Chunfeng Lian

An evidential classifier based on feature selection and two-step classification strategy

In this paper, we investigate ways to learn efficiently from uncertain data using belief functions. In order to extract more knowledge from imperfect and insufficient information and to improve classification accuracy, we propose a supervised learning method composed of a feature selection procedure and a two-step classification strategy. Using training information, the proposed feature selection procedure automatically determines the most informative feature subset by minimizing an objective function. The proposed two-step classification strategy further improves the decision-making accuracy by using complementary information obtained during the classification process. The performance of the proposed method was evaluated on various synthetic and real datasets. A comparison with other classification methods is also presented. HighlightsA classifier is based on Belief Functions to tackle uncertain data.The classifier composed by feature selection and a two-step classification.A new combination rule to better represent data uncertainty.A new feature selection is based on minimizing uncertainty with sparse constraint.Two-step classification improving accuracy of decision making.

Selecting radiomic features from FDG-PET images for cancer treatment outcome prediction

As a vital task in cancer therapy, accurately predicting the treatment outcome is valuable for tailoring and adapting a treatment planning. To this end, multi-sources of information (radiomics, clinical characteristics, genomic expressions, etc) gathered before and during treatment are potentially profitable. In this paper, we propose such a prediction system primarily using radiomic features (e.g., texture features) extracted from FDG-PET images. The proposed system includes a feature selection method based on Dempster-Shafer theory, a powerful tool to deal with uncertain and imprecise information. It aims to improve the prediction accuracy, and reduce the imprecision and overlaps between different classes (treatment outcomes) in a selected feature subspace. Considering that training samples are often small-sized and imbalanced in our applications, a data balancing procedure and specified prior knowledge are taken into account to improve the reliability of the selected feature subsets. Finally, the Evidential K-NN (EK-NN) classifier is used with selected features to output prediction results. Our prediction system has been evaluated by synthetic and clinical datasets, consistently showing good performance.

Dissimilarity Metric Learning in the Belief Function Framework

The evidential K-nearest-neighbor (EK-NN) method provided a global treatment of imperfect knowledge regarding the class membership of training patterns. It has outperformed traditional K-NN rules in many applications, but still shares some of their basic limitations, e.g., 1) classification accuracy depends heavily on how to quantify the dissimilarity between different patterns and 2) no guarantee for satisfactory performance when training patterns contain unreliable (imprecise and/or uncertain) input features. In this paper, we propose to address these issues by learning a suitable metric, using a low-dimensional transformation of the input space, so as to maximize both the accuracy and efficiency of the EK-NN classification. To this end, a novel loss function to learn the dissimilarity metric is constructed. It consists of two terms: the first one quantifies the imprecision regarding the class membership of each training pattern, while, by means of feature selection, the second one controls the influence of unreliable input features on the output linear transformation. The proposed method has been compared with some other metric learning methods on several synthetic and real datasets. It consistently led to comparable performance with regard to testing accuracy and class structure visualization.

Dempster-Shafer Theory Based Feature Selection with Sparse Constraint for Outcome Prediction in Cancer Therapy

As a pivotal task in cancer therapy, outcome prediction is the foundation for tailoring and adapting a treatment planning. In this paper, we propose to use image features extracted from PET and clinical characteristics. Considering that both information sources are imprecise or noisy, a novel prediction model based on Dempster-Shafer theory is developed. Firstly, a specific loss function with sparse regularization is designed for learning an adaptive dissimilarity metric between feature vectors of labeled patients. Through minimizing this loss function, a linear low-dimensional transformation of the input features is then achieved; meanwhile, thanks to the sparse penalty, the influence of imprecise input features can also be reduced via feature selection. Finally, the learnt dissimilarity metric is used with the Evidential K-Nearest-Neighbor (EK-NN) classifier to predict the outcome. We evaluated the proposed method on two clinical data sets concerning to lung and esophageal tumors, showing good performance.

Spatial Evidential Clustering With Adaptive Distance Metric for Tumor Segmentation in FDG-PET Images

While the accurate delineation of tumor volumes in FDG-positron emission tomography (PET) is a vital task for diverse objectives in clinical oncology, noise and blur due to the imaging system make it a challenging work. In this paper, we propose to address the imprecision and noise inherent in PET using Dempster–Shafer theory, a powerful tool for modeling and reasoning with uncertain and/or imprecise information. Based on Dempster–Shafer theory, a novel evidential clustering algorithm is proposed and tailored for the tumor segmentation task in three-dimensional. For accurate clustering of PET voxels, each voxel is described not only by the single intensity value but also complementarily by textural features extracted from a patch surrounding the voxel. Considering that there are a large amount of textures without consensus regarding the most informative ones, and some of the extracted features are even unreliable due to the low-quality PET images, a specific procedure is included in the proposed clustering algorithm to adapt distance metric for properly representing the clustering distortions and the similarities between neighboring voxels. This integrated metric adaptation procedure will realize a low-dimensional transformation from the original space, and will limit the influence of unreliable inputs via feature selection. A Dempster–Shafer-theory-based spatial regularization is also proposed and included in the clustering algorithm, so as to effectively quantify the local homogeneity. The proposed method has been compared with other methods on the real-patient FDG-PET images, showing good performance.

Robust Cancer Treatment Outcome Prediction Dealing with Small-Sized and Imbalanced Data from FDG-PET Images

Accurately predicting the outcome of cancer therapy is valuable for tailoring and adapting treatment planning. To this end, features extracted from multi-sources of information (e.g., radiomics and clinical characteristics) are potentially profitable. While it is of great interest to select the most informative features from all available ones, small-sized and imbalanced dataset, as often encountered in the medical domain, is a crucial challenge hindering reliable and stable subset selection. We propose a prediction system primarily using radiomic features extracted from FDG-PET images. It incorporates a feature selection method based on Dempster-Shafer theory, a powerful tool for modeling and reasoning with uncertain and/or imprecise information. Utilizing a data rebalancing procedure and specified prior knowledge to enhance the reliability and robustness of selected feature subsets, the proposed method aims to reduce the imprecision and overlaps between different classes in the selected feature subspace, thus finally improving the prediction accuracy. It has been evaluated by two clinical datasets, showing good performance.

Outcome prediction in tumour therapy based on Dempster-Shafer theory

Outcome prediction plays a vital role in cancer treatment. It can help to update and optimize the treatment planning. In this paper, we aim to find discriminant features from both PET images and clinical characteristics, so as to predict the outcome of a treatment to adapt the therapy. As both information sources are imprecise, we propose a novel feature selection method based on Dempster-Shafer theory to tackle this problem. Then, a specific objective function with spar-sity constraint is developed to search for a feature subset that leads to increasing prediction performance and decreasing data imprecision simultaneously. Our approach was applied to two real data sets concerning to lung tumour et esophageal tumour, showing good performance.

Joint Feature Transformation and Selection Based on Dempster-Shafer Theory

In statistical pattern recognition, feature transformation attempts to change original feature space to a low-dimensional subspace, in which new created features are discriminative and non-redundant, thus improving the predictive power and generalization ability of subsequent classification models. Traditional transformation methods are not designed specifically for tackling data containing unreliable and noisy input features. To deal with these inputs, a new approach based on Dempster-Shafer Theory is proposed in this paper. A specific loss function is constructed to learn the transformation matrix, in which a sparsity term is included to realize joint feature selection during transformation, so as to limit the influence of unreliable input features on the output low-dimensional subspace. The proposed method has been evaluated by several synthetic and real datasets, showing good performance.

A deep Boltzmann machine-driven level set method for heart motion tracking using cine MRI images

HighlightsThe DBM needs small‐sized data set to train, but imposes strong modeling ability.A three‐layer DBM can capture both local and global properties of heart contours.An efficient layer‐wise block‐Gibbs sampling is used to infer heart shape priors.The DBM‐induced heart shape priors are used as constraints of DRLSE evolution. Graphical abstract Figure. No caption available. ABSTRACT Heart motion tracking for radiation therapy treatment planning can result in effective motion management strategies to minimize radiation‐induced cardiotoxicity. However, automatic heart motion tracking is challenging due to factors that include the complex spatial relationship between the heart and its neighboring structures, dynamic changes in heart shape, and limited image contrast, resolution, and volume coverage. In this study, we developed and evaluated a deep generative shape model‐driven level set method to address these challenges. The proposed heart motion tracking method makes use of a heart shape model that characterizes the statistical variations in heart shapes present in a training data set. This heart shape model was established by training a three‐layered deep Boltzmann machine (DBM) in order to characterize both local and global heart shape variations. During the tracking phase, a distance regularized level‐set evolution (DRLSE) method was applied to delineate the heart contour on each frame of a cine MRI image sequence. The trained shape model was embedded into the DRLSE method as a shape prior term to constrain an evolutional shape to reach the desired heart boundary. Frame‐by‐frame heart motion tracking was achieved by iteratively mapping the obtained heart contour for each frame to the next frame as a reliable initialization, and performing a level‐set evolution. The performance of the proposed motion tracking method was demonstrated using thirty‐eight coronal cine MRI image sequences.

Tumor delineation in FDG-PET images using a new evidential clustering algorithm with spatial regularization and adaptive distance metric

While accurate tumor delineation in FDG-PET is a vital task, noisy and blurring imaging system makes it a challenging work. In this paper, we propose to address this issue using the theory of belief functions, a powerful tool for modeling and reasoning with uncertain and/or imprecise information. An automatic segmentation method based on clustering is developed in 3-D, where, different from available methods, PET voxels are described not only by intensities but also complementally by features extracted from patches. Considering there are a large amount of features without consensus regarding the most informative ones, and some of them are even unreliable due to image quality, a specific procedure is adopted to adapt distance metric for properly representing clustering distortions and neighborhood similarities. A specific spatial regularization is also included in the clustering algorithm to effectively quantify local homogeneity. The proposed method has been evaluated by real-patient images, showing good performance.