PP-Net improves biomedical images by removing scattered light and noise fast
PP-Net: A Hybrid Physical-Prior Neural Network for Scattered Light Removal in Biomedical Images on Embedded Devices
Computer Vision and Pattern RecognitionArtificial IntelligenceMachine Learning
Summary
Biomedical images often suffer from scattered light that makes them blurry and noisy, but it’s hard to remove because clear reference images are rare and the process requires complex calculations. The authors created PP-Net, a computer program that combines knowledge about how light behaves with smart learning techniques to clean these images effectively. Their method works well on realistic test images and real biomedical photos, and can run quickly on small devices often used in medical settings. This makes it easier to analyze and diagnose from microscopic or endoscopic images in healthcare environments.
What this means in practice
- •For medical device engineers: Integrate efficient image correction into biomedical microscopes and endoscopes to enhance image clarity on embedded hardware.
- •For iot system developers: Implement scattered light removal on edge devices in medical IoT setups to improve analysis speed and accuracy without cloud reliance.
Authors
Yongfei Guo, Tingjin Chu, Mengzhuo Liu, Hongwei Lou, Yuanhao Gong
Abstract
Scattered light is common in biomedical images, yet its removal remains challenging. The difficulty arises from three aspects: first, aligned scattered-light-free biomedical ground truth is often unavailable; second, scattering is coupled with weak illumination and sensor-induced noise; and third, many learning-based restoration models are computationally expensive for embedded devices in Internet of Medical Things (IoMT) scenarios. To address these issues, this paper proposes PP-Net, a hybrid physical-prior neural network for biomedical scattered light removal. The proposed method consists of three components: DFN-Net suppresses sensor-induced noise, ASAP estimates the scattering map and recovers a physics-based prior map, and GF-Net refines the prior map by fusing it with the denoised observation. To reduce the dependence on paired biomedical ground truth, a progressive synthetic training and cross-domain transfer strategy is developed. Experiments show that the physical-prior branch improves the peak signal-to-noise ratio (PSNR) by up to 1.26 dB on paired synthetic benchmarks. Under joint noise-and-scattering degradation, PP-Net improves PSNR by more than 10.8 dB and the structural similarity index measure (SSIM) by more than 0.62 compared with representative baseline methods. On real W2S biomedical images, the proposed method reduces the average Natural Image Quality Evaluator (NIQE) score by 43.3\%. Edge deployment with RKNN conversion and INT8 quantization achieves an average inference latency of approximately 200 ms per $512\times512$ image over 360 test images. These results demonstrate that PP-Net provides an effective and deployable solution for microscopic imaging, endoscopic inspection, and edge-assisted biomedical analysis in IoMT scenarios.