We have proposed a method for improving the visibility of lesions while retaining
the image features using a learning-based method with a visibility model.
While general image filters improve the visibility of the entire image,
they may lose local features.
Therefore, we have proposed a framework for learning only the image features of lesions
while maintaining image fidelity, and have developed a method for improving
the visibility of lesions in X-ray images.
R. Ishikawa, T. Yuzawa, T. Fukiage, M. Kagesawa, T. Watsuji, T. Oishi,
"Visibility Enhancement of Lesion Regions in Chest X-ray Images with Image Fidelity Preservation,"
in IEEE Access, vol. 13, pp. 11080-11094, 2025.
We proposed a novel registration method based on a coarse-to-fine IP representation.
The approach starts from a high-speed and reliable registration with a coarse (of low degree) IP model and
stops when the desired accuracy is achieved by a fine (of high degree) IP model.
Over the previous IP-point based methods our contributions are: (i) keeping the efficiency without requiring pair-wised
correspondences, (ii) enhancing the robustness, and (iii) improving the accuracy.
R. Ishikawa, T. Yuzawa, T. Fukiage, M. Kagesawa, T. Watsuji, T. Oishi,
"Visibility Enhancement of Lesion Regions in Chest X-ray Images with Image Fidelity Preservation,"
in IEEE Access, vol. 13, pp. 11080-11094, 2025.
B. Zheng, R. Ishikawa, J. Takamatsu, T. Oishi and K. Ikeuchi,
"A Coarse-to-fine IP-driven Registration for Pose Estimation from Single Ultrasound Image,"
Computer Vision and Image Understanding (CVIU), Vol.117, No. 12, pp. 1647-1658, 2013.
B. Zheng, R. Ishikawa, T. Oishi, J. Takamatsu and K. Ikeuchi,
"A Fast Registration Method Using IP and Its Application to Ultrasound Image Registration,"
IPSJ Transactions on Computer Vision and Applications (CVA), Vol. 1, 209-219, 2009.
