Cancer Detection in Breast Histopathological Images Using Extremely Randomized Trees
Intelligent Methods in Engineering Sciences · 30.04.2026
DOI: 10.58190/imiens.2026.167 ↗Kurz gefasst
Fachartikel in der Zeitschrift Intelligent Methods in Engineering Sciences, online erschienen am 30.04.2026. Verfasst von Mahendra Kanojia. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
This research aimed to develop an effective machine learning-based system for the automated detection of breast cancer using histopathological images, overcoming the limitations of manual examination. The study utilized a diverse dataset of 13,347 histopathological images from three secondary sources and one primary source. The inclusion of multiple image sources was intended to enhance the model’s versatility. Initially, images underwent pre-processing to reduce noise using a median filter and were converted to grayscale. Otsu's thresholding was then applied to enhance nucleus edges and reduce background noise. A recursive feature elimination algorithm was employed to reduce the initial 98 features to these 48 key ones, focusing on the area and shape of the nucleus, color-based features, and image texture. For classification, the Extremely Randomized Trees Classifier was used. The model was trained to classify images as benign or malignant. The results demonstrated high performance, with the model achieving an accuracy of 98.95%. Further evaluation revealed a sensitivity of 99.48%, indicating a low false negative rate. Specificity was 94.67%, correctly identifying benign cases. The model also achieved precision of 98.97% and recall of 99.48%, with a Kappa statistic of 97.62%, suggesting substantial agreement beyond chance. The ROC performance was 98.67%, indicating robust performance. This study highlights the potential of machine learning, specifically the Extremely Randomized Trees Classifier, for automated and accurate breast cancer detection from histopathological images. The high-performance metrics suggest the model can enhance diagnostic accuracy and assist pathologists in clinical decision-making.
Zitieren
APA
Kanojia, M. (2026). Cancer Detection in Breast Histopathological Images Using Extremely Randomized Trees. Intelligent Methods in Engineering Sciences. https://doi.org/10.58190/imiens.2026.167
Vancouver
Kanojia M. Cancer Detection in Breast Histopathological Images Using Extremely Randomized Trees. Intelligent Methods in Engineering Sciences. 2026. doi:10.58190/imiens.2026.167
BibTeX
@article{Kanojia2026,
author = {Kanojia, Mahendra},
title = {Cancer Detection in Breast Histopathological Images Using Extremely Randomized Trees},
journal = {Intelligent Methods in Engineering Sciences},
year = {2026},
doi = {10.58190/imiens.2026.167}
}
EUVIMED