Examinando por Autor "Marchant, Ivanny"

Mostrando 1 - 3 de 3
  • No hay miniatura disponible
    Ítem
    HER2 classification in breast cancer cells: A new explainable machine learning application for immunohistochemistry
    (Spandidos Publications, 2023-02) Cordova, Claudio; Muñoz, Roberto; Olivares, Rodrigo; Minonzio, Jean-Gabriel; Lozano, Carlo; Gonzalez, Paulina; Marchant, Ivanny; González-Arriagada, Wilfredo; Olivero, Pablo
    The immunohistochemical (IHC) evaluation of epidermal growth factor 2 (HER2) for the diagnosis of breast cancer is still qualitative with a high degree of inter-observer variability, and thus requires the incorporation of complementary techniques such as fluorescent in situ hybridization (FISH) to resolve the diagnosis. Implementing automatic algorithms to classify IHC biomarkers is crucial for typifying the tumor and deciding on therapy for each patient with better performance. The present study aims to demonstrate that, using an explainable Machine Learning (ML) model for the classification of HER2 photomicrographs, it is possible to determine criteria to improve the value of IHC analysis. We trained a logistic regression-based supervised ML model with 393 IHC microscopy images from 131 patients, to discriminate between upregulated and normal expression of the HER2 protein. Pathologists' diagnoses (IHC only) vs. the final diagnosis complemented with FISH (IHC + FISH) were used as training outputs. Basic performance metrics and receiver operating characteristic curve analysis were used together with an explainability algorithm based on Shapley Additive exPlanations (SHAP) values to understand training differences. The model could discriminate amplified IHC from normal expression with better performance when the training output was the IHC + FISH final diagnosis (IHC vs. IHC + FISH: area under the curve, 0.94 vs. 0.81). This may be explained by the increased analytical impact of the membrane distribution criteria over the global intensity of the signal, according to SHAP value interpretation. The classification model improved its performance when the training input was the final diagnosis, downplaying the weighting of the intensity of the IHC signal, suggesting that to improve pathological diagnosis before FISH consultation, it is necessary to emphasize subcellular patterns of staining. © 2023 Spandidos Publications. All rights reserved.
  • Miniatura
    Ítem
    Intracellular aggregated TRPV1 is associated with lower survival in breast cancer patients
    (Dove Medical Press Ltd., 2018) Lozano, Carlo; Córdova, Claudio; Marchant, Ivanny; Zúñiga, Rodrigo; Ochova, Paola; Ramírez-Barrantes, Ricardo; González-Arriagada, Wilfredo Alejandro; Rodriguez, Belén; Olivero, Pablo
    Background: Breast cancer is a malignant disease that represents an important public health burden. The description of new molecular markers can be important to diagnosis, classification, and treatment. Transient receptor potential vanilloid 1 (TRPV1) polymodal channel is expressed in different neoplastic tissues and cell lines of breast cancer and associated with the regulation of tumor growth, tumor neurogenesis, cancer pain, and malignant progression of cancer. In primary and metastatic breast cancer tumors, TRPV1 is expressed during neoplastic transformation, invasive behavior, and resistance to cytotoxic therapy. Objective: The objective of this study was to describe the subcellular distribution of TRPV1 in invasive breast carcinomas and its association with survival. Methods: In 33 cases of invasive breast carcinomas, we identified immunohistochemical and immunofluorescent expression patterns of TRPV1 compared to healthy breast tissue. We characterized the expression of TRPV1 induced by estrogens in breast cancer cell lines MCF-7 and MDA to establish a model of the TRPV1–estrogen relationship regarding the malignant potential. We examined the association of TRPV1 patterns with patients’ survival with the Kaplan–Meyer model, using the log-rank test at 5 years of follow-up. The relation of TRPV1 expression patterns to the St. Gallen breast cancer subtypes was also tested. Results: Based on immunohistochemical expression pattern of TRPV1, we distinguished two main categories of breast cancer tissue, a “classical category” that exhibited diffuse expression of the channel and a “non-classical category” that expressed the channel in aggregates at the ER/Golgi and/or surrounding these structures. The classical pattern of TRPV1 was associated with a higher survival rate. In breast cancer cell lines, increasing doses of estrogens induced increased TRPV1 expression with nonclassical patterns at higher doses via a mechanism dependent on ER α. Conclusion: The expression and distribution of TRPV1 in invasive breast carcinomas may be considered as a biomarker for prognosis of the disease and a probable therapeutic target. © 2018 Lozano et al.
  • Miniatura
    Ítem
    Proteostasis and Mitochondrial Role on Psychiatric and Neurodegenerative Disorders: Current Perspectives
    (Hindawi Limited, 2018) Olivero, Pablo; Lozano, Carlo; Sotomayor-Zárate, Ramón; Meza-Concha, Nicolás; Arancibia, Marcelo; Córdova, Claudio; González-Arriagada, Wilfredo; Ramírez-Barrantes, Ricardo; Marchant, Ivanny
    Proteostasis involves processes that are fundamental for neural viability. Thus, protein misfolding and the formation of toxic aggregates at neural level, secondary to dysregulation of the conservative mechanisms of proteostasis, are associated with several neuropsychiatric conditions. It has been observed that impaired mitochondrial function due to a dysregulated proteostasis control system, that is, ubiquitin-proteasome system and chaperones, could also have effects on neurodegenerative disorders. We aimed to critically analyze the available findings regarding the neurobiological implications of proteostasis on the development of neurodegenerative and psychiatric diseases, considering the mitochondrial role. Proteostasis alterations in the prefrontal cortex implicate proteome instability and accumulation of misfolded proteins. Altered mitochondrial dynamics, especially in proteostasis processes, could impede the normal compensatory mechanisms against cell damage. Thereby, altered mitochondrial functions on regulatory modulation of dendritic development, neuroinflammation, and respiratory function may underlie the development of some psychiatric conditions, such as schizophrenia, being influenced by a genetic background. It is expected that with the increasing evidence about proteostasis in neuropsychiatric disorders, new therapeutic alternatives will emerge. © 2018 Pablo Olivero et al.