Generation of synthetic CT using multi-scale and dual-contrast patches for brain MRI-only external beam radiotherapy

Aouadi, Souha; Vasic, Ana; Paloor, S.; Torfeh, Tarraf; McGarry, M.; Petrič, Primož; Riyas, M.; Hammoud, R.; Al-Hammadi, Noora

doi:10.1016/j.ejmp.2017.09.132

Cited by 23 publications

(21 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mean MAE obtained in this work for patients with brain cancer was 105 HU, while it was 112 HU for patients with HN cancer. This is comparable with a variety of recently proposed techniques for whole head CT synthesis for external beam radiation therapy [5,32,33]. These studies reported a mean MAE in the sCT ranging from 98 HU to 148 HU, and all reported acceptable dose calculations assessed by a variety of standard metrics such as γ-analysis, dose-volume histogram analysis, dose distribution difference maps, and dose profiles.…”

Section: Tablesupporting

confidence: 79%

“…These studies reported a mean MAE in the sCT ranging from 98 HU to 148 HU, and all reported acceptable dose calculations assessed by a variety of standard metrics such as γ-analysis, dose-volume histogram analysis, dose distribution difference maps, and dose profiles. One prior study reported a mean bone DSC of 0.8 [32], which is equivalent to the bone DSC reported in this work, and a maximum dose volume histogram deviation of 0.53% for the planning target volume and of 0.75% for organs at risk. A full dosimetric study would have exceeded the scope of this work, but will be carried out to evaluate the clinical use of our proposed approach within an appropriate evaluation framework.…”

Section: Tablesupporting

confidence: 71%

See 1 more Smart Citation

A role for magnetic susceptibility in synthetic computed tomography

et al. 2021

View full text Add to dashboard Cite

Section: Tablesupporting

confidence: 79%

Section: Tablesupporting

confidence: 71%

A role for magnetic susceptibility in synthetic computed tomography

et al. 2021

View full text Add to dashboard Cite

“…[18192425272829] The average MAEs for the multimodal methods showed 118.7 ± 10.4 HU for the voxel-based and 73.0 ± 6.4 HU for the patch-based algorithm[30] and 99.69 ± 11.07 HU for the multiscale and dual-contrast patch-based method using a MR target. [31] The feasibility of using from T1w and T2w as target for generating sCT in the brain was investigated that Mean absolute error for the sCT was 124 ± 10 HU. [32] Our results also included 78–93 HU and 0.80–0.89 for MAE and DSC bone respectively, which is in agreement with the results of previous studies.…”

Section: Discussionmentioning

confidence: 99%

Introduction of a simple algorithm to create synthetic-Computed tomography of the head from magnetic resonance imaging

Chegeni

Birgani

et al. 2019

J Med Signals Sens

View full text Add to dashboard Cite

Background: Recently, magnetic resonance imaging (MRI)-based radiotherapy has become a favorite science field for treatment planning purposes. In this study, a simple algorithm was introduced to create synthetic computed tomography (sCT) of the head from MRI. Methods: A simple atlas-based method was proposed to create sCT images based on the paired T1/T2-weighted MRI and bone/brain window CT. Dataset included 10 patients with glioblastoma multiforme and 10 patients with other brain tumors. To generate a sCT image, first each MR from dataset was registered to the target-MR, the resulting transformation was applied to the corresponding CT to create the set of deformed CTs. Then, deformed-CTs were fused to generate a single sCT image. The sCT images were compared with the real CT images using geometric measures (mean absolute error [MAE] and dice similarity coefficient of bone [DSC bone ]) and Hounsfield unit gamma-index (Г HU ) with criteria 100 HU/2 mm. Results: The evaluations carried out by MAE, DSC bone , and Г HU showed a good agreement between the synthetic and real CT images. The results represented the range of 78–93 HU and 0.80–0.89 for MAE and DSC bone , respectively. The Г HU also showed that approximately 91%–93% of pixels fulfilled the criteria 100 HU/2 mm for brain tumors. Conclusion: This method showed that MR sequence (T1w or T2w) should be selected depending on the type of tumor. In addition, the brain window synthetic CTs are in better agreement with real CT relative to bone window sCT images.

show abstract

“…Even though some authors rectify the image range from 0 to 1 prior to computing SSIM, 8 a significant portion of the medical image synthesis literature reports SSIM on negative images such as—but not limited to—CT. For instance, a large number of authors evaluated synthesized CT images quality using SSIM on the natural HU range, meaning that negative values were present 11,18–23 …”

Section: Introductionmentioning

confidence: 99%

On the proper use of structural similarity for the robust evaluation of medical image synthesis models

2022

View full text Add to dashboard Cite

To propose good practices for using the structural similarity metric (SSIM) and reporting its value. SSIM is one of the most popular image quality metrics in use in the medical image synthesis community because of its alleged superiority over voxel-by-voxel measurements like the average error or the peak signal noise ratio (PSNR). It has seen massive adoption since its introduction, but its limitations are often overlooked. Notably, SSIM is designed to work on a strictly positive intensity scale, which is generally not the case in medical imaging. Common intensity scales such as the Houndsfield units (HU) contain negative numbers, and they can also be introduced by image normalization techniques such as the z-normalization. Methods: We created a series of experiments to quantify the impact of negative values in the SSIM computation. Specifically, we trained a three-dimensional (3D) U-Net to synthesize T2-weighted MRI from T1-weighted MRI using the BRATS 2018 dataset. SSIM was computed on the synthetic images with a shifted dynamic range. Next, to evaluate the suitability of SSIM as a loss function on images with negative values, it was used as a loss function to synthesize znormalized images. Finally, the difference between two-dimensional (2D) SSIM and 3D SSIM was investigated using multiple 2D U-Nets trained on different planes of the images. Results:The impact of the misuse of the SSIM was quantified; it was established that it introduces a large downward bias in the computed SSIM. It also introduces a small random error that can change the relative ranking of models. The exact values for this bias and error depend on the quality and the intensity histogram of the synthetic images. Although small, the reported error is significant considering the small SSIM difference between state-of -the-art models. It was shown therefore that SSIM cannot be used as a loss function when images contain negative values due to major errors in the gradient calculation, resulting in under-performing models. 2D SSIM was also found to be overestimated in 2D image synthesis models when computed along the plane of synthesis, due to the discontinuities between slices that is typical of 2D synthesis methods. Conclusion: Various types of misuse of the SSIM were identified, and their impact was quantified. Based on the findings, this paper proposes good practices when using SSIM, such as reporting the average over the volume of the image containing tissue and appropriately defining the dynamic range.

show abstract

Generation of synthetic CT using multi-scale and dual-contrast patches for brain MRI-only external beam radiotherapy

Cited by 23 publications

References 29 publications

A role for magnetic susceptibility in synthetic computed tomography

A role for magnetic susceptibility in synthetic computed tomography

Introduction of a simple algorithm to create synthetic-Computed tomography of the head from magnetic resonance imaging

On the proper use of structural similarity for the robust evaluation of medical image synthesis models

Contact Info

Product

Resources

About