Improving resolution of medical images with deep dense convolutional neural network

Wei, Shanghai; Wu, Wei; Jeon, Gwanggil; Ahmad, Awais; Yang, Xiaobo

doi:10.1002/cpe.5084

Cited by 20 publications

(13 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wei et al investigated improving the resolution of medical images with deep dense convolutional neural networks. The authors have applied a deep dense SR (DDSR) convolutional neural networks model to two types of medical images, including Computerized Tomography (CT) and Magnetic Resonance imaging (MRI) images.…”

Section: Theme Of This Special Issuementioning

confidence: 99%

Convergence of deep machine learning and parallel computing environment for bio‐engineering applications

Sangaiah

Pham

Qiu

et al. 2019

Concurrency and Computation

View full text Add to dashboard Cite

Section: Theme Of This Special Issuementioning

confidence: 99%

Convergence of deep machine learning and parallel computing environment for bio‐engineering applications

Sangaiah

Pham

Qiu

et al. 2019

Concurrency and Computation

View full text Add to dashboard Cite

“…Recently, deep learning (DL) has reached promising achievements in medical imaging tasks, 5 such as segmentation, 6 registration, 7 image synthesizing, 8 and super resolution (SR). 9,10 There have many researchers explored the feasibility of DL-based MR image SR. 9,11,12 These investigations have suggested superior performances of the DL-based SR method over the conventional interpolation-and optimization-based methods 3,13 in terms of image quality and computation efficiency.…”

Section: Introductionmentioning

confidence: 99%

Synthesizing high‐resolution magnetic resonance imaging using parallel cycle‐consistent generative adversarial networks for fast magnetic resonance imaging

et al. 2021

View full text Add to dashboard Cite

The common practice in acquiring the magnetic resonance (MR) images is to obtain two-dimensional (2D) slices at coarse locations while keeping the high in-plane resolution in order to ensure enough body coverage while shortening the MR scan time. The aim of this study is to propose a novel method to generate HR MR images from low-resolution MR images along the longitudinal direction. In order to address the difficulty of collecting paired low-and highresolution MR images in clinical settings and to gain the advantage of parallel cycle consistent generative adversarial networks (CycleGANs) in synthesizing realistic medical images, we developed a parallel CycleGANs based method using a self -supervised strategy. Methods and materials:The proposed workflow consists of two parallely trained CycleGANs to independently predict the HR MR images in the two planes along the directions that are orthogonal to the longitudinal MR scan direction. Then, the final synthetic HR MR images are generated by fusing the two predicted images. MR images, including T1-weighted (T1), contrast enhanced T1-weighted (T1CE), T2-weighted (T2), and T2 Fluid Attenuated Inversion Recovery (FLAIR), of the multimodal brain tumor segmentation challenge 2020 (BraTS2020) dataset were processed to evaluate the proposed workflow along the cranial-caudal (CC), lateral, and anterior-posterior directions. Institutional collected MR images were also processed for evaluation of the proposed method. The performance of the proposed method was investigated via both qualitative and quantitative evaluations. Metrics of normalized mean absolute error (NMAE), peak signal-to-noise ratio (PSNR), edge keeping index (EKI), structural similarity index measurement (SSIM), information fidelity criterion (IFC), and visual information fidelity in pixel domain (VIFP) were calculated. Results: It is shown that the proposed method can generate HR MR images visually indistinguishable from the ground truth in the investigations on the BraTS2020 dataset. In addition, the intensity profiles, difference images and SSIM maps can also confirm the feasibility of the proposed method for synthesizing HR MR images. Quantitative evaluations on the BraTS2020 dataset shows that the calculated metrics of synthetic HR MR images can all be enhanced for the T1, T1CE, T2, and FLAIR images. The enhancements in the numerical metrics over the low-resolution and bi-cubic interpolated MR images, as well as those genearted with a comparative deep learning method, are statistically significant. Qualitative evaluation of the synthetic HR MR images of

show abstract

“…There are two significant reasons for this. The first is that the structure of medical images is different from natural images 8 . Unlike natural images, medical images can be in many other image modalities, 9 as in MRI, a slice by slice analysis may be required to diagnose a tumor 10 .…”

Section: Introductionmentioning

confidence: 99%

“…For example, there may be hundreds of slices belonging to a patient 11 . In addition, diseased tissues and anomalies have different characteristics from objects in natural images 8 . Another reason is that it is difficult to obtain medical images due to the low number of pictures taken compared to natural pictures.…”

Section: Introductionmentioning

confidence: 99%

False positive repression: Data centric pipeline for object detection in brain MRI

Terzı

Azgınoglu

Terzi

2021

Concurrency and Computation

View full text Add to dashboard Cite

One of the problems that often arise during the application of medical research to real life is the high number of false positive cases. This situation causes experts to be warned with false alarms unnecessarily and increases their workload. This study proposes a new data centric approach to reduce bias-based false positive predictions in brain MRI-specific medical object detection applications. The proposed method has been tested using two different datasets: Gazi Brains 2020 and BraTS 2020, and three different deep learning-based object detection models: Mask R-CNN, YOLOv5, and EfficientDet. According to the results, the proposed pipeline outperformed the classical pipeline, up to 18% on the Gazi Brains 2020 dataset, and up to 24% on the BraTS 2020 dataset for mean specificity value without much change in sensitivity metric. It means that the proposed pipeline reduces false positive rates due to bias in real-life applications and it can help to reduce the workload of experts.

show abstract

Improving resolution of medical images with deep dense convolutional neural network

Cited by 20 publications

References 27 publications

Convergence of deep machine learning and parallel computing environment for bio‐engineering applications

Convergence of deep machine learning and parallel computing environment for bio‐engineering applications

Synthesizing high‐resolution magnetic resonance imaging using parallel cycle‐consistent generative adversarial networks for fast magnetic resonance imaging

False positive repression: Data centric pipeline for object detection in brain MRI

Contact Info

Product

Resources

About