Classification of Content based Medical Image Retrieval Using Texture and Shape feature with Neural Network

Due to the complexity of medical images, traditional medical image classification methods have been unable to meet actual application needs. In recent years, the rapid development of deep learning theory has provided a technical approach for solving medical image classification tasks. However, deep learning has the following problems in medical image classification. First, it is impossible to construct a deep learning model hierarchy for medical image properties; second, the network initialization weights of deep learning models are not well optimized. Therefore, this paper starts from the perspective of network optimization and improves the nonlinear modeling ability of the network through optimization methods. A new network weight initialization method is proposed, which alleviates the problem that existing deep learning model initialization is limited by the type of the nonlinear unit adopted and increases the potential of the neural network to handle different visual tasks. Moreover, through an in‐depth study of the multicolumn convolutional neural network framework, this paper finds that the number of features and the convolution kernel size at different levels of the convolutional neural network are different. In contrast, the proposed method can construct different convolutional neural network models that adapt better to the characteristics of the medical images of interest and thus can better train the resulting heterogeneous multicolumn convolutional neural networks. Finally, using the adaptive sliding window fusion mechanism proposed in this paper, both methods jointly complete the classification task of medical images. Based on the above ideas, this paper proposes a medical classification algorithm based on a weight initialization/sliding window fusion for multilevel convolutional neural networks. The methods proposed in this study were applied to breast mass, brain tumor tissue, and medical image database classification experiments. The results show that the proposed method not only achieves a higher average accuracy than that of traditional machine learning and other deep learning methods but also is more stable and more robust.

Due to the complexity of medical images, traditional medical image classification methods have been unable to meet the actual application needs. In recent years, the rapid development of deep learning theory has provided a technical approach for solving medical image classification. However, deep learning has the following problems in the application of medical image classification. First, it is impossible to construct a deep learning model with excellent performance according to the characteristics of medical images. Second, the current deep learning network structure and training strategies are less adaptable to medical images. Therefore, this paper first introduces the visual attention mechanism into the deep learning model so that the information can be extracted more effectively according to the problem of medical images, and the reasoning is realized at a finer granularity. It can increase the interpretability of the model. Additionally, to solve the problem of matching the deep learning network structure and training strategy to medical images, this paper will construct a novel multiscale convolutional neural network model that can automatically extract high-level discriminative appearance features from the original image, and the loss function uses the Mahalanobis distance optimization model to obtain a better training strategy, which can improve the robust performance of the network model. The medical image classification task is completed by the above method. Based on the above ideas, this paper proposes a medical classification algorithm based on a visual attention mechanism-multiscale convolutional neural network. The lung nodules and breast cancer images were classified by the method in this paper. The experimental results show that the accuracy of medical image classification in this paper is not only higher than that of traditional machine learning methods but also improved compared with other deep learning methods, and the method has good stability and robustness.

Differential Methylation Profile of Ovarian Cancer in Tissues and Plasma

This chapter aims to clarify the terminology of and relations between ontological, epistemological, and semantic aspects of indeterminacy in medical classification systems. Although classifications of diseases and mental disorders are often characterized as having blurred boundaries, there is no consensus on what exactly this means. The following clarification may remedy this shortcoming: from an ontological point of view, disease entities are found to be discrete or continuous, depending on whether realisation gaps occur. From an epistemological perspective, the certainty of a classification depends on how controversial the assessment of its validity is throughout contexts and how much different legitimate interests of classification users vary. Finally, as semantic categories, medical classifications can be defined precisely or vaguely. The chapter analyses how the ontological, epistemological, and semantic levels are interrelated and how the proposed terminological clarifications may help to disentangle discussions about the validity of medical classifications.

This work presents a new approach for classification and retrieval of echocardiographic images from textual information of the anatomical structures and diagnosis features. These textual attributes will be acquired from the electronic medical report generated in an integrated healthcare environment. The medical report is provided by a specialist in the area during the analysis of the medical image stored in a PACS environment. Such innovation guarantees a more accurate classifier and a better optimization of the medical work, since the medical report and the attributes for the medical image classifier will be created at the same time. The system is being developed in the University Hospital of the University of Brasilia.

Machine learning based survival prediction of DLBCL: Using multimodal data.

Editorial Board

Interpreting medical images is certainly a complex task which requires extensive knowledge [1]. According to Computer Aided Diagnosis (CAD) serves as a second opinion that will help radiologists in diagnosis and on the other hand Content-based Image Retrieval uses visual content to help users browse, search and retrieve similar medical images from a database based on the user’s interest [2-4]. The competency of the CBMIR system depends on feature extraction methods [5]. The textural features are very important to determine the content of a medical image. Textural features provide scenic depth, the spatial distribution of tonal variation, and surface orientation [6]. Therefore, this study seeks to compare and evaluate some of the hand-crafted texture feature extraction techniques in CBMIR. This is to help those concerned in enhancing CBIR systems to make informed decisions concerning the selection of the best textural feature extraction techniques. Since there is no clear indication of which of the various texture feature extraction techniques is best suited for a given performance metric when considering which of the techniques to choose for a particular study in CBMIR systems. The objective of this work, therefore, is to comparatively evaluate the performance of the following texture feature extraction techniques; Local Binary Pattern (LBP), Gabor Filter, Gray-Level Co-occurrence Matrix (GLCM), Haralick Descriptor, Features from Accelerated Segment Test (FAST) and Features from Accelerated Segment Test and Binary Robust Independent Elementary Features (FAST &BRIEF) using the metrics; precision, recall, f1-score, mean squared error (MSE), accuracy and time. These techniques are coupled with specific similarity measure to obtain results. The results showed that LBP, Haralick Descriptor, FAST, and GLCM had the best results in terms of (Precision and Accuracy), Time, F1-Score, and Recall respectively. LBP had 82.05% and 88.23% scores for precision and accuracy respectively. The following scores represent the performance of the Haralick descriptor, FAST, and GLCM models respectively; 0.88s, 38.7%, and 44.82%. These test scores are obtained from datasets ranging from 1k-10.5k. Aside from LBP outperforming the other 5 models mentioned, it still outperformed the following proposed models ' [7]’, ‘Tamura texture feature and wavelet transform combined with Hausdorff distance - [8]’, ‘ [9]’ in terms of (precision, accuracy, and recall) and (precision and recall) respectively and probably f1-score (since f1-score is the weighted average of precision and recall). It is believed that an ensemble of LBP, Haralick descriptors, and Support Vector Machine (SVM) can represent a robust system for both medical image retrieval and classification.

Integration of computational methods in the early stages of drug discovery has been one of the key trends in the pharmaceutical industry. Starting with high quality drug candidates should ultimately minimize clinical attrition rates and give rise to higher success rates. In this paper, we present a novel approach for indexing oral druglikeness of compounds. With the Iterative Stochastic Elimination (ISE) Algorithm, we distinguish between orally available drugs and nondrugs by generating sets of optimized descriptors' ranges, each set constituting a "filter". We delineate in this paper how to produce an ensemble of best k-descriptor sets out of the huge number of possibilities, and how to construct a "filter bank" that retains diverse filters by clustering. Finally, we define the "orally bioavailable drug-like" character of individual molecules by combining the filters into an "Orally Bioavailable Druglike Index" (OB-DLI) which may be used to prioritize molecules in databases and discuss its uses in several potential applications. The predictive power with sets of 4-6 descriptors is high (i.e., one filter of 5 descriptors retrieved 81% true positives and >77% true negatives). Thus, OB-DLI has advantages over binary decisions (that use only one filter) not only in raising discriminative power but also in ranking drug candidates according to their chance to be successful oral drugs. We demonstrate the ability of our approach to discover molecular entities with the required property, orally bioavailable drug likeness, that are structurally dissimilar to those of the training set. Comparison of this ISE application to some of the current main methods for classification reveals that our approach has >13% improvement in the Matthews Correlation Coefficient, which measures the success of identifying true and false positives and negatives.

Purpose. At the present stage, network attack detection systems based on the following neural networks are most often offered: multilayer perceptron, Kohonen network or self-organizing map and their combinations. The efficiency problem of two approaches to detect attacks on a computer network using neural network technology based on the normalized data of the open NSL-KDD database is considered. Methodology. As an architectural solution to the network attack detection system, it is proposed to consider the following approaches: based on one neural network determining the attack class (first approach) and an ensemble of five neural networks (second approach), which at the first stage determines the attack category (DoS, Probe, U2R , R2L), and in the second stage, the attack class belonging to a certain category. Findings. Based on the neural networks created in the MatLAB program, a study was conducted of their error on the length of the training sample using various training algorithms: Levenberg-Marquardt; Bayesian Regularization; Scaled Conjugate Gradient with different numbers of hidden neurons (minimum, average and maximum). Certain optimal parameters of neural networks with two approaches were determined. Originality. In the course of conducting experiments with various approaches, the results obtained were: TP (True Positive); FP (False Positive); FN (False Negative); TN (True Negative), based on which the following indicators were calculated for assessing the quality of solutions: correct determination of network attacks; false positives; reliability; accuracy and completeness, which prove the feasibility of using an ensemble of neural networks (second approach). Practical value. On the created neural networks with various approaches, studies were conducted: the operating time of neural networks; errors of the first kind; errors of the second kind. According to the results of the first study, the average operating time of an ensemble of neural networks is 0.92 s, and the operating time of a neural network (according to the first approach) is 2.21 s. According to the results of the second study, the error of the first kind using an ensemble of neural networks is 2.17%, and using the neural network (the first approach) – 7.39%. According to the results of the third study, the error of the second kind using an ensemble of neural networks is 3.91%, and using the neural network (the first approach) – 6.96%, which is confirmed by the efficiency of using an ensemble of neural networks (second approach).

Extra-axillary nodal metastases in breast cancer: comparison of ultrasound, MRI, PET/CT, and CT

Deep learning methods, especially convolutional neural networks, have become more and more popular in medical image classifications. However, training a deep neural network from scratch can be a luxury for many medical image datasets as the process requires a large and well-balanced sample to output satisfactory results. Unlike natural image datasets, medical images are expensive to collect owing to labor and equipment costs. Besides, the class labels in medical image datasets are usually severely imbalanced subject to the availability of patients. Further, aggregating medical images from multiple sources can be challenging due to policy restrictions, privacy concerns, communication costs, and data heterogeneity caused by equipment differences and labeling discrepancies. In this paper, we propose to address these issues with the help of transfer learning and artificial samples created by generative models. Instead of requesting medical images from source data, our method only needs a parsimonious supplement of model parameters pre-trained on the source data. The proposed method preserves the data privacy in the source data and significantly reduces the communication cost. Our study shows transfer learning together with artificial samples can improve the pneumonia classification accuracy on a small but heavily imbalanced chest X-ray image dataset by \(11.53\%\) which performs even better than directly augmenting that source data into the training process.KeywordsDeep learningGenerative modelsMedical image classificationPrivacy preservationTransfer learning

Inadvertent injury of the recurrent laryngeal nerve can occur during radiofrequency ablation (RFA) of thyroid nodules. Methods to avoid permanent injury have not been described. Laryngeal ultrasonography (LUSG) can assess the function of vocal cords (VCs) in real time. The present study aimed to evaluate the feasibility and accuracy of LUSG in assessing real-time VC function during RFA of benign thyroid nodules. Consecutive patients undergoing RFA for benign thyroid nodules under local anesthesia were included. Spontaneous VC movements were checked with intra-operative LUSG (iLUSG) following each transverse ablation plane. In case of reduced VC movement, the ablation was stopped immediately. Post-ablation VC function was rechecked by LUSG on day-0 and flexible laryngoscopy (FL) on day-7. A concordance with day-0 LUSG or day-7 FL was a "true positive" or "true negative" depending on the presence or absence of VC palsy (VCP). Accuracy was calculated as the sum of all true positives and negatives divided by total nerves-at-risk. Of 65 eligible patients, 56 (86.2%) were females. Twelve (18.5%) patients had bilateral lobe RFA, while 53 (81.5%) had unilateral RFA. The total number of nerves-at-risk was 77. Three unilateral VCPs (3.9%) were initially detected on iLUSG and confirmed by day-0 LUSG. All recovered fully within one week. The overall accuracy of iLUSG was 100%. iLUSG is a highly accurate method that permits real-time feedback on the function of the VCs during RFA procedure. Real-time detection of VCP may prevent permanent injury. Methodological routine use of iLUSG is recommended during thyroid RFA.

The Sixth International Symposium on Neural Networks (ISNN 2009)

Medical imaging is becoming a vital component of war on cancer. Tremendous amounts of medical image data are captured and recorded in a digital format during cancer care and cancer research. Facing such an unprecedented volume of image data with heterogeneous image modalities, it is necessary to develop effective and efficient content-based medical image retrieval systems for cancer clinical practice and research. While substantial progress has been made in different areas of content-based image retrieval (CBIR) research, direct applications of existing CBIR techniques to the medical images produced unsatisfactory results, because of the unique characteristics of medical images. In this paper, we develop a new multimodal medical image retrieval approach based on the recent advances in the statistical graphic model and deep learning. Specifically, we first investigate a new extended probabilistic Latent Semantic Analysis model to integrate the visual and textual information from medical images to bridge the semantic gap. We then develop a new deep Boltzmann machine-based multimodal learning model to learn the joint density model from multimodal information in order to derive the missing modality. Experimental results with large volume of real-world medical images have shown that our new approach is a promising solution for the next-generation medical imaging indexing and retrieval system.