Multiclass tumor identification using combined texture and statistical features.

Fully automated multi-parametric brain tumour segmentation using superpixel based classification

A deep autoencoder approach for detection of brain tumor images

Accurate diagnosis of cancer at an early stage is the key to reduce cancer mortality and improve survival. PET imaging has high sensitivity but low spatial resolution, while CT imaging has good spatial location information. Therefore, the combination of PET and CT imaging can provide complementary advantages to achieve accurate early diagnosis of tumors. However, currently developed PET or CT imaging agents have only a single function. Here, we designed and constructed a self-assembled lipid nanocapsule encapsulated with iodixanol and labeled with self-chelated 64Cu for precise PET/CT imaging of tiny lung tumor. The lipid nanocapsule self-assembled in water using LPPC-Ce6, a conjugate of chlorin e6 (Ce6) and lysophosphatidylcholine (LPPC), to form a bilayer vesicular structure. 64Cu was embedded in the center of the tetrapyrrole ring of Ce6 by natural capture ability for Cu2+ ions. GLT21.T, the aptamer targeting lung cancer, was conjugated to the surface of the lipid nanocapsules. Iodixanol was loaded into the cavity of the lipid nanocapsule (64Cu@LCI-apt). In the nanostructure, the loading of iodixanol was sufficiently high, and the specific activity could be flexibly adjusted according to imaging requirements. The prepared 64Cu@LCI-apt achieves excellent radiolabeling efficiency, stability and effective targeting of lung tumor. In an early orthotopic lung cancer model, 64Cu@LCI-apt demonstrated the capabilities of sensitive PET imaging and enhanced contrast CT imaging to enable efficient high-quality PTE/CT imaging of tiny orthotopic lung tumor with a diameter of 500 μm. 64Cu@LCI-apt has great potential for early, sensitive, and accurate diagnosis of tumors through dual-mode PET/CT imaging.

Brain Tumor is a deadly diagnosis that, if not detected early on, can cause significant damage to a patient’s brain, disrupting the body’s functions and even leading to death. However, the conventional method of detecting brain tumors is conducting MRI scans which a medical expert then consults for diagnosis. While time-consuming, this method also leaves room for human error, especially in cases where the tumor is in its early stages. Thus, the diagnosis of brain tumors must be made accurately in the least time possible. This paper aims to prevent premature mortality, provide health in resource-constrained settings, and seek patients’ healthy lives, which can be done through timely and accurate diagnosis of brain tumors. In this paper, three different deep transfer learning models are used after adding fine-tuned layers to detect brain tumors in a dataset of 251 Magnetic Resonance Imaging (MRI) scans. The transfer learning models used are VGG16, InceptionV3, and ResNet50, with fine-tuned Dropout, Flatten, and Dense added layers. The highest accuracy was achieved with the VGG16 model, which had an accuracy of 91.58%. Thus, deep learning models are proven effective in detecting brain tumors without the unwanted expense of time and resources.

Despite advances in surgery and drug discovery, brain tumors remain fatal diseases. Early detection and diagnosis of brain tumors is of great importance for improving treatment outcomes. Magnetic resonance imaging (MRI) is a prominent, clinically-relevant imaging modality because of its excellent tissue contrast resolution, direct multiplanar imaging and increased sensitivity to edema. MRI utility is further enhanced with the use of magnetic iron oxide nanoparticles, which can function as both a contrast agent for imaging and as a drug delivery vehicle for treating brain cancer. In this review, the principles of various imaging modalities for brain tumors are discussed with focus on monocrystalline iron oxide nanoparticle (MION)-based MRI contrast agents. A summary is given on the mechanism of contrast effect, magnetophoretic mobility and magnetic retention, and strategies to enhance tumor selectivity, increase spatial resolution and reduce nonspecific uptake of MION.

Among the list of dreadful diseases, 'Brain Tumor and Brain Cancer' is one of them. According to survival rate, after the detection of cancerous Brain or Central Nervous System (CNS) tumor, 34% of men and 36% of women survive at least 5 years. Therefore, 'Early Detection of tumor' can be a savior for so many lives and artificial intelligence will make the way very accurate and appropriate. A new non-invasive approach to detect brain tumors in early-stage, cost-efficiently with the lowest risk factor is-'Liquid Biopsy'. It is a technique for analyzing non-solid biological tissue, i.e. - blood, plasma, cerebrospinal fluid (CSF). As human inspection maybe error full and inaccurate, in this paper, we have used 'k-means clustering' in 'Image Processing' as visual perception of artificial intelligence for detection of 'CTC' and we have used the technique 'Convolutional Neural Network' (CNN) for ctDNA detection and 'Support Vector Machine'(SVM) algorithm for classification of ctDNA and normal cell-free DNA (cfDNA). 'ctDNA' could provide clues for growth factor of cancerous cells, type of tumors, location, etc. Therefore, our work provides a new way to early detection and a new prospect for early cure.

This paper presents the methodology to detect and identify the type of fault that occurs in the shunt compensated static synchronous compensator (STATCOM) transmission line using a combination of Discrete Wavelet Transform (DWT) and Naive Bayes (NB) classifiers. To study this, the network model is designed using Matlab/Simulink. Different types of faults, such as Line to Ground (LG), Line to Line (LL), Double Line to Ground (LLG) and the three-phase (LLLG) fault, are applied at disparate zones of the system, with and without STATCOM, considering the effect of varying fault resistance. The three-phase fault current waveforms obtained are decomposed into several levels using Daubechies (db) mother wavelet of db4 to extract the features, such as the standard deviation (SD) and energy values. Then, the extracted features are used to train the classifiers, such as Multi-Layer Perceptron Neural Network (MLP), Bayes and the Naive Bayes (NB) classifier to classify the type of fault that occurs in the system. The results obtained reveal that the proposed NB classifier outperforms in terms of accuracy rate, misclassification rate, kappa statistics, mean absolute error (MAE), root mean square error (RMSE), percentage relative absolute error (% RAE) and percentage root relative square error (% RRSE) than both MLP and the Bayes classifier.

An accurate and early diagnosis of brain tumors based on medical imaging modalities is of great interest because brain tumors are a harmful threat to a person’s health worldwide. Several medical imaging techniques have been used to analyze brain tumors, including computed tomography (CT) and magnetic resonance imaging (MRI). CT provides information about dense tissues, whereas MRI gives information about soft tissues. However, the fusion of CT and MRI images has little effect on enhancing the accuracy of the diagnosis of brain tumors. Therefore, machine learning methods have been adopted to diagnose brain tumors in recent years. This paper intends to develop a novel scheme to detect and classify brain tumors based on fused CT and MRI images. The proposed approach starts with preprocessing the images to reduce the noise. Then, fusion rules are applied to get the fused image, and a segmentation algorithm is employed to isolate the tumor region from the background to isolate the tumor region. Finally, a machine learning classifier classified the brain images into benign and malignant tumors. Computing statistical measures evaluate the classification potential of the proposed scheme. Experimental outcomes are provided, and the Enhanced Flower Pollination Algorithm (EFPA) system shows that it outperforms other brain tumor classification methods considered for comparison.

In this paper, we present an approach for human emotion description based on proposed algorithm combines the strengths of two methods of analyzing textures, the Discrete Wavelet Transform (DWT) and the Grey Level Co-occurrence Matrix (GLCM). The proposed algorithm is introduced to extract the texture features by combining (1) wavelet statistical features extracted from the approximation and detail regions of three level discrete wavelet transform decomposed images and (2) grey level co-occurrence matrix features extracted from original image, approximation and detail sub-bands of one level discrete wavelet transform decomposed images at different angles . Experimental results are presented using image database consists of a set of photograph face images describing some human emotions, these images were generated by using a digital video camera. The experimental results show that the proposed algorithm is effective and achieves high similarity ratios.

A survey is given of the principles underlying the diagnosis of brain tumours. Traditionally diagnosis and localization of brain tumours have been based upon morphological criteria. Currently unsurpassed levels in imaging of anatomical details and topographical relations by the techniques of computed tomography (CT) and magnetic resonance imaging (MRI) have been achieved. The techniques of positron emission tomography (PET) and of magnetic resonance spectroscopy (MRS), which depict also metabolic and blood flow aspects, provide a refinement of our knowledge on the metabolism, structure and pathophysiological relations of a tumour to the surrounding parenchyma. Recent advances in the recording of function-related changes of the cerebral electro-magnetic field allow a better definition of critical functional areas.

Despite remarkable advances in molecular characterization, the diagnosis of brain tumors remains challenging, particularly in cases with ambiguous histology or contradictory molecular features. In this context, DNA methylation profiling plays an important role in improving diagnostic and prognostic accuracy. This review aims to provide diagnostic guidance regarding when DNA methylation arrays represent a useful tool for the diagnosis of primary brain tumors. Large-scale profiling has revealed that DNA methylation profiles of brain tumors are highly reproducible and stable. Therefore, DNA methylation profiling has been successfully used to classify brain tumors and identify new entities. This approach seems to be particularly promising for heterogeneous groups of tumors, such as IDH -wildtype gliomas, and glioneuronal and embryonal tumors, which include a variety of entities that are still under characterization. As underlined in the fifth edition of the WHO classification of central nervous system tumors, the diagnosis of brain tumors requires the integration of histological, molecular, clinical, and radiological features. Although advanced imaging and histological examination remain the standard diagnostic tools, DNA methylation analysis can significantly improve diagnostic accuracy, with a substantial impact on patient management.

Accurate prediction models for air pollutants are crucial for forecast and health alarm to local inhabitants. In recent literature, discrete wavelet transform (DWT) was employed to decompose a series of air pollutant levels, followed by modeling using support vector machine (SVM). This combination of DWT and SVM was reported to produce a more accurate prediction model for air pollutants by investigating different levels of frequency bands. However, DWT has a significant demand in model complexity, namely, the training time and the model size of the prediction model. In this paper, a new method called variation-oriented filtering (VF) is proposed to remove the data with low variation, which can be considered as noise to a prediction model. By VF, the noise and the size of the series of air pollutant levels can be reduced simultaneously and hence so are the training time and model size. The SO2 (sulfur dioxide) level in Macau was selected as a test case. Experimental results show that VF can effectively and efficiently reduce the model complexity with improvement in predictive accuracy.

Feature extraction plays a very important role in the speech classification process because a better feature is good for improving the classification rate. This paper presents a speech feature extraction method by using Discrete Wavelet Transform (DWT) at 7th level of decomposition with mother wavelet of Dau-bechies 2, Renyi Entropy (RE), Autoregressive Power Spectral Density (AR-PSD), Statistical, as well as the combination of each method for extracting and classifying the certain Indonesian velar-vowel and alveolar-vowel syllables. Five different features set used in this study, namely the combination features of DWT and statistical (WS), RE, the combination of AR-PSD and Statistical (PSDS), the combination of PSDS and the selected features of RE (RPSDS), and the combination of DWT, RE, and AR-PSD (WRPSDS). Each syllable is segmented at a certain length to form a consonant-vowel. Multi-layer perceptron is used as a classifier after feature extraction process. The results show that the rank of the average recognition rate are WRPSDS, WS, RPSDS, PSDS, and RE, respectively.

Introduction: Brain tumors pose a significant danger to human health due to their complexity, variety and ability to progressive progress. Early and accurate diagnosis is important for effective treatment and improvement in survival rates. Traditional clinical processes are often dependent on time programs, subjective and expensive clinical equipment. The project presents an integrated, AI operated, multi-phase system for brain tumor detection and recommendations of personal treatment. By combining symptomatic evaluation, biomarker analysis, advanced imaging interpretation and machine learning models, this system aims to help health professionals with quick and more accurate clinical decisions.Objectives: The main objective of this project is to develop an integrated, multi -phase system for early detection and personal treatment using a combination of clinical symptoms, molecular biomarkers, imaging and artificial intelligence. The system begins to evaluate patient -reported symptoms and risk factors to calculate a functional weighted risk index (FWRI) for initial risk assessment. It then analyzes a blood -based biomarker to generate a blood -based tumor signal index (BTSI), which provides insight at molecular level. Then it explains the ATR-FTIR and the Multi-Omics report through rule-based arguments for determining nonconformities. The MRI scan is then classified into tumors-types-glioma, meningioma, pituitary or no tumor-a fine- model VGG19 uses deep learning models. Finally, the system integrates the results of all previous stages to offer individual means based on tumor type, severity and general risk profile.Methods: The proposed system follows a sequential five-stage methodology for comprehensive brain tumor detection and remedy making plans. In Stage 1, users input symptom severity and history through an interactive interface, which calculates a Functional Weighted Risk Index (FWRI) to assess preliminary tumor chance. Stage 2 entails the input of blood biomarker ranges, which might be analyzed to generate a Blood-Based Tumor Signal Index (BTSI), reflecting molecular signs of tumor presence. Stage 3 allows users to add ATR-FTIR or Multi-Omics reviews,that are interpreted using rule-primarily based logic to identify unusual styles that warrant imaging. In Stage 4, customers add brain MRI scans which can be processed through a pre-trained VGG19 convolutional neural network to classify the tumor into one among four classes: glioma, meningioma, pituitary, or no tumor. Finally, Stage five combines the outputs from all previous levels to generate customized treatment tips, taking into consideration the identified tumor type, severity, biomarker signals, and medical danger ratingsResults: The multi -phase system demonstrated promising consequences in all components. In phase 1, FWRI is effectively stable in categories with low, medium and high risks based on symptom input and severity. Phase 2 has shown that BTSI values have become close in line with a biomarker threshold installed, which strengthens the system's ability to reflect molecular tumor designs. Phase 3 explained ATR-FFIR and Multi-Omics data successfully, the exact flag of the unusual profile for further imaging analysis. In Step 4, VGG19 was based MR classification model accuracy of more than 92%, which distinguishes well between glioma, meningoom, pituitary tumor and no tumor. Finally, step 5 recommendations generated clinically relevant and similar relevant medical guidelines, which demonstrate the system's ability to provide integrated, computer-driven support for individual brain tumor care.Conclusions: Finally, integrated five-phase brain tumor detection and treatment system effectively combine the evaluation of clinical symptoms, biomorker analysis, omics data interpretation, advanced MRI classification and individual treatment form into an integrated diagnostic pipeline. By taking advantage of rule -based arguments and deep teaching techniques, the system increases early identification accuracy, reduces clinical delays and supports data driven clinical decision -making. The sequential current ensures that each step does on the previous one, reduces false positive and optimizing patient -specific consequences. With further clinical verification, this AI-assisted framework has a strong ability to become a reliable and skilled tool in medical environments in the real world for early diagnosis and handling of brain tumors.

Accurate detection and diagnosis of brain tumor is one the crucial task of medical image analysis. Brain tumor classification system aids the physician to make accurate diagnosis and to provide effective treatment. Magnetic Resonance Imaging (MRI) is the gold standard imaging technique for brain tumor diagnosis. This paper proposes a method for brain tumor detection and classification using artificial neural network. The proposed method consists of four major processes such as preprocessing, region of interest segmentation, feature extraction and classification. Feed forward neural network is employed to classify the brain tumors. Classification performance of the proposed method is evaluated using 10-cross fold validation and compared with the previous methods. Empirical findings proved that the proposed method can efficiently classify the brain tumor with higher classification rate.