In their research paper published in the International Journal of Dermatology, Michelini et al. 1 aim to determine whether skin hydration could improve visibility of the dermal–epidermal junction (DEJ) in line-field confocal optical coherence tomography (LC-OCT) images of hyperkeratotic actinic keratosis (AK). The DEJ is the most important morphological marker for differentiating premalignant from invasive malignant lesions. In addition, the study assessed the PRO-score of the same lesions, a histopathological measure of dermal invasion. Hyperkeratotic AK lesions (i.e., Olsen Grades 2 and 3) were randomly assigned to receive either 20 min of tap water occlusion (n = 30) or 20% salicylic acid ointment (n = 30). Two blinded evaluators reached consensus on the visibility of the DEJ and the PRO grade of the included lesions, both before and after skin hydration. Interestingly, the authors observed a significant improvement in DEJ visibility after skin hydration, from 39.0% to 86.4% compared with baseline without hydration (p = 0.015). No notable difference was seen between tap water occlusion and salicylic acid ointment. Moreover, in 9 of 23 AKs with visible DEJ, PRO grade assessments changed after skin hydration, indicating that the outlined methods provided a platform for more accurate PRO grading. Consequently, this study is the first to describe preparatory conditions that may improve LC-OCT visibility of the DEJ and PRO grading in hyperkeratotic AKs. Perspectives beyond improving the visibility of the DEJ in hyperkeratotic AK include enhancing its detection in LC-OCT images of skin cancers, where interobserver agreement is reportedly low but necessary for accurate assessment of invasiveness 2. Specifically, improved DEJ assessment with LC-OCT could help more accurately classify in vivo carcinomas such as Bowen's disease from invasive SCCs. However, this is mostly speculative, and real-world clinical data are needed. Future work may include highlighting the DEJ and performing PRO grading of AKs with LC-OCT utilizing artificial intelligence (AI) 3. Deep learning-based AI algorithms have already been developed for skin layer segmentation of static LC-OCT images in AK (Figure 1). Looking ahead, the potential combination of LC-OCT with AI for assessing the DEJ of AKs in vivo could become a crucial part of clinical consultations if it offers both physicians and patients a comprehensive diagnosis and a severity assessment. A recent study presents a feasible ‘one-stop-shop’ workflow for margin mapping of skin cancers, such as basal cell carcinoma, using LC-OCT with AI 5, demonstrating the rapid advancements in noninvasive dermatology imaging. The question remains: can a similar workflow be developed for hyperkeratotic AKs and SCC? In conclusion, delineating the DEJ with LC-OCT in hyperkeratotic AKs and skin cancers can be challenging, emphasizing the need for approaches that improve its visibility. Michelini et al. proposed pre-hydrating hyperkeratotic AK lesions prior to LC-OCT scans, a promising strategy that could be applicable to skin cancer lesions, thereby fostering increased collaboration within the LC-OCT community. The authors are affiliated with the Danish Research Center for Skin Cancer, a public-private research partnership between Private Hospital Mølholm, Aalborg University Hospital, and Copenhagen University Hospital Bispebjerg. The authors would like to thank Clara Tavernier (DAMAE Medical, Paris, France) for her help with image editing. The authors have nothing to report. The authors declare no conflicts of interest. This article is linked to Michelini et al. paper. To view this article, visit https://doi.org/10.1111/ijd.70328. The data that support the findings of this study are available on request from the corresponding author. The data are not publicly available due to privacy or ethical restrictions.
Jacobsen et al. (Wed,) studied this question.