A machine learning-based sonomics for prediction of thyroid nodule malignancies

OBJECTIVES

This study aims to use ultrasound derived features as biomarkers to assess the malignancy of thyroid nodules in patients who were candidates for FNA according to the ACR TI-RADS guidelines.

METHODS

Two hundred and ten patients who met the selection criteria were enrolled in the study and subjected to ultrasound-guided FNA of thyroid nodules. Different radiomics features were extracted from sonographic images, including intensity, shape, and texture feature sets. Least Absolute Shrinkage and Selection Operator (LASSO), Minimum Redundancy Maximum Relevance (MRMR), and Random Forests/Extreme Gradient Boosting Machine (XGBoost) algorithms were used for feature selection and classification of the univariate and multivariate modeling, respectively. Evaluation of models performed using accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).

RESULTS

In the univariate analysis, Gray Level Run Length Matrix - Run-Length Non-Uniformity (GLRLM-RLNU) and gray-level zone length matrix - Run-Length Non-Uniformity (GLZLM-GLNU) (both with an AUC of 0.67) were top-performing for predicting nodules malignancy. In the multivariate analysis of the training dataset, the AUC of all combinations of feature selection algorithms and classifiers was 0.99, and the highest sensitivity was for XGBoost classifier and MRMR feature selection algorithms (0.99). Finally, the test dataset was used to evaluate our model in which XGBoost classifier with MRMR and LASSO feature selection algorithms had the highest performance (AUC = 0.95).

CONCLUSIONS

Ultrasound-extracted features can be used as non-invasive biomarkers for thyroid nodules' malignancy prediction.

COVID-19 prognostic modeling using CT radiomic features and machine learning algorithms: Analysis of a multi-institutional dataset of 14,339 patients

BACKGROUND

We aimed to analyze the prognostic power of CT-based radiomics models using data of 14,339 COVID-19 patients.

METHODS

Whole lung segmentations were performed automatically using a deep learning-based model to extract 107 intensity and texture radiomics features. We used four feature selection algorithms and seven classifiers. We evaluated the models using ten different splitting and cross-validation strategies, including non-harmonized and ComBat-harmonized datasets. The sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were reported.

RESULTS

In the test dataset (4,301) consisting of CT and/or RT-PCR positive cases, AUC, sensitivity, and specificity of 0.83 ± 0.01 (CI95%: 0.81-0.85), 0.81, and 0.72, respectively, were obtained by ANOVA feature selector + Random Forest (RF) classifier. Similar results were achieved in RT-PCR-only positive test sets (3,644). In ComBat harmonized dataset, Relief feature selector + RF classifier resulted in the highest performance of AUC, reaching 0.83 ± 0.01 (CI95%: 0.81-0.85), with a sensitivity and specificity of 0.77 and 0.74, respectively. ComBat harmonization did not depict statistically significant improvement compared to a non-harmonized dataset. In leave-one-center-out, the combination of ANOVA feature selector and RF classifier resulted in the highest performance.

CONCLUSION

Lung CT radiomics features can be used for robust prognostic modeling of COVID-19. The predictive power of the proposed CT radiomics model is more reliable when using a large multicentric heterogeneous dataset, and may be used prospectively in clinical setting to manage COVID-19 patients.

Ultra-low-dose chest CT imaging of COVID-19 patients using a deep residual neural network

OBJECTIVES

The current study aimed to design an ultra-low-dose CT examination protocol using a deep learning approach suitable for clinical diagnosis of COVID-19 patients.

METHODS

In this study, 800, 170, and 171 pairs of ultra-low-dose and full-dose CT images were used as input/output as training, test, and external validation set, respectively, to implement the full-dose prediction technique. A residual convolutional neural network was applied to generate full-dose from ultra-low-dose CT images. The quality of predicted CT images was assessed using root mean square error (RMSE), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR). Scores ranging from 1 to 5 were assigned reflecting subjective assessment of image quality and related COVID-19 features, including ground glass opacities (GGO), crazy paving (CP), consolidation (CS), nodular infiltrates (NI), bronchovascular thickening (BVT), and pleural effusion (PE).

RESULTS

The radiation dose in terms of CT dose index (CTDIvol) was reduced by up to 89%. The RMSE decreased from 0.16 ± 0.05 to 0.09 ± 0.02 and from 0.16 ± 0.06 to 0.08 ± 0.02 for the predicted compared with ultra-low-dose CT images in the test and external validation set, respectively. The overall scoring assigned by radiologists showed an acceptance rate of 4.72 ± 0.57 out of 5 for reference full-dose CT images, while ultra-low-dose CT images rated 2.78 ± 0.9. The predicted CT images using the deep learning algorithm achieved a score of 4.42 ± 0.8.

CONCLUSIONS

The results demonstrated that the deep learning algorithm is capable of predicting standard full-dose CT images with acceptable quality for the clinical diagnosis of COVID-19 positive patients with substantial radiation dose reduction.

KEY POINTS

• Ultra-low-dose CT imaging of COVID-19 patients would result in the loss of critical information about lesion types, which could potentially affect clinical diagnosis. • Deep learning-based prediction of full-dose from ultra-low-dose CT images for the diagnosis of COVID-19 could reduce the radiation dose by up to 89%. • Deep learning algorithms failed to recover the correct lesion structure/density for a number of patients considered outliers, and as such, further research and development is warranted to address these limitations.

Repeatability of radiomic features in magnetic resonance imaging of glioblastoma: Test-retest and image registration analyses

PURPOSE

To assess the repeatability of radiomic features in magnetic resonance (MR) imaging of glioblastoma (GBM) tumors with respect to test-retest, different image registration approaches and inhomogeneity bias field correction.

METHODS

We analyzed MR images of 17 GBM patients including T1- and T2-weighted images (performed within the same imaging unit on two consecutive days). For image segmentation, we used a comprehensive segmentation approach including entire tumor, active area of tumor, necrotic regions in T1-weighted images, and edema regions in T2-weighted images (test studies only; registration to retest studies is discussed next). Analysis included N3, N4 as well as no bias correction performed on raw MR images. We evaluated 20 image registration approaches, generated by cross-combination of four transformation and five cost function methods. In total, 714 images (17 patients × 2 images × ((4 transformations × 5 cost functions) + 1 test image) and 2856 segmentations (714 images × 4 segmentations) were prepared for feature extraction. Various radiomic features were extracted, including the use of preprocessing filters, specifically wavelet (WAV) and Laplacian of Gaussian (LOG), as well as discretization into fixed bin width and fixed bin count (16, 32, 64, 128, and 256), Exponential, Gradient, Logarithm, Square and Square Root scales. Intraclass correlation coefficients (ICC) were calculated to assess the repeatability of MRI radiomic features (high repeatability defined as ICC ≥ 95%).

RESULTS

In our ICC results, we observed high repeatability (ICC ≥ 95%) with respect to image preprocessing, different image registration algorithms, and test-retest analysis, for example: RLNU and GLNU from GLRLM, GLNU and DNU from GLDM, Coarseness and Busyness from NGTDM, GLNU and ZP from GLSZM, and Energy and RMS from first order. Highest fraction (percent) of repeatable features was observed, among registration techniques, for the method Full Affine transformation with 12 degrees of freedom using Mutual Information cost function (mean 32.4%), and among image processing methods, for the method Laplacian of Gaussian (LOG) with Sigma (2.5-4.5 mm) (mean 78.9%). The trends were relatively consistent for N4, N3, or no bias correction.

CONCLUSION

Our results showed varying performances in repeatability of MR radiomic features for GBM tumors due to test-retest and image registration. The findings have implications for appropriate usage in diagnostic and predictive models.

Prediction of Response to Neoadjuvant Chemoradiotherapy by MRI-Based Machine Learning Texture Analysis in Rectal Cancer Patients

INTRODUCTION

Neoadjuvant chemoradiotherapy (nCRT) followed by surgical resection is the standard treatment for locally advanced rectal cancer (LARC). Radiomics can be used as noninvasive biomarker for prediction of response to therapy. The main aim of this study was to evaluate the association of MRI texture features of LARC with nCRT response and the effect of Laplacian of Gaussian (LoG) filter and feature selection algorithm in prediction process improvement.

METHODS

All patients underwent MRI with a 3T clinical scanner, 1 week before nCRT. For each patient, intensity, shape, and texture-based features were derived from MRI images with LoG filter using the IBEX software and without preprocessing. We identified responder from a non-responder group using 9 machine learning classifiers. Then, the effect of preprocessing LoG filters with 0.5, 1 and 1.5 value on these classification algorithms' performance was investigated. Eventually, classification algorithm's results were compared in different feature selection methods.

RESULT

Sixty-seven patients with LARC were included in the study. Patients' nCRT responses included 11 patients with Grade 0, 19 with Grade 1, 26 with Grade 2, and 11 with Grade 3 according to AJCC/CAP pathologic grading. In MR Images which were not preprocessed, the best performance was for Ada boost classifier (AUC = 74.8) with T2W MR Images. In T1W MR Images, the best performance was for aba boost classifier (AUC = 78.1) with a σ = 1 preprocessing LoG filter. In T2W MR Images, the best performance was for naive Bayesian network classifier (AUC = 85.1) with a σ = 0.5 preprocessing LoG filter. Also, performance of machine learning models with CfsSubsetEval (CF SUB E) feature selection algorithm was better than others.

CONCLUSION

Machine learning can be used as a response predictor model in LARC patients, but its performance should be improved. A preprocessing LoG filter can improve the machine learning methods performance and at the end, the effect of feature selection algorithm on model's performance is clear.

Author Correction: Prediction of Response to Neoadjuvant Chemoradiotherapy by MRI-Based Machine Learning Texture Analysis in Rectal Cancer Patients

The original version of this article unfortunately contained a mistake. In the author group section, the correct name of the fourth author is "Reza Ghalehtaki." The authors apologize for this oversight and for any confusion it may have caused.

Neo-adjuvant chemoradiotherapy response prediction using MRI based ensemble learning method in rectal cancer patients

OBJECTIVES

The aim of this study was to investigate and validate the performance of individual and ensemble machine learning models (EMLMs) based on magnetic resonance imaging (MRI) to predict neo-adjuvant chemoradiation therapy (nCRT) response in rectal cancer patients. We also aimed to study the effect of Laplacian of Gaussian (LOG) filter on EMLMs predictive performance.

METHODS

98 rectal cancer patients were divided into a training (n = 53) and a validation set (n = 45). All patients underwent MRI a week before nCRT. Several features from intensity, shape and texture feature sets were extracted from MR images. SVM, Bayesian network, neural network and KNN classifiers were used individually and together for response prediction. Predictive performance was evaluated using the area under the receiver operator characteristic (ROC) curve (AUC).

RESULTS

Patients' nCRT responses included 17 patients with Grade 0, 28 with Grade 1, 34 with Grade 2, and 19 with Grade 3 according to AJCC/CAP pathologic grading. In without preprocessing MR Image the best result was for Bayesian network classifier with AUC and accuracy of 75.2% and 80.9% respectively, which was confirmed in the validation set with an AUC and accuracy of 74% and 79% respectively. In EMLMs the best result was for 4 (SVM.NN.BN.KNN) classifier EMLM with AUC and accuracy of 97.8% and 92.8% in testing and 95% and 90% in validation set respectively.

CONCLUSIONS

In conclusion, we observed that machine learning methods can used to predict nCRT response in patients with rectal cancer. Preprocessing LOG filters and EL models can improve the prediction process.