Non-invasive scoring of cellular atypia in keratinocyte cancers in 3D LC-OCT images using Deep Learning

Diagnosis based on histopathology for skin cancer detection is today’s gold standard and relies on the presence or absence of biomarkers and cellular atypia. However it suffers drawbacks: it requires a strong expertise and is time-consuming. Moreover the notion of atypia or dysplasia of the visible cells used for diagnosis is very subjective, with poor inter-rater agreement reported in the literature. Lastly, histology requires a biopsy which is an invasive procedure and only captures a small sample of the lesion, which is insufficient in the context of large fields of cancerization. Here we demonstrate that the notion of cellular atypia can be objectively defined and quantified with a non-invasive in-vivo approach in three dimensions (3D). A Deep Learning (DL) algorithm is trained to segment keratinocyte (KC) nuclei from Line-field Confocal Optical Coherence Tomography (LC-OCT) 3D images. Based on these segmentations, a series of quantitative, reproducible and biologically relevant metrics is derived to describe KC nuclei individually. We show that, using those metrics, simple and more complex definitions of atypia can be derived to discriminate between healthy and pathological skins, achieving Area Under the ROC Curve (AUC) scores superior than 0.965, largely outperforming medical experts on the same task with an AUC of 0.766. All together, our approach and findings open the door to a precise quantitative monitoring of skin lesions and treatments, offering a promising non-invasive tool for clinical studies to demonstrate the effects of a treatment and for clinicians to assess the severity of a lesion and follow the evolution of pre-cancerous lesions over time.

Spectrally Extended Line Field Optical Coherence Tomography Angiography

The widespread usage of optical coherence tomography angiography (OCTA) is hindered by technical gaps including limited field of view (FOV), lack of quantitative flow information, and suboptimal motion correction. We introduce spectrally extended line field (SELF) OCTA that provides advanced solutions to these challenges. SELF-OCTA breaks the speed limitation and achieves two-fold gain in FOV without sacrificing microvascular details and signal strength through parallel imaging. It also relieves the requirement for shorter exposure time in wide-field applications, so that sufficient sensitivity to slow flow is maintained, particularly in spectral-domain OCT. Towards quantitative angiography, the ‘frequency flow’ mechanism overcomes the speed bottleneck by obviating the requirement for superfluous B-scans. In addition, this mechanism facilitates OCTA-data based motion tracking. Since it can be implemented in existing OCT devices without significant hardware modification or affecting existing functions, SELF-OCTA will make non-invasive, wide-field, quantitative, and low-cost angiographic imaging available to larger patient populations.

Line-Field Confocal Optical Coherence Tomography May Enhance Monitoring of Superficial Basal Cell Carcinoma Treated with Imiquimod 5% Cream: A Pilot Study

Line-field confocal optical coherence tomography (LC-OCT) is a novel, non-invasive technique for real-time skin imaging. Imiquimod (IQ) 5% cream is an immune response modifier currently approved for the treatment of small, superficial basal cell carcinoma (BCC). The aim of this study was to investigate if LC-OCT may be useful to enhance the treatment monitoring of BCC. Twenty superficial BCCs from 12 patients were treated with IQ 5% cream once daily, five days a week, for six weeks. Clinical and LC-OCT evaluations were performed at baseline and 4 weeks after the end of treatment. At the end of the study, 13 lesions showed a complete clinical and LC-OCT response, 4 lesions a partial clinical and LC-OCT response, and 3 lesions a complete clinical response but residual tumoral signs at LC-OCT. Our pilot study suggests that LC-OCT may represent a promising tool able to enhance the evaluation of the treatment response of BCCs to non-invasive treatments. In our case series, its use highlighted, through a detailed, fast, and complete examination of the treated area, three cases of residual BCC that otherwise would have gone undetected at clinical examination. Future studies on larger series of patients treated with different modalities and with a longer follow-up are advisable.