PENet: Prior evidence deep neural network for bladder cancer staging.

Bladder cancer is a heterogeneous, complicated, and widespread illness with high rates of morbidity, death, and expense if not treated adequately. The accurate and exact stage of bladder cancer is fundamental for treatment choices and prognostic forecasts, as indicated by convincing evidence from randomized trials. The extraordinary capability of Deep Convolutional Neural Networks (DCNNs) to extract features is one of the primary advantages offered by these types of networks. DCNNs work well in numerous real clinical medical applications as it demands costly large-scale data annotation. However, a lack of background information hinders its effectiveness and interpretability. Clinicians identify the stage of a tumor by evaluating whether the tumor is muscle-invasive, as shown in images by the tumor's infiltration of the bladder wall. Incorporating this clinical knowledge in DCNN has the ability to enhance the performance of bladder cancer staging and bring the prediction into accordance with medical principles. Therefore, we introduce PENet, an innovative prior evidence deep neural network, for classifying MR images of bladder cancer staging in line with clinical knowledge. To do this, first, the degree to which the tumor has penetrated the bladder wall is measured to get prior distribution parameters of class probability called prior evidence. Second, we formulate the posterior distribution of class probability according to Bayesian Theorem. Last, we modify the loss function based on posterior distribution of class probability which parameters include both prior evidence and prediction evidence in the learning procedure. Our investigation reveals that the prediction error and the variance of PENet may be reduced by giving the network prior evidence that is consistent with the ground truth. Using MR image datasets, experiments show that PENet performs better than image-based DCNN algorithms for bladder cancer staging.

Combination of Transferable Classification With Multisource Domain Adaptation Based on Evidential Reasoning.

In applications of domain adaptation, there may exist multiple source domains, which can provide more or less complementary knowledge for pattern classification in the target domain. In order to improve the classification accuracy, a decision-level combination method is proposed for the multisource domain adaptation based on evidential reasoning. The classification results obtained from different source domains usually have different reliabilities/weights, which are calculated according to domain consistency. Therefore, the multiple classification results are discounted by the corresponding weights under belief functions framework, and then, Dempster's rule is employed to combine these discounted results. In order to reduce errors, a neighborhood-based cautious decision-making rule is developed to make the class decision depending on the combination result. The object is assigned to a singleton class if its neighborhoods can be (almost) correctly classified. Otherwise, it is cautiously committed to the disjunction of several possible classes. By doing this, we can well characterize the partial imprecision of classification and reduce the error risk as well. A unified utility value is defined here to reflect the benefit of such classification. This cautious decision-making rule can achieve the maximum unified utility value because partial imprecision is considered better than an error. Several real data sets are used to test the performance of the proposed method, and the experimental results show that our new method can efficiently improve the classification accuracy with respect to other related combination methods.

Joint Tumor Segmentation in PET-CT Images Using Co-Clustering and Fusion Based on Belief Functions.

Precise delineation of target tumor is a key factor to ensure the effectiveness of radiation therapy. While hybrid positron emission tomography-computed tomography (PET-CT) has become a standard imaging tool in the practice of radiation oncology, many existing automatic/semi-automatic methods still perform tumor segmentation on mono-modal images. In this paper, a co-clustering algorithm is proposed to concurrently segment 3D tumors in PET-CT images, considering that the two complementary imaging modalities can combine functional and anatomical information to improve segmentation performance. The theory of belief functions is adopted in the proposed method to model, fuse, and reason with uncertain and imprecise knowledge from noisy and blurry PET-CT images. To ensure reliable segmentation for each modality, the distance metric for the quantification of clustering distortions and spatial smoothness is iteratively adapted during the clustering procedure. On the other hand, to encourage consistent segmentation between different modalities, a specific context term is proposed in the clustering objective function. Moreover, during the iterative optimization process, clustering results for the two distinct modalities are further adjusted via a belief-functions-based information fusion strategy. The proposed method has been evaluated on a data set consisting of 21 paired PET-CT images for non-small cell lung cancer patients. The quantitative and qualitative evaluations show that our proposed method performs well compared with the state-of-the-art methods.

Classification using belief functions: relationship between case-based and model-based approaches.

The transferable belief model (TBM) is a model to represent quantified uncertainties based on belief functions, unrelated to any underlying probability model. In this framework, two main approaches to pattern classification have been developed: the TBM model-based classifier, relying on the general Bayesian theorem (GBT), and the TBM case-based classifier, built on the concept of similarity of a pattern to be classified with training patterns. Until now, these two methods seemed unrelated, and their connection with standard classification methods was unclear. This paper shows that both methods actually proceed from the same underlying principle, i.e., the GBT, and that they essentially differ by the nature of the assumed available information. This paper also shows that both methods collapse to a kernel rule in the case of precise and categorical learning data and for certain initial assumptions, and a simple relationship between basic belief assignments produced by the two methods is exhibited in a special case. These results shed new light on the issues of classification and supervised learning in the TBM. They also suggest new research directions and may help users in selecting the most appropriate method for each particular application, depending on the nature of the information at hand.

EVCLUS: evidential clustering of proximity data.

A new relational clustering method is introduced, based on the Dempster-Shafer theory of belief functions (or evidence theory). Given a matrix of dissimilarities between n objects, this method, referred to as evidential clustering (EVCLUS), assigns a basic belief assignment (or mass function) to each object in such a way that the degree of conflict between the masses given to any two objects reflects their dissimilarity. A notion of credal partition is introduced, which subsumes those of hard, fuzzy, and possibilistic partitions, allowing to gain deeper insight into the structure of the data. Experiments with several sets of real data demonstrate the good performances of the proposed method as compared with several state-of-the-art relational clustering techniques.

Neural networks for process control and optimization: two industrial applications.

The two most widely used neural models, multilayer perceptron (MLP) and radial basis function network (RBFN), are presented in the framework of system identification and control. The main steps for building such nonlinear black box models are regressor choice, selection of internal architecture, and parameter estimation. The advantages of neural network models are summarized: universal approximation capabilities, flexibility, and parsimony. Two applications are described in steel industry and water treatment, respectively, the control of alloying process in a hot dipped galvanizing line and the control of a coagulation process in a drinking water treatment plant. These examples highlight the interest of neural techniques, when complex nonlinear phenomena are involved, but the empirical knowledge of control operators can be learned.