Assessment of skin inflammation using near-infrared Raman spectroscopy combined with artificial intelligence analysis in an animal model

Kanemura, Yohei; Kanazawa, Meiko; Hashimoto, Satoru; Hayashi, Yoshihiko; Fujiwara, Erina; Suzuki, Ayako; Ishii, Takashige; Goto, Masakazu; Nozaki, Hirōshi; Inoue, Takanori; Takanari, Hiroki

doi:10.1039/d2an00193d

Cited by 8 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, RS combined with AI procedures has been adopted as a standard to distinguish different kinds of skin patterns. For instance, Ye et al [163] used a ML-based classification system to distinguish burn severities from ex vivo porcine skin tissue, while Kanemura et al [164] employed a near-infrared RS and ML techniques to classify inflammatory skin diseases. In the case of skin cancer detection, several investigations used RS as the main tool to analyze malignant skin samples, obtaining analysis up to a molecular level.…”

Section: Skin Cancermentioning

confidence: 99%

Raman Spectroscopy and AI Applications in Cancer Grading: An Overview

Conforti,

Lazzini,

Russo

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Raman spectroscopy (RS) is a label-free molecular vibrational spectroscopy technique that is able to identify the molecular fingerprint of various samples making use of the inelastic scattering of monochromatic light. Because of its advantages of non-destructive and accurate detection, RS is finding more and more use for benign and malignant tissues, tumor differentiation, tumor subtype classification, and section pathology diagnosis, operating either in vivo or in vitro. However, the high specificity of RS comes at a cost. The acquisition rate is low, depth information cannot be directly accessed, and the sampling area is limited. Such limitations can be contained if data pre-and post-processing methods are combined with current methods of Artificial Intelligence (AI), essentially, Machine Learning (ML) and Deep Learning (DL). The latter is modifying the approach to cancer diagnosis currently used to automate many cancer data analyses, and it has emerged as a promising option for improving healthcare accuracy and patient outcomes by abiliting prediction diseases tools. In a very broad context, Artificial Intelligence applications in oncology include risk assessment, early diagnosis, patient prognosis estimation, and treatment selection based on deep knowledge. The application of autonomous methods to datasets generated by RS analysis of benign and malignant tissues could make RS a rapid and stand-alone technique to help pathologists diagnose cancer with very high accuracy. This review describes the current milestones achieved by applying AI-based algorithms to RS analysis, grouped according to seven major types of cancers (Pancreatic, Breast, Skin, Brain, Prostate, Ovarian and Oral cavity). Additionally, it provides a theoretical foundation to tackle both present and forthcoming challenges in this domain. By exploring the current achievements and discussing the relative methodologies, this review offers recapitulative insights on recent and ongoing efforts to position RS as a rapid and effective cancer screening tool for pathologists. Accordingly, we aim to encourage future research endeavors and to facilitate the realization of the full potential of RS and AI applications in cancer grading.

show abstract

Section: Skin Cancermentioning

confidence: 99%

Raman Spectroscopy and AI Applications in Cancer Grading: An Overview

Conforti,

Lazzini,

Russo

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…As research progresses, future directions include refining AI models for greater accuracy, expanding their capabilities to cover more skin conditions, and integrating patient history and genetic information to provide a more comprehensive diagnostic tool. There is also a growing interest in developing models that can predict treatment outcomes and personalize treatment plans, marking a significant step towards precision medicine in dermatology [2,6].…”

Section: Challenges and Future Directionsmentioning

confidence: 99%

“…When combined with AI, it can predict cutaneous inflammation with high sensitivity and specificity. This approach has shown potential in accurately identifying changes in the skin associated with various diseases, offering insights into the pathology of skin inflammation without the need for invasive tissue histopath examinations [6].…”

Section: Raman Spectroscopy Combined With Aimentioning

confidence: 99%

“…Inflammatory skin disorders, with their significant impact on patients' quality of life and the healthcare system, are among the conditions that could greatly benefit from AI's capabilities [5]. These conditions often require ongoing management and treatment adjustments, which can be optimized through AI algorithms that analyze disease progression, treatment responses, and patient data to recommend personalized care plans [5,6].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence in Inflammatory Skin Disorders

Rokni,

Gholizadeh,

Babaei

et al. 2024

Dermatological Reviews

View full text Add to dashboard Cite

BackgroundThe integration of artificial intelligence (AI) in dermatology is revolutionizing the diagnostic methods and management strategies and hence is uplifting the overall patient care. AI technologies have shown a significant potential in automated diagnosis, severity assessment of chronic cutaneous diseases like psoriasis, and the development of comprehensive dermatological databases is helping in swift disease detection.ObjectiveThis review aims to explore the current landscape and future potential of AI in inflammatory skin diseases. It focuses on various automated diagnostic systems, the role of AI in assessment and staging of chronic inflammatory dermatological conditions, and the importance of dermatological databases. The review also addresses the various challenges associated with AI implementation.MethodsA extensive literature search was conducted from databases namely, PubMed, Google Scholar, and Embase. Search terms included combinations of “artificial intelligence,” “deep learning,” “dermatology,” “automated diagnosis,” and “dermatological databases” from different field of study. Articles were selected and reviewed based on relevance and quality, highlighting studies demonstrating AI's impact on diagnosis and management.ResultsAI‐powered diagnostic systems have ominously advanced, offering noninvasive and accessible diagnostic tool(s) that use extensive datasets to improve accuracy and efficacy across different populations. The development of dermatological databases is fundamental for training of different AI models. Despite these advances, challenges related to data privacy, regulatory oversight, and inclusivity in AI models persist. Addressing these challenges is essential for augmenting and optimizing AI's potential in dermatology.ConclusionAI is set to transmute dermatology by augmenting diagnostic precision, customizing treatment plans, and making dermatological care more reachable, particularly in underprivileged areas. This review highlights the various advances made in AI for the diagnosis and management of inflammatory skin disorders, acknowledging the ethical and technical hurdles that need to be addressed.

show abstract