Artificial Intelligence Techniques for Prostate Cancer Detection through Dual-Channel Tissue Feature Engineering
The optimal diagnostic and treatment strategies for prostate cancer (PCa) are constantly changing. Given the importance of accurate diagnosis, texture analysis of stained prostate tissues is important for automatic PCa detection. We used artificial intelligence (AI) techniques to classify dual-chann...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Cancers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-6694/13/7/1524 |
| _version_ | 1797539977084534784 |
|---|---|
| author | Cho-Hee Kim Subrata Bhattacharjee Deekshitha Prakash Suki Kang Nam-Hoon Cho Hee-Cheol Kim Heung-Kook Choi |
| author_facet | Cho-Hee Kim Subrata Bhattacharjee Deekshitha Prakash Suki Kang Nam-Hoon Cho Hee-Cheol Kim Heung-Kook Choi |
| author_sort | Cho-Hee Kim |
| collection | DOAJ |
| description | The optimal diagnostic and treatment strategies for prostate cancer (PCa) are constantly changing. Given the importance of accurate diagnosis, texture analysis of stained prostate tissues is important for automatic PCa detection. We used artificial intelligence (AI) techniques to classify dual-channel tissue features extracted from Hematoxylin and Eosin (H&E) tissue images, respectively. Tissue feature engineering was performed to extract first-order statistic (FOS)-based textural features from each stained channel, and cancer classification between benign and malignant was carried out based on important features. Recursive feature elimination (RFE) and one-way analysis of variance (ANOVA) methods were used to identify significant features, which provided the best five features out of the extracted six features. The AI techniques used in this study for binary classification (benign vs. malignant and low-grade vs. high-grade) were support vector machine (SVM), logistic regression (LR), bagging tree, boosting tree, and dual-channel bidirectional long short-term memory (DC-BiLSTM) network. Further, a comparative analysis was carried out between the AI algorithms. Two different datasets were used for PCa classification. Out of these, the first dataset (private) was used for training and testing the AI models and the second dataset (public) was used only for testing to evaluate model performance. The automatic AI classification system performed well and showed satisfactory results according to the hypothesis of this study. |
| first_indexed | 2024-03-10T12:53:30Z |
| format | Article |
| id | doaj.art-ade1b4c8d49d4a1babdbe4e00b35c362 |
| institution | Directory Open Access Journal |
| issn | 2072-6694 |
| language | English |
| last_indexed | 2024-03-10T12:53:30Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cancers |
| spelling | doaj.art-ade1b4c8d49d4a1babdbe4e00b35c3622023-11-21T12:06:17ZengMDPI AGCancers2072-66942021-03-01137152410.3390/cancers13071524Artificial Intelligence Techniques for Prostate Cancer Detection through Dual-Channel Tissue Feature EngineeringCho-Hee Kim0Subrata Bhattacharjee1Deekshitha Prakash2Suki Kang3Nam-Hoon Cho4Hee-Cheol Kim5Heung-Kook Choi6Department of Digital Anti-Aging Healthcare, Inje University, Gimhae 50834, KoreaDepartment of Computer Engineering, u-AHRC, Inje University, Gimhae 50834, KoreaDepartment of Computer Engineering, u-AHRC, Inje University, Gimhae 50834, KoreaDepartment of Pathology, Yonsei University Hospital, Seoul 03722, KoreaDepartment of Pathology, Yonsei University Hospital, Seoul 03722, KoreaDepartment of Digital Anti-Aging Healthcare, Inje University, Gimhae 50834, KoreaDepartment of Computer Engineering, u-AHRC, Inje University, Gimhae 50834, KoreaThe optimal diagnostic and treatment strategies for prostate cancer (PCa) are constantly changing. Given the importance of accurate diagnosis, texture analysis of stained prostate tissues is important for automatic PCa detection. We used artificial intelligence (AI) techniques to classify dual-channel tissue features extracted from Hematoxylin and Eosin (H&E) tissue images, respectively. Tissue feature engineering was performed to extract first-order statistic (FOS)-based textural features from each stained channel, and cancer classification between benign and malignant was carried out based on important features. Recursive feature elimination (RFE) and one-way analysis of variance (ANOVA) methods were used to identify significant features, which provided the best five features out of the extracted six features. The AI techniques used in this study for binary classification (benign vs. malignant and low-grade vs. high-grade) were support vector machine (SVM), logistic regression (LR), bagging tree, boosting tree, and dual-channel bidirectional long short-term memory (DC-BiLSTM) network. Further, a comparative analysis was carried out between the AI algorithms. Two different datasets were used for PCa classification. Out of these, the first dataset (private) was used for training and testing the AI models and the second dataset (public) was used only for testing to evaluate model performance. The automatic AI classification system performed well and showed satisfactory results according to the hypothesis of this study.https://www.mdpi.com/2072-6694/13/7/1524artificial intelligencetissue feature engineeringdual-channelprostate cancertexture analysisbinary classification |
| spellingShingle | Cho-Hee Kim Subrata Bhattacharjee Deekshitha Prakash Suki Kang Nam-Hoon Cho Hee-Cheol Kim Heung-Kook Choi Artificial Intelligence Techniques for Prostate Cancer Detection through Dual-Channel Tissue Feature Engineering Cancers artificial intelligence tissue feature engineering dual-channel prostate cancer texture analysis binary classification |
| title | Artificial Intelligence Techniques for Prostate Cancer Detection through Dual-Channel Tissue Feature Engineering |
| title_full | Artificial Intelligence Techniques for Prostate Cancer Detection through Dual-Channel Tissue Feature Engineering |
| title_fullStr | Artificial Intelligence Techniques for Prostate Cancer Detection through Dual-Channel Tissue Feature Engineering |
| title_full_unstemmed | Artificial Intelligence Techniques for Prostate Cancer Detection through Dual-Channel Tissue Feature Engineering |
| title_short | Artificial Intelligence Techniques for Prostate Cancer Detection through Dual-Channel Tissue Feature Engineering |
| title_sort | artificial intelligence techniques for prostate cancer detection through dual channel tissue feature engineering |
| topic | artificial intelligence tissue feature engineering dual-channel prostate cancer texture analysis binary classification |
| url | https://www.mdpi.com/2072-6694/13/7/1524 |
| work_keys_str_mv | AT choheekim artificialintelligencetechniquesforprostatecancerdetectionthroughdualchanneltissuefeatureengineering AT subratabhattacharjee artificialintelligencetechniquesforprostatecancerdetectionthroughdualchanneltissuefeatureengineering AT deekshithaprakash artificialintelligencetechniquesforprostatecancerdetectionthroughdualchanneltissuefeatureengineering AT sukikang artificialintelligencetechniquesforprostatecancerdetectionthroughdualchanneltissuefeatureengineering AT namhooncho artificialintelligencetechniquesforprostatecancerdetectionthroughdualchanneltissuefeatureengineering AT heecheolkim artificialintelligencetechniquesforprostatecancerdetectionthroughdualchanneltissuefeatureengineering AT heungkookchoi artificialintelligencetechniquesforprostatecancerdetectionthroughdualchanneltissuefeatureengineering |