workflows. To address these challenges, we introduce MedPrompt, a unified framework that combines a few-shot prompted Large Language Model (Llama-4-17B) for high-level task planning with a modular Convolutional Neural Network (DeepFusionLab) for low-level image processing. The LLM interprets user instructions and generates structured output to dynamically route task-specific pretrained weights. This weight routing approach avoids retraining the entire framework when adding new tasks-only task-specific weights are required, enhancing scalability and deployment. We evaluated MedPrompt across 19 public datasets, covering 12 tasks spanning 5 imaging modalities. The system achieves a 97% end-to-end correctness in interpreting and executing prompt-driven instructions, with an average inference latency of 2.5 seconds, making it suitable for near real-time applications. DeepFusionLab achieves competitive segmentation accuracy (e.g., Dice 0.9856 on lungs) and strong classification performance (F1 0.9744 on tuberculosis). Overall, MedPrompt enables scalable, prompt-driven medical imaging by combining the interpretability of LLMs with the efficiency of modular CNNs.

cs.CV↗