ACSwinNet: A Deep Learning-Based Rigid Registration Method for Head-Neck CT-CBCT Images in Image-Guided Radiotherapy.

Accurate and precise rigid registration between head-neck computed tomography (CT) and cone-beam computed tomography (CBCT) images is crucial for correcting setup errors in image-guided radiotherapy (IGRT) for head and neck tumors. However, conventional registration methods that treat the head and neck as a single entity may not achieve the necessary accuracy for the head region, which is particularly sensitive to radiation in radiotherapy. We propose ACSwinNet, a deep learning-based method for head-neck CT-CBCT rigid registration, which aims to enhance the registration precision in the head region.

LED chip visual servo positioning control under variable system parameters using adaptive dual rate Kalman filter with adaptive recursive least squares.

In the research, aiming at high positioning quality for LED chips under the variable system parameters, a real-time and robust visual positioning method is presented. At first, to solve the problems of delay in image system and measuring deviation in encoder, an adaptive dual rate Kalman filter technology is designed to estimate the accurate location of LED chip in real time. After sensitivity analysis, the changes of system parameters during manufacturing have a significant influence on estimation effect.

LED chip accurate positioning control based on visual servo using dual rate adaptive fading Kalman filter.

In this paper, to improve the positioning accuracy of LED chip, a dual rate adaptive fading Kalman filter algorithm with delay compensation is proposed and applied to the LED chip visual servo positioning system. Firstly, a structure of dual rate Kalman filter is introduced to the visual servo control system, which compensate the visual information delay and realize the accurate time sequential coordination of encoder and visual feedback. Then, considering the inaccuracy of system mathematical model, the adaptive forgetting factor is added to the iterative process of above algorithm, and the impact of accumulated model error on system stability is consequently mitigated.

A mathematical model of aortic aneurysm formation.

Abdominal aortic aneurysm (AAA) is a localized enlargement of the abdominal aorta, such that the diameter exceeds 3 cm. The natural history of AAA is progressive growth leading to rupture, an event that carries up to 90% risk of mortality. Hence there is a need to predict the growth of the diameter of the aorta based on the diameter of a patient's aneurysm at initial screening and aided by non-invasive biomarkers.

[An automatic 3D-locating couch for radiation therapy].

An intensity modulated method by scanning for the focusing therapy machine is introduced in this paper. At first, the 3-D model of the focus is delaminated through the treatment planning system, and the dose distributing of each lay is calculated by an inverse design method. Then, the exposure time of the focus at each position is determined and converted to a scanning parameter, such as position, speed and so on.