Clasificación de la expresión del receptor 2 del factor de crecimiento epidérmico humano en tejido mamario canceroso mediante inteligencia artificial.
Saved in:
| Title: | Clasificación de la expresión del receptor 2 del factor de crecimiento epidérmico humano en tejido mamario canceroso mediante inteligencia artificial. |
|---|---|
| Alternate Title: | Classification of human epidermal growth factor receptor 2 expression in cancerous breast tissue through artificial intelligence. |
| Authors: | Verónica Villota, Leidy1 veronicaver@unicauca.edu.co, Julieth Lasso, Jessica1, Noelia Muñoz, Elvia2, Vargas, Rubiel1 |
| Source: | Biomédica: Revista del Instituto Nacional de Salud. 2025 Special Issue, Vol. 45, p83-102. 20p. |
| Subjects: | BREAST cancer, HER2 protein, DEEP learning, CLASSIFICATION, ARTIFICIAL intelligence, COLLEGE of American Pathologists, HISTOLOGICAL techniques, DIAGNOSIS, BIOMARKERS |
| Abstract (English): | Introduction. Histological and molecular analysis of breast tissue is essential for the diagnosis, prognosis, and treatment of breast cancer. Key biomarkers include progesterone and estrogen receptors, as well as the human epidermal growth factor receptor 2 (HER2). HER2 overexpression indicates an aggressive subtype of breast cancer but enables targeted therapies that improve survival rates. However, its evaluation faces challenges, ranging from sample quality to interpretation variability. The College of American Pathologists classifies HER2 overexpression into four categories, but variations around the 10% expression threshold can lead to misinterpretations. Objective. To present an automated technique for classifying HER2-overexpressing cells in histological slides. Materials and methods. The Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology was applied using samples of 89 patients from the Unidad de Diagnóstico en Patología, covering all four HER2 expression levels. Deep learning techniques were employed, leveraging neural networks and vision transformer models through transfer learning. Additionally, a usability evaluation was conducted on the final version of the software. Results. The ViT-B/16 model achieved a classification accuracy of 90,65%, while the tool was evaluated with an acceptable level of satisfaction in its clinical application. Conclusion. Artificial intelligence demonstrated high accuracy and consistency in HER2 classification, reducing diagnostic variability and improving objectivity. However, further optimization of processing efficiency is required for broader applicability. [ABSTRACT FROM AUTHOR] |
| Abstract (Spanish): | Introducción. El análisis histológico y molecular del tejido mamario es clave para el diagnóstico, el pronóstico y el tratamiento del cáncer de mama. Entre los biomarcadores evaluados, se destacan los receptores de progesterona, los de estrógeno y el receptor 2 del factor de crecimiento epidérmico humano (HER2). La sobreexpresión de HER2 indica un subtipo agresivo de cáncer de mama, aunque permite el uso de terapias dirigidas que mejoran la tasa de supervivencia. No obstante, su evaluación enfrenta desafíos, desde la calidad de las muestras hasta la variabilidad en la interpretación. El College of American Pathologists clasifica la sobreexpresión de HER2 en cuatro categorías, pero la variabilidad en la expresión cercana al 10 % puede generar confusión. Objetivo. Presentar una técnica basada en la inteligencia artificial para clasificar células con sobreexpresión de HER2 en las placas histológicas. Materiales y métodos. Se aplicó la metodología Cross-Industry Standard Process for Data Mining (CRISP-DM) en muestras de 89 pacientes de la Unidad de Diagnóstico en Patología, abarcando los cuatro niveles de HER2. Se utilizaron redes neuronales y modelos de Vision Transformer (ViT) afinados mediante transferencia de aprendizaje. Además, se evaluó la facilidad de uso y, finalmente, la eficiencia del software presentado. Resultados. Con el modelo ViT-B/16, se obtuvo una exactitud del 90,65 % en la clasificación, mientras que la herramienta evaluada generó un grado aceptable de satisfacción con su aplicación clínica. Conclusión. La inteligencia artificial demostró gran precisión y concordancia en la clasificación del HER2, redujo la variabilidad diagnóstica y mejoró la objetividad, aunque aún se requiere optimizar la eficiencia del procesamiento. [ABSTRACT FROM AUTHOR] |
| Copyright of Biomédica: Revista del Instituto Nacional de Salud is the property of Instituto Nacional de Salud of Colombia and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | MedicLatina |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: lth DbLabel: MedicLatina An: 190598940 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Clasificación de la expresión del receptor 2 del factor de crecimiento epidérmico humano en tejido mamario canceroso mediante inteligencia artificial. – Name: TitleAlt Label: Alternate Title Group: TiAlt Data: Classification of human epidermal growth factor receptor 2 expression in cancerous breast tissue through artificial intelligence. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Verónica+Villota%2C+Leidy%22">Verónica Villota, Leidy</searchLink><relatesTo>1</relatesTo><i> veronicaver@unicauca.edu.co</i><br /><searchLink fieldCode="AR" term="%22Julieth+Lasso%2C+Jessica%22">Julieth Lasso, Jessica</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Noelia+Muñoz%2C+Elvia%22">Noelia Muñoz, Elvia</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Vargas%2C+Rubiel%22">Vargas, Rubiel</searchLink><relatesTo>1</relatesTo> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Biomédica%3A+Revista+del+Instituto+Nacional+de+Salud%22">Biomédica: Revista del Instituto Nacional de Salud</searchLink>. 2025 Special Issue, Vol. 45, p83-102. 20p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22BREAST+cancer%22">BREAST cancer</searchLink><br /><searchLink fieldCode="DE" term="%22HER2+protein%22">HER2 protein</searchLink><br /><searchLink fieldCode="DE" term="%22DEEP+learning%22">DEEP learning</searchLink><br /><searchLink fieldCode="DE" term="%22CLASSIFICATION%22">CLASSIFICATION</searchLink><br /><searchLink fieldCode="DE" term="%22ARTIFICIAL+intelligence%22">ARTIFICIAL intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22COLLEGE+of+American+Pathologists%22">COLLEGE of American Pathologists</searchLink><br /><searchLink fieldCode="DE" term="%22HISTOLOGICAL+techniques%22">HISTOLOGICAL techniques</searchLink><br /><searchLink fieldCode="DE" term="%22DIAGNOSIS%22">DIAGNOSIS</searchLink><br /><searchLink fieldCode="DE" term="%22BIOMARKERS%22">BIOMARKERS</searchLink> – Name: Abstract Label: Abstract (English) Group: Ab Data: Introduction. Histological and molecular analysis of breast tissue is essential for the diagnosis, prognosis, and treatment of breast cancer. Key biomarkers include progesterone and estrogen receptors, as well as the human epidermal growth factor receptor 2 (HER2). HER2 overexpression indicates an aggressive subtype of breast cancer but enables targeted therapies that improve survival rates. However, its evaluation faces challenges, ranging from sample quality to interpretation variability. The College of American Pathologists classifies HER2 overexpression into four categories, but variations around the 10% expression threshold can lead to misinterpretations. Objective. To present an automated technique for classifying HER2-overexpressing cells in histological slides. Materials and methods. The Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology was applied using samples of 89 patients from the Unidad de Diagnóstico en Patología, covering all four HER2 expression levels. Deep learning techniques were employed, leveraging neural networks and vision transformer models through transfer learning. Additionally, a usability evaluation was conducted on the final version of the software. Results. The ViT-B/16 model achieved a classification accuracy of 90,65%, while the tool was evaluated with an acceptable level of satisfaction in its clinical application. Conclusion. Artificial intelligence demonstrated high accuracy and consistency in HER2 classification, reducing diagnostic variability and improving objectivity. However, further optimization of processing efficiency is required for broader applicability. [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Abstract (Spanish) Group: Ab Data: Introducción. El análisis histológico y molecular del tejido mamario es clave para el diagnóstico, el pronóstico y el tratamiento del cáncer de mama. Entre los biomarcadores evaluados, se destacan los receptores de progesterona, los de estrógeno y el receptor 2 del factor de crecimiento epidérmico humano (HER2). La sobreexpresión de HER2 indica un subtipo agresivo de cáncer de mama, aunque permite el uso de terapias dirigidas que mejoran la tasa de supervivencia. No obstante, su evaluación enfrenta desafíos, desde la calidad de las muestras hasta la variabilidad en la interpretación. El College of American Pathologists clasifica la sobreexpresión de HER2 en cuatro categorías, pero la variabilidad en la expresión cercana al 10 % puede generar confusión. Objetivo. Presentar una técnica basada en la inteligencia artificial para clasificar células con sobreexpresión de HER2 en las placas histológicas. Materiales y métodos. Se aplicó la metodología Cross-Industry Standard Process for Data Mining (CRISP-DM) en muestras de 89 pacientes de la Unidad de Diagnóstico en Patología, abarcando los cuatro niveles de HER2. Se utilizaron redes neuronales y modelos de Vision Transformer (ViT) afinados mediante transferencia de aprendizaje. Además, se evaluó la facilidad de uso y, finalmente, la eficiencia del software presentado. Resultados. Con el modelo ViT-B/16, se obtuvo una exactitud del 90,65 % en la clasificación, mientras que la herramienta evaluada generó un grado aceptable de satisfacción con su aplicación clínica. Conclusión. La inteligencia artificial demostró gran precisión y concordancia en la clasificación del HER2, redujo la variabilidad diagnóstica y mejoró la objetividad, aunque aún se requiere optimizar la eficiencia del procesamiento. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Biomédica: Revista del Instituto Nacional de Salud is the property of Instituto Nacional de Salud of Colombia and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=lth&AN=190598940 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.7705/biomedica.7899 Languages: – Code: spa Text: Spanish PhysicalDescription: Pagination: PageCount: 20 StartPage: 83 Subjects: – SubjectFull: BREAST cancer Type: general – SubjectFull: HER2 protein Type: general – SubjectFull: DEEP learning Type: general – SubjectFull: CLASSIFICATION Type: general – SubjectFull: ARTIFICIAL intelligence Type: general – SubjectFull: COLLEGE of American Pathologists Type: general – SubjectFull: HISTOLOGICAL techniques Type: general – SubjectFull: DIAGNOSIS Type: general – SubjectFull: BIOMARKERS Type: general Titles: – TitleFull: Clasificación de la expresión del receptor 2 del factor de crecimiento epidérmico humano en tejido mamario canceroso mediante inteligencia artificial. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Verónica Villota, Leidy – PersonEntity: Name: NameFull: Julieth Lasso, Jessica – PersonEntity: Name: NameFull: Noelia Muñoz, Elvia – PersonEntity: Name: NameFull: Vargas, Rubiel IsPartOfRelationships: – BibEntity: Dates: – D: 03 M: 12 Text: 2025 Special Issue Type: published Y: 2025 Identifiers: – Type: issn-print Value: 01204157 Numbering: – Type: volume Value: 45 Titles: – TitleFull: Biomédica: Revista del Instituto Nacional de Salud Type: main |
| ResultId | 1 |
