Multiharmonic imaging-based automated recognition of cutaneous T-cell lymphoma
Bibliographic record
Abstract
BACKGROUND: Cutaneous T-cell lymphomas (CTCLs) 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. Diagnosis of MF is challenging, especially in its early stages when the number of atypical T lymphocytes is small, and clinical and histopathological changes are often nonspecific. This leads to significant delays of 3-5 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 and eosin-stained skin samples with NLOM and detect atypical epidermotropism and dermal cells in MF skin samples using an artificial intelligence (AI) model. METHODS: We used brightfield microscopy and NLOM to analyse haematoxylin and eosin-stained biopsy samples from MF skin lesions. Expert clinicians labelled the images, which were used to train a convolutional neural network to recognize skin lymphocytes. The model was applied to independent testing datasets obtained from both imaging modalities to assess its performance in detecting characteristic features of skin T lymphocytes. Additionally, NLOM was performed on fresh, unstained biopsy samples to highlight its potential for in vivo skin imaging. RESULTS: NLOM successfully imaged epidermal and dermal structures in haematoxylin and eosin-stained MF tissue sections with subcellular resolution. The trained AI model detected 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: We demonstrate that NLOM, combined with AI, can detect lymphocyte epidermotropism and dermal infiltration in haematoxylin and eosin-stained MF skin tissue. This approach offers dermatologists a powerful tool to improve the diagnosis and prognosis of MF, paving the way for more timely and precise therapeutic strategies. An author video to accompany this article is available online.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".