Quantitative Thermal Imaging Biomarkers to Detect Acute Skin Toxicity From Breast Radiation Therapy Using Supervised Machine Learning

Saednia, Khadijeh; Tabbarah, Sami; Lagree, Andrew; Wu, Tina; Klein, Jonathan; Díaz-Rubio, Eduardo; Hall, Michael; Chow, Edward; Rakovitch, Eileen; Childs, Charmaine; Sadeghi‐Naini, Ali; Tran, William T.

doi:10.1016/j.ijrobp.2019.12.032

Cited by 28 publications

(35 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CTCAE scales were found to be associated with a * and L * values, which are indicators of skin color alteration [ 13 ]. Saednia et al [ 17 ] reported that thermal imaging markers could be used to monitor RIT. Patients with a CTCAE toxicity score > 2 demonstrated a significant increase in skin temperature.…”

Section: Discussionmentioning

confidence: 99%

“…To avoid this bias, many objective assessment tools have been introduced for monitoring skin changes more accurately, including ultrasound [11][12][13], reflectance spectrophotometry [14][15][16], thermal images [17], laser Doppler flowmetry (LDF) [18] and other multiprobe devices which consists of various probes that can assess different skin parameters, including erythema, pigmentation, hydration; skin pH, skin temperature etc. [19][20][21].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Quantitative assessments of late radiation-induced skin and soft tissue toxicity and correlation with RTOG scales and biological equivalent dose in breast cancer

et al. 2021

View full text Add to dashboard Cite

Purpose Radiation-induced toxicity (RIT) is usually assessed by inspection and palpation. Due to their subjective and unquantitative nature, objective methods are required. This study aimed to determine whether a quantitative tool is able to assess RIT and establish an underlying BED-response relationship in breast cancer. Methods Patients following seven different breast radiation protocols were recruited to this study for RIT assessment with qualitative and quantitative examination. The biologically equivalent dose (BED) was used to directly compare different radiation regimens. RIT was subjectively evaluated by physicians using the Radiation Therapy Oncology Group (RTOG) late toxicity scores. Simultaneously an objective multiprobe device was also used to quantitatively assess late RIT in terms of erythema, hyperpigmentation, elasticity and skin hydration. Results In 194 patients, in terms of the objective measurements, treated breasts showed higher erythema and hyperpigmentation and lower elasticity and hydration than untreated breasts (p < 0.001, p < 0.001, p < 0.001, p = 0.019, respectively). As the BED increased, Δerythema and Δpigmentation gradually increased as well (p = 0.006 and p = 0.002, respectively). Regarding the clinical assessment, the increase in BED resulted in a higher RTOG toxicity grade (p < 0.001). Quantitative assessments were consistent with RTOG scores. As the RTOG toxicity grade increased, the erythema and pigmentation values increased, and the elasticity index decreased (p < 0.001, p = 0.016, p = 0.005, respectively). Conclusions The multiprobe device can be a sensitive and simple tool for research purpose and quantitatively assessing RIT in patients undergoing radiotherapy for breast cancer. Physician-assessed toxicity scores and objective measurements revealed that the BED was positively associated with the severity of RIT.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Quantitative assessments of late radiation-induced skin and soft tissue toxicity and correlation with RTOG scales and biological equivalent dose in breast cancer

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Few implementations of ML non-related to breast cancer diagnosis were found. Zadeh et al used fuzzy active contours to segment suspected breast tumor areas (ACC = 91.89%) and Saednia et al developed a supervised ML algorithm based on Random Forest to assess dermatitis caused by radiation therapy, reporting thermal markers indicative of radiation-induced skin toxicity with an ACC of 87% [51].…”

Section: Breast Cancermentioning

confidence: 99%

Meta-Analysis and Systematic Review of the Application of Machine Learning Classifiers in Biomedical Applications of Infrared Thermography

2021

View full text Add to dashboard Cite

Atypical body temperature values can be an indication of abnormal physiological processes associated with several health conditions. Infrared thermal (IRT) imaging is an innocuous imaging modality capable of capturing the natural thermal radiation emitted by the skin surface, which is connected to physiology-related pathological states. The implementation of artificial intelligence (AI) methods for interpretation of thermal data can be an interesting solution to supply a second opinion to physicians in a diagnostic/therapeutic assessment scenario. The aim of this work was to perform a systematic review and meta-analysis concerning different biomedical thermal applications in conjunction with machine learning strategies. The bibliographic search yielded 68 records for a qualitative synthesis and 34 for quantitative analysis. The results show potential for the implementation of IRT imaging with AI, but more work is needed to retrieve significant features and improve classification metrics.

show abstract

“…Current available literature includes only one abstract (11) and two full papers (10,12). In the study by Saednia et al, they proposed an innovative approach based on the detection of bodysurface temperature increase induced by radiation dermatitis.…”

Section: Breastmentioning

confidence: 99%

“…The Supplementary Material for this article can be found online at: https://www.frontiersin.org/articles/ 10…”

Section: Supplementary Materialsmentioning

confidence: 99%

Machine Learning-Based Models for Prediction of Toxicity Outcomes in Radiotherapy

et al. 2020

View full text Add to dashboard Cite

In order to limit radiotherapy (RT)-related side effects, effective toxicity prediction and assessment schemes are essential. In recent years, the growing interest toward artificial intelligence and machine learning (ML) within the science community has led to the implementation of innovative tools in RT. Several researchers have demonstrated the high performance of ML-based models in predicting toxicity, but the application of these approaches in clinics is still lagging, partly due to their low interpretability. Therefore, an overview of contemporary research is needed in order to familiarize practitioners with common methods and strategies. Here, we present a review of ML-based models for predicting and classifying RT-induced complications from both a methodological and a clinical standpoint, focusing on the type of features considered, the ML methods used, and the main results achieved. Our work overviews published research in multiple cancer sites, including brain, breast, esophagus, gynecological, head and neck, liver, lung, and prostate cancers. The aim is to define the current state of the art and main achievements within the field for both researchers and clinicians.

show abstract

Quantitative Thermal Imaging Biomarkers to Detect Acute Skin Toxicity From Breast Radiation Therapy Using Supervised Machine Learning

Cited by 28 publications

References 51 publications

Quantitative assessments of late radiation-induced skin and soft tissue toxicity and correlation with RTOG scales and biological equivalent dose in breast cancer

Quantitative assessments of late radiation-induced skin and soft tissue toxicity and correlation with RTOG scales and biological equivalent dose in breast cancer

Meta-Analysis and Systematic Review of the Application of Machine Learning Classifiers in Biomedical Applications of Infrared Thermography

Machine Learning-Based Models for Prediction of Toxicity Outcomes in Radiotherapy

Contact Info

Product

Resources

About