Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Jurnal Teknik Informatika (JUTIF)

PROTEGO: Improving Breast Cancer Diagnosis with Prototype-Contrastive Autoencoder and Conformal Prediction on the WDBC Dataset Hiswati, Marselina Endah; Diqi, Mohammad
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 5 (2025): JUTIF Volume 6, Number 5, Oktober 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.5.5294

Abstract

Breast cancer remains one of the leading causes of mortality among women, making accurate and trustworthy early detection a critical challenge in healthcare. To address this, we propose PROTEGO, a Prototype-Contrastive Autoencoder with integrated Conformal Prediction, designed to achieve both high diagnostic accuracy and reliable uncertainty quantification. The framework combines dual-head autoencoding, supervised contrastive learning, prototype-based regularization, and conformal calibration to generate discriminative yet interpretable representations. Using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset, PROTEGO was trained and evaluated through stratified data splits, with performance measured by AUROC, AUPRC, F1-score, Balanced Accuracy, Brier score, calibration error, and conformal coverage metrics. The results show that PROTEGO achieves highly competitive performance with an AUROC of 0.992 and an AUPRC of 0.995, while uniquely providing conformal coverage guarantees with an average set size close to one and more than 92% decisive predictions. Ablation studies confirm the complementary role of each component in enhancing both accuracy and calibration. These findings demonstrate that integrating prototype-guided representation learning with conformal prediction establishes a clinically meaningful diagnostic framework. PROTEGO highlights the importance of unifying precision and reliability in medical AI, offering a step toward more interpretable, safe, and clinically trustworthy systems for breast cancer detection.
GENERATIVE ADVERSARIAL NETWORKS FOR ANTERIOR CRUCIATE LIGAMENT INJURY DETECTION Mulyani, Sri Hasta; Diqi, Mohammad; Salsabil, Husna Arwa
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 1 (2024): JUTIF Volume 5, Number 1, February 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.1.1150

Abstract

This research explores the application of Generative Adversarial Networks (GANs) for detecting and classifying Anterior Cruciate Ligament (ACL) injuries using MRI images. The study utilized a dataset of 917 MRI images, each labeled as healthy, partially injured, or completely ruptured, to train the model. The performance of the GAN model was evaluated using a confusion matrix and a classification report, yielding an overall accuracy of 92%. The model demonstrated high proficiency in identifying healthy ACLs and partially injured ACLs but encountered some challenges in accurately identifying completely ruptured ACLs. Despite this, the results suggest that machine learning techniques, particularly GANs, have significant potential for enhancing the accuracy and efficiency of ACL injury detection. The ability of the model to distinguish between different degrees of injury could potentially aid in treatment planning. However, the study also underscores the need for further refinement of the model, particularly in improving its sensitivity in detecting severe ACL injuries. This research highlights the potential of machine learning in medical imaging and provides a solid foundation for future research in ACL injury detection and classification.