Approaches to preclinical studies with heterogeneous breast phantom using reconstruction and three‐dimensional image processing algorithms for diffuse optical imaging

Üncü, Yiğit Ali; Sevim, Gençay; Canpolat, Murat

doi:10.1002/ima.22648

Cited by 11 publications

(6 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although several reconstruction algorithms have been used for DOT systems, Krylov subspace algorithms provide a better solution [1], [3]. In our previous studies, we used both algebraic and subspace algorithms [1], [2], [20] - [22]. These algorithms are Algebraic Reconstruction, Simultaneous Iterative Reconstruction, SVD, CG, Bi-CG, and TFQMR techniques.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Difüz Optik Tomografi’de Modellenmiş Meme Tümörü Benzeri Dokuların Teşhisi için Simülasyon Deneyleriyle Geri Çatım Algoritmalarının Uygulanması

Sevim

Üncü²,

Canpolat³

2021

Düzce Üniversitesi Bilim Ve Teknoloji Dergisi

Self Cite

View full text Add to dashboard Cite

In Diffuse Optical Tomography (DOT), data processing and reconstruction stages are crucial to obtain high-quality images. Thus, choosing suitable algorithms for the system is a critical choice. This study aims to determine an appropriate reconstruction algorithm for DOT imaging. There are several reconstruction algorithms used in DOT systems. Some algorithms have been improved for solving specific cases, and some still need to be improved. In this study, we used three algorithms for the reconstruction process: Singular Value Decomposition (SVD), Bi-Conjugated Gradient (Bi-CG), and Transpose Free Quasi Minimal Residual (TFQMR). In testing the algorithms, data of the simulation experiments have been used. The simulation experiments model the tumoral tissue within the breast. All three algorithms were produced correct images while the tumor close to the surface. In the case of the tumor that is not close to the breast surface, the tumor location on the images created by Bi-CG and SVD algorithms was not its actual location. However, the tumor location in the image created by the TFQMR algorithm was close to its actual location. Outcomes of the reconstruction algorithms were evaluated based on correctly defining the location of the tumors by using Mean Percentage Error (MPE), Mean Squared Error (MSE), and Mean Absolute Error (MAE) metrics. We have demonstrated the TFQMR algorithm is a more appropriate reconstruction technique for DOT systems. Thus, we have concluded that TFQMR can have the potential to be used in medical imaging systems.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

Difüz Optik Tomografi’de Modellenmiş Meme Tümörü Benzeri Dokuların Teşhisi için Simülasyon Deneyleriyle Geri Çatım Algoritmalarının Uygulanması

Sevim

Üncü²,

Canpolat³

2021

Düzce Üniversitesi Bilim Ve Teknoloji Dergisi

Self Cite

View full text Add to dashboard Cite

show abstract

“…The UAV first accelerates to the cruising speed of 5m/s, and the forward flight speed of the UAV starts to slow down at about 2.7s, and then accelerates again at about 2.9s.. At this moment, the distance between the UAV and the obstacle was reduced to less than 10m, and the obstacle avoidance strategy module thought it was dangerous, and gave a deceleration signal. Before the speed was reduced to 3m/s, at about 2.8s, the obstacle avoidance strategy module thought that the horizontal obstacle avoidance had been completed, so it was unnecessary to decelerate, so the UAV began to return to normal cruising speed [7][8].…”

Section: Single-target Obstacle Avoidance Flight Testmentioning

confidence: 99%

Research on obstacle distance measurement method of UAV based on image processing technology

Lin

2024

International Conference on Algorithm, Imaging Processing, and Machine Vision (AIPMV 2023)

View full text Add to dashboard Cite

In order to understand the obstacle distance measurement method of UAV, a research on obstacle distance measurement method of UAV based on image processing technology is proposed. This paper proposes an obstacle detection algorithm based on edge extraction. The outline of the obstacle can be obtained by extracting the edge features in the image, and the size, shape and position of the obstacle can be obtained by using a rectangle to frame the outline. Then the distance of the obstacle can be extracted from the contour of the obstacle by using the depth map generated by the binocular camera. The millimeter wave radar in front is used to fuse ranging with the central area of binocular camera image to improve the update frequency of obstacle distance. Finally, the effectiveness of the obstacle avoidance control strategy is verified by the obstacle avoidance flight test, and the UAV can choose the optimal obstacle avoidance direction and successfully bypass when encountering obstacles. The comparison of obstacle avoidance results shows that the obstacle avoidance method in this paper is advanced and has certain engineering application value.

show abstract

“…Transform, recombination, and controlled randomised padding achieve conciseness without sacrificing efficiency. We use strong theoretical reasons and massive experimental data to further analyse [11]. This article discusses signal organisation in temporal and spatial capture and reconstruction.…”

Section: Related Workmentioning

confidence: 99%

Cloud-enabled Internet of Things Medical Image Processing Compressed Sensing Reconstruction

Kumar¹,

Venkatesan²,

S.Ravichandran³

2023

IJSMIEN

View full text Add to dashboard Cite

Deep learning compresses medical image processing in IoMT. CS-MRI acquires quickly. It has various medicinal uses due to its advantages. This lowers motion artifacts and contrast washout. Reduces patient pressure and scanning costs. CS-MRI avoids the Nyquist-Shannon sampling barrier. Parallel imagingbased fast MRI uses many coils to reconstruct MRI images with less raw data. Parallel imaging enables rapid MRI. This research developed a deep learning-based method for reconstructing CS-MRI images that bridges the gap between typical non-learning algorithms that employ data from a single image and enormous training datasets. Conventional approaches only reconstruct CS-MRI data from one picture. Reconstructing CS-MRI images. CS-GAN is recommended for CS-MRI reconstruction. For success. Refinement learning stabilizes our C-GAN-based generator, which eliminates aliasing artifacts. This improved newly produced data. Product quality increased. Adversarial and information loss recreated the picture. We should protect the image’s texture and edges. Picture and frequency domain data establish consistency. We want frequency and picture domain information to match. It offers visual domain data. Traditional CS-MRI reconstruction and deep learning were used in our broad comparison research. C-GAN enhances reconstruction while conserving perceptual visual information. MRI image reconstruction takes 5 milliseconds, allowing real-time analysis.

show abstract

Approaches to preclinical studies with heterogeneous breast phantom using reconstruction and three‐dimensional image processing algorithms for diffuse optical imaging

Cited by 11 publications

References 42 publications

Difüz Optik Tomografi’de Modellenmiş Meme Tümörü Benzeri Dokuların Teşhisi için Simülasyon Deneyleriyle Geri Çatım Algoritmalarının Uygulanması

Difüz Optik Tomografi’de Modellenmiş Meme Tümörü Benzeri Dokuların Teşhisi için Simülasyon Deneyleriyle Geri Çatım Algoritmalarının Uygulanması

Research on obstacle distance measurement method of UAV based on image processing technology

Cloud-enabled Internet of Things Medical Image Processing Compressed Sensing Reconstruction

Contact Info

Product

Resources

About