Browsing by Author "Jiménez Garay, Gabriel Alexandro"

Now showing 1 - 2 of 2

Deep Learning for Semantic Segmentation versus Classification in Computational Pathology: Application to mitosis analysis in Breast Cancer grading
(Pontificia Universidad Católica del Perú, 2019-04-12) Jiménez Garay, Gabriel Alexandro; Racoceanu, Daniel
Existing computational pathology approaches did not allow, yet, the emergence of effective/efficient computer-aided tools used as a second opinion for pathologists in the daily practice. Focusing on the case of computer-based qualification for breast cancer diagnosis, the present article proposes two deep learning architectures to efficiently and effectively detect and classify mitosis in a histopathological tissue sample. The first method consisted of two parts, entailing a preprocessing of the digital histological image and a free-handcrafted-feature Convolutional Neural Network (CNN) used for binary classification. Results show that the methodology proposed can achieve 95% accuracy in testing with an F1-score of 94.35%, which is higher than the results from the literature using classical image processing techniques and also higher than the approaches using handcrafted features combined with CNNs. The second approach was an end-to-end methodology using semantic segmentation. Results showed that this algorithm can achieve an accuracy higher than 95% in testing and an average Dice index of 0.6 which is higher than the results from the literature using CNNs (0.9 F1-score). Additionally, due to the semantic properties of the deep learning approach, an end-to-end deep learning framework is viable to perform both tasks: detection and classification of mitosis. The results showed the potential of deep learning in the analysis of Whole Slide Images (WSI) and its integration to computer-aided systems. The extension of this work to whole slide images is also addressed in the last two chapters; as well as, some computational key points that are useful when constructing a computer-aided-system inspired by the described technology.
Estudio de atipia celular utilizando redes neuronales convolucionales: aplicación en tejidos de cáncer de mama
(Pontificia Universidad Católica del Perú, 2021-02-15) Yacolca Huamán, Karla Lucía; Jiménez Garay, Gabriel Alexandro; Racoceanu, Daniel
La escala de Nottingham (NGS) se emplea para poder determinar el grado del cáncer de mama, y tiene 3 criterios a considerar: formación tubular, atipia nuclear y conteo de mitosis. A partir de los puntajes parciales de cada criterio se obtiene el grado del cáncer. Para poder asignar cada puntaje, el patólogo analiza, de forma manual, cada una de las muestras de tejido. La patología computacional surge como una alternativa para simplificar la tarea de análisis de tejido, pues integra la tecnología WSI (Whole Side Imaging), la cual permite obtener imágenes de tejido en formato digital, con herramientas de análisis de imágenes. El procesamiento de imágenes se realiza de dos formas: por medio de algoritmos de procesamiento clásico y algoritmos de aprendizaje profundo. Estos últimos emplean redes neuronales, las cuales automatizan el proceso de análisis de imágenes, y permiten generalizar el modelo ante variantes en las imágenes de entrada. En el presente trabajo se muestra el estudio del criterio de atipia nuclear empleando redes neuronales convolucionales, las cuales son un tipo de arquitectura de aprendizaje profundo, aplicado a tejidos de cáncer de mama. Además, se presenta el modelo de solución para poder asignar el puntaje al tejido según el criterio mencionado.