Keywords
Multi-window resampling
Lesion recognition
Medical image processing
Pseudo-color fusion
Submitted : 2026-01-14
Accepted : 2026-01-29
Published : 2026-02-13
Abstract
Accurate deep learning-based detection of nasopharyngeal carcinoma (NPC) magnetic resonance (MR) images is conducive to diagnosis and treatment. These images are characterized by high dimensionality, complex noise interference, and blurred tissue structure boundaries. How to extract key pathological features from massive imaging information and provide quantitative basis for clinical diagnosis remains an important challenge in the current field of medical image processing. This paper uses multi-window fusion technology to map multiple key window information to the pseudo-color space, realizing the integration of multi-dimensional feature information and compensating for the information limitations of single-window imaging. Experiments show that this method can effectively improve model accuracy.
References
Wang L, Zhou Y, Zhu X, et al., 2025, Research Progress on Writing Mechanism Based on Functional Magnetic Resonance Imaging Technology. Chinese Journal of Rehabilitation Medicine, 40(12): 1923–1929.
Lin X, Zhang J, Lin W, 2025, Prediction of Incidence and Mortality of Nasopharyngeal Carcinoma in China from 2022 to 2026: Based on GM (1,1) and ARIMA Models. New Medicine, 35(09): 1017–1023.
Zhou Z, Li K, Li N, et al., 2023, Age-Period-Cohort Model Analysis of Incidence and Mortality Trends of Nasopharyngeal Carcinoma in China from 1994 to 2019. Chinese Journal of Disease Control & Prevention, 27(08): 869–876 + 894.
Yu Q, Wang C, 2025, Research Status of Artificial Intelligence in Post-Processing of Imaging Technology Images. Imaging Technology, 37(06): 71–75.
Huang Y, 2025, Research on 3D Medical Image Registration Method Based on Dual-Window Attention and Dynamic Threshold, thesis, Guangxi University.
Tao G, Li H, Huang J, et al., 2022, SeqSeg: A Sequential Method to Achieve Nasopharyngeal Carcinoma Segmentation Free from Background Dominance. Medical Image Analysis, 78: 102381.
Ruan J, Xie M, Gao J, et al., 2023, EGE-UNet: An Efficient Group Enhanced UNet for Skin Lesion Segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, 481–490.
Wang S, Zhu Y, Lee S, et al., 2022, Global-Local Attention Network with Multi-Task Uncertainty Loss for Abnormal Lymph Node Detection in MR Images. Medical Image Analysis, 77: 102345.
Zhao W, Cheng M, 2023, DICOM Image Analysis and Measurement System Based on Contour Detection and Target Localization. Journal of Jiujiang University (Natural Science Edition), 38(03): 58–62.
Chen J, Yuan P, Hou H, et al., 2023, Adaptive Window Width and Window Level Algorithm for Medical CT Sequence Images. Journal of Northeastern University (Natural Science Edition), 44(10): 1392–1400.