Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

Classification of Breast Cancer Using a PNN Classifier Based on GLCM Feature Extraction and GMM Segmentation

Rektorat UDINUS 2020 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2020
Goals
Record
d868f300-72c0-4343-bad5-4d7cdcb59a81
Published
2026-10-30

Universitas Dian Nuswantoro conducted a research activity on breast cancer classification using mammographic images. The activity involved Fajri Riesaputri, Daffa; Atika Sari, Christy; Ignatius Moses Setiadi, De Rosal; and Hari Rachmawanto, Eko as participants. The research addressed breast cancer, which is described in the source as the most common cancer affecting women. The source also states that the continued annual increase in cases leads to the notion that this cancer cannot be cured. In this context, early detection was identified as helpful for minimizing the effects of the disease on sufferers.

The activity proposed a classification method based on mammographic images. A Probabilistic Neural Network was used as the classifier. To optimize the work of the classifier, preprocessing was conducted using median filters to minimize noise. The method also applied Gaussian Mixture Model segmentation and extracted features using the Gray Level Co-occurrence Matrix. The source explains that the Probabilistic Neural Network was selected because it can work effectively on small datasets.

Testing of the method produced an accuracy of 100 percent, as stated in the source. Through this activity, UDINUS addressed the stated goal through health-related research focused on breast cancer classification and early detection support. The activity demonstrates an institutional research contribution in applying image processing, segmentation, feature extraction, and classification methods to mammographic images. The evidence presented is limited to the research description and its reported testing result.

Reference https://www.scopus.com/pages/publications/85096836505?origin=resultslist