Quality Assurance for AI-Based Applications in Radiation Therapy

Claessens, Michaël; Oria, Carmen Seller; Brouwer, Charlotte L.; Ziemer, Benjamin; Scholey, Jonathan M.; Lin, Hui; Witztum, A.; Morin, Olivier; Naqa, Issam El; Elmpt, Wouter van; Verellen, Dirk

doi:10.1016/j.semradonc.2022.06.011

Cited by 34 publications

(22 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figures (6), ( 7) and ( 8) show the effect of micro-lead powder additive with loading ratios (0,20,40,60,80,100,150,200,250,300pphr) on some mechanical properties such as tensile, modulus of elasticity and elongation of the rubber compound consisting of silicone rubber (80). and polyurethane (20) for rubber batches, and as a result of the comparison between the effects of mechanical tests (tensile resistance, modulus of elasticity and elongation) as well as the radiation properties of the dough models, the sample (10) with components (SIR80/PU20 /Pb-micro) was more appropriate. It achieved the mechanical properties as We notice from the figures a slight increase in the tensile strength, modulus of elasticity and a decrease in the amount of elongation with the increase in the loading ratio of the micro-lead powder.…”

Section: Tensile Strength and Elastic Modulus And Elongation;mentioning

confidence: 99%

See 1 more Smart Citation

Preparation and mechanical characterization of (rubber blend - micro lead) rubbery composites for shielding application

Naeem¹,

Al-Nesrawy²,

Al-Maamori³

2023

JOBM

View full text Add to dashboard Cite

This present work, includes the preparation of rubber batches containing silicone rubber (SIR) (80pphr) and polyurethane (PU) (20pphr) with micro-lead powder in different loading, respectively (0,20.40,60,80,100,150,200,250,300pphr). The mechanical properties measured the device universal tensometer, such as tensile strength, elongation and modulus of elasticity, according standard specified of (ASTM D-412) were followed and the hardness property measured by (Hardness Shore A) was put through its steps according to the standard specification (ASTMD-1415). The results were selected, and the sample (10) consisting of (SIR 80/PU20 and micro-lead 300pphr) was chosen because it is more suitable for the required mechanical properties. The results observed that the ratios of micro-lead loading increased, the tensile and elongation decreased, and the hardness and elastic modulus increased. Rubber batches reinforced with micro-lead were exposed to an infrared (FTIR) test device with the addition of hexane, where there were no changes in the infrared spectrum of the rubber composites (SIR80/PU20/Micro-Pb). Sample No. (10) was shown that the scanning electron microscope (SEM) before and after adding hexane, where it was noted that the image (A) without hexane, the absence of homogeneity of lead. As for image (B) in the presence of hexane, we note the homogeneity of lead and the distribution of lead equally, so that radiation examination were measured the Geiger counter of two sources of radioactive elements were used, the caesium source Cs137 and the cobalt source Co60. The radiation is attenuated through the material, while the thickness of the half (X1/2) gradually contrasts according to the attenuation of the radiation. This work is applied in the applications of shields as a protective suit against harmful radiation.

show abstract

Section: Tensile Strength and Elastic Modulus And Elongation;mentioning

confidence: 99%

“…The materials used to manufacture the barrier (shield) are selected according to the type of radiation to be seized and the energy of that radiation. [10].…”

Section: Introductionmentioning

confidence: 99%

Preparation and mechanical characterization of (rubber blend - micro lead) rubbery composites for shielding application

Naeem¹,

Al-Nesrawy²,

Al-Maamori³

2023

JOBM

View full text Add to dashboard Cite

show abstract

“…Traditionally, evaluating the segmentation quality involves comparing the predicted contours with the ground-truth contours (manually generated by an experienced physicist and independently verified by a radiation oncologist). 19 , 20 However, it might be impossible to use the traditional measure to assess automatic segmentation quality if some contours lack the ground-truth contours. Therefore, a new method to evaluate segmentation quality without requiring ground-truth contours is crucial for clinical practice.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning-Based Quality Assurance for Automatic Segmentation of Head-and-Neck Organs-at-Risk in Radiotherapy

Luan

Xue

Wei

et al. 2023

Technol Cancer Res Treat

View full text Add to dashboard Cite

Purpose/Objective(s): With the development of deep learning, more convolutional neural networks (CNNs) are being introduced in automatic segmentation to reduce oncologists’ labor requirement. However, it is still challenging for oncologists to spend considerable time evaluating the quality of the contours generated by the CNNs. Besides, all the evaluation criteria, such as Dice Similarity Coefficient (DSC), need a gold standard to assess the quality of the contours. To address these problems, we propose an automatic quality assurance (QA) method using isotropic and anisotropic methods to automatically analyze contour quality without a gold standard. Materials/Methods: We used 196 individuals with 18 different head-and-neck organs-at-risk. The overall process has the following 4 main steps. (1) Use CNN segmentation network to generate a series of contours, then use these contours as organ masks to erode and dilate to generate inner/outer shells for each 2D slice. (2) Thirty-eight radiomics features were extracted from these 2 shells, using the inner/outer shells’ radiomics features ratios and DSCs as the input for 12 machine learning models. (3) Using the DSC threshold adaptively classified the passing/un-passing slices. (4) Through 2 different threshold analysis methods quantitatively evaluated the un-passing slices and obtained a series of location information of poor contours. Parts 1-3 were isotropic experiments, and part 4 was the anisotropic method. Result: From the isotropic experiments, almost all the predicted values were close to the labels. Through the anisotropic method, we obtained the contours’ location information by assessing the thresholds of the peak-to-peak and area-to-area ratios. Conclusion: The proposed automatic segmentation QA method could predict the segmentation quality qualitatively. Moreover, the method can analyze the location information for un-passing slices.

show abstract

“…Possible tests comprise qualitative and quantitative measurements, where the latter can be subdivided into geometric, dosimetric, and time-saving measures [6] , [8] , amongst others. Such approaches remain useful for on-going QA of auto-contouring post-deployment [9] . These measures are also relevant for studying inter-observer variation to investigate contouring differences (e.g.…”

Section: Introductionmentioning

confidence: 99%

Multicenter comparison of measures for quantitative evaluation of contouring in radiotherapy

Gooding¹,

Boukerroui²,

Osorio³

et al. 2022

Physics and Imaging in Radiation Oncology

View full text Add to dashboard Cite

Quality Assurance for AI-Based Applications in Radiation Therapy

Cited by 34 publications

References 81 publications

Preparation and mechanical characterization of (rubber blend - micro lead) rubbery composites for shielding application

Preparation and mechanical characterization of (rubber blend - micro lead) rubbery composites for shielding application

Machine Learning-Based Quality Assurance for Automatic Segmentation of Head-and-Neck Organs-at-Risk in Radiotherapy

Multicenter comparison of measures for quantitative evaluation of contouring in radiotherapy

Contact Info

Product

Resources

About