Artificial intelligence-based PRO score assessment in actinic keratoses from LC-OCT imaging using Convolutional Neural Networks.

BACKGROUND AND OBJECTIVES: The histological PRO score (I-III) helps to assess the malignant potential of actinic keratoses (AK) by grading the dermal-epidermal junction (DEJ) undulation. Line-field confocal optical coherence tomography (LC-OCT) provides non-invasive real-time PRO score quantification. From LC-OCT imaging data, training of an artificial intelligence (AI), using Convolutional Neural Networks (CNNs) for automated PRO score quantification of AK in vivo may be achieved. PATIENTS AND METHODS: CNNs were trained to segment LC-OCT images of healthy skin and AK. PRO score models were developed in accordance with the histopathological gold standard and trained on a subset of 237 LC-OCT AK images and tested on 76 images, comparing AI-computed PRO score to the imaging experts' visual consensus. RESULTS: Significant agreement was found in 57/76 (75%) cases. AI-automated grading correlated best with the visual score for PRO II (84.8%) vs. PRO III (69.2%) vs. PRO I (66.6%). Misinterpretation occurred in 25% of the cases mostly due to shadowing of the DEJ and disruptive features such as hair follicles. CONCLUSIONS: The findings suggest that CNNs are helpful for automated PRO score quantification in LC-OCT images. This may provide the clinician with a feasible tool for PRO score assessment in the follow-up of AK.

Assessing microbial plastic degradation requires robust methods.

Plastics are versatile materials that have the potential to propel humanity towards circularity and ultimate societal sustainability. However, the escalating concern surrounding plastic pollution has garnered significant attention, leading to widespread negative perceptions of these materials. Here, we question the role microbes may play in plastic pollution bioremediation by (i) defining polymer biodegradability (i.e., recalcitrant, hydrolysable and biodegradable polymers) and (ii) reviewing best practices for evaluating microbial biodegradation of plastics. We establish recommendations to facilitate the implementation of rigorous methodologies in future studies on plastic biodegradation, aiming to push this field towards the use of isotopic labelling to confirm plastic biodegradation and further determine the molecular mechanisms involved.

Line-field confocal optical coherence tomography coupled with artificial intelligence algorithms to identify quantitative biomarkers of facial skin ageing.

Quantitative biomarkers of facial skin ageing were studied from one hundred healthy Caucasian female volunteers, aged 20-70 years, using in vivo 3D Line-field Confocal Optical Coherence Tomography (LC-OCT) imaging coupled with Artificial Intelligence (AI)-based quantification algorithms. Layer metrics, i.e. stratum corneum thickness (SC), viable epidermal thickness and Dermal-Epidermal Junction (DEJ) undulation, as well as cellular metrics were measured for the temple, cheekbone and mandible. For all three investigated facial areas, minimal age-related variations were observed in the thickness of the SC and viable epidermis layers. A flatter and more homogeneous epidermis (decrease in the standard deviation of the number of layers means), a less dense cellular network with fewer cells per layer (decrease in cell surface density), and larger and more heterogeneous nuclei within each layer (increase in nuclei volume and their standard deviation) were found with significant variations with age. The higher atypia scores further reflected the heterogeneity of nuclei throughout the viable epidermis. The 3D visualisation of fine structures in the skin at the micrometric resolution and the 1200 µm × 500 µm field of view achieved with LC-OCT imaging enabled to compute relevant quantitative biomarkers for a better understanding of skin biology and the ageing process in vivo.

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.

A mechanistic understanding of polyethylene biodegradation by the marine bacterium Alcanivorax.

Polyethylene (PE) is one of the most recalcitrant carbon-based synthetic materials produced and, currently, the most ubiquitous plastic pollutant found in nature. Over time, combined abiotic and biotic processes are thought to eventually breakdown PE. Despite limited evidence of biological PE degradation and speculation that hydrocarbon-degrading bacteria found within the plastisphere is an indication of biodegradation, there is no clear mechanistic understanding of the process. Here, using high-throughput proteomics, we investigated the molecular processes that take place in the hydrocarbon-degrading marine bacterium Alcanivorax sp. 24 when grown in the presence of low density PE (LDPE). As well as efficiently utilising and assimilating the leachate of weathered LDPE, the bacterium was able to reduce the molecular weight distribution (Mw from 122 to 83 kg/mol) and overall mass of pristine LDPE films (0.9 % after 34 days of incubation). Most interestingly, Alcanivorax acquired the isotopic signature of the pristine plastic and induced an extensive array of metabolic pathways for aliphatic compound degradation. Presumably, the primary biodegradation of LDPE by Alcanivorax sp. 24 is possible via the production of extracellular reactive oxygen species as observed both by the material's surface oxidation and the measurement of superoxide in the culture with LDPE. Our findings confirm that hydrocarbon-biodegrading bacteria within the plastisphere may in fact have a role in degrading PE.