Computer-assisted framework for machine-learning–based delineation of GTV regions on datasets of planning CT and PET/CT images

Abstract We have proposed a computer-assisted framework for machine-learning–based delineation of gross tumor volumes (GTVs) following an optimum contour selection (OCS) method. The key idea of the proposed framework was to feed image features around GTV contours (determined based on the knowledge of radiation oncologists) into a machine-learning classifier during the training step, after which the classifier produces the ‘degree of GTV’ for each voxel in the testing step. Initial GTV regions were extracted using a support vector machine (SVM) that learned the image features inside and outside each tumor region (determined by radiation oncologists). The leave-one-out-by-patient test was employed for training and testing the steps of the proposed framework. The final GTV regions were determined using the OCS method that can be used to select a global optimum object contour based on multiple active delineations with a LSM around the GTV. The efficacy of the proposed framework was evaluated in 14 lung cancer cases [solid: 6, ground-glass opacity (GGO): 4, mixed GGO: 4] using the 3D Dice similarity coefficient (DSC), which denotes the degree of region similarity between the GTVs contoured by radiation oncologists and those determined using the proposed framework. The proposed framework achieved an average DSC of 0.777 for 14 cases, whereas the OCS-based framework produced an average DSC of 0.507. The average DSCs for GGO and mixed GGO were 0.763 and 0.701, respectively, obtained by the proposed framework. The proposed framework can be employed as a tool to assist radiation oncologists in delineating various GTV regions.

Download Full-text

Value of radiomics in differential diagnosis of chromophobe renal cell carcinoma and renal oncocytoma

Abdominal Radiology ◽

10.1007/s00261-019-02269-9 ◽

2019 ◽

Vol 45 (10) ◽

pp. 3193-3201 ◽

Cited By ~ 3

Author(s):

Yajuan Li ◽

Xialing Huang ◽

Yuwei Xia ◽

Liling Long

Keyword(s):

Machine Learning ◽

Differential Diagnosis ◽

Cell Carcinoma ◽

Area Under The Curve ◽

Image Features ◽

Renal Tumors ◽

Support Vector ◽

Svm Classifier ◽

Renal Oncocytoma ◽

Lasso Regression

Abstract Purpose To explore the value of CT-enhanced quantitative features combined with machine learning for differential diagnosis of renal chromophobe cell carcinoma (chRCC) and renal oncocytoma (RO). Methods Sixty-one cases of renal tumors (chRCC = 44; RO = 17) that were pathologically confirmed at our hospital between 2008 and 2018 were retrospectively analyzed. All patients had undergone preoperative enhanced CT scans including the corticomedullary (CMP), nephrographic (NP), and excretory phases (EP) of contrast enhancement. Volumes of interest (VOIs), including lesions on the images, were manually delineated using the RadCloud platform. A LASSO regression algorithm was used to screen the image features extracted from all VOIs. Five machine learning classifications were trained to distinguish chRCC from RO by using a fivefold cross-validation strategy. The performance of the classifier was mainly evaluated by areas under the receiver operating characteristic (ROC) curve and accuracy. Results In total, 1029 features were extracted from CMP, NP, and EP. The LASSO regression algorithm was used to screen out the four, four, and six best features, respectively, and eight features were selected when CMP and NP were combined. All five classifiers had good diagnostic performance, with area under the curve (AUC) values greater than 0.850, and support vector machine (SVM) classifier showed a diagnostic accuracy of 0.945 (AUC 0.964 ± 0.054; sensitivity 0.999; specificity 0.800), showing the best performance. Conclusions Accurate preoperative differential diagnosis of chRCC and RO can be facilitated by a combination of CT-enhanced quantitative features and machine learning.

Download Full-text

Impacts of multicollinearity on CAPT modalities: An heterogeneous machine learning framework for computer-assisted French phoneme pronunciation training

PLoS ONE ◽

10.1371/journal.pone.0257901 ◽

2021 ◽

Vol 16 (10) ◽

pp. e0257901

Author(s):

Yanjing Bi ◽

Chao Li ◽

Yannick Benezeth ◽

Fan Yang

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Support Vector Machines ◽

Partial Least Square ◽

Least Square ◽

Support Vector ◽

Computer Assisted ◽

Long Distance ◽

Relationship Analysis ◽

Vector Machines

Phoneme pronunciations are usually considered as basic skills for learning a foreign language. Practicing the pronunciations in a computer-assisted way is helpful in a self-directed or long-distance learning environment. Recent researches indicate that machine learning is a promising method to build high-performance computer-assisted pronunciation training modalities. Many data-driven classifying models, such as support vector machines, back-propagation networks, deep neural networks and convolutional neural networks, are increasingly widely used for it. Yet, the acoustic waveforms of phoneme are essentially modulated from the base vibrations of vocal cords, and this fact somehow makes the predictors collinear, distorting the classifying models. A commonly-used solution to address this issue is to suppressing the collinearity of predictors via partial least square regressing algorithm. It allows to obtain high-quality predictor weighting results via predictor relationship analysis. However, as a linear regressor, the classifiers of this type possess very simple topology structures, constraining the universality of the regressors. For this issue, this paper presents an heterogeneous phoneme recognition framework which can further benefit the phoneme pronunciation diagnostic tasks by combining the partial least square with support vector machines. A French phoneme data set containing 4830 samples is established for the evaluation experiments. The experiments of this paper demonstrates that the new method improves the accuracy performance of the phoneme classifiers by 0.21 − 8.47% comparing to state-of-the-arts with different data training data density.

Download Full-text

Computer Vision Classification of Barley Flour Based on Spatial Pyramid Partition Ensemble

Sensors ◽

10.3390/s19132953 ◽

2019 ◽

Vol 19 (13) ◽

pp. 2953 ◽

Cited By ~ 6

Author(s):

Jessica Fernandes Lopes ◽

Leniza Ludwig ◽

Douglas Fernandes Barbin ◽

Maria Victória Eiras Grossmann ◽

Sylvio Barbon

Keyword(s):

Machine Learning ◽

Computer Vision ◽

Image Features ◽

Machine Learning Algorithms ◽

Support Vector ◽

Human Consumption ◽

Barley Flour ◽

Quality Aspects ◽

Spatial Pyramid

Imaging sensors are largely employed in the food processing industry for quality control. Flour from malting barley varieties is a valuable ingredient in the food industry, but its use is restricted due to quality aspects such as color variations and the presence of husk fragments. On the other hand, naked varieties present superior quality with better visual appearance and nutritional composition for human consumption. Computer Vision Systems (CVS) can provide an automatic and precise classification of samples, but identification of grain and flour characteristics require more specialized methods. In this paper, we propose CVS combined with the Spatial Pyramid Partition ensemble (SPPe) technique to distinguish between naked and malting types of twenty-two flour varieties using image features and machine learning. SPPe leverages the analysis of patterns from different spatial regions, providing more reliable classification. Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), J48 decision tree, and Random Forest (RF) were compared for samples’ classification. Machine learning algorithms embedded in the CVS were induced based on 55 image features. The results ranged from 75.00% (k-NN) to 100.00% (J48) accuracy, showing that sample assessment by CVS with SPPe was highly accurate, representing a potential technique for automatic barley flour classification.

Download Full-text

Comparative Analysis of Machine Learning Algorithms for Computer-Assisted Reporting Based on Fully Automated Cross-Lingual RadLex® Mappings

10.20944/preprints202004.0354.v1 ◽

2020 ◽

Author(s):

Máté E. Maros ◽

Chang Gyu Cho ◽

Andreas G. Junge ◽

Benedikt Kämpgen ◽

Victor Saase ◽

...

Keyword(s):

Machine Learning ◽

Language Processing ◽

Confusion Matrix ◽

Imbalanced Data ◽

Machine Learning Algorithms ◽

Imaging Biomarkers ◽

Brier Score ◽

Support Vector ◽

Computer Assisted ◽

Cross Lingual

Objectives: Studies evaluating machine learning (ML) algorithms on cross-lingual RadLex® mappings for developing context-sensitive radiological reporting tools are lacking. Therefore, we investigated whether ML-based approaches can be utilized to assist radiologists in providing key imaging biomarkers – such as The Alberta stroke programme early CT score (APECTS). Material and Methods: A stratified random sample (age, gender, year) of CT reports (n=206) with suspected ischemic stroke was generated out of 3997 reports signed off between 2015-2019. Three independent, blinded readers assessed these reports and manually annotated clinico-radiologically relevant key features. The primary outcome was whether ASPECTS should have been provided (yes/no: 154/52). For all reports, both the findings and impressions underwent cross-lingual (German to English) RadLex®-mappings using natural language processing. Well-established ML-algorithms including classification trees, random forests, elastic net, support vector machines (SVMs) and boosted trees were evaluated in a 5 x 5-fold nested cross-validation framework. Further, a linear classifier (fastText) was directly fitted on the German reports. Ensemble learning was used to provide robust importance rankings of these ML-algorithms. Performance was evaluated using derivates of the confusion matrix and metrics of calibration including AUC, brier score and log loss as well as visually by calibration plots. Results: On this imbalanced classification task SVMs showed the highest accuracies both on human-extracted- (87%) and fully automated RadLex® features (findings: 82.5%; impressions: 85.4%). FastText without pre-trained language model showed the highest accuracy (89.3%) and AUC (92%) on the impressions. Ensemble learner revealed that boosted trees, fastText and SVMs are the most important ML-classifiers. Boosted trees fitted on the findings showed the best overall calibration curve. Conclusions: Contextual ML-based assistance suggesting ASPECTS while reporting neuroradiological emergencies is feasible, even if ML-models are restricted to be developed on limited and highly imbalanced data sets.

Download Full-text

A Survey and Analysis of Extreme Machine Learning Models and Its Techniques

10.21203/rs.3.rs-599856/v1 ◽

2021 ◽

Author(s):

Shubhangi Pande ◽

Neeraj Kumar Rathore ◽

Anuradha Purohit

Keyword(s):

Neural Network ◽

Machine Learning ◽

Support Vector Machine ◽

Learning Algorithm ◽

Feature Learning ◽

Global Optimum ◽

Least Square ◽

Support Vector ◽

Feed Forward Neural Network ◽

Feed Forward

Abstract Machine learning applications employ FFNN (Feed Forward Neural Network) in their discipline enormously. But, it has been observed that the FFNN requisite speed is not up the mark. The fundamental causes of this problem are: 1) for training neural networks, slow gradient descent methods are broadly used and 2) for such methods, there is a need for iteratively tuning hidden layer parameters including biases and weights. To resolve these problems, a new emanant machine learning algorithm, which is a substitution of the feed-forward neural network, entitled as Extreme Learning Machine (ELM) introduced in this paper. ELM also come up with a general learning scheme for the immense diversity of different networks (SLFNs and multilayer networks). According to ELM originators, the learning capacity of networks trained using backpropagation is a thousand times slower than the networks trained using ELM, along with this, ELM models exhibit good generalization performance. ELM is more efficient in contradiction of Least Square Support Vector Machine (LS-SVM), Support Vector Machine (SVM), and rest of the precocious approaches. ELM’s eccentric outline has three main targets: 1) high learning accuracy 2) less human intervention 3) fast learning speed. ELM consider as a greater capacity to achieve global optimum. The distribution of application of ELM incorporates: feature learning, clustering, regression, compression, and classification. With this paper, our goal is to familiarize various ELM variants, their applications, ELM strengths, ELM researches and comparison with other learning algorithms, and many more concepts related to ELM.

Download Full-text

An Analysis of Extreme Machine Learning Models

10.21203/rs.3.rs-667827/v1 ◽

2021 ◽

Author(s):

Shubhangi Pande ◽

Neeraj Rathore ◽

Anuradha Purohit

Keyword(s):

Neural Network ◽

Machine Learning ◽

Support Vector Machine ◽

Learning Algorithm ◽

Feature Learning ◽

Global Optimum ◽

Least Square ◽

Support Vector ◽

Feed Forward Neural Network ◽

Feed Forward

Download Full-text

Camera-based Water Stage and Discharge Prediction with Machine Learning

10.5194/hess-2020-575 ◽

2020 ◽

Author(s):

Kenneth W. Chapman ◽

Troy E. Gilmore ◽

Christian D. Chapman ◽

Mehrube Mehrubeoglu ◽

Aaron R. Mittelstet

Keyword(s):

Machine Learning ◽

Time Lapse ◽

Image Features ◽

Support Vector ◽

Learning Models ◽

Discharge Data ◽

Data Gaps ◽

Test Sets ◽

Machine Learning Models ◽

Training Sets

Abstract. Time-lapse imagery of streams and rivers provide new qualitative insights into hydrologic conditions at stream gauges, especially when site visits are biased toward baseflow or fair-weather conditions. Imagery from fixed, ground-based cameras is also rich in quantitative information that can improve streamflow monitoring. For instance, time-lapse imagery may be valuable for filling data gaps when sensors fail and/or during lapses in funding for monitoring programs. In this study, we automated the analysis of time-lapse imagery from a single camera at a single location, then built and tested machine learning models using programmatically calculable scalar image features to fill data gaps in stream gauge records. Time-lapse images were taken with a fixed, ground-based camera that is part of a documentary watershed imaging project (https://plattebasintimelapse.com/). Features were extracted from 40,000+ daylight images taken at one-hour intervals from 2012 to 2019. The algorithms removed dawn and dusk images that were too dark for feature extraction. The image features were merged with United States Geological Survey (USGS) stage and discharge data (i.e., response variables) from the site based on image capture times and USGS timestamps. We then developed a workflow to identify a suitable feature set to build machine learning models with a randomly selected training set of 30 % of the images with the remaining 70 % for a test set. Predictions were generated from Multi-layer Perceptron (MLP), Random Forest Regression (RFR), and Support Vector Regression (SVR) models. A Kalman filter was applied to the predictions to remove noise. Error metrics were calculated, including Nash-Sutcliffe Efficiency (NSE), Prediction Bias (PBIAS), RMSE-Standard Deviation Ratio (RSR), and an alternative metric that accounted for seasonal runoff. After suitable features were identified, the dataset was divided into test sets of simulated data gaps for 2015, 2016, and 2017. The training sets for each gap were features from contiguous images and sensor readings before and after the gaps. NSE for the year-long gap predictions ranged from 0.63 to 0.90 for discharge and 0.47 to 0.90 for stage. The predictions for 2015 and 2017 displayed lower prediction errors than for 2016. The 2016 discharge was significantly higher than training data, which could explain the poorer performance. First and second half-year test sets were created for 2016 along with MLP models from before/after training sets for each of the gaps that held discharge measurements similar to those in the gaps. The half-year gap models' predictions improved NSE, PBIAS and RSR. The results show it is possible to extract features from images taken with the downstream facing camera to build machine learning models that produce accurate stage and discharge predictions. The methods employed should be transferrable to other sites with ground-based cameras.

Download Full-text

A rainfall forecasting method using machine learning models and its application to the Fukuoka city case

International Journal of Applied Mathematics and Computer Science ◽

10.2478/v10006-012-0062-1 ◽

2012 ◽

Vol 22 (4) ◽

pp. 841-854 ◽

Cited By ~ 33

Author(s):

S. Monira Sumi ◽

M. Faisal Zaman ◽

Hideo Hirose

Keyword(s):

Machine Learning ◽

Moving Average ◽

Principal Component ◽

Processing Technique ◽

Monthly Rainfall ◽

Multivariate Adaptive Regression Splines ◽

Support Vector ◽

Rainfall Forecasting ◽

Cross Validation Error ◽

Leave One Out

In the present article, an attempt is made to derive optimal data-driven machine learning methods for forecasting an average daily and monthly rainfall of the Fukuoka city in Japan. This comparative study is conducted concentrating on three aspects: modelling inputs, modelling methods and pre-processing techniques. A comparison between linear correlation analysis and average mutual information is made to find an optimal input technique. For the modelling of the rainfall, a novel hybrid multi-model method is proposed and compared with its constituent models. The models include the artificial neural network, multivariate adaptive regression splines, the k-nearest neighbour, and radial basis support vector regression. Each of these methods is applied to model the daily and monthly rainfall, coupled with a pre-processing technique including moving average and principal component analysis. In the first stage of the hybrid method, sub-models from each of the above methods are constructed with different parameter settings. In the second stage, the sub-models are ranked with a variable selection technique and the higher ranked models are selected based on the leave-one-out cross-validation error. The forecasting of the hybrid model is performed by the weighted combination of the finally selected models.

Download Full-text

Intelligent Identification for Rock-Mineral Microscopic Images Using Ensemble Machine Learning Algorithms

Sensors ◽

10.3390/s19183914 ◽

2019 ◽

Vol 19 (18) ◽

pp. 3914 ◽

Cited By ~ 2

Author(s):

Ye Zhang ◽

Mingchao Li ◽

Shuai Han ◽

Qiubing Ren ◽

Jonathan Shi

Keyword(s):

Machine Learning ◽

Model Performance ◽

Image Features ◽

Machine Learning Algorithms ◽

Support Vector ◽

K Nearest Neighbors ◽

Microscopic Images ◽

Rock Mineral ◽

Ensemble Machine Learning ◽

Significant Performance

It is significant to identify rock-mineral microscopic images in geological engineering. The task of microscopic mineral image identification, which is often conducted in the lab, is tedious and time-consuming. Deep learning and convolutional neural networks (CNNs) provide a method to analyze mineral microscopic images efficiently and smartly. In this research, the transfer learning model of mineral microscopic images is established based on Inception-v3 architecture. The four mineral image features, including K-feldspar (Kf), perthite (Pe), plagioclase (Pl), and quartz (Qz or Q), are extracted using Inception-v3. Based on the features, the machine learning methods, logistic regression (LR), support vector machine (SVM), random forest (RF), k-nearest neighbors (KNN), multilayer perceptron (MLP), and gaussian naive Bayes (GNB), are adopted to establish the identification models. The results are evaluated using 10-fold cross-validation. LR, SVM, and MLP have a significant performance among all the models, with accuracy of about 90.0%. The evaluation result shows LR, SVM, and MLP are the outstanding single models in high-dimensional feature analysis. The three models are also selected as the base models in model stacking. The LR model is also set as the meta classifier in the final prediction. The stacking model can achieve 90.9% accuracy, which is higher than all the single models. The result also shows that model stacking effectively improves model performance.

Download Full-text

Machine Learning and Feature Selection Methods for EGFR Mutation Status Prediction in Lung Cancer

Applied Sciences ◽

10.3390/app11073273 ◽

2021 ◽

Vol 11 (7) ◽

pp. 3273

Author(s):

Joana Morgado ◽

Tania Pereira ◽

Francisco Silva ◽

Cláudia Freitas ◽

Eduardo Negrão ◽

...

Keyword(s):

Machine Learning ◽

Lung Cancer ◽

Feature Selection ◽

Egfr Mutation ◽

Feature Selection Method ◽

Principal Component ◽

Image Features ◽

Support Vector ◽

Selection Methods ◽

Mutation Status

The evolution of personalized medicine has changed the therapeutic strategy from classical chemotherapy and radiotherapy to a genetic modification targeted therapy, and although biopsy is the traditional method to genetically characterize lung cancer tumor, it is an invasive and painful procedure for the patient. Nodule image features extracted from computed tomography (CT) scans have been used to create machine learning models that predict gene mutation status in a noninvasive, fast, and easy-to-use manner. However, recent studies have shown that radiomic features extracted from an extended region of interest (ROI) beyond the tumor, might be more relevant to predict the mutation status in lung cancer, and consequently may be used to significantly decrease the mortality rate of patients battling this condition. In this work, we investigated the relation between image phenotypes and the mutation status of Epidermal Growth Factor Receptor (EGFR), the most frequently mutated gene in lung cancer with several approved targeted-therapies, using radiomic features extracted from the lung containing the nodule. A variety of linear, nonlinear, and ensemble predictive classification models, along with several feature selection methods, were used to classify the binary outcome of wild-type or mutant EGFR mutation status. The results show that a comprehensive approach using a ROI that included the lung with nodule can capture relevant information and successfully predict the EGFR mutation status with increased performance compared to local nodule analyses. Linear Support Vector Machine, Elastic Net, and Logistic Regression, combined with the Principal Component Analysis feature selection method implemented with 70% of variance in the feature set, were the best-performing classifiers, reaching Area Under the Curve (AUC) values ranging from 0.725 to 0.737. This approach that exploits a holistic analysis indicates that information from more extensive regions of the lung containing the nodule allows a more complete lung cancer characterization and should be considered in future radiogenomic studies.

Download Full-text