Evaluation of two histological classifications for actinic keratoses - PRO classification scored highest inter-rater reliability

Interdisciplinary management of skin cancer

The interdisciplinary treatment of skin cancer in the head and neck area requires close collaboration between different specialist disciplines. The most common non-melanoma skin cancer tumor entities are cutaneous squamous cell carcinoma and basal cell carcinoma as well as their precursor lesions. One of the less common tumors is Merkel cell carcinoma, which also occurs primarily in light-exposed areas and, in contrast to squamous and basal cell carcinoma, is more likely to metastasize. Due to the low tendency of basal cell carcinoma as well as cutaneous squamous cell carcinoma to metastasize, a cure can often be achieved by surgery. If the tumor growth exceeds certain levels it may require collaboration between dermatology and otorhinolaryngology. The primary goal of this interdisciplinary collaboration is to achieve a functional, cosmetically and aesthetically acceptable result in addition to adequate tumor treatment. Depending on the stage of the tumor and the clinical course, a case may be discussed in an interdisciplinary tumor board in order to determine a personalised, appropriate and adequate treatment concept for each patient, including prevention, therapy and follow-up.

An overview of cutaneous squamous cell carcinoma imaging diagnosis methods

Cutaneous squamous cell carcinoma, a type of non-melanoma skin cancer, is a form of keratinocyte carcinoma that stands as one of the most prevalent cancers, exhibiting a rising frequency. This review provides an overview of the latest literature on imaging methods for diagnosing squamous cell carcinoma (SCC) and actinic keratosis (AK). It discusses the diagnostic criteria, advantages, and disadvantages of various techniques such as dermatoscopy, skin ultrasound (US), in vivo and ex-vivo reflectance confocal microscopy (RCM), and line-field confocal optical coherence tomography (LC-OCT). These methods offer benefits including non-invasiveness, rapidity, comprehensive lesion imaging, and enhanced sensitivity, but face challenges like high costs and the need for specialized expertise. Despite obstacles, the use of these innovative techniques is expected to increase with ongoing technological advancements, improving diagnosis and treatment planning for keratinocyte carcinomas. Standardizing LC-OCT imaging algorithms for AK, Bowen's disease, and SCC remains an area for further research.

KI-basierte Bestimmung des PRO-Scores in aktinischen Keratosen anhand von LC-OCT-Bilddatensätzen: Artificial intelligence-based PRO score assessment in actinic keratoses from LC-OCT imaging using Convolutional Neural Networks

Hintergrund

Mit Hilfe des histologischen PRO‐Scores (I–III) kann das Risiko einer malignen Transformation aktinischer Keratosen (AK) abgeschätzt werden, indem er das Ausmaß der Undulation und basalen Proliferation der dermoepidermalen Junktionszone (DEJ) bewertet. Die konfokale Line‐Field optische Kohärenztomographie (LC‐OCT) ermöglicht eine nichtinvasive Bestimmung des PRO‐Scores in Echtzeit. Anhand von LC‐OCT‐Bilddatensätzen kann eine künstliche Intelligenz (KI) mit Hilfe von Convolutional Neural Networks (CNN) zur automatischen Quantifizierung des PRO‐Scores von AK in vivo trainiert werden.

Patienten und Methodik

Convolutional Neural Networks wurden trainiert, um LC‐OCT‐Bilder von gesunder Haut und von AK zu segmentieren. PRO‐Score‐Modelle wurden in Übereinstimmung mit dem histopathologischen Goldstandard entwickelt und an einer Teilmenge von 237 LC‐OCT‐AK‐Bildern trainiert und an 76 Bildern getestet, wobei der von der KI‐berechnete PRO‐Score mit dem visuellen Konsens der Bildgebungsexperten verglichen wurde.

Ergebnisse

Eine signifikante Übereinstimmung wurde in 57/76 (75%) Fällen festgestellt. Die KI‐basierte Bewertung des PRO‐Scores korrelierte am besten mit dem visuellen Score für PRO II (84,8%) vs. PRO III (69,2%) vs. PRO I (66,6%). In 25% der Fälle kam es zu Fehlinterpretationen, die meist auf eine Verschattung der DEJ sowie störende Merkmale wie Haarfollikel zurückzuführen waren.

Schlussfolgerungen

Die Ergebnisse deuten darauf hin, dass CNN für die automatische Quantifizierung des PRO‐Scores in LC‐OCT‐Bilddatensätzen hilfreich sind. Dies könnte zur nichtinvasiven Bewertung des Proliferationsrisikos in der Diagnostik und Nachsorge von AK herangezogen werden.

Artificial intelligence-based PRO score assessment in actinic keratoses from LC-OCT imaging using Convolutional Neural Networks

BACKGROUND AND OBJECTIVES

The histological PRO score (I-III) helps to assess the malignant potential of actinic keratoses (AK) by grading the dermal-epidermal junction (DEJ) undulation. Line-field confocal optical coherence tomography (LC-OCT) provides non-invasive real-time PRO score quantification. From LC-OCT imaging data, training of an artificial intelligence (AI), using Convolutional Neural Networks (CNNs) for automated PRO score quantification of AK in vivo may be achieved.

PATIENTS AND METHODS

CNNs were trained to segment LC-OCT images of healthy skin and AK. PRO score models were developed in accordance with the histopathological gold standard and trained on a subset of 237 LC-OCT AK images and tested on 76 images, comparing AI-computed PRO score to the imaging experts' visual consensus.

RESULTS

Significant agreement was found in 57/76 (75%) cases. AI-automated grading correlated best with the visual score for PRO II (84.8%) vs. PRO III (69.2%) vs. PRO I (66.6%). Misinterpretation occurred in 25% of the cases mostly due to shadowing of the DEJ and disruptive features such as hair follicles.

CONCLUSIONS

The findings suggest that CNNs are helpful for automated PRO score quantification in LC-OCT images. This may provide the clinician with a feasible tool for PRO score assessment in the follow-up of AK.

The Promise of Semantic Segmentation in Detecting Actinic Keratosis Using Clinical Photography in the Wild

AK is a common precancerous skin condition that requires effective detection and treatment monitoring. To improve the monitoring of the AK burden in clinical settings with enhanced automation and precision, the present study evaluates the application of semantic segmentation based on the U-Net architecture (i.e., AKU-Net). AKU-Net employs transfer learning to compensate for the relatively small dataset of annotated images and integrates a recurrent process based on convLSTM to exploit contextual information and address the challenges related to the low contrast and ambiguous boundaries of AK-affected skin regions. We used an annotated dataset of 569 clinical photographs from 115 patients with actinic keratosis to train and evaluate the model. From each photograph, patches of 512 × 512 pixels were extracted using translation lesion boxes that encompassed lesions in different positions and captured different contexts of perilesional skin. In total, 16,488 translation-augmented crops were used for training the model, and 403 lesion center crops were used for testing. To demonstrate the improvements in AK detection, AKU-Net was compared with plain U-Net and U-Net++ architectures. The experimental results highlighted the effectiveness of AKU-Net, improving upon both automation and precision over existing approaches, paving the way for more effective and reliable evaluation of actinic keratosis in clinical settings.

Innovation in Actinic Keratosis Assessment: Artificial Intelligence-Based Approach to LC-OCT PRO Score Evaluation

Actinic keratosis (AK) is a common skin cancer in situ that can progress to invasive SCC. Line-field confocal optical coherence tomography (LC-OCT) has emerged as a non-invasive imaging technique that can aid in diagnosis. Recently, machine-learning algorithms have been developed that can automatically assess the PRO score of AKs based on the dermo-epidermal junction's (DEJ's) protrusion on LC-OCT images. A dataset of 19.898 LC-OCT images from 80 histologically confirmed AK lesions was used to test the performance of a previous validated artificial intelligence (AI)-based LC-OCT assessment algorithm. AI-based PRO score assessment was compared to the imaging experts' visual score. Additionally, undulation of the DEJ, the number of protrusions detected within the image, and the maximum depth of the protrusions were computed. Our results show that AI-automated PRO grading is highly comparable to the visual score, with an agreement of 71.3% for the lesions evaluated. Furthermore, this AI-based assessment was significantly faster than the regular visual PRO score assessment. The results confirm our previous findings of the pilot study in a larger cohort that the AI-based grading of LC-OCT images is a reliable and fast tool to optimize the efficiency of visual PRO score grading. This technology has the potential to improve the accuracy and speed of AK diagnosis and may lead to better clinical outcomes for patients.

In Vivo Reflectance Confocal Microscopy as a Response Monitoring Tool for Actinic Keratoses Undergoing Cryotherapy and Photodynamic Therapy

Simple Summary

The assessment of actinic keratoses (AKs) in prevention and therapeutic trials, as well as clinical practice, could significantly benefit from the incorporation of non-invasive imaging technology. Such technology has the potential to enhance the objective evaluation of clinical and subclinical AKs with the added advantage of sequential monitoring. In vivo reflectance confocal microscopy (RCM) allows for the non-invasive imaging of AKs at a cellular level. We aimed to establish an in in vivo RCM protocol for AK response monitoring, ultimately leading to more reliable characterization of longitudinal responses and therapy optimization.

Abstract

Reflectance confocal microscopy (RCM) presents a non-invasive method to image actinic keratosis (AK) at a cellular level. However, RCM criteria for AK response monitoring vary across studies and a universal, standardized approach is lacking. We aimed to identify reliable AK response criteria and to compare the clinical and RCM evaluation of responses across AK severity grades. Twenty patients were included and randomized to receive either cryotherapy (n = 10) or PDT (n = 10). Clinical assessment and RCM evaluation of 12 criteria were performed in AK lesions and photodamaged skin at baseline, 3 and 6 months. We identified the RCM criteria that reliably characterize AK at baseline and display significant reduction following treatment. Those with the highest baseline odds ratio (OR), good interobserver agreement, and most significant change over time were atypical honeycomb pattern (OR: 12.7, CI: 5.7–28.1), hyperkeratosis (OR: 13.6, CI: 5.3–34.9), stratum corneum disruption (OR: 7.8, CI: 3.5–17.3), and disarranged epidermal pattern (OR: 6.5, CI: 2.9–14.8). Clinical evaluation demonstrated a significant treatment response without relapse. However, in grade 2 AK, 10/12 RCM parameters increased from 3 to 6 months, which suggested early subclinical recurrence detection by RCM. Incorporating standardized RCM protocols for the assessment of AK may enable a more meaningful comparison across clinical trials, while allowing for the early detection of relapses and evaluation of biological responses to therapy over time.

Guidelines of care for the management of actinic keratosis

BACKGROUND

Actinic keratoses (AK) are rough scaly patches that arise on chronically ultraviolet-exposed skin and can progress to keratinocyte carcinoma.

OBJECTIVE

This analysis examined the literature related to the management of AK to provide evidence-based recommendations for treatment. Grading, histologic classification, natural history, risk of progression, and dermatologic surveillance of AKs are also discussed.

METHODS

A multidisciplinary Work Group conducted a systematic review to address 5 clinical questions on the management of AKs and applied the Grading of Recommendations, Assessment, Development, and Evaluation approach for assessing the certainty of the evidence and formulating and grading clinical recommendations. Graded recommendations were voted on to achieve consensus.

RESULTS

Analysis of the evidence resulted in 18 recommendations.

LIMITATIONS

This analysis is based on the best available evidence at the time it was conducted. The pragmatic decision to limit the literature review to English language randomized trials may have excluded data published in other languages or limited identification of relevant long-term follow-up data.

CONCLUSIONS

Strong recommendations are made for using ultraviolet protection, topical imiquimod, topical 5-fluorouracil, and cryosurgery. Conditional recommendations are made for the use of photodynamic therapy and diclofenac for the treatment of AK, both individually and as part of combination therapy regimens.

Line-field confocal optical coherence tomography for the in vivo real-time diagnosis of different stages of keratinocyte skin cancer: a preliminary study

BACKGROUND

The treatment of keratinocyte cancers (KC) strictly depends on their differentiation and invasiveness. Non-invasive diagnostic techniques can support the diagnosis in real time, avoiding unnecessary biopsies. This study aimed to preliminarily define main imaging criteria and histological correlations of actinic keratosis (AK), Bowen's disease (BD) and squamous cell carcinoma (SCC) using the novel device line-field confocal optical coherence tomography (LC-OCT).

METHODS

Dermoscopy and LC-OCT images of 73 histopathologically confirmed lesions (46 AKs, 11 BD and 16 SCCs) were included in the study. Exemplary lesions (10 AKs, 5 BD and 5 SCCs) were additionally investigated with optical coherence tomography and reflectance confocal microscopy.

RESULTS

Most common LC-OCT findings of KC in the descriptive statistics were hyperkeratosis/parakeratosis, disruption of stratum corneum, broadened epidermis, basal and suprabasal keratinocyte atypia, dilated vessels/neoangiogenesis and elastosis/collagen alterations. In the univariate multinomial logistic regression, a preserved DEJ was less common in SCC compared with AK and BD, BD displayed marked keratinocyte atypia involving all epidermal layers (bowenoid pattern), while SCC showed ulceration, increased epidermal thickness, keratin plugs, acantholysis, not visible/interrupted DEJ and epidermal bright particles. LC-OCT increased the diagnostic confidence by 24.7% compared with dermoscopy alone.

CONCLUSIONS

Our study describes for the first time specific LC-OCT features of different stages of KC and their histopathological correlates, focusing on keratinocyte morphology and architecture of the epidermis and DEJ. LC-OCT may open new scenarios in the bedside diagnosis, treatment planning and follow-up of KC.

In-Vivo LC-OCT Evaluation of the Downward Proliferation Pattern of Keratinocytes in Actinic Keratosis in Comparison with Histology: First Impressions from a Pilot Study

It is known that actinic keratoses (AKs) can progress to invasive squamous cell carcinoma (SCC). The histological PRO grading of AKs is based on the growth pattern of basal keratinocytes and relates to their progression risk. AKs can be non-invasively characterized by line-field confocal optical coherence tomography (LC-OCT). The aim of the study was to define criteria for an LC-OCT grading of AKs based on the PRO classification and to correlate it with its histological counterpart. To evaluate the interobserver agreement for the LC-OCT PRO classification, fifty AKs were imaged by LC-OCT and biopsied for histopathology. PRO histological grading was assessed by an expert consensus, while two evaluator groups separately performed LC-OCT grading on vertical sections. The agreement between LC-OCT and histological PRO grading was 75% for all lesions (weighted kappa 0.66, 95% CI 0.48-0.83, p ≤ 0.001) and 85.4% when comparing the subgroups PRO I vs. PRO II/III (weighted kappa 0.64, 95% CI 0.40-0.88, p ≤ 0.001). The interobserver agreement for LC-OCT was 90% (Cohen's kappa 0.84, 95% CI 0.71-0.91, p ≤ 0.001). In this pilot study, we demonstrated that LC-OCT is potentially able to classify AKs based on the basal growth pattern of keratinocytes, in-vivo reproducing the PRO classification, with strong interobserver agreement and a good correlation with histopathology.

Histological classification of cutaneous squamous cell carcinomas with different severity

Cutaneous squamous cell carcinoma (cSCC) is the second most common non-melanoma skin cancer. Histology represents the gold standard to confirm the diagnosis of cSCC and is mandatory to determine important findings for tumour grading, such as tumour thickness, depth of invasion, degree of differentiation and histological subtype, perineural and vascular invasion, and assessing tumour margins. In daily clinical practice, the combination of clinical and histological features should be considered when grading the tumours and treating the patients, accordingly. This article aims to provide a structured overview of the most common histological findings of in situ and invasive cSCCs, namely those relevant to their severity, and should facilitate the understanding and evaluation of these results.