Detection Of Cancer Tumors Research Articles

Ensemble approach of deep learning models for binary and multiclass classification of histopathological images for breast cancer

Breast cancer (BC) is the most frequently occurring cancer disease observed in women after lung cancer. Out of different stages, invasive ductal BC causes maximum deaths in women. In this work, three deep learning (DL) models such as Vision Transformer (ViT), Convmixer, and Visual Geometry Group-19 (VGG-19) are implemented for the detection and classification of different breast cancer tumors with the help of Breast cancer histopathological (Break His) image database. The performance of each model is evaluated using an 80:20 training scheme and measured in terms of accuracy, precision, recall, loss, F1-score, and area under the curve (AUC). From the simulation result, ViT showed the best performance for binary classification of breast cancer tumors with accuracy, precision, recall, and F1-score of 99.89 %, 98.29 %, 98.29 %, and 98.29 %, respectively. Also, ViT showed the best performance in terms of accuracy (98.21 %), average Precision (89.84 %), recall (89.97 %), and F1-score (88.75) for eight class classifications. Moreover, we have also ensemble the ViT-Convmixer model and observed that the performance of the ensemble model is reduced as compared to the ViT model. We have also compared the performance of the proposed best model with other existing models reported by several research groups. The study will help find suitable models that will increase accuracy in early diagnoses of BC. We hope the study will also help to minimize human errors in the early diagnosis of this fatal disease and administer appropriate treatment. The proposed model may also be implemented for the detection of other diseases with improved accuracy.

A ResNet based transfer learning pulmonary medical image disease detection system

Medical imaging represents a significant application of deep learning. In response to the vast domain of medical image analysis and the limitations and inefficiencies of conventional methods for diagnosing brain diseases, this paper explores the application of an enhanced ResNet-50 model in the classification of brain CT images. The goal is to improve the detection and classification accuracy of aneurysms, cancer, and malignant tumors. The study utilized 259 images, undergoing training, validation, and testing processes to verify the model's efficacy. The ResNet-50 model addresses the issue of vanishing gradients in deep networks through residual learning, making it suitable for high-resolution images and small datasets. Results indicate good training performance, though some fluctuations in validation performance, achieving a validation accuracy of 0.960. This research not only enhances diagnostic accuracy for brain diseases but also paves a new path for the further application of deep learning technologies in the medical field.

Design of Terahertz Refractive Index-Based Spiral Hollow-Core Photonic Crystal Biosensor Using Enhanced Probabilistic Pyramid Neural Networks for Brain Tumor Detection

Cancer diagnosis is difficult and costly due to the complexity of the brain. Photonic technology-based biosensors show potential for identifying malignant tissues, including brain tumors, but they are often costly, time-consuming, and computationally difficult. To address these challenges, we propose an enhanced probabilistic pyramid neural networks (EPPNN)-based hollow-core photonic crystal fiber (PCF) biosensor with terahertz refractive index (THzBio-ECPPN) for detection of cancerous brain tumors. The approach is divided into two stages: biosensor design and brain tumor detection. Initially, PCF geometry with suspended cladding and a spiral-shaped hollow-core in the terahertz (THz) band is proposed. The PCF biosensors’ characteristics are then calculated using the EPPNN model. The EPPNN model’s hyperparameters are modified using the circle-inspired optimization algorithm to maximize accuracy and minimize effective mode loss. The proposed biosensor is then used to identify brain tumors. Experimental evaluations utilizing MATLAB show that the suggested strategy surpasses earlier methods, with a higher sensitivity (98%). The sensor has exceptional performance characteristics, such as a high figure of merit of 1.25–1.35 RI range and sensitivity of 50000 nm RIU−1, indicating its potential for precise detection of changes in refractive index. This combination of photonic crystal structures and neural networks has enormous potential for improving cancerous tumor accuracy to 99.92%, precision to 99.23%, specificity to 99.73%,and sensitivity to 99.36% of brain tumor diagnosis.

Detection of Early Gastric Cancer and Lesion Segmentation Based on Deep Learning

Background: Early detection and precise identification of gastric cancer tumors significantly enhance patient outcomes. Conventional methods often rely on manual interpretation of endoscopic images, which can be time-consuming and subjective. Recent advancements in deep learning offer promising alternatives for automating and improving these diagnostic processes. Objective: The primary objective of this study is to explore the effectiveness of a deep learning model in detecting early gastric cancer and segmenting lesions from endoscopic images. Methods: This retrospective study was conducted at Khalifa Gul Nawaz Teaching Hospital /BMC Bannu, from December 2021 to November 2022. Medical records and endoscopic images from 180 patients with suspected or confirmed gastric lesions were analyzed. Images were diversified in terms of lesion types and characteristics. Preprocessing steps including standardization and enhancement techniques were applied to improve image quality for analysis. Results: The deep learning model achieved an accuracy of 90% in identifying gastric cancer lesions, with a sensitivity of 85% and specificity of 92%. The area under the curve (AUC-ROC) was calculated to be 0.61, indicating a good discriminative performance of the model. Conclusion: The deep learning model demonstrated significant potential for enhancing the detection and segmentation of early gastric cancer from endoscopic images, providing a valuable tool for gastroenterologists in the early diagnosis and treatment planning.

Study of a Deep Convolution Network with Enhanced Region Proposal Network in the Detection of Cancerous Lung Tumors.

A deep convolution network that expands on the architecture of the faster R-CNN network is proposed. The expansion includes adapting unsupervised classification with multiple backbone networks to improve the Region Proposal Network in order to improve accuracy and sensitivity in detecting minute changes in images. The efficiency of the proposed architecture is investigated by applying it to the detection of cancerous lung tumors in CT (computed tomography) images. This investigation used a total of 888 images from the LUNA16 dataset, which contains CT images of both cancerous and non-cancerous tumors of various sizes. These images are divided into 80% and 20%, which are used for training and testing, respectively. The result of the investigation through the experiment is that the proposed deep-learning architecture could achieve an accuracy rate of 95.32%, a precision rate of 94.63%, a specificity of 94.84%, and a high sensitivity of 96.23% using the LUNA16 images. The result shows an improvement compared to a reported accuracy of 93.6% from a previous study using the same dataset.

PSMA-Targeted Therapy: Advancements in Detection and Treatment Modalities with Dr. Scott T. Tagawa.

Prostate cancer is one of the most challenging malignancies due to its high incidence and prevalence, as it is the most frequently diagnosed non-skin cancer in men. The timely identification of prostate cancer and its metastasis is paramount for ensuring favorable outcomes for patients. Prostate-specific membrane antigen (PSMA) emerges as a promising biomarker for its detection, due to its specificity. This makes it an ideal target for the early identification of a metastatic phenotype. Situated on the membrane of tumor cells, PSMA facilitates the attachment of PSMA-targeting particles, enabling their detection through positron emission tomography (PET) scans with relative ease. Utilizing these imaging agents in conjunction with PET scans enhances the accuracy of prostate cancer tumor detection compared to PET scans alone. The advancement in prostate cancer imaging has paved the way for innovative treatment modalities. Prostate-specific membrane antigen-targeted radionuclide therapies (PSMA-TRT) exploit PSMA imaging agents to target identified prostate cancer malignancies with precise radiation, thereby reducing or eliminating the tumor mass. PSMA-TRT exhibits significant promise in prostate cancer therapy, evident from the notable declines in prostate-specific antigen (PSA) levels post treatment. However, PSMA-TRT carries both beneficial and adverse effects. While it represents a substantial leap forward in tumor cell imaging, PSMA-based antigens, being larger particles than ligands, offer prolonged imaging capabilities. Yet, the long-term effects of PSMA-TRT remain unknown, with the short-term adverse ones including fatigue, nausea, pain flares, and potential radiation exposure to others.

Efficient Machine Learning and Deep Learning Techniques for Detection of Breast Cancer Tumor

The detection of cancer tumors is an essential component that has important consequences for the speedy involvement of medical professionals and the enhancement of patient outcomes. This review paper presents a complete study of the current body of research and methodology, as well as an in-depth assessment of the use of machine learning (ML) and deep learning (DL) in the detection of cancer tumors. In addition, the article gives a full analysis of the approaches involved. Machine learning and deep learning, which effectively handle ambiguity in the identification of malignant tumors, provide an alternative method for dealing with the complexity of brain tissue. This method is offered by a combination of machine learning and deep learning. The first part of the review draws attention to the significance of making an accurate diagnosis of breast cancer, highlights the limits of traditional diagnostic methods, and investigates the cutting-edge area of medical imaging technology. After that, it investigates the fundamentals of ML and DL and how they might be used to deal with the challenges that are inherent in the interpretation of complicated imaging data. In addition, the paper explores the ways in which models enhance the processes of feature extraction, picture segmentation, and classification in breast tumor detection systems.

MAMILNet: advancing precision oncology with multi-scale attentional multi-instance learning for whole slide image analysis.

Whole Slide Image (WSI) analysis, driven by deep learning algorithms, has the potential to revolutionize tumor detection, classification, and treatment response prediction. However, challenges persist, such as limited model generalizability across various cancer types, the labor-intensive nature of patch-level annotation, and the necessity of integrating multi-magnification information to attain a comprehensive understanding of pathological patterns. In response to these challenges, we introduce MAMILNet, an innovative multi-scale attentional multi-instance learning framework for WSI analysis. The incorporation of attention mechanisms into MAMILNet contributes to its exceptional generalizability across diverse cancer types and prediction tasks. This model considers whole slides as "bags" and individual patches as "instances." By adopting this approach, MAMILNet effectively eliminates the requirement for intricate patch-level labeling, significantly reducing the manual workload for pathologists. To enhance prediction accuracy, the model employs a multi-scale "consultation" strategy, facilitating the aggregation of test outcomes from various magnifications. Our assessment of MAMILNet encompasses 1171 cases encompassing a wide range of cancer types, showcasing its effectiveness in predicting complex tasks. Remarkably, MAMILNet achieved impressive results in distinct domains: for breast cancer tumor detection, the Area Under the Curve (AUC) was 0.8872, with an Accuracy of 0.8760. In the realm of lung cancer typing diagnosis, it achieved an AUC of 0.9551 and an Accuracy of 0.9095. Furthermore, in predicting drug therapy responses for ovarian cancer, MAMILNet achieved an AUC of 0.7358 and an Accuracy of 0.7341. The outcomes of this study underscore the potential of MAMILNet in driving the advancement of precision medicine and individualized treatment planning within the field of oncology. By effectively addressing challenges related to model generalization, annotation workload, and multi-magnification integration, MAMILNet shows promise in enhancing healthcare outcomes for cancer patients. The framework's success in accurately detecting breast tumors, diagnosing lung cancer types, and predicting ovarian cancer therapy responses highlights its significant contribution to the field and paves the way for improved patient care.

A Modified LeNet CNN for Breast Cancer Diagnosis in Ultrasound Images.

Convolutional neural networks (CNNs) have been extensively utilized in medical image processing to automatically extract meaningful features and classify various medical conditions, enabling faster and more accurate diagnoses. In this paper, LeNet, a classic CNN architecture, has been successfully applied to breast cancer data analysis. It demonstrates its ability to extract discriminative features and classify malignant and benign tumors with high accuracy, thereby supporting early detection and diagnosis of breast cancer. LeNet with corrected Rectified Linear Unit (ReLU), a modification of the traditional ReLU activation function, has been found to improve the performance of LeNet in breast cancer data analysis tasks via addressing the "dying ReLU" problem and enhancing the discriminative power of the extracted features. This has led to more accurate, reliable breast cancer detection and diagnosis and improved patient outcomes. Batch normalization improves the performance and training stability of small and shallow CNN architecture like LeNet. It helps to mitigate the effects of internal covariate shift, which refers to the change in the distribution of network activations during training. This classifier will lessen the overfitting problem and reduce the running time. The designed classifier is evaluated against the benchmarking deep learning models, proving that this has produced a higher recognition rate. The accuracy of the breast image recognition rate is 89.91%. This model will achieve better performance in segmentation, feature extraction, classification, and breast cancer tumor detection.

Biyomedikal Uygulamalar için Esnek Alt Tabakalar Kullanarak Frekans-Yapılandırılabilir Yeni Bir Yama Anten Tasarımı

The purpose of this research was to design and implement a flexible horizontal H-shaped microstrip antenna (flexible-HHMA) using various materials for cancer tumor detection. Microstrip antennas, which can also be utilized as tumor detection sensors and can function as both a receiver and a transmitter, are composed of two major components: the patch and the ground plane. The copper tape was used to analyze various materials’ impacts on antenna performance to form the patch and ground planes, and felt, jean, and photo paper was employed as the substrate. To accomplish this, antennas operating at frequencies ranging from 2 to 10 GHz, frequently used in biomedical applications, were constructed and computations performed using a full wave electromagnetic solver based on finite integration technique (FIT). The proposed microstrip antennas may be used as sensors in biomedical measurement systems that make use of the dielectric contrast between the healthy and malignant tissues at microwave frequencies.

Breast Cancer Detection by Terahertz UWB Microstrip Patch Antenna Loaded with 6X6 SRR Array

This paper presents cancer tumor detection in the breast phantom and cancer tissue detection in the excised breast tissue phantom by the ultra-wideband terahertz microstrip patch antenna. The proposed antenna structure consists of a silicon dioxide substrate with a dielectric constant of 3.9 and a thickness of 200 µm, a radiating gold patch of length 560 µm, width 700 µm, and thickness 36 µm which is on top of the substrate, and an array of 6 × 6 gold Split Ring Resonator at the ground plane. Each SRR is separated by 28.75 µm. An array of SRR at the antenna's ground plane enhances bandwidth, efficiency, gain, directivity and reduces back radiation. The antenna operates in the frequency range of 0.1-3 THz, with a gain of 19.22 dBi and an efficiency of 98.74%. The antenna setup with the breast phantom and excised breast tissue phantom in between have been designed and analyzed in the CST microwave studio 2019 version. Tumor in the breast phantom and the cancerous tissue in the breast tissue phantom can be detected by placing the phantoms between the two identical antennas. The difference in the dielectrics of the breast and the tumor layers can determine the difference between healthy and malignant tissue. A typical breast phantom model that replicates a real-human breast and a specific excised tissue that replicates the actual breast tissue with and without cancer tissue in terms of dielectric and optical properties has been employed in this study to detect the tumor and cancerous tissue.

Cyclic Voltammetry of Screen-Printed Carbon Electrode Coated with Ag-ZnO Nanoparticles in Chitosan Matrix.

In this paper, the authors describe the fabrication of nanocomposite chitosan-based systems of zinc oxide (ZnO), silver (Ag) and Ag-ZnO. Recently, the development of coated screen-printed electrodes using metal and metal oxide nanoparticles (NPs) for the specific detection and monitoring of different cancer tumors has been obtaining important results. Ag, ZnO NPs and Ag-ZnO prepared by the hydrolysis of zinc acetate blended with a chitosan (CS) matrix were used for the surface modification of screen-printed carbon electrodes (SPCEs) in order to analyze the electrochemical behavior of the typical redox system of a 10 mM potassium ferrocyanide-0.1 M buffer solution (BS). The solutions of CS, ZnO/CS, Ag/CS and Ag-ZnO/CS were prepared in order to modify the carbon electrode surface, and were measured at different scan rates from 0.02 V/s to 0.7 V/s by cyclic voltammetry. The cyclic voltammetry (CV) was performed on a house-built potentiostat (HBP). The cyclic voltammetry of the measured electrodes showed the influence of varying the scan rate. The variation of the scan rate has an influence on the intensity of the anodic and cathodic peak. Both values of currents (anodic and cathodic currents) have higher values for 0.1 V/s (Ia = 22 μA and Ic = -25 μA) compared to the values for 0.06 V/s (Ia = 10 μA and Ic = -14 μA). The CS, ZnO/CS, Ag/CS and Ag-ZnO/CS solutions were characterized using a field emission scanning electron microscopy (FE-SEM) with EDX elemental analysis. The modified coated surfaces of screen-printed electrodes were analyzed using optical microscopy (OM). The present coated carbon electrodes showed a different waveform compared to the voltage applied to the working electrode, depending on the scan rate and chemical composition of the modified electrodes.

P226 Indocyanine green fluorescence imaging for real-time detection of breast cancer tumors: a systematic review

P226 Indocyanine green fluorescence imaging for real-time detection of breast cancer tumors: a systematic review

Thermograms-based detection of cancerous tumors in breasts applying texture features

ABSTRACT In a global scenario, it is a fact that the disease of breast cancer among women is the major cause of death as recorded in the last three decades. The detection of cancerous tumour at an early stage helps to prevail a better chance of survival. Among different modalities such as Mammography, Ultrasound, X-Ray and various others, Thermography is considered to be an early detector of breast tumour. In this study, images are considered from the database available at public repository, Visual Labs, Brazil. The texture characteristics for every region of image are unique. To capture the variation in the texture caused by the tumour, the different texture features based on statistical analysis are extracted from the breast thermograms. Two different feature selection methods have been considered in this study, namely, Least Absolute Shrinkage and Selection Operator (LASSO) Regression and Adaptive LASSO Regression. The final set of features is classified using Support Vector Machine (SVM) with different kernel functions. Among LASSO Regression and Adaptive LASSO Regression, the latter is being observed to yield a better accuracy on SVM classifier with 96.79% by applying Radial basis function (RBF) kernel as compared to the former giving 90.07% with quadratic kernel.

Retracted: Gene Mutation Classification through Text Evidence Facilitating Cancer Tumour Detection

Retracted: Gene Mutation Classification through Text Evidence Facilitating Cancer Tumour Detection

Using Stepwise Method to Find the Most Influencing Feature to the Cell Nuclei of a Breast Mass

In real life, the influencing factors that lead to an outcome are varied and complex. However, how to organize the complex variable relationship into a concise and effective model for prediction is critical. Therefore, the Stepwise method was used in this study to organize the relationship between malignant and benign detection of breast cancer tumors and changes in cell characteristics into a model. In this paper, the diagnosis data of breast cancer of patients in the hospital were quoted. The benign and malignant characteristics of breast cancer were taken as independent variables, and the characteristic changes of cells were taken as dependent variables to conduct data analysis with R language, so as to obtain the most effective model. The results show that the prediction accuracy of the model obtained by AIC method is the highest. AIC selected seven dependent variables and reached 79.8 percent. The model prediction accuracy of BIC was 77.2 percent. Compared with AIC method, BIC only selected four dependent variables and obtained a more concise model. However, BIC is too concise and loses the accuracy of model prediction in some aspects.

Optimized textural features for mass classification in digital mammography using a weighted average gravitational search algorithm

Early detection of breast cancer cells can be predicted through a precise feature extraction technique that can produce efficient features. The application of Gabor filters, gray level co-occurrence matrices (GLCM) and other textural feature extraction techniques have proven to achieve promising results but were often characterized by a high false-positive rate (FPR) and false-negative rate (FNR) with high computational complexities. This study optimized textural features for mass classification in digital mammography using the weighted average gravitational search algorithm (WA-GSA). The Gabor and GLCM features were fused and optimized using WA-GSA to overcome the weakness of the textural feature techniques. With support vector machine (SVM) used as the classifier, the proposed algorithm was compared with commonly applied techniques. Experimental results show that the SVM with WA-GSA features achieved FPR, FNR and accuracy of 1.60%, 9.68% and 95.71% at 271.83 s, respectively. Meanwhile, SVM with Gabor features achieved FPR, FNR and accuracy of 3.21%, 12.90% and 93.57% at 2351.29 s, respectively, while SVM with GLCM features achieved FPR, FNR and accuracy of 4.28%, 18.28% and 91.07% at 384.54 s, respectively. The obtained results show the prevalence of the proposed algorithm, WA-GSA, in the classification of breast cancer tumor detection.

Cancerous brain tumor detection using hybrid deep learning framework

Computational <span>models based on deep learning (DL) algorithms have multiple processing layers representing data at multiple levels of abstraction. Deep learning has exploded in popularity in recent years, particularly in medical image processing, medical image analysis, and bioinformatics. As a result, deep learning has effectively modified and strengthened the means of identification, prediction, and diagnosis in several healthcare fields, including pathology, brain tumours, lung cancer, the abdomen, cardiac, and retina. In general, brain tumours are among the most common and aggressive malignant tumour diseases, with a limited life span if diagnosed at a higher grade. After identifying the tumour, brain tumour grading is a crucial step in evaluating a successful treatment strategy. This research aims to propose a cancerous brain tumor detection and classification using deep learning. In this paper, numerous soft computing techniques and a deep learning model to summarise the pathophysiology of brain cancer, imaging modalities for brain cancer, and automated computer-assisted methods for brain cancer characterization is used. In the sense of machine learning and the deep learning model, paper has highlighted the association between brain cancer and other brain disorders such as epilepsy, stroke, Alzheimer's, Parkinson's, and Wilson's disease, leukoaraiosis, and other neurological disorders.</span>

A novel work function tuning strategy-based ECL sensor with sulfur dots and Au NP@MoS2 nanosheet heterostructure for triple-negative breast cancer diagnosis

In this work, a novel biosensor has been developed based on the sulfur dots and Au NP@MoS2 nanosheet heterostructure. On the one hand, highly luminescent sulfur dots were prepared by the microwave-assisted synthesis method as electrochemiluminescence (ECL) emitter. On the other hand, in order to regulate the ECL signal, Au NP@MoS2 nanosheet heterostructure has been constructed. In the heterostructure, the work function of 2-D MoS2 nanosheet with excellent electronic properties was relatively low than that of Au NPs. Due to the work function tuning strategy, there were local electrophilic or nucleophilic regions in the heterostructure. The resulted self-driven charge transfer at the interface further increased the local electron density of Au NPs. Therefore, the ECL quenching effect caused by the close-range electron transfer between the sulfur dots and the Au NPs has been effectively suppressed. And the localized surface plasmon resonance (LSPR) effect of Au NPs played a primary role to amplify the ECL signal of sulfur dots. Finally, the sensing system was designed for the detection of miRNA-210 from 0.1 pM to 10 nM. The ECL sensor showed good analytical performance in the detection of triple-negative breast cancer tumor and paracancerous tissues with the recoveries ranging from 91.7% to 102.4%. The satisfactory results indicated the work function tuning strategy-based sensor with sulfur dots and Au NP@MoS2 nanosheet heterostructure possessed great potential in the ECL research and clinical analysis.

Employing the Defective Photonic Crystal Composed of Nanocomposite Superconducting Material in Detection of Cancerous Brain Tumors Biosensor: Computational Study

The present research is focused on the externally tunable defect mode properties of a one dimensional (1D) defective photonic crystal (DPhC) for fast detection of cancerous brain tumors. The proposed design has utilized conventional 1D DPhC whose cavity is coated with SiO2 nanoparticles embedded in a superconducting material layer called a nanocomposite layer. The purpose of a nanocomposite superconducting layer is to induce temperature dependent external tuning of the defect mode inside PBG, in addition, to changing in the angle of incidence. The inclusion of a nanocomposite layer also improves the interaction between light and different brain tissue samples under examination. In order to investigate the transmission properties of the proposed structure the transfer matrix formulation in addition to the MATLAB computational tool has been used. First, we have chosen the optimized internal parameters at normal incidence to obtain the maximum performance of the design. Secondly, the effect of change in angle of incidence has been studied to further increase the performance by means of sensitivity, quality factor, the figure of merit and limit of detection to ensure external tuning of defect mode. After achieving a maximum value of sensitivity (4139.24 nm/RIU) corresponding to a sample containing a wall of brain tissues at θ = 63° we have further investigated the effect of change in temperature of nanocomposite layers on the position and intensity both of the defect mode inside PBG. We have found that the increase in temperature results in minute changes in sensitivity but a significant increase in the intensity of defect mode which is highly required in any photonic biosensing design. The findings of this study may be very useful for designing various bio-sensing structures which could have a significant and decisive role in the field of biomedical applications.