Method For Detection Of Tumors Research Articles

Deep Learning Approach for Brain Tumor Classification

Tumors are complex. There are a lot of variations in sizes and location of tumor. This makes it really hard for complete understanding of tumor. Brain tumour is the abnormal growth of cells inside the brain cranium which limits the functioning of brain. Now a days, medical images processing is a most challenging and developing field. Automated detection of tumor in MRI is extremely crucial because it provides information about abnormal tissues which is important for planning treatment. The conventional method for defect detection in resonance brain images is time consuming. So, automated tumor detection methods are developed because it would save radiologist time and acquire a tested accuracy. The MRI brain tumor detection is complicated task due to complexity and variance of tumors.There are many previously implemented approaches on detecting these kinds of brain tumors. In this paper, we used and implement Convolutional Neural Network (CNN) which is one among the foremost widely used deep learning architectures for classifying a brain tumor into four types. i.e Glioma , Meningioma, Pituitary and No tumour. CNN may be used to effectively locate most cancers cells in brain via MRI. classification.

Targeted imaging of esophageal adenocarcinoma with a near-infrared fluorescent peptide

BackgroundTargeted optical imaging offers a noninvasive and accurate method for the early detection of gastrointestinal tumors, especially for flat appearances. In our previous study, a sequence of SNFYMPL (SNF) was identified as a specific peptide to bind to esophageal carcinoma using phage-display technology. This study aimed to evaluate the tumor-targeting efficacy of Cy5.5-conjugated SNF probe for imaging of esophageal carcinoma in vitro and in vivo.MethodsThe SNF-Cy5.5 probe was synthesized and then identified using High Performance Liquid Chromatography (HPLC) and mass spectrometry (MS). Confocal fluorescence imaging and Flow cytometry analysis were performed to evaluate the binding specificity and the receptor binding affinity of SNF-Cy5.5 to OE33. In vivo imaging was performed to evaluate the targeting ability of SNF-Cy5.5 to esophageal carcinoma.ResultsThe confocal imaging and flow cytometry analysis showed that SNF-Cy5.5 bound specifically to the plasma membrane of OE33 cells with a high affinity. In vivo, for non-block group, SNF-Cy5.5 probe exhibited rapid OE33 tumor targeting during 24 h p.i. and excellent tumor-to-background contrast at 2 h p.i. For the block group, SNF-Cy5.5 was not observed in the mice after 4 h p.i. Ex vivo imaging also revealed that a higher fluorescent signal intensity value of the tumors was clearly observed in the non-block group than that in the block group (2.6 ± 0.32 × 109 vs. 0.8 ± 0.08 × 109, p < 0.05).ConclusionsSNF-Cy5.5 was synthesized and characterized with a high efficiency and purity. The higher affinity, specificity, and tumor targeting efficacy of SNF-Cy5.5 were confirmed by in vitro and in vivo tests. SNF-Cy5.5 is a promising optical probe for the imaging of esophageal adenocarcinoma.

Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning.

We address the challenging problem of whole slide image (WSI) classification. WSIs have very high resolutions and usually lack localized annotations. WSI classification can be cast as a multiple instance learning (MIL) problem when only slide-level labels are available. We propose a MIL-based method for WSI classification and tumor detection that does not require localized annotations. Our method has three major components. First, we introduce a novel MIL aggregator that models the relations of the instances in a dual-stream architecture with trainable distance measurement. Second, since WSIs can produce large or unbalanced bags that hinder the training of MIL models, we propose to use self-supervised contrastive learning to extract good representations for MIL and alleviate the issue of prohibitive memory cost for large bags. Third, we adopt a pyramidal fusion mechanism for multiscale WSI features, and further improve the accuracy of classification and localization. Our model is evaluated on two representative WSI datasets. The classification accuracy of our model compares favorably to fully-supervised methods, with less than 2% accuracy gap across datasets. Our results also outperform all previous MIL-based methods. Additional benchmark results on standard MIL datasets further demonstrate the superior performance of our MIL aggregator on general MIL problems.

56P The impact of tumour detection method on genomic and clinical risk and chemotherapy recommendation in early hormone receptor positive breast cancer

Symptomatic breast cancers share aggressive clinico-pathological characteristics compared to screen-detected breast cancers. The decision to administer adjuvant chemotherapy for early hormone receptor positive (HR+) HER-2 negative (HER2-) breast cancer patients, is guided by both the genomic and the clinical risk of disease recurrence. We assessed the association between the method of cancer detection and genomic and clinical risk, and its effect on adjuvant chemotherapy recommendation. Patients with early HR+ HER2- breast cancer, and known OncotypeDX Breast Recurrence Score (RS) test were included. A natural language processing (NLP) algorithm was used to identify the method of cancer detection. The clinical and genomic risks of symptomatic and screen-detected tumors were compared. The NLP algorithm identified the method of detection of 401 patients, with 216 (54%) diagnosed by routine screening, and the remainder secondary to symptoms. The distribution of OncotypeDX RS varied between the groups. In the symptomatic group there were lower proportions of low RS (13 vs 23%) and higher proportions of high RS (24 vs. 13%) compared to the screen-detected group (p=.03). Symptomatic tumors were significantly more likely to have a high clinical risk (59 vs 40%; p<.0001). Based on genomic and clinical risk and current guidelines, we found that women aged 50 and under, with symptomatic cancer, had an increased probability of receiving adjuvant chemotherapy recommendation compared to women with screen-detected cancers (57 vs. 35%; p=.03). We demonstrated an association between the method of cancer detection and both genomic and clinical risk. Symptomatic breast cancer, especially in young women, remains a poor prognostic factor that should be taken into account when evaluating patient prognosis and determining adjuvant treatment plans.

Big Data Brain Image Data Repair and Diagnosis Technology Based on Deep Learning

In this paper, we propose an automatic tumor detection algorithm in MRI brain images based on significance modeling based on directional features.Firstly, the MRI brain image is preprocessed to remove the interference of the skull region in the image.Then, directional-feature-based saliency detection is used to increase the contrast of the lesion area to achieve more accurate extraction of the tumor image area.A large number of experiments have been carried out on the brain image data sets, and compared with the mainstream automatic tumor detection methods, the effectiveness of the proposed algorithm has been proved.

A Hybrid Method for Brain Tumor Detection in Medical Image

Recognition of Brain Tumor is really a troublesome errand and the right investigation of the Tumor structure is likewise troublesome thus a programmed technique for the location of Tumor is in use these days. Without a doubt, this spares the time just as it gives increasingly exact outcomes as in contrast with manual location. The proposed technique is a hybrid methodology for discovery Tumor alongside the capacity to figure the territory (%age) involved by the Tumor in the general synapses, Right off the bat, Tumor locales from a MR picture are divided utilizing an OSTU Algorithm. Here, in addition KNN&amp; LLOYED are utilized for recognizing, Tumor influenced tissues from the not influenced tissues in this work.

Breast Tumor Detection in MR Images Based on Density

Breast cancer is dangerous in women. It is generally found after the symptoms appear. Detecting the breast cancer at an early stage and understanding the treatment are the most important strategies to prevent death from cancer. Generally, for detection of breast cancer, breast Magnetic Resonance Image (MRI) takes place. It is one of the best approaches to detect tumor in women. In this research paper, a combination of selection methods for seed region growing image segmentation is suggested to detect breast tumor. The suggested method has been divided into following parts: First, the pre-processing of breast image is performed. Second, the automatic threshold for binarization process is calculated. Third, the number of seed points and its position in the breast image are determined automatically using density of pixels value. Fourth, a method for calculation of threshold value is proposed for the purpose of region creation in seed region growing. For the evaluation purpose, the proposed method was applied and tested on the RIDER MRI breast dataset from National Biomedical Imaging Archive (NBIA). After the test was performed, it was observed that proposed algorithm gives 90% accuracy, 88% True Negative Fraction, 91% True Positive Fraction, 10% Misclassification Rate, 94% Precision and 86% Relative Overlap which is better than other existing methods. It not only gives better evaluation measure but also provides segmentation method for multiple tumor detection.

Raman Microspectroscopic Investigation and Classification of Breast Cancer Pathological Characteristics.

Breast cancer is one of the major cancers of women in the world. Despite significant progress in its treatment, an early diagnosis can effectively reduce its incidence rate and mortality. To improve the reliability of Raman-based tumor detection and analysis methods, we conducted an ex vivo study to unveil the compositional features of healthy control (HC), solid papillary carcinoma (SPC), mucinous carcinoma (MC), ductal carcinoma in situ (DCIS), and invasive ductal carcinoma (IDC) tissue samples. Following the identification of biological variations occurring as a result of cancer invasion, principal component analysis followed by linear discriminate analysis (PCA-LDA) algorithm were adopted to distinguish spectral variations among different breast tissue groups. The achieved results confirmed that after training, the constructed classification model combined with the leave-one-out cross-validation (LOOCV) method was able to distinguish the different breast tissue types with 100% overall accuracy. The present study demonstrates that Raman spectroscopy combined with multivariate analysis technology has considerable potential for improving the efficiency and performance of breast cancer diagnosis.

3D multi-view tumor detection in automated whole breast ultrasound using deep convolutional neural network

In recent years, automated whole breast ultrasound (ABUS) has drawn attention to breast disease detection and diagnosis applications. However, reviewing ABUS volumes is a time-costing task and some subtle tumors may be missed. In this paper, a 3D multi-view tumor detection method is proposed for ABUS volumes. Firstly, a layer connected feature extraction network is designed for Faster R-CNN. Then, orthogonal multi-view slices are reconstructed and detected using this modified Faster R-CNN to extract 2D candidates. Finally, a 3D multi-view position analysis scheme is designed to fuse 2D detection results and get final 3D bounding boxes. The performance of this proposed method is evaluated on a data set of 158 volumes from 75 patients by 5-fold cross-validation. Experimental results show that our method achieves a sensitivity of 95.06% with 0.57 false positives (FPs) per volume. Compared with existing detection methods, the proposed method is more effective and general.

Brain Tumor Diagnosis Support System: A Decision Fusion Framework

The early and accurate detection of brain tumors is important in providing effective and efficient therapy and thus can result in increased survival rates. Current image-based tumor detection and diagnosis methods depend heavily on the interpretation of the neuro specialists and/or radiologists. Therefore, it is quite possible for the interpretation process to be time-consuming, and prone to human error and subjectivity. Automatic detection and classification of brain tumors have the potential to achieve efficiency and higher degree of predictable accuracy. However, it is well established that the accuracy performance of automatic detection and classification techniques varies from technique to technique, and tends to be image modality dependent. Thus, it is prudent to explore the variability in the performance of these techniques as a means to achieve consistent high accuracy performance. This paper presents a framework for fusing multiple tumor classifiers. The fusion process is based on the Dempster Shafer evidence fusion theory. Several tumor classifiers are employed. Experimental results will be presented to validate the efficiency of the proposed framework. It is concluded that fusing the classification decisions made by the various classifiers it is conceivable that efficient and consistent high accuracy classification performance can be attained.

Structural Characterization of the Solution Chemistry of Zirconium(IV) Desferrioxamine: A Coordination Sphere Completed by Hydroxides.

Positron emission tomography (PET) using radiolabeled, monoclonal antibodies has become an effective, noninvasive method for tumor detection and is a critical component of targeted radionuclide therapy. Metal ion chelator and bacterial siderophore desferrioxamine (DFO) is the gold standard compound for incorporation of zirconium-89 in radiotracers for PET imaging because it is thought to form a stable chelate with [89Zr]Zr4+. However, DFO may not bind zirconium-89 tightly in vivo, with free zirconium-89 reportedly liberated into the bones of experimental mouse models. Although high bone uptake has not been observed to date in humans, this potential instability has been proposed to be related to the unsaturated coordination sphere of [89Zr]Zr-DFO, which is thought to consist of the 3 hydroxamate groups of DFO and 1 or 2 water molecules. In this study, we have used a combination of X-ray absorption spectroscopy and density functional theory (DFT) geometry optimization calculations to further probe the coordination chemistry of this complex in solution. We find the extended X-ray absorption fine structure (EXAFS) curve fitting of an aqueous solution of Zr(IV)-DFO to be consistent with an 8-coordinate Zr with oxygen ligands. DFT calculations suggest that the most energetically favorable Zr(IV) coordination environment in DFO likely consists of the 3 hydroxamate ligands from DFO, each with bidentate coordination, and 2 hydroxide ligands. Further EXAFS curve fitting provides additional support for this model. Therefore, we propose that the coordination sphere of Zr(IV)-DFO is most likely completed by 2 hydroxide ligands rather than 2 water molecules, forming Zr(DFO)(OH)2.

Robust spatial information based tumour detection for brain MR images

Multimodal brain MR image analysis is still a challenging research area due to its complex intensity distribution and sensitivity towards the noise. Tumourous cells have different characteristics than normal human cells, which makes them more salient. In this Letter, the authors propose a novel unsupervised spatial information based saliency boosting tumour detection method which will help to identify tumourous cells by making it more clearly visible. Initially, a pseudo-coloured MR image is formed using the CIELab colour space. Saliency map has been established by calculating distance among scales varying elliptical windows in both spatial and colour space. Elliptical windows endeavour to cover-up curved outliers of the brain images. The average intensity value is kept constant by fixing the axis ratio for each window. The proposed algorithm has been evaluated on both real and simulated brain images of different patients from MICCAI-BRATS database. The performance analysis of the new algorithm exhibits higher accuracy with a low computational complexity as compared to other state of the art. The efficacy is due to the immobility of the window across rows and columns to move over the image. The novelty of the proposed technique is that neither it downscales the input images nor require any training bases.

Performance Analysis of Glioma Brain Tumor Segmentation Using Ridgelet Transform and Co-Active Adaptive Neuro Fuzzy Expert System Methodology

Objective: The Glioma brain tumor detection and segmentation methods are proposed in this paper using machine learning approaches. The primary objective of this paper is to provide high level of tumor region segmentation using optimization and machine learning techniques. Methods: The boundary edge pixels are detected using Kirsch's edge detectors and then contrast adaptive histogram equalization method is applied on the edge detected pixels. Then, Ridgelet transform is applied on this enhanced brain image in order to obtain the Ridgelet multi resolution coefficients. Further, features are derived from the Ridgelet transformed coefficients and the features are optimized using Principal Component Analysis (PCA) method and these optimized features are classified into Glioma or non-Glioma brain images using Co-Active Adaptive Neuro Fuzzy Expert System (CANFES) classifier. Results: The proposed method with PCA and CANFES classification approach obtains 97.6% of sensitivity (Se), 98.56% of Specificity (sp), 98.73% of Accuracy (Acc), 98.85% of Precision (Pr), 98.11% of False Positive Rate (FPR) and 98.185 of False Negative Rate (FNR), then the proposed Glioma brain tumor detection method using CANFES classification approach only.

SERS-based sensor for direct L-selectin level determination in plasma samples as alternative method of tumor detection.

Selectin ligands are present on the surface of tumor cells, for this reason lowering the L-selectin level in the blood and lymph can indicate presence of the tumor. Therefore the selectin level in the plasma are potential targets for anticancer therapy. We demonstrate the surface enhanced Raman spectroscopy (SERS)-based sensor for the determination of L-selectin level in biological samples that can be used in medical diagnosis. The combination of SERS with the method of multivariate analysis as principle component analysis (PCA) allows to strengthen the presented data analysis. The loadings of PCA permit to indicate those vibration modes, that are the most important for the assumed identification (bands at 1574, 1450, 1292 cm-1 ). Two bands at 1286 and 1580 cm-1 were selected for the determination of the calibration curve (bands intensities I1286 /I1580 ratio). The L-selectin level of biological samples can be read, directly from the calibration curve. The presented sensor is as a sensitive tool with good specificity and selectivity of L-selectin, even in the case of coexistence of P- and E-selectin.

3D tumor detection in automated breast ultrasound using deep convolutional neural network.

Automated breast ultrasound (ABUS) has drawn attention in breast disease detection and diagnosis applications. Reviewing hundreds of slices produced by ABUS is time-consuming. In this paper, a tumor detection method for ABUS image based on convolutional neural network is proposed. First, integrating multitask learning with YOLOv3, an improved YOLOv3 detection network is designed to detect tumor candidate in two-dimensional (2D) slices. Two-dimensional detection separately treats each slice, leading to larger differences of position and score for tumor candidate in adjacent slices. Due to the influence of artifact, noise, and mammary tissues, 2D detection may include many false positive regions. To alleviate these problems, a rescoring processing algorithm is first designed. Then three-dimensional volume forming and FP reduction scheme are built. This method was tested on 340 volumes (124 patients, 181 tumors) with fivefold cross validation. It achieved sensitivities of 90%, 85%, 80%, 75%, and 70% at 7.42, 3.31, 1.62, 1.23, and 0.88 false positives per volume. Compared with existing ABUS tumor detection methods, our method gets a promising result.

Brain Tumor Detection Using Multipath Convolution Neural Network (CNN)

Brain tumor segmentation is an emerging application of automated medical image diagnosis. Robust approach of brain tumor segmentation and detection is a research problem, and the performance metrics of the existing tumor detection methods are not appropriately known. Deep neural network using convolution neural network (CNN) is being researched in this direction, but no general architecture is found that can be used as robust method for brain tumor detection. The authors have proposed a multipath CNN architecture for brain tumor segmentation and detection, which provides improved results as compared to existing methods. The proposed work has been tested for datasets BRATS2013, BRTAS2015, and BRATS2017 with significant improvement in dice index and timing values by utilizing the capability of multipath CNN architecture, which combines both local and global paths.

Fractional wavelet transform based diagnostic system for brain tumor detection in MR imaging

AbstractThe brain tumor detection is a highly complicated but significant task. The early detection of a brain tumor can increase the survival rate of an individual by providing proper treatment. This work proposes a computer‐aided diagnostic method for brain tumor detection using fractional wavelet transform (FrDWT) with different values of alpha (α) ranging from (0.1‐1), histogram‐based various local feature descriptors, feature selectors, and two classification methods, that is, support vector machine (SVM) as well as artificial neural network (ANN). The brain MR images dataset is taken from BraTS 2015, e‐health laboratory, and Harvard Medical School. The FrDWT and the local feature descriptors used are combined to extract features. Some of the features are selected using Eigenvector centrality and Laplacian Score techniques. The selected features are trained and classified by the two classifiers, SVM and ANN. It is a type of binary classification, so the labels provided to the classifier are named “normal” and “abnormal.” The performance is estimated using parameters like accuracy, sensitivity, precision, specificity, and F1 score. The results of FrDWT are compared with conventional discrete wavelet transform (DWT), and it is observed that FrDWT outperforms DWT at alpha (α) values lower than 0.5.

Detection and diagnosis of brain tumors‐framework using extreme machine learning and CANFIS classification algorithms

AbstractIn this paper, brain tumors are detected and diagnosed using machine learning approaches in brain magnetic resonance imaging (MRI), which has many real time clinical applications. Noise variations in brain images are detected and removed using index filter, which is proposed in this paper. Brain images devoid of noise content are in spatial domain format, which are not suitable for further feature extraction process. Hence, there is a need for converting all the spatial pixels into multi orientation pixels. In this paper, Gabor transform is used for spatial into multi oriented image conversion. The noise filtered images are transformed into multi orientation‐based brain image using Gabor transform method. Then, the hybrid features which are the integration of statistical and texture features (GLCM, gray level co‐occurrence matrix, and LDP, local derivative pattern), are computed from this transformed brain image. These computed features are classified using extreme machine learning (EML) approach, which categorizes the source brain image as normal or abnormal. Then, the segmented tumor regions are diagnosed using co‐active adaptive neuro fuzzy inference system (CANFIS) classifier, which classifies the segmented regions as mild or severe. The proposed tumor detection and diagnosis methods are applied and tested on the brain images which are available as open access dataset. The performance of the proposed brain tumor detection method is analyzed in terms of sensitivity, specificity, and accuracy with classification rate.

Efficient isolation and quantification of circulating tumor cells in non-small cell lung cancer patients using peptide-functionalized magnetic nanoparticles.

BackgroundCirculating tumor cells (CTCs) carry a wealth of information on primary and metastatic tumors critical for enhancing the understanding of the occurrence, progression and metastasis of non-small cell lung cancer (NSCLC). However, the low sensitivity of traditional tumor detection methods limits the application of CTCs in the treatment and disease surveillance of NSCLC. Therefore, CTCs isolation and detection with high sensitivity is highly desired especially for NSCLC patients, which is significant because of high occurrence and mortality. While it is very challenging because of the lower expression of CTC positive biomarkers such as epithelial cell adhesion molecules and cytokeratins (EpCAM and CKs), herein we report a method based on peptide-functionalized magnetic nanoparticles with high CTC capture efficiency, which demonstrates superiority in NSCLC clinical applications.MethodsFor analysis and comparison of the peptide-functionalized magnetic nanoparticles (TumorFisher, Nanopep Corp.) and the antibody-modified magnetic beads (CellSearch, Janssen Diagnostics, LLC), two NSCLC cell lines, A549 and NCI-H1975 were chosen to measure the binding affinity and capture efficiency. In order to compare the effect of the clinical application of these two detection systems, 7 early stage patients with NSCLC were enrolled in this study. To further explore the clinical utility of CTC counting in different stages, 81 NSCLC patients in stage I–IV were enrolled for CTC enumeration and statistical analysis.ResultsThe binding affinities of the recognition peptide to A549 and NCI-H1975 are 76.7%±11.0% and 70.1%±4.8%, respectively, which is similar with the positive control group (anti-EpCAM antibodies). CTCs were captured in 5/7 (71.4%) of early stage NSCLC patients with NSCLC in TumorFisher system, which is higher than CellSearch, and the false negative of TumorFisher is much lower than CellSearch. In a larger clinical cohort, the CTC numbers of NSCLC patients varied in different stages and the overall detection rate of TumorFisher was 59/81 (72.8%), with the similar proportion in stage I (21/29, 72.4%), II (17/22, 77.3%) and III (16/21, 76.2%).ConclusionsHighly efficient CTC isolation technique based on peptide-magnetic nanoparticles was firstly applied in NSCLC patients. Compared with the antibody-based the technique, the higher CTC detection rates (71.4%) in NSCLC patient blood samples were demonstrated for the patients in different stages, I–IV, especially in early stages. This indicates the feasibility of the clinical utility of this new technique in early stage screening, prognosis and therapy evaluation of NSCLC.

RETRACTED ARTICLE: Computer-aided detection of brain tumor from magnetic resonance images using deep learning network

Brain tumor can be considered to be a fatal and life-threatening disease caused by undesirable cell proliferation in the human brain. Out of the several diseases in the field of medical science, brain tumor turns out to be one of the most uncompromising problems. A tumor can be categorized as benign or malignant types in which benign tumors are non-cancerous while malignant tumors are cancerous tumors. There are numerous tumor detection methods but there are still more research going on in this area since quantitative analysis, an accurate disease diagnosis and detection of brain tumor are very much essential with scientific proofs. Therefore, timely planning can be prepared to save a person’s life with brain tumor. This paper presents a computer aided approach with a 2D convolutional neural network for classifying the brain MRI images into two classes: Normal class and tumor class. In this paper, other classification methods are also used for comparison. The results are compared in terms of precision value, Recall value, F1-Score value. This proposed method shows better accuracy of 97% than the other methods.