Development of a method to create uniform phantoms for task‐based assessment of CT image quality

Conzelmann, Juliane; Schwarz, Felix; Hamm, Bernd; Scheel, Michael; Jahnke, Paul

doi:10.1002/acm2.12974

Cited by 8 publications

(13 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A more practical assessment procedure should mimic clinical practice as much as possible. This principle is also consistent with some task-based evaluation procedures proposed by other studies [ 30 , 31 ].…”

Section: Discussionsupporting

confidence: 91%

The dosimetric impact of deep learning-based auto-segmentation of organs at risk on nasopharyngeal and rectal cancer

et al. 2021

View full text Add to dashboard Cite

Purpose To investigate the dosimetric impact of deep learning-based auto-segmentation of organs at risk (OARs) on nasopharyngeal and rectal cancer. Methods and materials Twenty patients, including ten nasopharyngeal carcinoma (NPC) patients and ten rectal cancer patients, who received radiotherapy in our department were enrolled in this study. Two deep learning-based auto-segmentation systems, including an in-house developed system (FD) and a commercial product (UIH), were used to generate two auto-segmented OARs sets (OAR_FD and OAR_UIH). Treatment plans based on auto-segmented OARs and following our clinical requirements were generated for each patient on each OARs sets (Plan_FD and Plan_UIH). Geometric metrics (Hausdorff distance (HD), mean distance to agreement (MDA), the Dice similarity coefficient (DICE) and the Jaccard index) were calculated for geometric evaluation. The dosimetric impact was evaluated by comparing Plan_FD and Plan_UIH to original clinically approved plans (Plan_Manual) with dose-volume metrics and 3D gamma analysis. Spearman’s correlation analysis was performed to investigate the correlation between dosimetric difference and geometric metrics. Results FD and UIH could provide similar geometric performance in parotids, temporal lobes, lens, and eyes (DICE, p > 0.05). OAR_FD had better geometric performance in the optic nerves, oral cavity, larynx, and femoral heads (DICE, p < 0.05). OAR_UIH had better geometric performance in the bladder (DICE, p < 0.05). In dosimetric analysis, both Plan_FD and Plan_UIH had nonsignificant dosimetric differences compared to Plan_Manual for most PTV and OARs dose-volume metrics. The only significant dosimetric difference was the max dose of the left temporal lobe for Plan_FD vs. Plan_Manual (p = 0.05). Only one significant correlation was found between the mean dose of the femoral head and its HD index (R = 0.4, p = 0.01), there is no OARs showed strong correlation between its dosimetric difference and all of four geometric metrics. Conclusions Deep learning-based OARs auto-segmentation for NPC and rectal cancer has a nonsignificant impact on most PTV and OARs dose-volume metrics. Correlations between the auto-segmentation geometric metric and dosimetric difference were not observed for most OARs.

show abstract

Section: Discussionsupporting

confidence: 91%

The dosimetric impact of deep learning-based auto-segmentation of organs at risk on nasopharyngeal and rectal cancer

et al. 2021

View full text Add to dashboard Cite

show abstract

“…), furniture (door canopies, functional balustrades), welfare (cabinets), lighting (transparency and brilliance optical applications), etc. [10][11][12][13][14][15].…”

Section: Introductionmentioning

confidence: 99%

A Generalised Approach on Kerf Geometry Prediction during CO2 Laser cut of PMMA Thin Plates using Neural Networks

Kechagias

Ninikas

Stavropoulos

et al. 2021

Lasers Manuf. Mater. Process.

View full text Add to dashboard Cite

This study presents an application of feedforward and backpropagation neural network (FFBP-NN) for predicting the kerf characteristics, i.e. the kerf width in three different distances from the surface (upper, middle and down) and kerf angle during laser cutting of 4 mm PMMA (polymethyl methacrylate) thin plates. Stand-off distance (SoD: 7, 8 and 9 mm), cutting speed (CS: 8, 13 and 18 mm/sec) and laser power (LP: 82.5, 90 and 97.5 W) are the studied parameters for low power CO 2 laser cutting. A three-parameter three-level full factorial array has been used, and twentyseven (3 3 ) cuts are performed. Subsequently, the upper, middle and down kerf widths (Wu, Wm and Wd) and the kerf angle (KA) were measured and analysed through ANOM (analysis of means), ANOVA (analysis of variances) and interaction plots. The statistical analysis highlighted that linear modelling is insufficient for the precise prediction of kerf characteristics. An FFBP-NN was developed, trained, validated and generalised for the accurate prediction of the kerf geometry. The FFBP-NN achieved an R-all value of 0.98, in contrast to the ANOVA linear models, which achieved Rsq values of about 0.86. According to the ANOM plots, the parameter values which optimize the KA resulting in positive values close to zero degrees were the 7 mm SoD, 8 mm/s CS and 97.5 W LP.

show abstract

“…Lesion contrasts were 4, 9, 18, 30, and 38 HU (uniform phantom) and 10, 18, 30, and 38 HU (anatomical phantom). The lesion contrasts were validated in previous studies by HU measurement in 2700 images acquired with six different dose levels (uniform phantom) and in 2808 images acquired with twentyseven different dose levels (anatomical phantom) [10,11]. In these validation experiments, lesion contrast was calculated as HU difference between regions of interest (ROIs) of 0.5 cm 2 inside the lesions and six ROIs of 4.9 cm 2 (uniform phantom) and one ROI of 3 cm 2 (anatomical phantom) surrounding the lesions.…”

Section: Phantomsmentioning

confidence: 99%

Comparison of low-contrast detectability between uniform and anatomically realistic phantoms—influences on CT image quality assessment

et al. 2021

Self Cite

View full text Add to dashboard Cite

Objectives To evaluate the effects of anatomical phantom structure on task-based image quality assessment compared with a uniform phantom background. Methods Two neck phantom types of identical shape were investigated: a uniform type containing 10-mm lesions with 4, 9, 18, 30, and 38 HU contrast to the surrounding area and an anatomically realistic type containing lesions of the same size and location with 10, 18, 30, and 38 HU contrast. Phantom images were acquired at two dose levels (CTDIvol of 1.4 and 5.6 mGy) and reconstructed using filtered back projection (FBP) and adaptive iterative dose reduction 3D (AIDR 3D). Detection accuracy was evaluated by seven radiologists in a 4-alternative forced choice experiment. Results Anatomical phantom structure impaired lesion detection at all lesion contrasts (p < 0.01). Detectability in the anatomical phantom at 30 HU contrast was similar to 9 HU contrast in uniform images (91.1% vs. 89.5%). Detection accuracy decreased from 83.6% at 5.6 mGy to 55.4% at 1.4 mGy in uniform FBP images (p < 0.001), whereas AIDR 3D preserved detectability at 1.4 mGy (80.7% vs. 85% at 5.6 mGy, p = 0.375) and was superior to FBP (p < 0.001). In the assessment of anatomical images, superiority of AIDR 3D was not confirmed and dose reduction moderately affected detectability (74.6% vs. 68.2%, p = 0.027 for FBP and 81.1% vs. 73%, p = 0.018 for AIDR 3D). Conclusions A lesion contrast increase from 9 to 30 HU is necessary for similar detectability in anatomical and uniform neck phantom images. Anatomical phantom structure influences task-based assessment of iterative reconstruction and dose effects. Key Points • A lesion contrast increase from 9 to 30 HU is necessary for similar low-contrast detectability in anatomical and uniform neck phantom images. • Phantom background structure influences task-based assessment of iterative reconstruction and dose effects. • Transferability of CT assessment to clinical imaging can be expected to improve as the realism of the test environment increases.

show abstract

Development of a method to create uniform phantoms for task‐based assessment of CT image quality

Cited by 8 publications

References 20 publications

The dosimetric impact of deep learning-based auto-segmentation of organs at risk on nasopharyngeal and rectal cancer

The dosimetric impact of deep learning-based auto-segmentation of organs at risk on nasopharyngeal and rectal cancer

A Generalised Approach on Kerf Geometry Prediction during CO2 Laser cut of PMMA Thin Plates using Neural Networks

Comparison of low-contrast detectability between uniform and anatomically realistic phantoms—influences on CT image quality assessment

Contact Info

Product

Resources

About