T1-weighted and T2-weighted MRI image synthesis with convolutional generative adversarial networks

Kawahara, Daisuke; Nagata, Yasushi

doi:10.5603/rpor.a2021.0005

Cited by 36 publications

(26 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been reported that the number of the input image pixels affects image synthesis using GAN, increasing the computation time to create the training model, while improving synthesis quality. 33 Since there is little difference in the image generation time of the model after training, the proposed GAN model is clinically applicable with larger number of pixels. On the other hand, the complexity of the treatment plan is different depending on the treatment site.…”

Section: Discussionmentioning

confidence: 99%

“…Examples of style transfer that have been performed in medical imaging are image synthesis from an input image to different modalities and contrast images (T1‐MRI to CT, T2‐MRI to T1‐MRI, single energy CT to dual‐energy CT, etc.) 32–35 . If the virtual QA method using the image synthesis technique could synthesize the gamma distribution, the predicted QA outcome would be highly reliable.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A synthesized gamma distribution‐based patient‐specific VMAT QA using a generative adversarial network

et al. 2023

Self Cite

View full text Add to dashboard Cite

Background Artificial intelligence (AI)‐based gamma passing rate (GPR) prediction has been proposed as a time‐efficient virtual patient‐specific QA method for the delivery of volumetric modulation arc therapy (VMAT). However, there is a limitation that the GPR value loses the locational information of dose accuracy. Purpose The objective was to predict the failing points in the gamma distribution and the GPR using a synthesized gamma distribution of VMAT QA with a deep convolutional generative adversarial network (GAN). Methods The fluence maps of 270 VMAT beams for prostate cancer were measured using an electronic portal imaging device and analyzed using gamma evaluation with 3%/2‐mm, 2%/1‐mm, 1%/1‐mm, and 1%/0.5‐mm tolerances. The 270 gamma distributions were divided into two datasets: 240 training datasets for creating a model and 30 test datasets for evaluation. The image prediction network for the fluence maps calculated by the treatment planning system (TPS) to the gamma distributions was created using a GAN. The sensitivity, specificity, and accuracy of detecting failing points were evaluated using measured and synthesized gamma distributions. In addition, the difference between measured GPR (mGPR) and predicted GPR (pGPR) values calculated from the synthesized gamma distributions was evaluated. Results The root mean squared errors between mGPR and pGPR were 1.0%, 2.1%, 3.5%, and 3.6% for the 3%/2‐mm, 2%/1‐mm, 1%/1‐mm, and 1%/0.5‐mm tolerances, respectively. The accuracies for detecting failing points were 98.9%, 96.9%, 94.7%, and 93.7% for 3%/2‐mm, 2%/1‐mm, 1%/1‐mm, and 1%/0.5‐mm tolerances, respectively. The sensitivity and specificity were the highest for 1%/0.5‐mm and 3%/2‐mm tolerances, which were 82.7% and 99.6%, respectively. Conclusions We developed a novel system using a GAN to generate a synthesized gamma distribution‐based patient‐specific VMAT QA. The system is promising from the point of view of quality assurance in radiotherapy because it shows high performance and can detect failing points.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A synthesized gamma distribution‐based patient‐specific VMAT QA using a generative adversarial network

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…The proposed GWO-K-means algorithm has been implemented using MATLAB 2019 on an HP Laptop with an Intel Core i7-6700 GHz running at 3.4 GHz with a memory of 16 GB. For verification purposes to examine the proposed algorithm, MRI image datasets containing T1-weighted and T2-weighted MRI types were used [28]. The grey wolf population is set to 100 search agents, and the iteration number is set to 300.…”

Section: Resultsmentioning

confidence: 99%

“…Table 18 shows the clustering accuracy for the six images in Table 10, which validates the performance of the proposed algorithm. The same dataset was used for all the tasks to measure the accuracy of classification, which were MRI image datasets containing T1-weighted and T2-weighted MRI types [28]. [12] 51.7 Xilinx Virtex4 XC4VLX25 Reference [36] 20.6 Xilinx Kintex-7 Reference [37] 30 Xilinx XC2V6000 Proposed method 88.17 Xilinx Kintex7 XC7K160t FPGA 484-1…”

Section: Resultsmentioning

confidence: 99%

Optimized FPGA-Based Implementation of Brain Tumor Detection by Combining K-Means and Grey Wolf Optimization Algorithms

Jarrah¹,

Amri²

2022

View full text Add to dashboard Cite

There is a need for fast, accurate, and real-time algorithms to detect brain tumors effectively to support the physician's decision-making for treatment purposes. A brain tumor is a lifethreatening uncontrolled growth of cells and tissues that may cause death due to inaccurate and late detection. K-means clustering is one of the clustering techniques that is widely used in brain tumor detection, but it has some drawbacks such as dependency on initial centroid values and a tendency to fall on local optima. This research proposes a new model that uses grey wolf optimization to find the optimal value of K (clusters number) of the k-means algorithm to avoid local optima. A parallel implementation of the K-means clustering algorithm on a field-programmable gate array (FPGA) is also proposed to enhance the performance by reducing the processing time and the power consumption. Moreover, the proposed algorithm is implemented using the Vivado HLS tool on Xilinx Kintex7 XC7K160t FPGA 484-1 where different optimization techniques are adopted and applied, such as loop unrolling, loop pipelining, dataflow, and loop merging. The achieved speed-up of the parallel implementation compared with sequential implementation was 88.17, where the obtained average clustering accuracy was 97.11%.

show abstract

“…The paramagnetic effect of Gd in contrast enhancement of MRI images is by decreasing the relaxation times of T2 and T1 on protons. With the use of iron oxide, the dephasing rate of T2 * increases as well as T2 and T1 in the protons [7,8,9].…”

Section: Introductionmentioning

confidence: 99%

Quantitative Analysis of Electrical Current Effect on Magnetic Resonance Image Tissue Intensity

Ain

Choridah²,

Kurniadi³

et al. 2023

Jurnal Teknologi

View full text Add to dashboard Cite

Recent studies in magnetic resonance imaging (MRI) aim to improve image quality while reducing scan time. Electrical current injection in the form of magnetic resonance electrical impedance tomography (MREIT) is believed to be affecting image quality and scan time thus can improve the possibility of becoming a non-chemical contrast agent in MRI. This study will observe and analyze the effect of electrical current injection on a phantom object to determine whether there is a different tissue image intensity. A thigh of lamb was used as a biological tissue phantom. The scan was performed on both T1and T2-weighted without and with an electrical current injection of 0.5 mA Electrical current injection decreased mean of tissue image intensity on T1-weighted images on both muscle (1759 vs 794) and bone (2752 vs 1550) (p<0.05). On the other hand, the electrical current increased mean of tissue image intensity on T2-weighted images on both muscle (303 vs 897) and bone (579 vs 1499) (p<0.05). There is also a difference in tissue image intensity on both T1 and T2-weighted images with and without electrical current injection on bone and muscle. The implication of this difference in image quality is a subject for further study.

show abstract

T1-weighted and T2-weighted MRI image synthesis with convolutional generative adversarial networks

Cited by 36 publications

References 16 publications

A synthesized gamma distribution‐based patient‐specific VMAT QA using a generative adversarial network

A synthesized gamma distribution‐based patient‐specific VMAT QA using a generative adversarial network

Optimized FPGA-Based Implementation of Brain Tumor Detection by Combining K-Means and Grey Wolf Optimization Algorithms

Quantitative Analysis of Electrical Current Effect on Magnetic Resonance Image Tissue Intensity

Contact Info

Product

Resources

About