Deep learning-based image reconstruction for few-view computed tomography

2021 ◽  
pp. 165594
Author(s):  
Dobin Yim ◽  
Seungwan Lee ◽  
Kibok Nam ◽  
Dahye Lee ◽  
Do Kyung Kim ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Image Reconstruction

scholarly journals Machine Friendly Machine Learning: Interpretation of Computed Tomography Without Image Reconstruction

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Hyunkwang Lee ◽  
Chao Huang ◽  
Sehyo Yune ◽  
Shahein H. Tajmir ◽  
Myeongchan Kim ◽  
...  
Keyword(s):  
Machine Learning ◽  
Computed Tomography ◽  
Deep Learning ◽  
Image Reconstruction ◽  
Medical Images ◽  
Medical Image Analysis ◽  
Image Space ◽  
Sensor Data ◽  
Reconstruction Process ◽  
Partial Representation

Abstract Recent advancements in deep learning for automated image processing and classification have accelerated many new applications for medical image analysis. However, most deep learning algorithms have been developed using reconstructed, human-interpretable medical images. While image reconstruction from raw sensor data is required for the creation of medical images, the reconstruction process only uses a partial representation of all the data acquired. Here, we report the development of a system to directly process raw computed tomography (CT) data in sinogram-space, bypassing the intermediary step of image reconstruction. Two classification tasks were evaluated for their feasibility of sinogram-space machine learning: body region identification and intracranial hemorrhage (ICH) detection. Our proposed SinoNet, a convolutional neural network optimized for interpreting sinograms, performed favorably compared to conventional reconstructed image-space-based systems for both tasks, regardless of scanning geometries in terms of projections or detectors. Further, SinoNet performed significantly better when using sparsely sampled sinograms than conventional networks operating in image-space. As a result, sinogram-space algorithms could be used in field settings for triage (presence of ICH), especially where low radiation dose is desired. These findings also demonstrate another strength of deep learning where it can analyze and interpret sinograms that are virtually impossible for human experts.

scholarly journals Deep learning based image reconstruction algorithm for limited-angle translational computed tomography

PLoS ONE ◽  
2020 ◽  
Vol 15 (1) ◽  
pp. e0226963
Author(s):  
Jiaxi Wang ◽  
Jun Liang ◽  
Jingye Cheng ◽  
Yumeng Guo ◽  
Li Zeng
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Image Reconstruction ◽  
Reconstruction Algorithm ◽  
Image Reconstruction Algorithm ◽  
Limited Angle

scholarly journals Validation of Deep-Learning Image Reconstruction for Low-Dose Chest Computed Tomography Scan: Emphasis on Image Quality and Noise

2021 ◽  
Vol 22 (1) ◽  
pp. 131 ◽  
Author(s):  
Joo Hee Kim ◽  
Hyun Jung Yoon ◽  
Eunju Lee ◽  
Injoong Kim ◽  
Yoon Ki Cha ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Image Reconstruction ◽  
Image Quality ◽  
Low Dose ◽  
Computed Tomography Scan ◽  
Chest Computed Tomography ◽  
Tomography Scan

scholarly journals Image quality assessment of deep learning image reconstruction in computed tomography using tube current modulation: a phantom study

2021 ◽  
Author(s):  
kazuhiro takeuchi ◽  
Yasuhiro Ide ◽  
Yuichiro Mori ◽  
Yusuke Uehara ◽  
Hiroshi Sukeishi ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Image Reconstruction ◽  
Image Quality ◽  
Quality Characteristics ◽  
Image Noise ◽  
Tube Current Modulation ◽  
Current Modulation ◽  
Tube Current ◽  
The Impact

Abstract The novel deep learning image reconstruction (DLIR) is known to change its image quality characteristics according to object contrast and image noise. In clinical practice, computed tomography (CT) image noise is usually controlled by tube current modulation (TCM) to accommodate changes in object size. This study aimed to evaluate the image quality characteristics of DLIR for different object sizes when in-plane noise is controlled by TCM. We used Mercury 4.0 phantoms with different object sizes. Phantom image acquisition was performed on a GE Revolution CT system to investigate the impact of the DLIR algorithm compared to standard reconstructions: filtered back projection (FBP) and hybrid iterative reconstruction (hybrid-IR). For image quality evaluation, the noise power spectrum (NPS), task-based transfer function (TTF), and detectability index (d') were determined. The NPS of DLIR was very similar to that of FBP, and the information in the high-frequency region was maintained. In terms of TTF, DLIR showed higher resolution than hybrid-IR at low- to medium-contrast (Δ50, Δ90HU), but not necessarily higher than FBP. At the simulated contrast and lesion size, DLIR showed higher detectability than hybrid-IR, regardless of the phantom size. In this study, we evaluated a novel DLIR algorithm by reproducing clinical behaviors. The findings indicate that DLIR produces higher image quality than hybrid-IR regardless of the phantom size, although it depends on the reconstruction strength.

scholarly journals Performance of clinically available deep learning image reconstruction in computed tomography: a phantom study

2020 ◽  
Vol 7 (06) ◽  
Author(s):  
Hiroki Kawashima ◽  
Katsuhiro Ichikawa ◽  
Tadanori Takata ◽  
Wataru Mitsui ◽  
Hiroshi Ueta ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Image Reconstruction ◽  
Phantom Study
Sign in / Sign up

Export Citation Format

Share Document