Advancements in Diagnosis of Neoplastic and Inflammatory Skin Diseases: Old and Emerging Approaches

Abstract

Background: In recent decades, dermatological diagnostics have undergone a profound transformation, driven by the integration of new technologies alongside traditional methods. Classic techniques such as the Tzanck smear, potassium hydroxide (KOH) preparation, and Wood's lamp examination remain fundamental in everyday clinical practice due to their simplicity, speed, and accessibility. At the same time, the development of non-invasive imaging technologies and the application of artificial intelligence (AI) have opened new frontiers in the early detection and monitoring of both neoplastic and inflammatory skin diseases. Methods: This review aims to provide a comprehensive overview of how conventional and emerging diagnostic tools can be integrated into dermatologic practice. Results: We examined a broad spectrum of diagnostic methods currently used in dermatology, ranging from traditional techniques to advanced approaches such as digital dermoscopy, reflectance confocal microscopy (RCM), optical coherence tomography (OCT), line-field confocal OCT (LC-OCT), 3D total body imaging systems with AI integration, mobile applications, electrical impedance spectroscopy (EIS), and multispectral imaging. Each method is discussed in terms of diagnostic accuracy, clinical applications, and potential limitations. While traditional methods continue to play a crucial role-especially in resource-limited settings or for immediate bedside decision-making-modern tools significantly enhance diagnostic precision. Dermoscopy and its digital evolution have improved the accuracy of melanoma and basal cell carcinoma detection. RCM and LC-OCT allow near-histological visualization of skin structures, reducing the need for invasive procedures. AI-powered platforms support lesion tracking and risk stratification, though their routine implementation requires further clinical validation and regulatory oversight. Tools like EIS and multispectral imaging may offer additional value in diagnostically challenging cases. An effective diagnostic approach in dermatology should rely on a thoughtful combination of methods, selected based on clinical suspicion and guided by Bayesian reasoning. Conclusions: Rather than replacing traditional tools, advanced technologies should complement them-optimizing diagnostic accuracy, improving patient outcomes, and supporting more individualized, evidence-based care.

Keywords: artificial intelligence; confocal microscopy; dermatologic diagnosis; dermoscopy; digital health; inflammatory skin diseases; line-field OCT; skin cancer.

Figure 1

An example of preparation with KOH for the detection of filamentous fungi.

Figure 2

Microscopic examination with potassium hydroxide (KOH) preparation for the detection of eggs of Sarcoptes scabiei.

Figure 3

Erythrasma under Wood’s light.

Figure 4

Left: Atypical melanocytic nevus visualized with 20× dermoscopy using the Medicam 1000s camera and D-Scope IV lens (Fotofinder System). An atypical pigment network with some globules is observed. Right: With optical super high magnification dermoscopy (OSHMD) using the D-Scope III lens and the same camera (Fotofinder System, Bad Birnbach, Germany), the pigment network appears as in-focus brown rings composed of small round or polygonal brown structures surrounding dermal papillae; within the papillae, small capillary loops can be seen (black arrows).

Figure 5

Reflectance confocal microscopy images of a lentigo maligna. Elongated nest of a lentigo maligna with folliculotrophophic hyper-reflective atypical cells forming a “caput medusae” structure (A). Atypical diffuse hyperreflective melanoma cells forming elongated nests and invading the dermo-epidermal junction, which appears blurred and disrupted due to the downward migration of hyper-reflective atypical cells into the dermis, leading to a non-edged papillae pattern (B). (field of view of 500 × 500 μm).

Figure 6

LC-OCT: Superficial basal cells carcinoma under line-field confocal optical coherence tomography. In the left image a superficial basal cells carcinoma is seen with a millefouille pattern and clefting at the periphery (A). In the right image the same BCC is shown with the artificial intelligence assistant BCC prediction scoring a 100% probability of BCC (B).

Figure 7

Vectra WB360 (Canfield Scientific): automated 3D full-body imaging system integrating synchronized cameras and linked dermoscopy modules for contactless skin surface acquisition and longitudinal lesion monitoring.

Figure 8

AI-assisted dermoscopic follow-up using the D200 system (Canfield Scientific) with integration of the DEXI cognitive assistant. Automated risk scores, morphometric parameters (asymmetry, border, color, and diameter), and lesion similarity matching from reference databases are displayed. This tool complements clinical visual assessment, supporting diagnostic prioritization in high-risk settings.

Figure 9

iToBoS prototype: European Horizon 2020 Intelligent Total Body Scanner platform integrating multiple high-resolution 2D cameras with liquid lenses, multispectral illumination, and AI-based data fusion to reconstruct 3D anatomical models for melanoma risk assessment.

Figure 10

Non-contact dermoscopic image acquired with the iToBoS system. A melanocytic lesion is observed, showing an atypical pigment network and irregularly contoured areas of hyperpigmentation. The system uses liquid lenses and super-resolution algorithms to optimize morphological detail without requiring direct skin contact.

Figure 11

Graphical interface of the iToBoS system showing lesion prioritization through artificial intelligence. The platform integrates 2D body images with automated analysis, including risk scores, malignancy probability, morphological changes, and dermoscopic structure classification. It enables longitudinal follow-up and generates individualized risk assessments to support clinical decision-making.

Figure 12

Impact of diagnostic test accuracy and pre-test probability on post-test outcomes in dermatology. This composite image illustrates how diagnostic test performance influences post-test probability across different levels of pre-test probability, according to Bayes’ theorem. The three panels represent tests with increasing accuracy: sensitivity and specificity of 60%, 75%, and 90%. The dashed diagonal line marks the identity line, where the post-test probability equals the pre-test probability, indicating that the test result does not alter diagnostic confidence. The blue and orange curves depict the post-test probability when the test results are positive and negative, respectively. Superimposed on each curve are three points, represented by blue Xs on the positive-result curve and orange Xs on the negative-result curve, corresponding to pre-test probabilities of 3%, 50%, and 97%. These illustrate how the diagnostic yield of a test varies across different clinical contexts. When test accuracy is low, or when the pre-test probability is extremely low or high, the result has little impact on decision-making. In contrast, high-performance tests applied in settings of diagnostic uncertainty (pre-test probability around 30–50%) significantly shift the post-test probability, thereby enhancing diagnostic precision and clinical utility.