National Taiwan University

Yu-Chun Chien

Si-Chen Lee

Che-Wei Chang

Chung-Ming Chen

Wan-Jou Lee

Chia-Yen Lee

This algorithm provides a marker-free approach to establishing the pixel correspondence among the IR images taken at different times, which is the basis for quantitatively characterizing the variation of the heat energy and patterns pixel-wise on a breast surface. The idea is to use the corner points of the heat pattern and the branch points of the skeletons of the heat pattern on the body surface as the initial fiducial points for the longitudinal IR image registration. The Thin-Plate Spline technique is used to model the nonlinear deformation between two IR images taken at two different times. Mutual information between the TPS-transformed image and the target image is employed as the metric quantifying the quality of the longitudinal IR image registration. To optimize the registration, Nelder-Mead simplex method is used to locally modify the pairings of the fiducial points in the source and target IR images to maximize the mutual information.

Longitudinal image registration algorithm for infrared images for chemotherapy response monitoring and early detection of breast cancers

It is developed a Dual-Spectrum Heat Pattern Separation (DS-HPS) algorithm to quantify the energy from the area of the high temperature tissues, called qmap, and decompose the body surface into the high and normal temperature areas based on a pair of middle-wave Infra-red images and long-wave Infra-red images. Further, with longitudinal registration, we can detect the cancerous tissues and assess the chemotherapy treatment response on a pixel by pixel basis according to the change of the qmap derived by the DS-HPS algorithm. The preliminary result shows the area and the qvalues in the high temperature area are decreased as the patients receive more chemotherapy. These suggest the proposed algorithm could capture the incremental or decremental of the energies emitted by the cancerous tissues, which has the potentials for chemotherapy assessment and early detection.

Dual-spectrum heat pattern separation algorithm for assessing chemotherapy treatment response and early detection

Infra-red images of tumors carry the information of normal and cancerous tissues in every pixel. We developed a Dual-Spectrum Heat Pattern Separation (DS-HPS) algorithm to quantify the energy from the area of the high temperature tissues, called qmap, and decompose the body surface into the high and normal temperature areas based on a pair of middle-wave Infra-red images and long-wave Infra-red images. Further, with longitudinal registration, we can detect the cancerous tissues and assess the chemotherapy treatment response on a pixel by pixel basis according to the change of the qmap derived by the DS-HPS algorithm. The preliminary result shows the area and the qvalues in the high temperature area are decreased as the patients receive more chemotherapy. These suggest the proposed algorithm could capture the incremental or decremental of the energies emitted by the cancerous tissues, which has the potentials for chemotherapy assessment and early detection.

Growing community of inventors

Taipei, Taiwan

Yu-Chun Chien