Department of Mechanical Engineering, Petroleum University of Technology, Ahvaz, Iran.
Department of Electrical Engineering, Amirkabir University of Technology, Tehran, Iran.
BMC Med Imaging. 2023 Nov 22;23(1):195. doi: 10.1186/s12880-023-01140-0.
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.
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.
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.
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.
本研究旨在探讨利用多参数磁共振成像（mpMRI）的放射组学和深度学习特征对前列腺癌进行分级。我们提出了一种名为多风味特征提取或张量的新方法，该方法结合了四种 mpMRI 图像，使用八种不同的融合技术为每位患者创建 52 张图像或数据集。我们评估了这种方法在前列腺癌分级中的有效性，并将其与传统方法进行了比较。
我们使用了包含 111 名患者的 T2W-横断、T2W-矢状、DWI 和 ADC 图像的 PROSTATEx-2 数据集。我们使用八种融合技术融合 T2W、DWI 和 ADC 图像，分别是拉普拉斯金字塔、低通金字塔比、离散小波变换、双树复小波变换、Curvelet 变换、小波融合、加权融合和主成分分析。前列腺癌图像由手动分割，使用 Python 中的 Pyradiomics 库提取放射组学特征。我们还使用了自动编码器进行深度学习特征提取。我们使用了五个不同的特征集来训练分类器：所有放射组学特征、所有深度学习特征、与 PCA 相关联的放射组学特征、与 PCA 相关联的深度学习特征以及放射组学和深度学习特征的组合。我们对数据进行了处理，包括平衡、标准化、PCA、相关性和最小绝对收缩和选择算子（LASSO）回归。最后，我们使用九个分类器对不同的 Gleason 等级进行分类。
我们的结果表明，与 PCA 相关联的深度学习特征的 SVM 分类器取得了最有希望的结果，AUC 为 0.94，平衡准确率为 0.79。仅使用深度学习特征时，逻辑回归的表现最佳，AUC 为 0.93，平衡准确率为 0.76。与其他分类器相比，高斯朴素贝叶斯的性能较低，而 KNN 使用与 PCA 相关联的深度学习特征则表现出色。随机森林与深度学习特征和放射组学特征的组合表现良好，AUC 为 0.94，平衡准确率为 0.76。仅使用深度学习特征时，投票分类器的性能更高，其中投票 2 表现最佳，AUC 为 0.95，平衡准确率为 0.78。
我们的研究得出结论，使用放射组学和深度学习特征的提出的多风味特征提取或张量方法可以是一种有效的前列腺癌分级方法。我们的研究结果表明，在准确分类前列腺癌方面，深度学习特征可能比放射组学特征更有效。
