Browsing by Author "Vidaurre, Soledad"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    A methodology for developing dermatological datasets: lessons from retrospective data collection for AI-based applications
    (2025) Pedro Pérez, Alma Alheli; Romero Jofré, Pamela Ignacia; Vidaurre, Soledad; Cabanas, Ana M.; Galaz, Atsuko; Hidalgo Acuña, Leonel Esteban; Carrasco, Karina; Tamez-Peña, José Gerardo; Díaz-Domínguez, Ricardo; Navarrete Dechent, Cristian Patricio; Mery Quiroz, Domingo Arturo
    Purpose The integration of artificial intelligence into dermatological research has underscored the need for robust and well-structured dermatological datasets. However, these datasets vary widely in their development processes, and there is currently no standard methodology to create such datasets. This work identifies three pressing needs for the building of dermatological datasets focus on skin tumor classification: the need for multimodal datasets, the definition of minimum metadata requirements, and the inclusion of underrepresented populations to address the scarcity of health data. Methods We propose a practical methodology to create dermatological datasets from clinical records, incorporating both images and patient metadata. The process consists of four key stages: getting the institutional review board approval and analysis of clinical information sources, data recording and structuring, processing of clinical data and images, and quality assessment. This methodology was derived from hands-on experience in building two datasets from Chilean and Mexican populations, respectively. Results The methodology allows the creation of well-structured datasets by simplifying data organization and enabling replication. Each step includes practical guidance for dealing with typical challenges, such as image metadata categorization and technical validation by dermatologists and computer scientists. Conclusion Our contribution offers a reproducible, scalable, and interdisciplinary framework for creating dermatological datasets, especially useful for countries initiating dataset creation. In addition to the methodological proposal, we highlight common pitfalls and offer recommendations to mitigate them.
  • No Thumbnail Available
    Item
    A Review of Metadata and Deep Learning Strategies for Skin Lesion Classification
    (2025) Pedro Perez, Alma Alheli; Romero Jofre, Pamela Ignacia; Vidaurre, Soledad; Navarrete Dechent, Cristian Patricio; Mery Quiroz, Domingo Arturo
  • Thumbnail Image
    Item
    Creating a dermatologic database for artificial intelligence, a Chilean experience, and advice from ChatGPT
    (John Wiley and Sons Inc, 2024) Hidalgo Acuña, Leonel Esteban; Salinas, María Paz; Sepúlveda, Javiera; Carrasco, Karina; Romero, Pamela; Pedro, Alma; Vidaurre, Soledad; Mery, Domingo; Navarrete Dechent, Cristian
  • Thumbnail Image
    Item
    Targeting antisense mitochondrial ncRNAs inhibits murine melanoma tumor growth and metastasis through reduction in survival and invasion factors
    (IMPACT JOURNALS LLC, 2016) Lobos Gonzalez, Lorena; Silva, Veronica; Araya, Mariela; Restovic, Franko; Echenique, Javiera; Oliveira Cruz, Luciana; Fitzpatrick, Christopher; Briones, Macarena; Villegas, Jaime; Villota, Claudio; Vidaurre, Soledad; Borgna, Vincenzo; Socias, Miguel; Valenzuela, Sebastian; Lopez, Constanza; Socias, Teresa; Varas, Manuel; Diaz, Jorge; Burzio, Luis O.; Burzio, Veronica A.
    We reported that knockdown of the antisense noncoding mitochondrial RNAs (ASncmtRNAs) induces apoptotic death of several human tumor cell lines, but not normal cells, suggesting this approach for selective therapy against different types of cancer. In order to translate these results to a preclinical scenario, we characterized the murine noncoding mitochondrial RNAs (ncmtRNAs) and performed in vivo knockdown in syngeneic murine melanoma models. Mouse ncmtRNAs display structures similar to the human counterparts, including long double-stranded regions arising from the presence of inverted repeats. Knockdown of ASncmtRNAs with specific antisense oligonucleotides (ASO) reduces murine melanoma B16F10 cell proliferation and induces apoptosis in vitro through downregulation of pro-survival and metastasis markers, particularly survivin. For in vivo studies, subcutaneous B16F10 melanoma tumors in C57BL/6 mice were treated systemically with specific and control antisense oligonucleotides (ASO). For metastasis studies, tumors were resected, followed by systemic administration of ASOs and the presence of metastatic nodules in lungs and liver was assessed. Treatment with specific ASO inhibited tumor growth and metastasis after primary tumor resection. In a metastasis-only assay, mice inoculated intravenously with cells and treated with the same ASO displayed reduced number and size of melanoma nodules in the lungs, compared to controls. Our results suggest that ASncmtRNAs could be potent targets for melanoma therapy. To our knowledge, the ASncmtRNAs are the first potential non-nuclear targets for melanoma therapy.