Abstract Background Cutaneous T-cell lymphomas (CTCL) are a heterogeneous group of non-Hodgkin lymphomas, with mycosis fungoides (MF) being the most common type, accounting for approximately 60% of all lymphomas arising primarily in the skin. The diagnosis of MF is challenging, especially in its early stages when the number of atypical T-lymphocytes is small, and clinical and histopathologic changes are often nonspecific. This leads to significant delays of three to five years in diagnosis and treatment. Thus, novel diagnostic methods are needed to adjust the diagnostic and therapeutic strategies of CTCL. Nonlinear optical microscopy (NLOM) is promising for its sensitivity to specific tissue structures through harmonic generation and its ability to image in three dimensions. Objectives To image haematoxylin & eosin (H&E) stained skin samples with NLOM and detect atypical epidermotropism and dermal cells in MF skin samples using an artificial intelligence (AI) model. Methods We utilise both brightfield microscopy and NLOM to analyse H&E-stained biopsy samples from MF skin lesions. Expert clinicians label the images, which are used to train a convolutional neural network (CNN) to recognise skin lymphocytes. The model is applied to independent testing datasets obtained from both imaging modalities to assess its performance in detecting characteristic features of skin T-lymphocytes. Additionally, NLOM is performed on fresh, unstained biopsy samples to highlight its potential for in vivo skin imaging. Results NLOM successfully images epidermal and dermal structures in H&E-stained MF tissue sections with sub-cellular resolution. The trained AI model detects lymphocyte epidermotropism and dermal infiltration in the images. Moreover, NLOM imaged fresh, unstained biopsies up to 400 µm deep through the epidermis to the dermis. Conclusions This study demonstrates that NLOM, combined with AI, can detect lymphocyte epidermotropism and dermal infiltration in MF H&E-stained skin tissue. This approach offers dermatologists a powerful tool to improve the diagnosis and prognosis of MF-CTCL, paving the way for more timely and precise therapeutic strategies.
Ghosh et al. (Thu,) studied this question.