Accelerated Proton Resonance Frequency-based Magnetic Resonance Thermometry by Optimized Deep Learning Method
- URL: http://arxiv.org/abs/2407.03308v1
- Date: Wed, 3 Jul 2024 17:49:38 GMT
- Title: Accelerated Proton Resonance Frequency-based Magnetic Resonance Thermometry by Optimized Deep Learning Method
- Authors: Sijie Xu, Shenyan Zong, Chang-Sheng Mei, Guofeng Shen, Yueran Zhao, He Wang,
- Abstract summary: This work aims to enhance temporal resolution in dynamic MR temperature map reconstruction using an improved deep learning method.
The training-optimized methods and five classical neural networks were applied on the 2-fold and 4-fold under-sampling k-space data.
Deep learning-based reconstruction can significantly enhance the accuracy and efficiency of MR thermometry for clinical FUS thermal therapies.
- Score: 5.861289150568138
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Proton resonance frequency (PRF) based MR thermometry is essential for focused ultrasound (FUS) thermal ablation therapies. This work aims to enhance temporal resolution in dynamic MR temperature map reconstruction using an improved deep learning method. The training-optimized methods and five classical neural networks were applied on the 2-fold and 4-fold under-sampling k-space data to reconstruct the temperature maps. The enhanced training modules included offline/online data augmentations, knowledge distillation, and the amplitude-phase decoupling loss function. The heating experiments were performed by a FUS transducer on phantom and ex vivo tissues, respectively. These data were manually under-sampled to imitate acceleration procedures and trained in our method to get the reconstruction model. The additional dozen or so testing datasets were separately obtained for evaluating the real-time performance and temperature accuracy. Acceleration factors of 1.9 and 3.7 were found for 2 times and 4 times k-space under-sampling strategies and the ResUNet-based deep learning reconstruction performed exceptionally well. In 2-fold acceleration scenario, the RMSE of temperature map patches provided the values of 0.888 degree centigrade and 1.145 degree centigrade on phantom and ex vivo testing datasets. The DICE value of temperature areas enclosed by 43 degree centigrade isotherm was 0.809, and the Bland-Altman analysis showed a bias of -0.253 degree centigrade with the apart of plus or minus 2.16 degree centigrade. In 4 times under-sampling case, these evaluating values decreased by approximately 10%. This study demonstrates that deep learning-based reconstruction can significantly enhance the accuracy and efficiency of MR thermometry for clinical FUS thermal therapies.
Related papers
- Evaluating probabilistic and data-driven inference models for fiber-coupled NV-diamond temperature sensors [0.7140163200313723]
We evaluate the impact of inference model on uncertainties when using continuous wave Optically Detected Magnetic Resonance (ODMR) measurements to infer temperature.
This model effectively utilizes the temperature dependence of spin Hamiltonian parameters to infer temperature from spectral features in the ODMR data.
arXiv Detail & Related papers (2024-09-14T17:23:20Z) - PhysRFANet: Physics-Guided Neural Network for Real-Time Prediction of
Thermal Effect During Radiofrequency Ablation Treatment [0.9895793818721335]
We propose a physics-guided neural network model, named PhysRFANet, to enable real-time prediction of thermal effect during RFA treatment.
Our model demonstrated a 96% Dice score in predicting the lesion volume and an RMSE of 0.4854 for temperature distribution when tested with foreseen tumor images.
arXiv Detail & Related papers (2023-12-21T15:36:52Z) - Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation [71.24808323646167]
We propose textbfDiffusionPose, a new scheme for learning keypoints heatmaps by a neural network.
During training, the keypoints are diffused to random distribution by adding noises and the diffusion model learns to recover ground-truth heatmaps from noised heatmaps.
Experiments show the prowess of our scheme with improvements of 1.6, 1.2, and 1.2 mAP on widely-used COCO, CrowdPose, and AI Challenge datasets.
arXiv Detail & Related papers (2023-06-29T16:24:32Z) - Generalizable synthetic MRI with physics-informed convolutional networks [57.628770497971246]
We develop a physics-informed deep learning-based method to synthesize multiple brain magnetic resonance imaging (MRI) contrasts from a single five-minute acquisition.
We investigate its ability to generalize to arbitrary contrasts to accelerate neuroimaging protocols.
arXiv Detail & Related papers (2023-05-21T21:16:20Z) - DistilPose: Tokenized Pose Regression with Heatmap Distillation [81.21273854769765]
We propose a novel human pose estimation framework termed DistilPose, which bridges the gaps between heatmap-based and regression-based methods.
DistilPose maximizes the transfer of knowledge from the teacher model (heatmap-based) to the student model (regression-based) through Token-distilling (TDE) and Simulated Heatmaps.
arXiv Detail & Related papers (2023-03-04T16:56:29Z) - A deep learning method based on patchwise training for reconstructing
temperature field [10.422905687540172]
This work proposes a novel deep learning method based on patchwise training to reconstruct the temperature field of electronic equipment accurately from limited observation.
The maximum absolute errors of the reconstructed temperature field are less than 1K under the patchwise training approach.
arXiv Detail & Related papers (2022-01-26T10:42:23Z) - SOUL: An Energy-Efficient Unsupervised Online Learning Seizure Detection
Classifier [68.8204255655161]
Implantable devices that record neural activity and detect seizures have been adopted to issue warnings or trigger neurostimulation to suppress seizures.
For an implantable seizure detection system, a low power, at-the-edge, online learning algorithm can be employed to dynamically adapt to neural signal drifts.
SOUL was fabricated in TSMC's 28 nm process occupying 0.1 mm2 and achieves 1.5 nJ/classification energy efficiency, which is at least 24x more efficient than state-of-the-art.
arXiv Detail & Related papers (2021-10-01T23:01:20Z) - Measurement of the Low-temperature Loss Tangent of High-resistivity
Silicon with a High Q-factor Superconducting Resonator [58.720142291102135]
We present the direct loss tangent measurement of a high-resist intrinsicivity (100) silicon wafer in the temperature range from 70 mK to 1 K.
The measurement was performed using a technique that takes advantage of a high quality factor superconducting niobium resonator.
arXiv Detail & Related papers (2021-08-19T20:13:07Z) - Deep correction of breathing-related artifacts in real-time
MR-thermometry [0.5727060643816255]
A convolutional neural network (CNN) was designed to learn the apparent temperature perturbation from images acquired during a preparative learning stage prior to hyperthermia.
During the subsequent hyperthermia procedure, the recent magnitude image is used as an input in order to generate an on-line correction for the current temperature map.
The method's artifact suppression performance was evaluated on 12 free breathing volunteers and was found robust and artifact-free in all examined cases.
arXiv Detail & Related papers (2020-11-10T10:30:41Z) - Real-time estimation of the optically detected magnetic resonance shift
in diamond quantum thermometry [47.50219326456544]
We investigate the real-time estimation protocols for the frequency shift of optically detected magnetic resonance (ODMR) of nitrogen-vacancy centers in nanodiamonds (NDs)
Efficiently integrating multipoint ODMR measurements and ND particle tracking into fluorescence microscopy has recently demonstrated stable monitoring of the temperature inside living animals.
arXiv Detail & Related papers (2020-06-12T01:44:35Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.