Medical Diagnosis Problems Research Articles

Multi-branch cross attention model for prediction of KRAS mutation in rectal cancer with t2-weighted MRI

The accurate identification of KRAS mutation status on medical images is critical for doctors to specify treatment options for patients with rectal cancer. Deep learning methods have recently been successfully introduced to medical diagnosis and treatment problems, although substantial challenges remain in the computer-aided diagnosis (CAD) due to the lack of large training datasets. In this paper, we propose a multi-branch cross attention model (MBCAM) to separate KRAS mutation cases from wild type cases using limited T2-weighted MRI data. Our model is built on multiple different branches generated based on our existing MRI data, which can take full advantage of the information contained in small data sets. The cross attention block (CA block) is proposed to fuse formerly independent branches to ensure that the model can learn as many common features as possible for preventing the overfitting of the model due to the limited dataset. The inter-branch loss is proposed to constrain the learning range of the model, confirming that the model can learn more general features from multi-branch data. We tested our method on the collected dataset and compared it to four previous works and five popular deep learning models using transfer learning. Our result shows that the MBCAM achieved an accuracy of 88.92% for the prediction of KRAS mutations with an AUC of 95.75%. These results are a significant improvement over those existing methods (p < 0.05).

A novel dice similarity measure for IFSs and its applications in pattern and face recognition

In the theory of Intuitionistic fuzzy set (IFS), similarity measure is an effective instrument to measure similarity between IFSs. In this paper, we mention limitations of various existing similarity measures and propose a novel dice similarity measure for IFSs. Proposed dice similarity measure is based on inner product and overcomes limitations of existing similarity measures. In order to show the suitability and applicability of proposed dice similarity measure, we implement it on various classification problems of pattern recognition and medical diagnosis. Experimental results show that this does not only overcome limitations of existing similarity measures but also outperforms in pattern recognition and medical diagnosis problems. In this paper, we also propose an algorithm for face recognition problem using proposed dice similarity measure. This algorithm is demonstrated by an example and performance is compared with few existing methods for face recognition problems.

Numbering and Classification of Panoramic Dental Images Using 6-Layer Convolutional Neural Network

Deep Convolution Neural Network is one of the most powerful tools to solve complex problems of image classification, image recognition, financial analysis, medical diagnosis and many similar problems. A dental panoramic image consists of collection of teeth of both upper jaw and lower jaw. Automatic classification of dental panoramic images into various tooth types such as canines, incisors, premolars and molars has been a challenging task and involves crucial role of an experienced dentist. In this paper, we propose a technique for numbering and classification of the panoramic dental images. The proposed algorithm consists of four stages namely pre-processing, segmentation, numbering and classification. The pre-processed panoramic dental images are segmented using fuzzy c-mean clustering and subjected to vertical integral projection to extract a single tooth. The image dataset consists of 400 dental panoramic images collected from various dental clinics. The 400 dental images are divided into 240 training samples and 160 testing samples. The image data set is augmented by applying various transformations. Panoramic dental images are further numbered using a universal dental numbering system. Finally, the classification is done with the help of 6-layer deep convolution neural network (DCNN) consisting of 3 convolutional neural network and 3 fully connected network. The tooth is classified as canine, incisor, molar and premolar. An accuracy of 95% has been achieved for augmented database and 92% for original dataset with the proposed algorithm. The proposed numbering and classification of dental panoramic images is useful in biomedical application and postmortem recording of dental records. In case of big calamity, the system can also assist the dentist in recording post mortem dental record that is a very lengthy and arduous task.

A soft set based VIKOR approach for some decision-making problems under complex neutrosophic environment

Applications in various fields of neutrosophic soft set theory enhance its appreciation to the researchers. Although, this uncertain solving tool can accomplish several types of real-life problems, but not able to deal with the decision-making problems in which considering an additional information of a corresponding parameter is needed to get a proper decision from a problem. But, complex neutrosophic soft sets can handle such type of decision-making problems. Consequently, in this study, we have given concentration on solving soft set based decision-making problems in the field of complex neutrosophic environment. Firstly, we have introduced some basic set-theoretic operations of complex neutrosophic sets including different types of unions, intersections and aggregations. Then, a new definition of score function of a complex neutrosophic number has been proposed. Additionally, the above-defined unions and intersections of complex neutrosophic sets have been stated for complex neutrosophic soft sets. Finally, by utilizing these proposed notions, we have offered a complex neutrosophic soft VIKOR approach to get a compromise optimal solution for single as well as multiple decision-maker based problems. Our proposed approach has been clarified by several real life-related problems including medical diagnosis problem, sustainable manufacturing material selection problem, company’s manager selection problem, etc. The feasibility and effectiveness of our proposed approach have also been included in the article.

A new multi-criteria decision making algorithm for medical diagnosis and classification problems using divergence measure of picture fuzzy sets

A new multi-criteria decision making algorithm for medical diagnosis and classification problems using divergence measure of picture fuzzy sets

On hesitant neutrosophic rough set over two universes and its application

As a further generalization of the concepts of fuzzy set, intuitionistic fuzzy set, single valued neutrosophic refined set, hesitant fuzzy set, and dual hesitant fuzzy set, Ye (J Intell Syst 24(1):23–36, 2015) proposed the concept of hesitant neutrosophic sets (also called single valued neutrosophic hesitant fuzzy sets). Following the idea of hesitant neutrosophic sets as introduced by Ye, in this paper, the model of hesitant neutrosophic rough sets is proposed, then the join semi-lattice structure of lower and upper hesitant neutrosophic rough approximation operators over two universes is given. In addition, an algorithm to handle decision making problem in medical diagnosis based on hesitant neutrosophic rough sets over two universes is provided. Finally, a numerical example is employed to demonstrate the validness of the proposed hesitant neutrosophic rough sets.

Quantifying gesture information in brain hemorrhage patients using probabilistic dual hesitant fuzzy sets with unknown probability information

Uncertainty occurs an a relevant amount in the medical problems where the patient cannot communicate his symptoms to the doctor. This often occurs in intense hemorrhage cases. In such situations, there might be over one membership (non-membership) values, and they might have different occurrence probabilities associated with them. Because of these hesitant values and their probabilities, there are huge chances for the loss of information during addressing sensitive situations. To avoid such valuable information in the medical diagnosis of hemorrhage strokes, probabilistic dual hesitant fuzzy sets (PDHFSs) can be used which embeds the features of dual hesitant fuzzy sets (DHFSs) with the probabilistic information to represent the imprecise available information. Meanwhile, a Maclaurin symmetric mean (MSM) has a prominent characteristic and striking ability to capture inter-relationship among the multi-input arguments. So making full utilization of the features possessed by PDHFSs and MSM, in this paper, we propose some weighted averaging and geometric MSM aggregation operators to address the uncertainties in the medical diagnosis problems and handle the gesture quantification. Some desirable properties of the operators are discussed and an optimization model for determining the probabilities in PDHFSs is framed making use of Shanon’s entropy. A decision-making (DM) approach is framed based on the proposed operators followed by comparison analysis and a case study on gesture quantification of a patient suffering from hemorrhage strokes is conducted. The validity of the proposed method is examined with several predominating studies.

Chaotic multi-swarm whale optimizer boosted support vector machine for medical diagnosis

Support vector machine (SVM) is a widely used pattern classification method that its classification accuracy is greatly influenced by both kernel parameter setting and feature selection. Therefore, in this study, to perform parameter optimization and feature selection simultaneously for SVM, we propose an improved whale optimization algorithm (CMWOA), which combines chaotic and multi-swarm strategies. Using several well-known medical diagnosis problems of breast cancer, diabetes, and erythemato-squamous, the proposed SVM model, termed CMWOAFS-SVM, was compared with multiple competitive SVM models based on other optimization algorithms including the original algorithm, particle swarm optimization, bacterial foraging optimization, and genetic algorithms. The experimental results demonstrate that CMWOAFS-SVM significantly outperformed all the other competitors in terms of classification performance and feature subset size.

An Ideal Technique for Decision-Making Problems for Uncertain Data and Its Application In Medical Science

For representing and manipulating uncertain information like fuzzy, incomplete, inconsistent or imprecise, Neutrosophic relation database model is a more general platform, in the human decision-making process. Neutrosophic sets can easily handle real world problems. A new correlation method is introduced in this paper to construct similarity measure, by which decision making problem that exist in real world situation can be easily handled in regard of multiple existing criteria’s or incomplete or inconsistent information. The selection of the best option of alternative can be done by ranking all the other options as per similarity measure depending on concept of similarity. Later in this paper, an explanatory example is given of the proposed method and the comparison results are also presented to show the effective output.. The application in certain domains of medical diagnosis problems having multiple criteria’s in decision making are also discussed in the end of the proposed method.

Decision making using algebraic operations on soft effect matrix as new category of similarity measures and study their application in medical diagnosis problems

A new category of similarity measures is investigated in this work, we first introduce the concept of effect matrix T∧(R1×R2,pn,qm) of type 2-tuple and study some of their properties. Moreover, from the soft set we find the pictures of type regular and irregular using effect matrix T∧(R1×R2,pn, qm) of type 2-tuple. An effect matrix T∧(R1×R2,pn,qm) of type 2-tuple is better than effect matrix E∧(R,pn,qm) of type 1-tuple, because we can deal with two different sets R1 (a family of objectives) and R2 (a family of parameters) in the same problem. This burden can be alleviated by application of type 2-tuple. Some applications of soft effect matrix of type 2-tuple T∧(R1×R2,pn,qm) in decision making problems are studied and explained. In this work we deal with pictures. Moreover, the similarity measure between two different soft sets under the same universal soft set (R1×R2) can be studied and explained its applications in medical diagnosis problems.

Logarithmic similarity measure of dynamic neutrosophic cubic sets and its application in medical diagnosis

In the medical diagnosis process, the symptoms of patients are always changing with time and relative to dynamical information at different time intervals. However, existing information expression methods usually neglect the temporal correlation of information expression, and hardly depict certain and uncertain information on complex medical diagnosis problems. For the first time, the study presents dynamic neutrosophic cubic set (DNCS) to express the patient's disease symptoms in a time sequence (different time intervals). Then, the logarithmic similarity measure (LSM) of DNCSs is put forward and their properties are verified. After that, a medical diagnosis method is constructed on the basis of the proposed logarithmic similarity measure in DNCS setting, where the disease symptom information collected from different time intervals is given by the form of DNCSs. Lastly, a medical diagnosis example is used to demonstrate its applicability, and then the diagnosis results indicate that the presented method is effective and feasible.

Redes bayesianas y diagnóstico médico. Una forma diferente de aprender probabilidades condicionadas

Las redes bayesianas constituyen una herramienta formal que permite modelar procesos caracterizados por la incertidumbre, lo cual es propio de muchos problemas reales. Con una red bayesiana se puede establecer un modelo completo sobre un conjunto de variables aleatorias y sus relaciones. Dicho modelo se puede utilizar para estimar probabilidades de ciertas variables de la red, que se denominan variables de estado, cuando son fijadas otras variables, llamadas variables de evidencia. El proceso de obtener la distribución de probabilidad de las variables de estado dadas las evidencias se denomina inferencia probabilística bayesiana. En este trabajo, tras introducir las redes bayesianas, se expone cómo utilizarlas en el aula analizando problemas de diagnóstico médico. Con esto se persigue un aprendizaje más significativo de los conceptos de independencia y de probabilidad condicional, que son esenciales para una correcta aplicación de numerosos métodos probabilísticos y estadísticos.

Symmetric fuzzy divergence measure, decision making and medical diagnosis problems

Symmetric fuzzy divergence measure, decision making and medical diagnosis problems

A novel similarity measure between intuitionistic fuzzy sets based on the mid points of transformed triangular fuzzy numbers with applications to pattern recognition and medical diagnosis

Similarity measure is an essential tool to compare and determine the degree of similarity between intuitionistic fuzzy sets (IFSs). In this paper, a new similarity measure between intuitionistic fuzzy sets based on the mid points of transformed triangular fuzzy numbers is proposed. The proposed similarity measure provides reasonable results not only for the sets available in the literature but also gives very reasonable results, especially for fuzzy sets as well as for most intuitionistic fuzzy sets. To provide supportive evidence, the proposed similarity measure is tested on certain sets available in literature and is also applied to pattern recognition and medical diagnosis problems. It is observed that the proposed similarity measure provides a very intuitive quantification.

Feature selection strategy based on hybrid crow search optimization algorithm integrated with chaos theory and fuzzy c-means algorithm for medical diagnosis problems

Powerful knowledge acquisition tools and techniques have the ability to increase both the quality and the quantity of knowledge-based systems for real-world problems. In this paper, we designed a hybrid crow search optimization algorithm integrated with chaos theory and fuzzy c-means algorithm denoted as CFCSA for feature selection problems of medical diagnosis. In the proposed CFCSA framework, the crow search algorithm adopts the global optimization technique to avoid the sensitivity of local optimization. The fuzzy c-means (FCM) objective function is used as a cost function for the chaotic crow search optimization algorithm. The proposed algorithm CFCSA is benchmarked against the binary crow search algorithm (BCSA), chaotic ant lion optimization algorithm (CALO), binary ant lion optimization algorithm (BALO) and bat algorithm relevant methods. The proposed CFCSA algorithm vs. BCSA, CALO, BALO and bat algorithm is tested on diabetes, heart, Radiopaedia CT liver, breast cancer, lung cancer, cardiotocography, ILPD, liver disorders, hepatitis and arrhythmia. Experimental results show the proposed method CFCSA is better against comparative models in feature selection on the medical diagnosis data sets.

Divergence measure of Pythagorean fuzzy sets and its application in medical diagnosis

The Pythagorean fuzzy set (PFS) which is an extension of intuitionistic fuzzy set, is more capable of expressing and handling the uncertainty under uncertain environments, so that it was broadly applied in a variety of fields. Whereas, how to measure PFSs’ distance appropriately is still an open issue. It is well known that the square root of Jensen–Shannon divergence is a true metric in the probability distribution space which is a useful measure of distance. On account of this point, a novel divergence measure between PFSs is proposed by taking advantage of the Jensen–Shannon divergence in this paper, called as PFSJS distance. This is the first work to consider the divergence of PFSs for measuring the discrepancy of data from the perspective of the relative entropy. The new PFSJS distance measure has some desirable merits, in which it meets the distance measurement axiom and can better indicate the discrimination degree of PFSs. Then, numerical examples demonstrate that the PFSJS distance can avoid generating counter-intuitive results which is more feasible, reasonable and superior than existing distance measures. Additionally, a new algorithm based on the PFSJS distance measure is designed to solve the problems of medical diagnosis. By comparing the different methods in the medical diagnosis application, it is found that the new algorithm is as efficient as the other methods. These results prove that the proposed method is practical in dealing with the medical diagnosis problems.

Improved composite relation for pythagorean fuzzy sets and its application to medical diagnosis

Uncertainty is an important factor in any decision-making process. Different mathematical frameworks have been introduced to cope the ambiguity of decision-making. The concept of Pythagorean fuzzy sets (PFSs) is one of the latest mathematical frameworks that deals with uncertainty. Pythagorean fuzzy sets generalize intuitionistic fuzzy sets with a wider scope of applications, and hence, the motivation for investigating into its applicability in tackling uncertainty imbedded in medical diagnosis. This paper studies the approach of max–min–max composite relation for Pythagorean fuzzy sets, improves upon the approach, and applies its to medical diagnosis problem. The validity of the improved composite relation for Pythagorean fuzzy sets is carried out in comparison to the max–min–max composite relation for Pythagorean fuzzy sets using numerical experiments. The improved composite relation for Pythagorean fuzzy sets yields a better relation with a greater relational value when compared to the aforementioned composite relation and, hence, its choice to solving medical diagnosis problem. To this end, an application of the improved composite relation for Pythagorean fuzzy sets is explored in medical diagnosis using hypothetical medical database. This improved composite relation could be used as a sustainable approach in applying Pythagorean fuzzy sets to multi-criteria decision-making (MCDM) problems, multi-attribute decision-making (MADM) problems, pattern recognition problems, among others.

A Robust Single-Valued Neutrosophic Soft Aggregation Operators in Multi-Criteria Decision Making

Molodtsov originated soft set theory that was provided a general mathematical framework for handling with uncertainties in which we meet the data by affix parameterized factor during the information analysis as differentiated to fuzzy as well as neutrosophic set theory. The main object of this paper is to lay a foundation for providing a new approach of single-valued neutrosophic soft tool which is considering many problems that contain uncertainties. In present study, a new aggregation operators of single-valued neutrosophic soft numbers have so far not yet been applied for ranking of the alternatives in decision-making problems. To this propose work, single-valued neutrosophic soft weighted arithmetic averaging (SVNSWA) operator, single-valued neutrosophic soft weighted geometric averaging (SVNSWGA) operator have been used to compare two single-valued neutrosophic soft numbers (SVNSNs) for aggregating different single-valued neutrosophic soft input arguments in neutrosophic soft environment. Then, its related properties have been investigated. Finally, a practical example for Medical diagnosis problems provided to test the feasibility and applicability of the proposed work.

Imbalanced biomedical data classification using self-adaptive multilayer ELM combined with dynamic GAN

BackgroundImbalanced data classification is an inevitable problem in medical intelligent diagnosis. Most of real-world biomedical datasets are usually along with limited samples and high-dimensional feature. This seriously affects the classification performance of the model and causes erroneous guidance for the diagnosis of diseases. Exploring an effective classification method for imbalanced and limited biomedical dataset is a challenging task.MethodsIn this paper, we propose a novel multilayer extreme learning machine (ELM) classification model combined with dynamic generative adversarial net (GAN) to tackle limited and imbalanced biomedical data. Firstly, principal component analysis is utilized to remove irrelevant and redundant features. Meanwhile, more meaningful pathological features are extracted. After that, dynamic GAN is designed to generate the realistic-looking minority class samples, thereby balancing the class distribution and avoiding overfitting effectively. Finally, a self-adaptive multilayer ELM is proposed to classify the balanced dataset. The analytic expression for the numbers of hidden layer and node is determined by quantitatively establishing the relationship between the change of imbalance ratio and the hyper-parameters of the model. Reducing interactive parameters adjustment makes the classification model more robust.ResultsTo evaluate the classification performance of the proposed method, numerical experiments are conducted on four real-world biomedical datasets. The proposed method can generate authentic minority class samples and self-adaptively select the optimal parameters of learning model. By comparing with W-ELM, SMOTE-ELM, and H-ELM methods, the quantitative experimental results demonstrate that our method can achieve better classification performance and higher computational efficiency in terms of ROC, AUC, G-mean, and F-measure metrics.ConclusionsOur study provides an effective solution for imbalanced biomedical data classification under the condition of limited samples and high-dimensional feature. The proposed method could offer a theoretical basis for computer-aided diagnosis. It has the potential to be applied in biomedical clinical practice.

Medical Diagnosis Via Distances Measures Between Credibility Distributions

The uncertain, vague, imprecise nature of medical documentation and information make the field of medical diagnosis is the most important and interesting area for applications of fuzzy variables. Furthermore, due to lots of factors to analyze for the diagnosis of the disease makes the doctor/physician's work complicated. In literature, most of medical diagnosis problems are fuzzy variables-based methods. However, no attempt has been seen using a credibility theory. This article presents a maiden effort to carry out medical diagnoses using distance measures between credibility distributions of fuzzy variables. Furthermore, some properties of distance measures on credibility distributions are also studied.