An Information-Extreme Algorithm for Universal Nuclear Feature-Driven Automated Classification of Breast Cancer Cells
<b>Background/Objectives:</b> Breast cancer diagnosis heavily relies on histopathological assessment, which is prone to subjectivity and inefficiency, especially with whole-slide imaging (WSI). This study addressed these limitations by developing an automated breast cancer cell classific...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/15/11/1389 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849722537358917632 |
|---|---|
| author | Taras Savchenko Ruslana Lakhtaryna Anastasiia Denysenko Anatoliy Dovbysh Sarah E. Coupland Roman Moskalenko |
| author_facet | Taras Savchenko Ruslana Lakhtaryna Anastasiia Denysenko Anatoliy Dovbysh Sarah E. Coupland Roman Moskalenko |
| author_sort | Taras Savchenko |
| collection | DOAJ |
| description | <b>Background/Objectives:</b> Breast cancer diagnosis heavily relies on histopathological assessment, which is prone to subjectivity and inefficiency, especially with whole-slide imaging (WSI). This study addressed these limitations by developing an automated breast cancer cell classification algorithm using an information-extreme machine learning approach and universal cytological features, aiming for objective and generalized histopathological diagnosis. <b>Methods</b>: Digitized histological images were processed to identify hyperchromatic cells. A set of 21 cytological features (10 geometric and 11 textural), chosen for their potential universality across cancers, were extracted from individual cells. These features were then used to classify cells as normal or malignant using an information-extreme algorithm. This algorithm optimizes an information criterion within a binary Hamming space to achieve robust recognition with minimal input features. The architectural innovation lies in the application of this information-extreme approach to cytological feature analysis for cancer cell classification. <b>Results</b>: The algorithm’s functional efficiency was evaluated on a dataset of 176 labeled cell images, yielding promising results: an accuracy of 89%, a precision of 85%, a recall of 84%, and an F1-score of 88%. These metrics demonstrate a balanced and effective model for automated breast cancer cell classification. <b>Conclusions</b>: The proposed information-extreme algorithm utilizing universal cytological features offers a potentially objective and computationally efficient alternative to traditional methods and may mitigate some limitations of deep learning in histopathological analysis. Future work will focus on validating the algorithm on larger datasets and exploring its applicability to other cancer types. |
| format | Article |
| id | doaj-art-9ba1941f89384bf6ba56050cddf809ce |
| institution | DOAJ |
| issn | 2075-4418 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-9ba1941f89384bf6ba56050cddf809ce2025-08-20T03:11:18ZengMDPI AGDiagnostics2075-44182025-05-011511138910.3390/diagnostics15111389An Information-Extreme Algorithm for Universal Nuclear Feature-Driven Automated Classification of Breast Cancer CellsTaras Savchenko0Ruslana Lakhtaryna1Anastasiia Denysenko2Anatoliy Dovbysh3Sarah E. Coupland4Roman Moskalenko5Department of Computer Science, Sumy State University, 40000 Sumy, UkraineDepartment of Pathology, Sumy State University, 40000 Sumy, UkraineDepartment of Pathology, Sumy State University, 40000 Sumy, UkraineDepartment of Computer Science, Sumy State University, 40000 Sumy, UkraineDepartment of Eye and Vision Science, Institute of Life Course and Medical Sciences, University of Liverpool, Liverpool L69 7ZX, UKDepartment of Pathology, Sumy State University, 40000 Sumy, Ukraine<b>Background/Objectives:</b> Breast cancer diagnosis heavily relies on histopathological assessment, which is prone to subjectivity and inefficiency, especially with whole-slide imaging (WSI). This study addressed these limitations by developing an automated breast cancer cell classification algorithm using an information-extreme machine learning approach and universal cytological features, aiming for objective and generalized histopathological diagnosis. <b>Methods</b>: Digitized histological images were processed to identify hyperchromatic cells. A set of 21 cytological features (10 geometric and 11 textural), chosen for their potential universality across cancers, were extracted from individual cells. These features were then used to classify cells as normal or malignant using an information-extreme algorithm. This algorithm optimizes an information criterion within a binary Hamming space to achieve robust recognition with minimal input features. The architectural innovation lies in the application of this information-extreme approach to cytological feature analysis for cancer cell classification. <b>Results</b>: The algorithm’s functional efficiency was evaluated on a dataset of 176 labeled cell images, yielding promising results: an accuracy of 89%, a precision of 85%, a recall of 84%, and an F1-score of 88%. These metrics demonstrate a balanced and effective model for automated breast cancer cell classification. <b>Conclusions</b>: The proposed information-extreme algorithm utilizing universal cytological features offers a potentially objective and computationally efficient alternative to traditional methods and may mitigate some limitations of deep learning in histopathological analysis. Future work will focus on validating the algorithm on larger datasets and exploring its applicability to other cancer types.https://www.mdpi.com/2075-4418/15/11/1389breast cancerautomated classificationinformation-extreme algorithmcytological featureshistopathologywhole-slide imaging |
| spellingShingle | Taras Savchenko Ruslana Lakhtaryna Anastasiia Denysenko Anatoliy Dovbysh Sarah E. Coupland Roman Moskalenko An Information-Extreme Algorithm for Universal Nuclear Feature-Driven Automated Classification of Breast Cancer Cells Diagnostics breast cancer automated classification information-extreme algorithm cytological features histopathology whole-slide imaging |
| title | An Information-Extreme Algorithm for Universal Nuclear Feature-Driven Automated Classification of Breast Cancer Cells |
| title_full | An Information-Extreme Algorithm for Universal Nuclear Feature-Driven Automated Classification of Breast Cancer Cells |
| title_fullStr | An Information-Extreme Algorithm for Universal Nuclear Feature-Driven Automated Classification of Breast Cancer Cells |
| title_full_unstemmed | An Information-Extreme Algorithm for Universal Nuclear Feature-Driven Automated Classification of Breast Cancer Cells |
| title_short | An Information-Extreme Algorithm for Universal Nuclear Feature-Driven Automated Classification of Breast Cancer Cells |
| title_sort | information extreme algorithm for universal nuclear feature driven automated classification of breast cancer cells |
| topic | breast cancer automated classification information-extreme algorithm cytological features histopathology whole-slide imaging |
| url | https://www.mdpi.com/2075-4418/15/11/1389 |
| work_keys_str_mv | AT tarassavchenko aninformationextremealgorithmforuniversalnuclearfeaturedrivenautomatedclassificationofbreastcancercells AT ruslanalakhtaryna aninformationextremealgorithmforuniversalnuclearfeaturedrivenautomatedclassificationofbreastcancercells AT anastasiiadenysenko aninformationextremealgorithmforuniversalnuclearfeaturedrivenautomatedclassificationofbreastcancercells AT anatoliydovbysh aninformationextremealgorithmforuniversalnuclearfeaturedrivenautomatedclassificationofbreastcancercells AT sarahecoupland aninformationextremealgorithmforuniversalnuclearfeaturedrivenautomatedclassificationofbreastcancercells AT romanmoskalenko aninformationextremealgorithmforuniversalnuclearfeaturedrivenautomatedclassificationofbreastcancercells AT tarassavchenko informationextremealgorithmforuniversalnuclearfeaturedrivenautomatedclassificationofbreastcancercells AT ruslanalakhtaryna informationextremealgorithmforuniversalnuclearfeaturedrivenautomatedclassificationofbreastcancercells AT anastasiiadenysenko informationextremealgorithmforuniversalnuclearfeaturedrivenautomatedclassificationofbreastcancercells AT anatoliydovbysh informationextremealgorithmforuniversalnuclearfeaturedrivenautomatedclassificationofbreastcancercells AT sarahecoupland informationextremealgorithmforuniversalnuclearfeaturedrivenautomatedclassificationofbreastcancercells AT romanmoskalenko informationextremealgorithmforuniversalnuclearfeaturedrivenautomatedclassificationofbreastcancercells |