Novel cellular systems unveil mucosal melanoma initiating cells and a role for PI3K/Akt/mTOR pathway in mucosal melanoma fitness.

BACKGROUND: Mucosal Melanomas (MM) are highly aggressive neoplasms arising from mucosal melanocytes. Current treatments offer a limited survival benefit for patients with advanced MM; moreover, the lack of pre-clinical cellular systems has significantly limited the understanding of their immunobiology. METHODS: Five novel cell lines were obtained from patient-derived biopsies of MM arising in the sino-nasal mucosa and designated as SN-MM1-5. The morphology, ultrastructure and melanocytic identity of SN-MM cell lines were validated by transmission electron microscopy and immunohistochemistry. Moreover, in vivo tumorigenicity of SN-MM1-5 was tested by subcutaneous injection in NOD/SCID mice. Molecular characterization of SN-MM cell lines was performed by a mass-spectrometry proteomic approach, and their sensitivity to PI3K chemical inhibitor LY294002 was validated by Akt activation, measured by pAkt(Ser473) and pAkt(Thr308) in immunoblots, and MTS assay. RESULTS: This study reports the validation and functional characterization of five newly generated SN-MM cell lines. Compared to the normal counterpart, the proteomic profile of SN-MM is consistent with transformed melanocytes showing a heterogeneous degree of melanocytic differentiation and activation of cancer-related pathways. All SN-MM cell lines resulted tumorigenic in vivo and display recurrent structural variants according to aCGH analysis. Of relevance, the microscopic analysis of the corresponding xenotransplants allowed the identification of clusters of MITF-/CDH1-/CDH2 + /ZEB1 + /CD271 + cells, supporting the existence of melanoma-initiating cells also in MM, as confirmed in clinical samples. In vitro, SN-MM cell lines were sensitive to cisplatin, but not to temozolomide. Moreover, the proteomic analysis of SN-MM cell lines revealed that RICTOR, a subunit of mTORC2 complex, is the most significantly activated upstream regulator, suggesting a relevant role for the PI3K-Akt-mTOR pathway in these neoplasms. Consistently, phosphorylation of NDRG1 and Akt activation was observed in SN-MM, the latter being constitutive and sustained by PTEN loss in SN-MM2 and SN-MM3. The cell viability impairment induced by LY294002 confirmed a functional role for the PI3K-Akt-mTOR pathway in SN-MM cell lines. CONCLUSIONS: Overall, these novel and unique cellular systems represent relevant experimental tools for a better understanding of the biology of these neoplasms and, as an extension, to MM from other sites.

Natural Language Processing to extract SNOMED-CT codes from pathological reports.

Objective: The use of standardized structured reports (SSR) and suitable terminologies like SNOMED-CT can enhance data retrieval and analysis, fostering large-scale studies and collaboration. However, the still large prevalence of narrative reports in our laboratories warrants alternative and automated labeling approaches. In this project, natural language processing (NLP) methods were used to associate SNOMED-CT codes to structured and unstructured reports from an Italian Digital Pathology Department. Methods: Two NLP-based automatic coding systems (support vector machine, SVM, and long-short term memory, LSTM) were trained and applied to a series of narrative reports. Results: The 1163 cases were tested with both algorithms, showing good performances in terms of accuracy, precision, recall, and F1 score, with SVM showing slightly better performances as compared to LSTM (0.84, 0.87, 0.83, 0.82 vs 0.83, 0.85, 0.83, 0.82, respectively). The integration of an explainability allowed identification of terms and groups of words of importance, enabling fine-tuning, balancing semantic meaning and model performance. Conclusions: AI tools allow the automatic SNOMED-CT labeling of the pathology archives, providing a retrospective fix to the large lack of organization of narrative reports.

The development of artificial intelligence in the histological diagnosis of Inflammatory Bowel Disease (IBD-AI).

BACKGROUND: Inflammatory bowel disease (IBD) includes Crohn's Disease (CD) and Ulcerative Colitis (UC). Correct diagnosis requires the identification of precise morphological features such basal plasmacytosis. However, histopathological interpretation can be challenging, and it is subject to high variability. AIM: The IBD-Artificial Intelligence (AI) project aims at the development of an AI-based evaluation system to support the diagnosis of IBD, semi-automatically quantifying basal plasmacytosis. METHODS: A deep learning model was trained to detect and quantify plasma cells on a public dataset of 4981 annotated images. The model was then tested on an external validation cohort of 356 intestinal biopsies of CD, UC and healthy controls. AI diagnostic performance was calculated compared to human gold standard. RESULTS: The system correctly found that CD and UC samples had a greater prevalence of basal plasma cells with mean number of PCs within ROIs of 38.22 (95 % CI: 31.73, 49.04) for CD, 55.16 (46.57, 65.93) for UC, and 17.25 (CI: 12.17, 27.05) for controls. Overall, OR=4.968 (CI: 1.835, 14.638) was found for IBD compared to normal mucosa (CD: +59 %; UC: +129 %). Additionally, as expected, UC samples were found to have more plasma cells in colon than CD cases. CONCLUSION: Our model accurately replicated human assessment of basal plasmacytosis, underscoring the value of AI models as a potential aid IBD diagnosis.