Hyperspectral imaging assessment for radiotherapy induced skin-erythema: Pilot study

Hemoglobin Concentration as an Indicator of Skin Radiation Damage During Radiation Therapy Treatments

PURPOSE

Acute radiation dermatitis (ARD) is the most common side effect reported by patients undergoing radiation therapy (RT). Currently, the assessment of the severity of the reaction is based on the visual assessment of the skin, which is a subjective method, depending on many factors. The main aim of this study was to investigate the usefulness of hyperspectral imaging (HSI) in the assessment of ARD and find physiological factors that could be correlated with ARD.

METHODS AND MATERIALS

In this clinical pilot trial, weekly acquisitions of hyperspectral camera images of irradiated skin were performed for 5 weeks of RT and at the posttreatment follow-up visit which took place 30 to 40 days after the last fraction of RT. At the same time, the severity of radiodermatitis was assessed based on the criteria of the National Cancer Institute Common Terminology Criteria for Adverse Events (CTCAE). The content and concentration of chromophores in irradiated skin were quantitatively determined using a hyperspectral camera.

RESULTS

The use of HSI supported by image analysis and processing methods allowed for the determination of the content and distribution of hemoglobin and melanin in the irradiated skin. It was found that the hemoglobin concentration is correlated with the subjective assessment made according to the CTCAE protocol.

CONCLUSIONS

HSI is a sensitive and specific method of analyzing the concentration of chromophores in the skin, including hemoglobin. A clear correlation was found between hemoglobin concentration and CTCAE v.5 scale because of which HSI can be considered as an objective method of skin assessment during RT.

Highly bioactive triple-helical nano collagens for accelerated treatment of photodamaged skin

Skin damage caused by excessive UV exposure has gradually become one of the most common skin diseases, leading to desquamation, scab formation, inflammation and even skin cancer. Animal-derived hydrolyzed collagen peptides have been developed to treat UV-damaged skin; however, they have raised severe concerns such as potential viral transmission, random sequences and the lack of a triple helix structure. Nano collagen, a novel type of short collagen, has attracted increasing attention in the mimicking of natural collagen, while its applications in UV-damaged skin treatment remains unexplored. Herein, we have created a series of nano collagens and for the first time studied their capability of accelerating UV-damaged skin healing. Nano collagens, consisting of repetitive (GPO)n triplets and a GFOGER motif, display a stable triple-helical structure, significantly promoting fibroblast adhesion, proliferation, and migration. The repair effects of nano collagens have been investigated using an acute UV-damaged skin mouse model. Combo evaluations indicate that nano collagens contribute to recovering the dermis density and erythema index of UV-damaged skin. Histological analysis further demonstrates their capability of promoting the healing of damaged skin by accelerating re-epithelialization and collagen regeneration. These highly bioactive triple-helical nano collagens present a novel strategy for the treatment of UV-damaged skin, providing promising applications in cosmetics and dermatology.

Global hotspots and research trends of radiation-induced skin injury: a bibliometric analysis from 2004 to 2023

Background

Radiation therapy has become an important treatment for many malignant tumours after surgery and for palliative tumour care. Although modern radiotherapy technology is constantly improving, radiation damage to normal tissues is often difficult to avoid, and radiation-induced skin injury (RSI) is a common complication, manifested as skin erythema, peeling, ulceration, and even bone and deep organ damage, seriously affect the quality of life for patients. Basic research and clinical trials related to RSI have achieved certain results, while no researchers have conducted comprehensive bibliometric studies.

Objective

A comprehensive bibliometric analysis of publications on RSI published between 2004 and 2023 was conducted to identify current hotspots and future directions in this area of study.

Methods

RSI-related publications published between January 1, 2004, and December 31, 2023, were retrieved from the Web of Science Core Collection (WoSCC) database for analysis using VOSviewer and CiteSpace analytics.

Results

A total of 1009 publications on RSI from 2004 to 2023 were included in the WoSCC database. The United States had the highest productivity with 299 papers, accounting for 29.63% of the total production, followed by China with 193 papers (19.13%) and Japan with 111 papers (11.00%). In terms of research institutions and journals, the University of Toronto and Journal of Supportive Care in Cancer published the highest number of papers. Professor Edward Chow published the most articles, while Professor Shuyu Zhang was the most cited. The top ten most-cited papers focused on the pathogenesis, prevention, and management of RSI. Keyword co-occurrence analysis and the top 25 keywords with the strongest citation bursts suggest that current research focuses on the pathogenesis, prevention, and treatment management of RSI.

Conclusion

This study conducted a systematic bibliometric analysis of RSI publications from 2004 to 2023; identified the trends in RSI publications, major research countries, major research institutions, major research journals, major research authors, and major research keywords; and revealed the future development direction and research hotspots of this field. This study provides a valuable reference for future RSI research.

Lung image segmentation via generative adversarial networks

Introduction

Lung image segmentation plays an important role in computer-aid pulmonary disease diagnosis and treatment.

Methods

This paper explores the lung CT image segmentation method by generative adversarial networks. We employ a variety of generative adversarial networks and used their capability of image translation to perform image segmentation. The generative adversarial network is employed to translate the original lung image into the segmented image.

Results

The generative adversarial networks-based segmentation method is tested on real lung image data set. Experimental results show that the proposed method outperforms the state-of-the-art method.

Discussion

The generative adversarial networks-based method is effective for lung image segmentation.

Hyperspectral imaging-based erythema classification in atopic dermatitis

BACKGROUND/PURPOSE

Among the characteristics that appear in the epidermis of the skin, erythema is primarily evaluated through qualitative scales, such as visual assessment (VA). However, VA is not ideal because it relies on the experience and skill of dermatologists. In this study, we propose a new evaluation method based on hyperspectral imaging (HSI) to improve the accuracy of erythema diagnosis in clinical settings and investigate the applicability of HSI to skin evaluation.

METHODS

For this study, 23 subjects diagnosed with atopic dermatitis were recruited. The inside of the right arm is selected as the target area and photographed using a hyperspectral camera (HS). Subsequently, based on the erythema severity visually assessed by a dermatologist, the severity classification performance of the RGB and HS images is compared.

RESULTS

Erythema severity is classified as high when using (i) all reflectances of the entire HSI band and (ii) a combination of color features (R of RGB, a* of CIEL*a*b*) and five selected bands through band selection. However, as the number of features increases, the amount of calculation increases and becomes inefficient; therefore, (ii), which uses only seven features, is considered to perform classification more efficiently than (i), which uses 150 features.

CONCLUSION

In conclusion, we demonstrate that HSI can be applied to erythema severity classification, which can further increase the accuracy and reliability of diagnosis when combined with other features observed in erythema. Additionally, the scope of its application can be expanded to various studies related to skin pigmentation.

Acceleration of Hyperspectral Skin Cancer Image Classification through Parallel Machine-Learning Methods

Hyperspectral imaging (HSI) has become a very compelling technique in different scientific areas; indeed, many researchers use it in the fields of remote sensing, agriculture, forensics, and medicine. In the latter, HSI plays a crucial role as a diagnostic support and for surgery guidance. However, the computational effort in elaborating hyperspectral data is not trivial. Furthermore, the demand for detecting diseases in a short time is undeniable. In this paper, we take up this challenge by parallelizing three machine-learning methods among those that are the most intensively used: Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGB) algorithms using the Compute Unified Device Architecture (CUDA) to accelerate the classification of hyperspectral skin cancer images. They all showed a good performance in HS image classification, in particular when the size of the dataset is limited, as demonstrated in the literature. We illustrate the parallelization techniques adopted for each approach, highlighting the suitability of Graphical Processing Units (GPUs) to this aim. Experimental results show that parallel SVM and XGB algorithms significantly improve the classification times in comparison with their serial counterparts.

Diffuse Reflectance Spectroscopy of Changes in Tumor Microenvironment in Response to Different Doses of Radiation

Radiation therapy plays an important role in cancer treatment, as it is an established method used as part of the treatment plan for the majority of cancer patients. Real-time monitoring of the effects of radiation on the tumor microenvironment can contribute to the development of better treatment plans. In this study, we use diffuse reflectance spectroscopy, a non-invasive optical fiber-based technique, to determine the effects of different doses of radiation on the tumor microenvironment, as well as to determine the sensitivity of diffuse reflectance spectroscopy to low doses of radiation that are used in the treatment of certain cancers. We injected 4T1 cells into 50 Balb/c mice to generate tumor xenografts. When the tumors grew to 200 mm3, we distributed the mice into a control group or one of three radiation groups: 1, 2, or 4 Gy/fraction, and they underwent treatment for five consecutive days. We measured the tumor volume and collected diffuse reflectance spectra every day, with optical measurements being acquired both before and one h postirradiation on the five days of treatment. Based on the diffusely reflected light, we quantified vascular oxygenation, total hemoglobin content, and tissue scattering within these tumors. There was a significant increase in tumor vascular oxygenation, which was primarily due to an increase in oxygenated hemoglobin, in response to a 1 Gy/fraction of radiation, while there was a decrease in tissue scattering in response to all doses of radiation. Immunohistochemical analysis revealed that tumor cell proliferation and apoptosis were higher in irradiated groups compared to the control group. Our findings show that diffuse reflectance spectroscopy is sensitive to microenvironmental changes in tumors treated with doses of radiation as low as 1 Gy/fraction.

Potential Use of Novel Image and Signal Processing Methods to Develop a Quantitative Assessment of the Severity of Acute Radiation Dermatitis in Breast Cancer Radiotherapy

More than 95% of patients who undergo radiotherapy report symptoms of radiation dermatitis, which is a side effect of this therapy. Erythema, edema, dry and moist desquamation intensify with each fraction of irradiation and can significantly reduce a patient's quality of life. Therefore, an effective skin care procedure is needed for skin that has been exposed to ionizing radiation in order to avoid unplanned treatment interruptions. The methods that are currently used to assess the severity of an acute radiation reaction are based on visual scales (RTOG, EORTC, NCI CTCAE, LENT-SOMA). Because the assessment is made subjectively, the results depend on the researchers, their experience and perceptiveness. Until now, several studies have been carried out to check the possibility of using an objective methods like hyperspectral imaging, thermal imaging, laser Doppler flowmetry, dielectric and electrochemical methods, reflection spectrophotometry and Courage-Khazaka Multi-skin instrument to radiation-induced dermatitis assessment. Unfortunately, due to various limitations that occurred in the research, none of these techniques was successfully implement as alternative for visual assessment. The continuous development of technology enables researchers to access new techniques that might constitute useful diagnostic and cognitive tools. Infrared thermal imaging, hyperspectral imaging and reflectance spectroscopy are examples of the visual techniques that have been used for many years in various fields of medicine, including dermatology and chronic wound or burn care. They provide information on the skin parameters, such as the temperature, concentration and distribution of chromophores (eg, hemoglobin and melanin), saturation or perfusion changes. The aim of this study is to review the available literature on the use of imaging methods in the clinical assessment of skin with lesions of various origins, evaluation of their suitability for the assessment of radiation reaction and consideration the possibility of creating a quantitative scale for assessing severity of acute radiation dermatitis.