Multi-Harmonic Imaging-Based Automated Recognition of Cutaneous T-Cell Lymphoma

Article Article scientifique Article Multi-Harmonic Imaging-Based Automated Recognition of Cutaneous T-Cell Lymphoma eng 2025-09-04 author Ghosh Shayantani Nonlinear Bioimaging Lab, Department of Applied Physics, Université de Genève, Geneva, Switzerland. 937060 Serv com physique appliquée (FIGCO) author Pavlova Olesya Department of Dermatology and Venereology, University Hospital Centre (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland. 595879 author Latshaw Alexandra Lane Nonlinear Bioimaging Lab, Department of Applied Physics, Université de Genève, Geneva, Switzerland. 404426 Serv com physique appliquée (FIGCO) author Kim Doyoung Nonlinear Bioimaging Lab, Department of Applied Physics, Université de Genève, Geneva, Switzerland. 921633 Serv com physique appliquée (FIGCO) author Iselin Christoph Department of Dermatology and Venereology, University Hospital Centre (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland.,Clinical Department of Immunodermatology, Kepler University Hospital, Johannes Kepler University, Linz, Austria. author Bernard Pauline Department of Dermatology and Venereology, University Hospital Centre (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland. author Prompsy Pacome 0000-0003-4375-7583 Department of Dermatology and Venereology, University Hospital Centre (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland.,Clinical Department of Immunodermatology, Kepler University Hospital, Johannes Kepler University, Linz, Austria. author Chang Yun-Tsan Department of Dermatology and Venereology, University Hospital Centre (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland.,Clinical Department of Immunodermatology, Kepler University Hospital, Johannes Kepler University, Linz, Austria. author Staedler Davide Department of Biomedical Sciences, University of Lausanne, 1011 Lausanne, Switzerland. author Tsai Yi-Chien Department of Dermatology and Venereology, University Hospital Centre (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland.,Clinical Department of Immunodermatology, Kepler University Hospital, Johannes Kepler University, Linz, Austria. author Bonacina Luigi 0000-0003-0476-4473 Nonlinear Bioimaging Lab, Department of Applied Physics, Université de Genève, Geneva, Switzerland. 632447 Serv com physique appliquée (FIGCO) author Guenova Emmanuella 0000-0001-5478-8735 Department of Dermatology and Venereology, University Hospital Centre (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland.,Clinical Department of Immunodermatology, Kepler University Hospital, Johannes Kepler University, Linz, Austria.,Clinical Research Institute for Inflammatory Medicine, Kepler University Hospital, Johannes Kepler University, Linz, Austria. ljaf345 10.1093/bjd/ljaf345 40906883 0007-0963 https://academic.oup.com/bjd/advance-article/doi/10.1093/bjd/ljaf345/8248128 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. Dewey 500.2 35 Groupe de physique appliquée 135 false 1414 Groupe Bonacina British journal of dermatology 68579b6c-f96f-47a0-86e0-cb99ec5f848d Article (Accepted version) Public ljaf345.pdf 2057317 application/pdf CC BY-NC-4.0 96ca5abbc7ab3bc806b6355b682df2325abf43fa170432b8c8ca0fe1f3358e26 openAccess Faculté des sciences / Section de physique / Groupe de physique appliquée

Title	Published in	Access level	OA Policy	Year	Views	Downloads

Multi-Harmonic Imaging-Based Automated Recognition of Cutaneous T-Cell Lymphoma	British journal of dermatology			2025	64	45

Archive ouverte UNIGE

Pavlova, Olesya