A Comparative Analysis of Deep Learning Models for Prediction of Microsatellite Instability in Colorectal Cancer
Colorectal cancer remains one of the most prevalent and fatal malignancies worldwide, underscoring the necessity for early and precise diagnostic approaches to enhance patient prognoses. This study proposes a deep learning-based model for predicting microsatellite instability (MSI) in colorectal can...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sakarya University
2025-03-01
|
| Series: | Sakarya University Journal of Computer and Information Sciences |
| Subjects: | |
| Online Access: | https://dergipark.org.tr/en/download/article-file/4603040 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850214808877531136 |
|---|---|
| author | Ziynet Pamuk Hüseyin Erikçi |
| author_facet | Ziynet Pamuk Hüseyin Erikçi |
| author_sort | Ziynet Pamuk |
| collection | DOAJ |
| description | Colorectal cancer remains one of the most prevalent and fatal malignancies worldwide, underscoring the necessity for early and precise diagnostic approaches to enhance patient prognoses. This study proposes a deep learning-based model for predicting microsatellite instability (MSI) in colorectal cancer using hematoxylin and eosin (H&E)-stained histopathological tissue slides. A classification framework was constructed using convolutional neural networks (CNN) and optimized through transfer learning techniques. The dataset, comprising 150,000 unique H&E-stained histologic image patches, was sourced from an open-access Kaggle repository, with 80% allocated to training and 20% to testing. A comparative evaluation of nine pre-trained models demonstrated that the VGG19 architecture yielded the highest classification performance, achieving an accuracy of 90.60%, a precision of 88.60%, a sensitivity of 93.10%, and an AUC score of 90.60%. Considering its high performance, the proposed model is expected to assist pathologists in clinical decision-making, potentially enhancing diagnostic accuracy in real-world medical applications. |
| format | Article |
| id | doaj-art-dfcf931a3d044c4e9e5221a218e4a67f |
| institution | OA Journals |
| issn | 2636-8129 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Sakarya University |
| record_format | Article |
| series | Sakarya University Journal of Computer and Information Sciences |
| spelling | doaj-art-dfcf931a3d044c4e9e5221a218e4a67f2025-08-20T02:08:47ZengSakarya UniversitySakarya University Journal of Computer and Information Sciences2636-81292025-03-018113615110.35377/saucis...163842428A Comparative Analysis of Deep Learning Models for Prediction of Microsatellite Instability in Colorectal CancerZiynet Pamuk0https://orcid.org/0000-0003-3792-2183Hüseyin Erikçihttps://orcid.org/0000-0003-3988-9823ZONGULDAK BULENT ECEVİT UNIVERSITYColorectal cancer remains one of the most prevalent and fatal malignancies worldwide, underscoring the necessity for early and precise diagnostic approaches to enhance patient prognoses. This study proposes a deep learning-based model for predicting microsatellite instability (MSI) in colorectal cancer using hematoxylin and eosin (H&E)-stained histopathological tissue slides. A classification framework was constructed using convolutional neural networks (CNN) and optimized through transfer learning techniques. The dataset, comprising 150,000 unique H&E-stained histologic image patches, was sourced from an open-access Kaggle repository, with 80% allocated to training and 20% to testing. A comparative evaluation of nine pre-trained models demonstrated that the VGG19 architecture yielded the highest classification performance, achieving an accuracy of 90.60%, a precision of 88.60%, a sensitivity of 93.10%, and an AUC score of 90.60%. Considering its high performance, the proposed model is expected to assist pathologists in clinical decision-making, potentially enhancing diagnostic accuracy in real-world medical applications.https://dergipark.org.tr/en/download/article-file/4603040microsatellite instabilitydeep learningcolorectal cancerhistopathologic image |
| spellingShingle | Ziynet Pamuk Hüseyin Erikçi A Comparative Analysis of Deep Learning Models for Prediction of Microsatellite Instability in Colorectal Cancer Sakarya University Journal of Computer and Information Sciences microsatellite instability deep learning colorectal cancer histopathologic image |
| title | A Comparative Analysis of Deep Learning Models for Prediction of Microsatellite Instability in Colorectal Cancer |
| title_full | A Comparative Analysis of Deep Learning Models for Prediction of Microsatellite Instability in Colorectal Cancer |
| title_fullStr | A Comparative Analysis of Deep Learning Models for Prediction of Microsatellite Instability in Colorectal Cancer |
| title_full_unstemmed | A Comparative Analysis of Deep Learning Models for Prediction of Microsatellite Instability in Colorectal Cancer |
| title_short | A Comparative Analysis of Deep Learning Models for Prediction of Microsatellite Instability in Colorectal Cancer |
| title_sort | comparative analysis of deep learning models for prediction of microsatellite instability in colorectal cancer |
| topic | microsatellite instability deep learning colorectal cancer histopathologic image |
| url | https://dergipark.org.tr/en/download/article-file/4603040 |
| work_keys_str_mv | AT ziynetpamuk acomparativeanalysisofdeeplearningmodelsforpredictionofmicrosatelliteinstabilityincolorectalcancer AT huseyinerikci acomparativeanalysisofdeeplearningmodelsforpredictionofmicrosatelliteinstabilityincolorectalcancer AT ziynetpamuk comparativeanalysisofdeeplearningmodelsforpredictionofmicrosatelliteinstabilityincolorectalcancer AT huseyinerikci comparativeanalysisofdeeplearningmodelsforpredictionofmicrosatelliteinstabilityincolorectalcancer |