Association between cumulative radiation dose, adverse skin reactions, and changes in surface hemoglobin among women undergoing breast conserving therapy

Chin, Michael S.; Siegel-Reamer, Leah; FitzGerald, Gordon; Wyman, Allison; Connor, Nikole M.; Lo, Yuan‐Chyuan; Sioshansi, Shirin; Moni, Janaki; Cicchetti, M. Giulia; Lalikos, Janice F.; Fitzgerald, Thomas J.

doi:10.1016/j.ctro.2017.03.003

Cited by 12 publications

(10 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Radiation-induced dermatitis is a common and serious side effect in patients with breast cancer or head and neck cancer who receive radiotherapy 31,32 ; however, there is currently no effective treatment, thus remaining a significant clinical concern that further negatively affects the patient's quality of life. 3,33 Towards promoting research into the pathophysiology of this response, we successfully established radiation-induced acute and chronic dermatitis rat models using 90 Gy of radiation exposure to the skin.…”

Section: Discussionmentioning

confidence: 99%

Establishment and characterization of a radiation‐induced dermatitis rat model

Sheng

Zhou

Wang

et al. 2019

J Cellular Molecular Medi

View full text Add to dashboard Cite

Radiation‐induced dermatitis is a common and serious side effect after radiotherapy. Current clinical treatments cannot efficiently or fully prevent the occurrence of post‐irradiation dermatitis, which remains a significant clinical problem. Resolving this challenge requires gaining a better understanding of the precise pathophysiology, which in turn requires establishment of a suitable animal model that mimics the clinical condition, and can also be used to investigate the mechanism and explore effective treatment options. In this study, a single dose of 90 Gy irradiation to rats resulted in ulceration, dermal thickening, inflammation, hair follicle loss, and sebaceous glands loss, indicating successful establishment of the model. Few hair follicle cells migrated to form epidermal cells, and both the severity of skin fibrosis and hydroxyproline levels increased with time post‐irradiation. Radiation damaged the mitochondria and induced both apoptosis and autophagy of the skin cells. Therefore, irradiation of 90 Gy can be used to successfully establish a rat model of radiation‐induced dermatitis. This model will be helpful for developing new treatments and gaining a better understanding of the pathological mechanism of radiation‐induced dermatitis. Specifically, our results suggest autophagy regulation as a potentially effective therapeutic target.

show abstract

Section: Discussionmentioning

confidence: 99%

Establishment and characterization of a radiation‐induced dermatitis rat model

Sheng

Zhou

Wang

et al. 2019

J Cellular Molecular Medi

View full text Add to dashboard Cite

show abstract

“…For quantitative measurement of RID reactions the use of spectrophotometric measurements of the skin color or the oxygenated hemoglobin level have been suggested by previous authors [4–8,10]. The practical advantage of our novel image analysis method over these methods is that no additional hardware equipment is needed.…”

Section: Discussionmentioning

confidence: 99%

“…In several publications, a subjective assessment of RID was complemented by using instruments to measure skin color, skin hydration or dermal oxygenation of hemoglobin [4–7] with methods that measure patches of skin only a few millimeters across, which is problematic because irradiated skin reacts inhomogenously on this scale, depending for example on skin thickness, skin folds, mechanical stress; to estimate RID accurately, an evaluation of the whole irradiated area is needed. Chin et al [8] used a spectrophotometric device for imaging defined areas within the irradiated breast controlling for the non-irradiated breast before and after each treatment fraction and observed a strong correlation between changes in oxygenated hemoglobin and skin reaction as well as between radiation exposure and changes in skin reaction.…”

Section: Introductionmentioning

confidence: 99%

Testing the feasibility of augmented digital skin imaging to objectively compare the efficacy of topical treatments for radiodermatitis

et al. 2019

View full text Add to dashboard Cite

Introduction Radiation-induced dermatitis (RID) is routinely graded by visual inspection. Inter-observer variability makes this approach inadequate for an objective assessment of the efficacy of different topical treatments. In this study we report on the first clinical application of a new image-analysis tool developed to measure the relevant effects quantitatively and to compare the effects of two different topical preparations used to treat RID. Materials and methods After completion of radiotherapy, RID was retrospectively assessed in 100 white female breast cancer patients who had received adjuvant breast irradiation. Of these patients, 34 were treated with R1&R2, a Lactokine-fluid derived from milk proteins, and 66 were treated with Bepanthen. In addition RID was graded independently by two experienced radiation oncologists in accordance with the Common Terminology Criteria for Adverse Events (CTCAE). For quantitative evaluation, the irradiated breast and the non-irradiated contralateral breast were photographed in a standardized manner including a color reference card. For analysis, all images were converted into the color space L*a*b* and mean values were calculated for each of the color parameters. Results The CTCAE-based grading revealed statistically significant inter-observer variability in the scoring of RID Grades 1, 2 and 3 (p<0.001). A difference between the two topical products could not be observed with visual inspection. By using augmented image analysis methods a statistically significant increase in a*-values (mean 4.15; 95%CI: 5.97–2.33, p<0.001) in patients treated with R1&R2 indicated more intense reddening. Digital subtraction was used to eliminate differences in individual baseline skin tone to generate a new, low-scatter parameter (ΔSEV). Conclusions Visual CTCAE-based evaluation of RID was not suitable for assessing the efficacy of the skin treatment products. In contrast, the novel image analysis enabled a quantitative evaluation independent of skin type and baseline skin tone in our cohort suggesting that augmented image analysis may be a suitable tool for this type of investigation. Prospective studies are needed to validate our findings.

show abstract

“…To overcome these shortcomings, efforts have been made to develop alternative approaches for erythema assessment. An increasing number of data have demonstrated that methods objectively measuring the skin color or dermal oxygenation of hemoglobin can provide additional information [8, 9, 10, 11, 12]. Spectra-based methods illuminate the patient’s skin with a certain wavelength or whole spectrum and measure the reflected light.…”

Section: Introductionmentioning

confidence: 99%

The mathematics of erythema: Development of machine learning models for artificial intelligence assisted measurement and severity scoring of radiation induced dermatitis

Ranjan¹,

Partl

Erhart³

et al. 2021

Preprint

View full text Add to dashboard Cite

Although significant advancements in computer-aided diagnostics using artificial intelligence (AI) have been made, to date, no viable method for radiation-induced skin reaction (RISR) analysis and classification is available. The objective of this single-center study was to develop machine learning and deep learning approaches using deep convolutional neural networks (CNNs) for automatic classification of RISRs according to the Common Terminology Criteria for Adverse Events (CTCAE) grading system. ScarletredⓇ Vision, a novel and state-of-the-art digital skin imaging method capable of remote monitoring and objective assessment of acute RISRs was used to convert 2D digital skin images using the CIELAB color space and conduct SEV* measurements. A set of different machine learning and deep convolutional neural network-based algorithms has been explored for the automatic classification of RISRs. A total of 2263 distinct images from 209 patients were analyzed for training and testing the machine learning and CNN algorithms. For a 2-class problem of healthy skin (grade 0) versus erythema (grade ≥ 1), all machine learning models produced an accuracy of above 70%, and the sensitivity and specificity of erythema recognition were 67-72% and 72-83%, respectively. The CNN produced a test accuracy of 74%, sensitivity of 66%, and specificity of 83% for predicting healthy and erythema cases. For the severity grade prediction of a 3-class problem (grade 0 versus 1 versus 2), the test accuracy was 60-67%, and the sensitivity and specificity were 56-82%, 35-59%, and 65-72%, respectively. For estimating the severity grade of each class, the CNN obtained an accuracy of 73%, 66%, and 82%, respectively. Ensemble learning combines several individual predictions to obtain a better generalization performance. Furthermore, we exploited ensemble learning by deploying a CNN model as a meta-learner. The ensemble CNN based on bagging and majority voting shows an accuracy, sensitivity and specificity of 87%, 90%, and 82% for a 2-class problem, respectively. For a 3-class problem, the ensemble CNN shows an overall accuracy of 66%, while for each grade (0, 1, and 2) accuracies were 0.76%, 0.69%, and 0.87%, sensitivities were 0.70%, 0.57%, and 0.71%, and specificities were 0.78%, 0.75%, and 0.95%, respectively. This study is the first to focus on erythema in radiation-dermatitis and produces benchmark results using machine learning models. The outcome of this study validates that the proposed system can act as a pre-screening and decision support tool for oncologists or patients to provide fast, reliable, and efficient assessment of erythema grading.

show abstract

Association between cumulative radiation dose, adverse skin reactions, and changes in surface hemoglobin among women undergoing breast conserving therapy

Cited by 12 publications

References 33 publications

Establishment and characterization of a radiation‐induced dermatitis rat model

Establishment and characterization of a radiation‐induced dermatitis rat model

Testing the feasibility of augmented digital skin imaging to objectively compare the efficacy of topical treatments for radiodermatitis

The mathematics of erythema: Development of machine learning models for artificial intelligence assisted measurement and severity scoring of radiation induced dermatitis

Contact Info

Product

Resources

About