Positron Emission Tomography Lung Image Respiratory Motion Correcting with Equivariant Transformer

In addressing the challenge of motion artifacts in Positron Emission Tomography (PET) lung scans, our studyintroduces the Triple Equivariant Motion Transformer (TEMT), an innovative, unsupervised, deep-learningbasedframework for efficient respiratory motion correction in PET imaging. Unlike traditional techniques,which segment PET data into bins throughout a respiratory cycle and often face issues such as inefficiency andoveremphasis on certain artifacts, TEMT employs Convolutional Neural Networks (CNNs) for effective featureextraction and motion decomposition.TEMT’s unique approach involves transforming motion sequences into Liegroup domains to highlight fundamental motion patterns, coupled with employing competitive weighting forprecise target deformation field generation. Our empirical evaluations confirm TEMT’s superior performancein handling diverse PET lung datasets compared to existing image registration networks. Experimental resultsdemonstrate that TEMT achieved Dice indices of 91.40%, 85.41%, 79.78%, and 72.16% on simulated geometricphantom data, lung voxel phantom data, cardiopulmonary voxel phantom data, and clinical data, respectively. Tofacilitate further research and practical application, the TEMT framework, along with its implementation detailsand part of the simulation data, is made publicly accessible at https://github.com/yehaowei/temt.

RESPIRATORY MOTION ESTIMATION USING VIBRATION MODEL AND REDUCING MOTION BLUR THROUGH DECONVOLUTION

The respiratory motion leads to significant motion artifacts of the positron emission tomography （PET） image, thus influencing diagnoses and treatments in the radiation oneology. The existing approaches to correct motion artifacts involve using gating devices and/or four-dimensional （4-D） computed tomography （CT）. However, they have the disadvantages of high CT dose and high computational burden. Hence, a sinusoid vibration model is presented to simulate the respiratory motion. The motion extent and the direction are derived from the Radon transform of the cepstrum of the blurred image. Then, two typical deeonvolution algorithms, i.e. , Wiener filter （WF） and the Richardson-Lucy （RL） algorithms are used to eliminate the motion blur according to the estimated parameters and their de-blurring results are compared. Experiments on both synthetic and phantom images show good performance of the presented model for identifying vibration modeled respiration motion and reducing the motion blur. The method has advantages of safety, convenience, and economy. And it is promising to correct the motion artifacts of the non-gated PET image.

Automatic Anomaly Detection of Respiratory Motion Based on Singular Spectrum Analysis

The realization of automatic anomaly detection of respiratory motion could be very useful to prevent accidental damage during radiation therapy. In this paper, we proposed an automatic anomaly detection method using singular value decomposition analysis. Before applying this method, the investigator needs a normal respiratory motion data of a patient. From these data, a trajectory matrix representing normal time-series feature is created. Decomposing the matrix, we obtained the feature of normal time series. Then, we applied the same procedure to real-time data and obtained real-time features. Calculating the similarity of those feature matrixes, an anomaly score was obtained. Patient motion was observed by a depth camera. In our simulation, two types of motion e.g. cough and sudden stop of breathing were successfully detected, while gradual change of respiratory cycle frequency was not detected clearly.

Impact of Field Strength and Respiratory Motion Control on Diffusion-Weighted MR Imaging of the Liver

Purpose: To evaluate the impact of field strength and respiratory motion control on diffusion-weighted MR imaging (DWI) of the liver at 1.5 and 3 T. Material and Methods: Three DWI sequences using seven b-values from 20 - 400 s/mm2 were designed with identical parameters but with different handling of respiratory motion [respiratory triggered (RT), free breathing (FB), breath hold (BH)] on 3 T and 1.5 T. Thirteen volunteers were examined at a 3 T and six of them also at a 1.5 T magnet. DW images were analyzed quantitatively and qualitatively. Regions of interest were placed in cranial, middle and caudal parts of the right liver lobe (RLL) and ADC and SNR were calculated. Results: ADC in RLL tended to be lower at 3 T MRI. Least inter-subject ADC variability was found with RT in the middle RLL at 3 T. Highest ADCs were found caudally in the RLL. Significant differences in ADC between middle and caudal RLL were calculated in FB and RT at 3 T and FB and BH at 1.5 T, respectively. No significant difference in SNR was found between 3 T and 1.5 T. There were significantly more artifacts in the left liver lobe (LLL) compared to the RLL in all sequences and in the LLL at 3 T compared to 1.5 T. Conclusion: Our study suggests that longitudinal hepatic ADC measurements should be performed using equivalent field strength, b-values, and acquisition technique, given influence of these factors on ADC measurements.

Dlung:Unsupervised Few-Shot Diffeomorphic Respiratory Motion Modeling

Lung image registration plays an important role in lung analysis applications,such as respiratory motion modeling.Unsupervised learning-based image registration methods that can compute the deformation without the requirement of supervision attract much attention.However,it is noteworthy that they have two drawbacks:they do not handle the problem of limited data and do not guarantee diffeomorphic(topologypreserving)properties,especially when large deformation exists in lung scans.In this paper,we present an unsupervised few-shot learning-based diffeomorphic lung image registration,namely Dlung.We employ fine-tuning techniques to solve the problem of limited data and apply the scaling and squaring method to accomplish the diffeomorphic registration.Furthermore,atlas-based registration on spatio-temporal(4D)images is performed and thoroughly compared with baseline methods.Dlung achieves the highest accuracy with diffeomorphic properties.It constructs accurate and fast respiratory motion models with limited data.This research extends our knowledge of respiratory motion modeling.

Preliminary clinical application of total free-breathing cardiac MR examination

Objective To observe the clinical application value of total free-breathing cardiac MR(CMR)examination preliminarily.Methods Two patients who underwent CMR scanning under free-breathing state,including cine,motion correction T1 and T2 mapping,blood flow imaging,and late gadolinium enhancement scanning were retrospectively enrolled,and the qualities of the above images were evaluated and compared with that of conventional CMR images under breath-holding state.Results No significant difference of imaging quality was found between total free-breathing and conventional breath-holding CMR.The differences of left ventricular ejection fraction,cardiac output,left ventricular end-diastolic volume index and left ventricular mass measured based on CMR images under different breath conditions were limited.Conclusion Total free-breathing CMR was feasible in clinical practice,which could provide"one-stop"evaluation of cardiac structure,function and myocardial histological characteristics,hence having promising clinical prospects.

Fast-response,high-sensitivity multi-modal tactile sensors based on PPy/Ti_(3)C_(2)T_(x) films for multifunctional applications

In recent years,multi-modal flexible tactile sensors have become an important direction in the development of electronic skin because of their excellent sensitivity,flexibility and wearable properties.In this work,a humidity-pressure multi-modal flexible sensor based on polypyrrole(PPy)/Ti_(3)C_(2)T_(x) sensitive film packaged with porous polydimethylsiloxane(PDMS)is investigated by combining the sensitive structure generation mechanism of in situ polymerization to achieve the simultaneous detection of humidity and pressure,which has a sensitivity of 89,113.4Ω/%RH in a large humidity range of 0%-97%RH,and response/recovery time of 2.5/1.9 s.The tactile pressure sensing has a high sensitivity,a fast response of 67/52 ms,and a wide detection limit.The device also has excellent performance in terms of stability and repeatability,making it promising for respiratory pattern and motion detection.This work provides a new solution to address the construction of multi-modal tactile sensors with potential applications in the fields of medical health,epidemic prevention.

Correction of Breathing Motion in the Thorax for Helical CT

This paper investigates a reconstruction method for helical computed tomography which compensates for the motion artifacts in the thorax caused by patient breathing. The method takes into account a motion vector field determined from a four-dimensional （4-D） uncompensated image data set. Surface models of the lung and the ribs are tracked through the 4-D data set to create motion information within the entire thorax. Finally, an image is reconstructed using motion compensated back-projection. The results show that due to the use of shape models for the motion estimation, the method is fast and robust. Furthermore, since the surfaces are tracked individually, reconciling the opposite motion direction of the lung and rib cage in one motion vector field is avoided.