Machine learning-based radiomic models to predict intensity-modulated radiation therapy response, Gleason score and stage in prostate cancer

Abdollahi, Hamid; Mofid, Bahram; Shiri, Isaac; Razzaghdoust, Abolfazl; Saadipoor, Afshin; Mahdavi, Arash; Galandooz, Hassan Maleki; Mahdavi, Seied Rabi

doi:10.1007/s11547-018-0966-4

Cited by 96 publications

(65 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Radiomics is a new era of science which faces many challenges, including image acquisition (22), reconstruction (23,24), processing (25), and model development (26,27) to provide robust and reproducible models. Previous studies have shown that the radiomics signature is valuable for differentiating high/low grade ccRCC tumors (28,29).…”

Section: Introductionmentioning

confidence: 99%

Noninvasive Fuhrman grading of clear cell renal cell carcinoma using computed tomography radiomic features and machine learning

et al. 2020

Self Cite

View full text Add to dashboard Cite

To identify optimal classification methods for computed tomography (CT) radiomicsbased preoperative prediction of clear cells renal cell carcinoma (ccRCC) grade.Methods and material: Seventy-one ccRCC patients (31 low-grade and 40 high-grade) were included in the study. All tumors were segmented manually on CT images, and three image preprocessing techniques (Laplacian of Gaussian, wavelet filter, and discretization of the intensity values) were applied on tumor volumes. In total, 2530 radiomics features (tumor shape and size, intensity statistics, and texture) were extracted from each segmented tumor volume. Univariate analysis was performed to assess the association of each feature with the histological condition. In the case of multivariate analysis, the following was implemented: three feature selection including the least absolute shrinkage and selection operator (LASSO), student's t-test and minimum Redundancy Maximum Relevance (mRMR) algorithms. These selected features were then used to construct three classification models (SVM, random forest, and logistic regression) to discriminate the high from low-grade ccRCC at nephrectomy. Lastly, multivariate model performance was evaluated on the bootstrapped validation cohort using the area under receiver operating characteristic curve (AUC).Results: Univariate analysis demonstrated that among different image sets, 128 bin discretized images have statistically significant different (q-value < 0.05) texture parameters with a mean of AUC 0.74±3 (q-value < 0.05). The three ML-based classifier shows proficient discrimination of the high from low-grade ccRCC. The AUC was 0.78 in logistic regression, 0.62 in random forest, and 0.83 in SVM model, respectively. Conclusion:Radiomics features can be a useful and promising non-invasive method for preoperative evaluation of ccRCC Fuhrman grades.

show abstract

Section: Introductionmentioning

confidence: 99%

Noninvasive Fuhrman grading of clear cell renal cell carcinoma using computed tomography radiomic features and machine learning

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Machine learning (ML) is a subset of AI, providing a promising tool for the development of diagnostic, prognostic and predictive modelling tools from multimodality medical image data [19,20]. The combination of image-derived features and ML algorithms are used to build more accurate models in the era of precision medicine [21]. It is hypothesized that conventional diagnostic methods of many diseases could be replaced by ML radiomics in the future.…”

Section: Introductionmentioning

confidence: 99%

Radiomics for classification of bone mineral loss: A machine learning study

Rastegar

Vaziri

Qasempour

et al. 2020

Diagnostic and Interventional Imaging

View full text Add to dashboard Cite

show abstract

“…Additionally, the impact of MR image pre-processing and combining regions with differing MLs on the prediction of tumor MGMT mutation status was evaluated. However, this field lacks a comprehensive guideline for the optimal usage of robots features (39)(40)(41), classifiers (14). Therefore, this study attempted to determine the best classifier and feature selector for such investigations.…”

Section: Discussionmentioning

confidence: 99%

Noninvasive O6 Methylguanine-DNA Methyltransferase Status Prediction in Glioblastoma Multiforme Cancer Using Magnetic Resonance Imaging Radiomics Features: Univariate and Multivariate Radiogenomics Analysis

et al. 2019

Self Cite

View full text Add to dashboard Cite

Background and aim:This study aimed to predict methylation status of the O-6 methyl guanine-DNA methyl transferase (MGMT) gene promoter status by using MRI radiomics features, as well as univariate and multivariate analysis. Material and Methods:Eighty-two patients who had a MGMT methylation status were include in this study. Tumor were manually segmented in the four regions of MR images, a) whole tumor, b) active/enhanced region, c) necrotic regions and d) edema regions (E). About seven thousand radiomics features were extracted for each patient. Feature selection and classifier were used to predict MGMT status through different machine learning algorithms. The area under the curve (AUC) of receiver operating characteristic (ROC) curve was used for model evaluations. Results:Regarding univariate analysis, the Inverse Variance feature from gray level co-occurrence matrix (GLCM) in Whole Tumor segment with 4.5 mm Sigma of Laplacian of Gaussian filter with AUC: 0.71 (p-value: 0.002) was found to be the best predictor. For multivariate analysis, the decision tree classifier with Select from Model feature selector and LOG filter in Edema region had the highest performance (AUC: 0.78), followed by Ada Boost classifier with Select from Model feature selector and LOG filter in Edema region (AUC: 0.74). Conclusion:This study showed that radiomics using machine learning algorithms is a feasible, noninvasive approach to predict MGMT methylation status in GBM cancer patients

show abstract

Machine learning-based radiomic models to predict intensity-modulated radiation therapy response, Gleason score and stage in prostate cancer

Cited by 96 publications

References 44 publications

Noninvasive Fuhrman grading of clear cell renal cell carcinoma using computed tomography radiomic features and machine learning

Noninvasive Fuhrman grading of clear cell renal cell carcinoma using computed tomography radiomic features and machine learning

Radiomics for classification of bone mineral loss: A machine learning study

Noninvasive O6 Methylguanine-DNA Methyltransferase Status Prediction in Glioblastoma Multiforme Cancer Using Magnetic Resonance Imaging Radiomics Features: Univariate and Multivariate Radiogenomics Analysis

Contact Info

Product

Resources

About