Exploring the efficacy of multi-flavored feature extraction with radiomics and deep features for prostate cancer grading on mpMRI
Abstract Background The purpose of this study is to investigate the use of radiomics and deep features obtained from multiparametric magnetic resonance imaging (mpMRI) for grading prostate cancer. We propose a novel approach called multi-flavored feature extraction or tensor, which combines four mpM...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-11-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-023-01140-0 |
| _version_ | 1797451040203735040 |
|---|---|
| author | Hasan Khanfari Saeed Mehranfar Mohsen Cheki Mahmoud Mohammadi Sadr Samir Moniri Sahel Heydarheydari Seyed Masoud Rezaeijo |
| author_facet | Hasan Khanfari Saeed Mehranfar Mohsen Cheki Mahmoud Mohammadi Sadr Samir Moniri Sahel Heydarheydari Seyed Masoud Rezaeijo |
| author_sort | Hasan Khanfari |
| collection | DOAJ |
| description | Abstract Background The purpose of this study is to investigate the use of radiomics and deep features obtained from multiparametric magnetic resonance imaging (mpMRI) for grading prostate cancer. We propose a novel approach called multi-flavored feature extraction or tensor, which combines four mpMRI images using eight different fusion techniques to create 52 images or datasets for each patient. We evaluate the effectiveness of this approach in grading prostate cancer and compare it to traditional methods. Methods We used the PROSTATEx-2 dataset consisting of 111 patients’ images from T2W-transverse, T2W-sagittal, DWI, and ADC images. We used eight fusion techniques to merge T2W, DWI, and ADC images, namely Laplacian Pyramid, Ratio of the low-pass pyramid, Discrete Wavelet Transform, Dual-Tree Complex Wavelet Transform, Curvelet Transform, Wavelet Fusion, Weighted Fusion, and Principal Component Analysis. Prostate cancer images were manually segmented, and radiomics features were extracted using the Pyradiomics library in Python. We also used an Autoencoder for deep feature extraction. We used five different feature sets to train the classifiers: all radiomics features, all deep features, radiomics features linked with PCA, deep features linked with PCA, and a combination of radiomics and deep features. We processed the data, including balancing, standardization, PCA, correlation, and Least Absolute Shrinkage and Selection Operator (LASSO) regression. Finally, we used nine classifiers to classify different Gleason grades. Results Our results show that the SVM classifier with deep features linked with PCA achieved the most promising results, with an AUC of 0.94 and a balanced accuracy of 0.79. Logistic regression performed best when using only the deep features, with an AUC of 0.93 and balanced accuracy of 0.76. Gaussian Naive Bayes had lower performance compared to other classifiers, while KNN achieved high performance using deep features linked with PCA. Random Forest performed well with the combination of deep features and radiomics features, achieving an AUC of 0.94 and balanced accuracy of 0.76. The Voting classifiers showed higher performance when using only the deep features, with Voting 2 achieving the highest performance, with an AUC of 0.95 and balanced accuracy of 0.78. Conclusion Our study concludes that the proposed multi-flavored feature extraction or tensor approach using radiomics and deep features can be an effective method for grading prostate cancer. Our findings suggest that deep features may be more effective than radiomics features alone in accurately classifying prostate cancer. |
| first_indexed | 2024-03-09T14:49:13Z |
| format | Article |
| id | doaj.art-4b7273404f2c4cbdb4690c9b760b4736 |
| institution | Directory Open Access Journal |
| issn | 1471-2342 |
| language | English |
| last_indexed | 2024-03-09T14:49:13Z |
| publishDate | 2023-11-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj.art-4b7273404f2c4cbdb4690c9b760b47362023-11-26T14:35:12ZengBMCBMC Medical Imaging1471-23422023-11-0123111310.1186/s12880-023-01140-0Exploring the efficacy of multi-flavored feature extraction with radiomics and deep features for prostate cancer grading on mpMRIHasan Khanfari0Saeed Mehranfar1Mohsen Cheki2Mahmoud Mohammadi Sadr3Samir Moniri4Sahel Heydarheydari5Seyed Masoud Rezaeijo6Department of Mechanical Engineering, Petroleum University of TechnologyDepartment of Electrical Engineering, Amirkabir University of TechnologyDepartment of Medical Imaging and Radiation Sciences, Faculty of Paramedicine, Ahvaz Jundishapur University of Medical SciencesDepartment of Medical Physics, School of Medicine, Isfahan University of Medical SciencesDepartment of Medical Imaging and Radiation Sciences, Faculty of Paramedicine, Ahvaz Jundishapur University of Medical SciencesDepartment of Medical Imaging and Radiation Sciences, Faculty of Paramedicine, Ahvaz Jundishapur University of Medical SciencesDepartment of Medical Physics, Faculty of Medicine, Ahvaz Jundishapur University of Medical SciencesAbstract Background The purpose of this study is to investigate the use of radiomics and deep features obtained from multiparametric magnetic resonance imaging (mpMRI) for grading prostate cancer. We propose a novel approach called multi-flavored feature extraction or tensor, which combines four mpMRI images using eight different fusion techniques to create 52 images or datasets for each patient. We evaluate the effectiveness of this approach in grading prostate cancer and compare it to traditional methods. Methods We used the PROSTATEx-2 dataset consisting of 111 patients’ images from T2W-transverse, T2W-sagittal, DWI, and ADC images. We used eight fusion techniques to merge T2W, DWI, and ADC images, namely Laplacian Pyramid, Ratio of the low-pass pyramid, Discrete Wavelet Transform, Dual-Tree Complex Wavelet Transform, Curvelet Transform, Wavelet Fusion, Weighted Fusion, and Principal Component Analysis. Prostate cancer images were manually segmented, and radiomics features were extracted using the Pyradiomics library in Python. We also used an Autoencoder for deep feature extraction. We used five different feature sets to train the classifiers: all radiomics features, all deep features, radiomics features linked with PCA, deep features linked with PCA, and a combination of radiomics and deep features. We processed the data, including balancing, standardization, PCA, correlation, and Least Absolute Shrinkage and Selection Operator (LASSO) regression. Finally, we used nine classifiers to classify different Gleason grades. Results Our results show that the SVM classifier with deep features linked with PCA achieved the most promising results, with an AUC of 0.94 and a balanced accuracy of 0.79. Logistic regression performed best when using only the deep features, with an AUC of 0.93 and balanced accuracy of 0.76. Gaussian Naive Bayes had lower performance compared to other classifiers, while KNN achieved high performance using deep features linked with PCA. Random Forest performed well with the combination of deep features and radiomics features, achieving an AUC of 0.94 and balanced accuracy of 0.76. The Voting classifiers showed higher performance when using only the deep features, with Voting 2 achieving the highest performance, with an AUC of 0.95 and balanced accuracy of 0.78. Conclusion Our study concludes that the proposed multi-flavored feature extraction or tensor approach using radiomics and deep features can be an effective method for grading prostate cancer. Our findings suggest that deep features may be more effective than radiomics features alone in accurately classifying prostate cancer.https://doi.org/10.1186/s12880-023-01140-0Radiomics featuresDeep featuresGradingProstate cancermpMRI |
| spellingShingle | Hasan Khanfari Saeed Mehranfar Mohsen Cheki Mahmoud Mohammadi Sadr Samir Moniri Sahel Heydarheydari Seyed Masoud Rezaeijo Exploring the efficacy of multi-flavored feature extraction with radiomics and deep features for prostate cancer grading on mpMRI BMC Medical Imaging Radiomics features Deep features Grading Prostate cancer mpMRI |
| title | Exploring the efficacy of multi-flavored feature extraction with radiomics and deep features for prostate cancer grading on mpMRI |
| title_full | Exploring the efficacy of multi-flavored feature extraction with radiomics and deep features for prostate cancer grading on mpMRI |
| title_fullStr | Exploring the efficacy of multi-flavored feature extraction with radiomics and deep features for prostate cancer grading on mpMRI |
| title_full_unstemmed | Exploring the efficacy of multi-flavored feature extraction with radiomics and deep features for prostate cancer grading on mpMRI |
| title_short | Exploring the efficacy of multi-flavored feature extraction with radiomics and deep features for prostate cancer grading on mpMRI |
| title_sort | exploring the efficacy of multi flavored feature extraction with radiomics and deep features for prostate cancer grading on mpmri |
| topic | Radiomics features Deep features Grading Prostate cancer mpMRI |
| url | https://doi.org/10.1186/s12880-023-01140-0 |
| work_keys_str_mv | AT hasankhanfari exploringtheefficacyofmultiflavoredfeatureextractionwithradiomicsanddeepfeaturesforprostatecancergradingonmpmri AT saeedmehranfar exploringtheefficacyofmultiflavoredfeatureextractionwithradiomicsanddeepfeaturesforprostatecancergradingonmpmri AT mohsencheki exploringtheefficacyofmultiflavoredfeatureextractionwithradiomicsanddeepfeaturesforprostatecancergradingonmpmri AT mahmoudmohammadisadr exploringtheefficacyofmultiflavoredfeatureextractionwithradiomicsanddeepfeaturesforprostatecancergradingonmpmri AT samirmoniri exploringtheefficacyofmultiflavoredfeatureextractionwithradiomicsanddeepfeaturesforprostatecancergradingonmpmri AT sahelheydarheydari exploringtheefficacyofmultiflavoredfeatureextractionwithradiomicsanddeepfeaturesforprostatecancergradingonmpmri AT seyedmasoudrezaeijo exploringtheefficacyofmultiflavoredfeatureextractionwithradiomicsanddeepfeaturesforprostatecancergradingonmpmri |