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

Feature-Based vs. Deep-Learning Fusion Methods for the In Vivo Detection of Radiation Dermatitis Using Optical Coherence Tomography, a Feasibility Study

Acute radiation dermatitis (ARD) is a common and distressing issue for cancer patients undergoing radiation therapy, leading to significant morbidity. Despite available treatments, ARD remains a distressing issue, necessitating further research to improve prevention and management strategies. Moreover, the lack of biomarkers for early quantitative assessment of ARD impedes progress in this area. This study aims to investigate the detection of ARD using intensity-based and novel features of Optical Coherence Tomography (OCT) images, combined with machine learning. Imaging sessions were conducted twice weekly on twenty-two patients at six neck locations throughout their radiation treatment, with ARD severity graded by an expert oncologist. We compared a traditional feature-based machine learning technique with a deep learning late-fusion approach to classify normal skin vs. ARD using a dataset of 1487 images. The dataset analysis demonstrates that the deep learning approach outperformed traditional machine learning, achieving an accuracy of 88%. These findings offer a promising foundation for future research aimed at developing a quantitative assessment tool to enhance the management of ARD.

Utilizing radiomics and dosiomics with AI for precision prediction of radiation dermatitis in breast cancer patients

PURPOSE

This study explores integrating clinical features with radiomic and dosiomic characteristics into AI models to enhance the prediction accuracy of radiation dermatitis (RD) in breast cancer patients undergoing volumetric modulated arc therapy (VMAT).

MATERIALS AND METHODS

This study involved a retrospective analysis of 120 breast cancer patients treated with VMAT at Kaohsiung Veterans General Hospital from 2018 to 2023. Patient data included CT images, radiation doses, Dose-Volume Histogram (DVH) data, and clinical information. Using a Treatment Planning System (TPS), we segmented CT images into Regions of Interest (ROIs) to extract radiomic and dosiomic features, focusing on intensity, shape, texture, and dose distribution characteristics. Features significantly associated with the development of RD were identified using ANOVA and LASSO regression (p-value < 0.05). These features were then employed to train and evaluate Logistic Regression (LR) and Random Forest (RF) models, using tenfold cross-validation to ensure robust assessment of model efficacy.

RESULTS

In this study, 102 out of 120 VMAT-treated breast cancer patients were included in the detailed analysis. Thirty-two percent of these patients developed Grade 2+ RD. Age and BMI were identified as significant clinical predictors. Through feature selection, we narrowed down the vast pool of radiomic and dosiomic data to 689 features, distributed across 10 feature subsets for model construction. In the LR model, the J subset, comprising DVH, Radiomics, and Dosiomics features, demonstrated the highest predictive performance with an AUC of 0.82. The RF model showed that subset I, which includes clinical, radiomic, and dosiomic features, achieved the best predictive accuracy with an AUC of 0.83. These results emphasize that integrating radiomic and dosiomic features significantly enhances the prediction of Grade 2+ RD.

CONCLUSION

Integrating clinical, radiomic, and dosiomic characteristics into AI models significantly improves the prediction of Grade 2+ RD risk in breast cancer patients post-VMAT. The RF model analysis demonstrates that a comprehensive feature set maximizes predictive efficacy, marking a promising step towards utilizing AI in radiation therapy risk assessment and enhancing patient care outcomes.

Risk Prediction Model for Radiation-induced Dermatitis in Patients with Cervical Carcinoma Undergoing Chemoradiotherapy

PURPOSE

Radiation-induced dermatitis (RD) is a common side-effect of therapeutic ionizing radiation that can severely affect patient quality of life. This study aimed to develop a risk prediction model for the occurrence of RD in patients with cervical carcinoma undergoing chemoradiotherapy using electronic medical records (EMRs).

METHODS

Using EMRs, the clinical data of patients who underwent simultaneous radiotherapy and chemotherapy at a tertiary cancer hospital between 2017 and 2022 were retrospectively collected, and the patients were divided into two groups: a training group and a validation group. A predictive model was constructed to predict the development of RD in patients who underwent concurrent radiotherapy and chemotherapy for cervical cancer. Finally, the model's efficacy was validated using a receiver operating characteristic curve.

RESULTS

The incidence of radiation dermatitis was 89.5% (560/626) in the entire cohort, 88.6% (388/438) in the training group, and 91.5% (172/188) in the experimental group. The nomogram was established based on the following factors: age, the days between the beginning and conclusion of radiotherapy, the serum albumin after chemoradiotherapy, the use of single or multiple drugs for concurrent chemotherapy, and the total dose of afterloading radiotherapy. Internal and external verification indicated that the model had good discriminatory ability. Overall, the model achieved an area under the receiver operating characteristic curve of .66.

CONCLUSIONS

The risk of RD in patients with cervical carcinoma undergoing chemoradiotherapy is high. A risk prediction model can be developed for RD in cervical carcinoma patients undergoing chemoradiotherapy, based on over 5 years of EMR data from a tertiary cancer hospital.

Clinical characteristics of the well-defined upper eyelid vascular network pattern in patients with rosacea

BACKGROUND

Rosacea is a chronic inflammatory skin disease. The diagnosis is based on the symptoms and physical signs, which still lacks objective laboratory tests or imaging tests.

OBJECTIVES

To propose and evaluate the upper eyelid network pattern in rosacea.

METHODS

Participants included patients diagnosed with rosacea, other facial erythematous skin diseases, and normal controls, all of whom underwent full-face imaging utilizing the VISIA® system software. According to these images, researchers evaluated the condition of the upper eyelid vascular network, developed the grading scale and then compared the difference of distribution in the three groups.

RESULTS

The occurrence rate of upper eyelid vascular network in rosacea was significantly higher than that in other facial erythematous skin diseases (84.3 vs. 32.0%, P < 0.001) and normal controls (84.3 vs. 28.0%, P < 0.001). The upper eyelid vascular network pattern was proposed (none [no clearly reticular vessels], mild [10-50% area of reticular vessels], moderate-to-severe [>50% area of reticular vessels]). Moderate-to-severe grade was defined as well-defined upper eyelid vascular network pattern, which was specific to patients with rosacea (rosacea vs. other facial erythematous skin diseases, adjusted odds ratio [aOR] = 5.814, 95% confidence interval [CI]: 3.899-8.670) (rosacea vs. heathy controls, aOR = 12.628, 95% CI: 8.334-19.112). The severity of the well-defined pattern had no significant association with age, duration, and phenotypes of rosacea (P > 0.05).

CONCLUSION

The well-defined upper eyelid vascular network pattern specifically appeared in patients with rosacea, which could be a possible clue to the diagnosis of rosacea.

Automated classification of hidradenitis suppurativa disease severity by convolutional neural network analyses using calibrated clinical images

BACKGROUND

The assessment of hidradenitis suppurativa (HS) severity requires detailed, and error-prone lesion counts. This proof-of-concept study aimed to automatically classify HS disease severity using machine learning of clinical smartphone images.

METHODS

777 ambient-light and size-controlled images were used to build a class-balanced synthetic dataset (n = 7675). Convolutional neural networks (CNN) were used for automated severity classification (scale 0-3), and to assess disease-dynamics. International Hidradenitis Suppurativa Severity Score System (IHS4) served as reference. A U-NET algorithm was implemented for automated localization of diseased skin.

RESULTS

CNNs were able to distinguish no/mild from moderate/severe disease with an overall prediction accuracy of 78% [receiver operating curve (AUC) 0.85]. Correct IHS4 classification was achieved with an overall accuracy of 72% (AUC 0.84-0.89). In addition, disease dynamics using IHS4 numerical values aligned with CNN outputs (NRMSE 0.262). The UNET algorithm localized lesions with a pixel accuracy of 88.1% and test loss of 0.42.

LIMITATIONS

Limitations in assessing tattooed and hairy skin. Limited number of patients with dark skin colour and Hurley I.

CONCLUSION

CNNs were able to distinguish no/mild from moderate/severe disease, classify disease severity over time, and automatically identify diseased skin areas and the skin phototype. This study breaks new grounds for fast, reliable, reproducible and easy-to-use HS severity assessments using clinical images.

Deciphering the fibrotic process: mechanism of chronic radiation skin injury fibrosis

This review explores the mechanisms of chronic radiation-induced skin injury fibrosis, focusing on the transition from acute radiation damage to a chronic fibrotic state. It reviewed the cellular and molecular responses of the skin to radiation, highlighting the role of myofibroblasts and the significant impact of Transforming Growth Factor-beta (TGF-β) in promoting fibroblast-to-myofibroblast transformation. The review delves into the epigenetic regulation of fibrotic gene expression, the contribution of extracellular matrix proteins to the fibrotic microenvironment, and the regulation of the immune system in the context of fibrosis. Additionally, it discusses the potential of biomaterials and artificial intelligence in medical research to advance the understanding and treatment of radiation-induced skin fibrosis, suggesting future directions involving bioinformatics and personalized therapeutic strategies to enhance patient quality of life.

Factors associated with the quality of life of women undergoing radiotherapy

OBJECTIVE

To evaluate the skin characteristics and quality of life of patients with breast cancer undergoing radiotherapy.

METHOD

Cross-sectional study conducted with 60 women. The classification scales of skin changes resulting from exposure to ionizing radiation (RTOG) and the validated versions in Portuguese of those that classified skin types (Fitzpatrick), symptoms (RISRAS) and quality of life (DLQI) were applied. in the period between December 2021 and October 2022. For data analysis, Fisher's Exact Test, Chi-Square and Asymptotic General Independence Test were used.

RESULTS

100% of patients had skin irritation. As the treatment progressed and the radiodermatitis appeared or worsened, there was a tendency for the intensity of signs and symptoms to increase, such as: sensitivity, discomfort or pain, itching, burning and heat, dry and wet desquamation, which may have impacted the quality of life and reflected in other aspects, such as: shopping activities or outings (p=0.0020), social activities or leisure activities (p=0.0420).

CONCLUSION

Radiodermatitis is a common condition that affects women with breast cancer undergoing radiotherapy, skin characteristics and quality of life of patients affected during this treatment.

RISREAC Study: Assessment of Cutaneous Radiation Injury Through Clinical Documentation

OBJECTIVE

Radiation dermatitis (RD) occurs in 95% of patients receiving radiation therapy (RT) for cancer treatment, affecting 800 million patients annually. We aimed to demonstrate the feasibility of developing a historical RD cohort, Radiation Induced Skin Reactions (RISREAC) cohort.

METHODS

This retrospective study evaluated RD-related clinical documentation for 245 breast cancer patients who received RT at the University of Rochester Medical Center, to understand the RD progression, scoring, and management. All statistical analyses were performed at 0.05 level of significance.

RESULTS

Clinician-documented RD severity was observed for 169 (69%) patients with a mean severity of 1.57 [1.46, 1.68]. The mean descriptor-based severity score of 2.31 [2.18, 2.45] moderately correlated (r = 0.532, P < 0.0001) with documented RD grade. Most patients (91.8%) received skin care treatment during RT, with 66.7% receiving more than 2 modalities.

CONCLUSIONS

The RISREAC cohort is the first retrospective cohort established from clinical documentation of radiation-induced skin changes for the study of RD and cutaneous radiation injury (CRI). RD symptom descriptors were more reliably documented and suitable for all skin types compared to Radiation Therapy Oncology Group (RTOG) or Common Toxicity Criteria for Adverse Events (CTCAE) grades. A new descriptor-based scoring tool would be useful for RD and CRI.

Analysis of facial vascular pattern characteristics in the Korean population

BACKGROUND

Facial erythema is a common problem among patients visiting dermatologists. However, data on the clinical characteristics of facial erythema in healthy people are lacking. We aimed to compare and analyze the severity and pattern of facial vascularity in healthy subjects based on their age and gender.

MATERIALS AND METHODS

This study included 198 Korean volunteers (126 females and 72 males) with Fitzpatrick skin types II, III, or IV. Fourteen different anatomical areas on the face were divided into facial erythema units. Each unit was scored from one (least erythematous) to five (most erythematous) according to the observed level of erythema on the red images implemented as hemoglobin content. We also evaluated the presence of facial telangiectatic macules.

RESULTS

On average, the perinasal, nasal, and cheek units were the most hypervascular regions. In contrast, the degree of facial erythema was lowest in the labial (perioral), neck, and temporal regions. The average value of erythema was higher in males than in females. Additionally, the severity of erythema tended to increase with age. In both males and females, the number of telangiectatic macules increased with age.

CONCLUSIONS

We analyzed the clinical characteristics of erythema in healthy subjects with Fitzpatrick skin types II, III, or IV in the Korean population. This study is expected to be used to identify the neurovascular pathogenesis of the most common regions of facial dermatosis in the future.

Wavelength-Dependent Effects of Photobiomodulation for Wound Care in Diabetic Wounds

Photobiomodulation, showing positive effects on wound healing processes, has been performed mainly with lasers in the red/infrared spectrum. Light of shorter wavelengths can significantly influence biological systems. This study aimed to evaluate and compare the therapeutic effects of pulsed LED light of different wavelengths on wound healing in a diabetic (db/db) mouse excision wound model. LED therapy by Repuls was applied at either 470 nm (blue), 540 nm (green) or 635 nm (red), at 40 mW/cm² each. Wound size and wound perfusion were assessed and correlated to wound temperature and light absorption in the tissue. Red and trend-wise green light positively stimulated wound healing, while blue light was ineffective. Light absorption was wavelength-dependent and was associated with significantly increased wound perfusion as measured by laser Doppler imaging. Shorter wavelengths ranging from green to blue significantly increased wound surface temperature, while red light, which penetrates deeper into tissue, led to a significant increase in core body temperature. In summary, wound treatment with pulsed red or green light resulted in improved wound healing in diabetic mice. Since impeded wound healing in diabetic patients poses an ever-increasing socio-economic problem, LED therapy may be an effective, easily applied and cost-efficient supportive treatment for diabetic wound therapy.

Financial impact of cost of capital on tourism-based SMEs in COVID-19: implications for tourism disruption mitigation

Opportunities for funding Tourism SMEs are emerging globally due to the expansion of tourism sector. However, it is still being determined how these financial arrangements will be controlled at more significant sizes equitably. In the contemporary period, E7 economy is deficient in producing the financial resources to ensure the availability of funds for the acquisition of funds for tourism-based SMEs. However, this research tested the empirical position of cost of debt in E-7 economies during COVID-19 crises. Study findings have shown significant outcomes between the constructs. The variation of conditions, structural uncertainty, transection systems, and variation in support by the financial institution for tourism-based SMEs are the main reasons that lessen borrowing and lending system of funds, from banks to SMEs. However, theorists must revisit the transaction system of debt financing for SMEs. Policymakers are suggested to develop viable and SME system-friendly policies to finance through debt capital from the banks in the time of structural imposed crises, like COVID-19.

Assessing financial factors for oil supply disruptions and its impact on oil supply security and transportation risks

The evaluation of energy security offers a standard for policy research and highlights the problems of securing the energy supply. A composite index for analyzing the risk of Southeast Asian nations' oil supply is developed in this study. Indicators used to calculate the index include the import-to-LGE ratio, GPR, market liquidity, gross domestic product, the import-to-consumption ratio, heterogeneity, oil price volatility, US$ volatility, and transportation risk. The index is based on these and other factors. According to the findings, Nepal and Sri Lanka are the most susceptible to oil supply interruptions. This indicates that India is more likely to shift its oil suppliers. At the same time, Maldives, Nepal, and Sri Lanka have the lowest supply risk scores, indicating that they are the most vulnerable to supply disruptions. Reduce the effect of oil supply risk by enacting policies such as the adoption of renewable technologies, nuclear power generation, diversification of exporting supplies, and reducing fossil fuel subsidies.

Correction: Wind et al. Topical Bimiralisib Shows Meaningful Cutaneous Drug Levels in Healthy Volunteers and Mycosis Fungoides Patients but No Clinical Activity in a First-in-Human, Randomized Controlled Trial. Cancers 2022, 14, 1510

The authors wish to make the following corrections to this paper [...].

A New Approach to Quantify and Grade Radiation Dermatitis Using Deep-Learning Segmentation in Skin Photographs

AIMS

Objective evaluation of radiation dermatitis is important for analysing the correlation between the severity of radiation dermatitis and dose distribution in clinical practice and for reliable reporting in clinical trials. We developed a novel radiation dermatitis segmentation system based on convolutional neural networks (CNNs) to consistently evaluate radiation dermatitis.

MATERIALS AND METHODS

The radiation dermatitis segmentation system is designed to segment the radiation dermatitis occurrence area using skin photographs and skin-dose distribution. A CNN architecture with a dilated convolution layer and skip connection was designed to estimate the radiation dermatitis area. Seventy-three skin photographs obtained from patients undergoing radiotherapy were collected for training and testing. The ground truth of radiation dermatitis segmentation is manually delineated from the skin photograph by an experienced radiation oncologist and medical physicist. We converted the skin photographs to RGB (red-green-blue) and CIELAB (lightness (L^∗), red-green (a^∗) and blue-yellow (b^∗)) colour information and trained the network to segment faint and severe radiation dermatitis using three different input combinations: RGB, RGB + CIELAB (RGBLAB) and RGB + CIELAB + skin-dose distribution (RGBLAB_D). The proposed system was evaluated using the Dice similarity coefficient (DSC), sensitivity, specificity and normalised Matthews correlation coefficient (nMCC). A paired t-test was used to compare the results of different segmentation performances.

RESULTS

Optimal data composition was observed in the network trained for radiation dermatitis segmentation using skin photographs and skin-dose distribution. The average DSC, sensitivity, specificity and nMCC values of RGBLAB_D were 0.62, 0.61, 0.91 and 0.77, respectively, in faint radiation dermatitis, and 0.69, 0.78, 0.96 and 0.83, respectively, in severe radiation dermatitis.

CONCLUSION

Our study showed that CNN-based radiation dermatitis segmentation in skin photographs of patients undergoing radiotherapy can describe radiation dermatitis severity and pattern. Our study could aid in objectifying the radiation dermatitis grading and analysing the reliable correlation between dosimetric factors and the morphology of radiation dermatitis.