An Efficient Lightweight CNN and Ensemble Machine Learning Classification of Prostate Tissue Using Multilevel Feature Analysis
Prostate carcinoma is caused when cells and glands in the prostate change their shape and size from normal to abnormal. Typically, the pathologist’s goal is to classify the staining slides and differentiate normal from abnormal tissue. In the present study, we used a computational approach to classi...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/22/8013 |
| _version_ | 1797548152313610240 |
|---|---|
| author | Subrata Bhattacharjee Cho-Hee Kim Deekshitha Prakash Hyeon-Gyun Park Nam-Hoon Cho Heung-Kook Choi |
| author_facet | Subrata Bhattacharjee Cho-Hee Kim Deekshitha Prakash Hyeon-Gyun Park Nam-Hoon Cho Heung-Kook Choi |
| author_sort | Subrata Bhattacharjee |
| collection | DOAJ |
| description | Prostate carcinoma is caused when cells and glands in the prostate change their shape and size from normal to abnormal. Typically, the pathologist’s goal is to classify the staining slides and differentiate normal from abnormal tissue. In the present study, we used a computational approach to classify images and features of benign and malignant tissues using artificial intelligence (AI) techniques. Here, we introduce two lightweight convolutional neural network (CNN) architectures and an ensemble machine learning (EML) method for image and feature classification, respectively. Moreover, the classification using pre-trained models and handcrafted features was carried out for comparative analysis. The binary classification was performed to classify between the two grade groups (benign vs. malignant) and quantile-quantile plots were used to show their predicted outcomes. Our proposed models for deep learning (DL) and machine learning (ML) classification achieved promising accuracies of 94.0% and 92.0%, respectively, based on non-handcrafted features extracted from CNN layers. Therefore, these models were able to predict nearly perfectly accurately using few trainable parameters or CNN layers, highlighting the importance of DL and ML techniques and suggesting that the computational analysis of microscopic anatomy will be essential to the future practice of pathology. |
| first_indexed | 2024-03-10T14:55:26Z |
| format | Article |
| id | doaj.art-f5157800ee2c4a37aba125edf016a6f5 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T14:55:26Z |
| publishDate | 2020-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-f5157800ee2c4a37aba125edf016a6f52023-11-20T20:41:50ZengMDPI AGApplied Sciences2076-34172020-11-011022801310.3390/app10228013An Efficient Lightweight CNN and Ensemble Machine Learning Classification of Prostate Tissue Using Multilevel Feature AnalysisSubrata Bhattacharjee0Cho-Hee Kim1Deekshitha Prakash2Hyeon-Gyun Park3Nam-Hoon Cho4Heung-Kook Choi5Department of Computer Engineering, u-AHRC, Inje University, Gimhae 50834, KoreaDepartment 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 Computer Engineering, u-AHRC, Inje University, Gimhae 50834, KoreaProstate carcinoma is caused when cells and glands in the prostate change their shape and size from normal to abnormal. Typically, the pathologist’s goal is to classify the staining slides and differentiate normal from abnormal tissue. In the present study, we used a computational approach to classify images and features of benign and malignant tissues using artificial intelligence (AI) techniques. Here, we introduce two lightweight convolutional neural network (CNN) architectures and an ensemble machine learning (EML) method for image and feature classification, respectively. Moreover, the classification using pre-trained models and handcrafted features was carried out for comparative analysis. The binary classification was performed to classify between the two grade groups (benign vs. malignant) and quantile-quantile plots were used to show their predicted outcomes. Our proposed models for deep learning (DL) and machine learning (ML) classification achieved promising accuracies of 94.0% and 92.0%, respectively, based on non-handcrafted features extracted from CNN layers. Therefore, these models were able to predict nearly perfectly accurately using few trainable parameters or CNN layers, highlighting the importance of DL and ML techniques and suggesting that the computational analysis of microscopic anatomy will be essential to the future practice of pathology.https://www.mdpi.com/2076-3417/10/22/8013prostate carcinomamicroscopicconvolutional neural networkmachine learningdeep learninghandcrafted |
| spellingShingle | Subrata Bhattacharjee Cho-Hee Kim Deekshitha Prakash Hyeon-Gyun Park Nam-Hoon Cho Heung-Kook Choi An Efficient Lightweight CNN and Ensemble Machine Learning Classification of Prostate Tissue Using Multilevel Feature Analysis Applied Sciences prostate carcinoma microscopic convolutional neural network machine learning deep learning handcrafted |
| title | An Efficient Lightweight CNN and Ensemble Machine Learning Classification of Prostate Tissue Using Multilevel Feature Analysis |
| title_full | An Efficient Lightweight CNN and Ensemble Machine Learning Classification of Prostate Tissue Using Multilevel Feature Analysis |
| title_fullStr | An Efficient Lightweight CNN and Ensemble Machine Learning Classification of Prostate Tissue Using Multilevel Feature Analysis |
| title_full_unstemmed | An Efficient Lightweight CNN and Ensemble Machine Learning Classification of Prostate Tissue Using Multilevel Feature Analysis |
| title_short | An Efficient Lightweight CNN and Ensemble Machine Learning Classification of Prostate Tissue Using Multilevel Feature Analysis |
| title_sort | efficient lightweight cnn and ensemble machine learning classification of prostate tissue using multilevel feature analysis |
| topic | prostate carcinoma microscopic convolutional neural network machine learning deep learning handcrafted |
| url | https://www.mdpi.com/2076-3417/10/22/8013 |
| work_keys_str_mv | AT subratabhattacharjee anefficientlightweightcnnandensemblemachinelearningclassificationofprostatetissueusingmultilevelfeatureanalysis AT choheekim anefficientlightweightcnnandensemblemachinelearningclassificationofprostatetissueusingmultilevelfeatureanalysis AT deekshithaprakash anefficientlightweightcnnandensemblemachinelearningclassificationofprostatetissueusingmultilevelfeatureanalysis AT hyeongyunpark anefficientlightweightcnnandensemblemachinelearningclassificationofprostatetissueusingmultilevelfeatureanalysis AT namhooncho anefficientlightweightcnnandensemblemachinelearningclassificationofprostatetissueusingmultilevelfeatureanalysis AT heungkookchoi anefficientlightweightcnnandensemblemachinelearningclassificationofprostatetissueusingmultilevelfeatureanalysis AT subratabhattacharjee efficientlightweightcnnandensemblemachinelearningclassificationofprostatetissueusingmultilevelfeatureanalysis AT choheekim efficientlightweightcnnandensemblemachinelearningclassificationofprostatetissueusingmultilevelfeatureanalysis AT deekshithaprakash efficientlightweightcnnandensemblemachinelearningclassificationofprostatetissueusingmultilevelfeatureanalysis AT hyeongyunpark efficientlightweightcnnandensemblemachinelearningclassificationofprostatetissueusingmultilevelfeatureanalysis AT namhooncho efficientlightweightcnnandensemblemachinelearningclassificationofprostatetissueusingmultilevelfeatureanalysis AT heungkookchoi efficientlightweightcnnandensemblemachinelearningclassificationofprostatetissueusingmultilevelfeatureanalysis |