Detection Of Breast Cancer Tumors Research Articles

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

BackgroundWhole 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.MethodsIn 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.ResultsOur 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.ConclusionThe 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.

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

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.

Early Detection of Breast Cancer Tumors using Linear Discriminant Analysis Feature Selection with Different Machine Learning Classification Methods

Globally, the frequency of breast cancer and its morality speak to a critical and developing risk for the developing countries. In Asia, Pakistan has the biggest rate of breast cancer. It is evaluated that every year 83,000 cases were reported in Pakistan and over 40,000 deaths are caused by breast cancer. Patients suffering from this malignancy have a better chance of surviving if they are diagnosed early. Many Early identification of breast cancer can be achieved using data mining techniques, allowing preventative treatments to be done. In this research Wisconsin Breast Cancer Dataset (WBCD) and Duke Breast cancer dataset (DBDS) are used with Linear Discriminant Analysis (LDA) feature selection with Support Vector Machine (SVM), Decision Tree (DT), Neural Network and Random Forest (RF) machine learning classifiers to predict breast cancer tumors. The finding of the proposed model is that feature selections through LDA improve the accuracy of detecting tumors and also reduce time duration of executing model. The best machine learning model with LDA feature selection is Neural Network Model with highest accuracy 1.00 among all classification models and also consume less time.

Early Detection of Breast Cancer Tumors Using Linear Discriminant Analysis Feature Selection with Different Classification Methods

Globally, the frequency of breast cancer and its morality speaks to a critical and developing risk for developing countries. In Asia, Pakistan has the biggest rate of breast cancer. It is evaluated that every year 83,000 cases were reported in Pakistan and over 40,000 deaths are caused by breast cancer. Many Early identifications of breast cancer can be achieved using data mining techniques, allowing preventative treatments to be done. Patients suffering from this malignancy have a better chance of surviving if they are diagnosed early. So, there is a need to develop a system to diagnose breast cancer tumors at an early stage. In this research WBCD and Duke Breast cancer datasets (DBDS) are used with Linear Discriminant Analysis (LDA) feature selection. Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF) are classifiers to predict breast cancer tumors.

Application of the migration method for radiotomography of breast cancer

A new method to visualize microwave image is presented to early non-invasive detection of breast cancer tumors. A new processing method to compute microwave images of heterogeneity in a biological environment is described here, as well as a new algorithm for accelerating the calculation of three-dimensional radio images. Sounding of synthetic phantoms with dielectric properties of breast tissue was carried out in the range of 2–8 GHz using a special radar system developed by the authors. Results show that it is possible to use this microwave imaging method to form 3D accurate images using hemispherical scan Images of tumor phantoms were obtained during probing in the 2–8 GHz range with a resolution of about 5–7 mm.According to the results of the reconstruction of three-dimensional radio images, it was revealed that the calculation time can be reduced by at least 2 times with an insignificant loss of quality.

Highly compact sized circular microstrip patch antenna with partial ground for biomedical applications

Miniaturized patch antenna is mostly preferable for biomedical applications like stroke imaging, tumor detection in breast cancer to characterize malignant, benign, and normal breast tissues etc. In this paper highly compact sized circular microstrip patch antenna with partial ground is being developed on FR4 substrate with 13 × 12 × 1.6 mm3 dimensions of compact and simple structure. The simulated results of the proposed antenna show, that the antenna can be used for the biomedical applications. The proposed antenna obtained good results with a high bandwidth of 11.2 GHz and with a moderate directivity and gain of 3.2 dBi and 1.2 dBi each. This antenna can also be used for therapeutic applications based on local heating: prostate hyperplasia, heart and other tissue ablation, angioplasty which come under Ultra-wideband microwave radar techniques. The design is verified using CST Studio for simulation.

Implementation of Compact Ultra wide Band Antenna Design for Breast Cancer Tumor detection

One of the applications of UWB antenna is for detecting a cancer tumor according to breast cancer model system. The absolute dimensions of antenna are 44x30mm2 having a thickness of 1.6 mm. It involves Ultra wide band of 80% frequency range of 3 GHz–12 GHz for the FCC band. The proposed antenna resulted high gain and omni-directional radiation patterns and a considerable impedance matching. The optimized functioning of the antenna is illustrated by the simulation results. This antenna has been implemented in a designed system model with dielectric properties of a human breast capable to detect peculiar bodies. The tumor is detected and examined by the received Proportions and Positional coordinates, accessed by the application of UWB antenna. The accurate position coordinates of the tumor inside the breast are obtained at the places with the least Specific absorption rate (SAR). The antenna was used to localize the tumor precisely which shows the excellent functioning of the antenna and device. The proposed device is simulated by using Ansoft HFSS software and also CST Microwave studio simulator developed the breast model.

Abstract P2-14-29: Image guided surgery for tumor detection in breast cancer using the PH activated micellar tracer ONM-100: The SHINE study

Abstract Background: Currently, no reliable intra-operative tumor detection and margin assessment technologies during breast conserving surgery are available. Fluorescence-guided surgery (FGS) using tumor specific fluorescent tracers can improve intra-operative tumor detection. However, a major limitation is the lack of broad tumor applicability due to complex oncogenotypes and histologic phenotypes. A strategy to overcome this challenge is targeting metabolic vulnerabilities that are more ubiquitous and regarded as generic hallmarks of cancer. The extracellular environment of tumors is relatively acidic compared to healthy tissue due to aerobic glycolysis, the so-called Warburg effect. ONM-100, a micellar polymer tracer labeled with the fluorescent imaging dye Indocyanine Green (ICG), has an exquisitely pH-sensitive binary on/off mechanism. The micelles dissociate in acidic environments causing the unquenching and fluorescent activation of the ICG dye. As most solid cancer types are acidotic, ONM-100 acts as a generic tracer targeting a broad range of tumors. This proof of concept, first in-human study, investigates the safety and feasibility of ONM-100 as an intra-operative fluorescent tracer in breast cancer (BC) patients. Methods: In this phase 1 study, the pH-activated fluorescent tracer ONM-100 was administered 24±8h prior to surgery in a dose escalation scheme ranging from 0.1 mg/kg to 0.8 mg/kg in groups of 3 patients each. Patients with biopsy proven BC were included. Patients that had undergone neoadjuvant therapy were excluded. Blood was drawn up to day 10 to assess safety and pharmacokinetic data. Intra-operative images were collected of the tumor before and after excision and of the wound bed. Immediately after excision ex vivo fluorescence images were obtained from the serially sliced specimen and the formalin fixated paraffin embedded tissue blocks. Fluorescence images were correlated with histopathological assessment on Hematoxylin and Eosin (H/E) stained sections. Results: In this ongoing clinical trial, 4 patients with BC were enrolled between March and May 2018. No tracer related (serious) adverse events were observed. A strong and sharply demarcated fluorescent signal in tumor tissue was observed in all 4 patients with in- and ex vivo imaging (median Contrast to Noise Ratio 6.5; IQR 7.25), which correlated with areas of tumor involvement on histopathology. In one BC patient, an intra-operatively unnoticed tumor positive margin was detected using fluorescence imaging. Additionally, a BC satellite lesion was detected, which was otherwise missed by the pathologist. Conclusion: Preliminary results of this ongoing first in-human study with the pH-activated tracer ONM-100 shows that ONM-100 is well tolerated and safe and allows fluorescent tumor visualization both in- and ex vivo. Here, we provide the first data that this pH-sensitive optical tracer can be used as a tracer for FGS and for margin detection. Further analysis on microscopic biodistribution of ONM-100 is currently being performed and possibilities for metastatic lymph node detection will be explored. Citation Format: Steinkamp PJ, Voskuil FJ, Koller M, van der Vegt B, Doff JJ, Zhao T, Hartung J, Jayalakshmi Y, Sumer BD, Gao J, Witjes MJ, van Dam GM. Image guided surgery for tumor detection in breast cancer using the PH activated micellar tracer ONM-100: The SHINE study [abstract]. In: Proceedings of the 2018 San Antonio Breast Cancer Symposium; 2018 Dec 4-8; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2019;79(4 Suppl):Abstract nr P2-14-29.

Design of I-shaped dual C-slotted rectangular microstrip patch antenna (I-DCSRMPA) for breast cancer tumor detection

Cancer is the uncontrolled growth of abnormal cells; if not detected and treated at the early stage cancer would become fatal. Breast cancer remains the second leading cause of cancer induced deaths, despite the advances taken place in treatment methods. The incidence of breast cancer in India is on the rise that one in 22 women in India is likely to suffer from breast cancer during her lifetime. One in eight women is affected by this dangerous disease in America. Cancer always a major problem to the world however various methods are available. Some of methods for breast cancer detection are X-ray mammography, MRI and ultrasound. However, they have some limitations to detect the breast cancer but microwave imaging is a safer method as compared to the X-ray. In this Paper cancer tumour in the breast is detected by I-shaped dual C-slotted microstrip patch antenna is designed for 10 GHz. The proposed antenna has a bandwidth of 7.51 dB covering the frequency range 4.9–7.89 GHz, the return loss below − 37 dB and antenna gain of 2.45 dB. The flexible this patch antenna holds good efficiency of 87.1%.

Privacy Preserving with M-SVM Classifier of Tumor Classification in Mammography Images Using Multiple Otsu'S Thresholding Technique

Breast Cancer is formed by an abnormal development of cells in breast. The cells of body separate in an incessant method and occupy to surrounding tissues. It is the important reason of death amongst women and after lung cancer breast cancer is second cause of women deaths. Early breast cancer detection can lead to death rate decrease. The mammography is executed to discover the breast cancer tumor at earlier stages. Early breast cancer tumors detection based on the both the radiologists capability to read mammogram images and image quality. The tumors classification is a medical application that set a huge issue for in the breast cancer recognition area. Therefore, in this paper, a multiple otsu's thresholding method is presented with Mutlti-class SVM (M-SVM) classifier to enhance the tumor classification in mammogram images for cancer tumor detection. In this process, elimination of artifacts, noise and surplus parts that are presented in mammogram images by employing preprocessing tasks and after that it improves the mammogram image contrast utilizing CLAHE (Contrast Limited Adaptive Histrogram Equalization) technique for simpler recognition of tumors in breast. We segment the images using Multiple Otsu's thresholding technique to identify the region of interest in mammogram image after preprocessing and image enhancement. The GLDM (Gray Level Difference Method) is exploited to extract the features from the mammogram image. Feature extraction has been employed to with hindsight examine screening mammograms in use prior to the malignant mass discovery for early breast cancer tumor detection. The extracted features can be given to the M-SVM Classifier to classify the tumor in mammogram image into malignant, benign or normal based on the features. The classification accurateness based on the stage of feature extraction. Results of mammogram image is planned by classification and lastly image categorized into Normal, malignant or Benign. Experimental results of proposed method can show that this presented technique executes well with the accurateness of classification reaching almost 84% in evaluation with existing algorithms.

Semi-automated breast cancer tumor detection with thermographic video imaging.

Screening for breast cancer enables early detection by which curative treatment can be possible. While mammography is the current gold standard for screening, it has low sensitivity in younger women and its harmful X-rays in frequent screening can increase the risk of cancer. Incidence rates are rising in younger women, causing a relook at thermography for low cost and non-harmful screening. In this paper, thermography is compared to mammography correlated with sono-mammography in 65 FNAC/biopsy proven cancer subjects in India. Thermography is comparable to mammography correlated with sono-mammography, having 94% and 95% sensitivity, respectively. A novel semi-automated thermographic tumor detection and location algorithm used in this paper also provides 97% sensitivity. This shows the promise of automated thermographic screening for reaching large populations in a cost effective manner in low resource settings in countries like India. Further studies in a large scale need to be done to evaluate the specificity to enable such solutions.

Analysis of a UWB Hemispherical Antenna Array in FDTD With a Time Domain Huygens Method

Electromagnetic modeling is needed in a wide variety of large and complex situations. Existing numerical techniques such as finite difference time domain (FDTD) can, in principle, solve any problem no matter how large or complicated given a sufficiently powerful computer. However, in practice, there remain problems which require more computer power than is available. Recently, the time-domain Huygens (TDH) approach has been shown to be effective for enabling large problems such as propagation on body area networks (BANs) to be modeled in FDTD. In this paper, it is shown that the much larger problem of the conformal antenna array, which is used in the MARIA breast cancer tumor detection system, is also very amenable to this technique with even greater savings in computer resources. Accurate results are obtained using less that a tenth of the resources needed to solve the same problem using existing advanced FDTD tools. The details of how this method is applied, and the choices which need to be made, are discussed.

Tumor size and detection in breast cancer: Self-examination and clinical breast examination are at their limit

Background: This study investigates to what extent tumor detection methods in breast cancer have changed and how this has influenced tumor size at initial diagnosis. Methods: 1054 breast carcinomas ≤5 cm, newly diagnosed between 1990 and 2006, were evaluated for the tumor detection methods used, namely self-detection (SD, n = 568), clinical breast examination (CBE, n = 212), and radiological breast examination (RBE, n = 237), and their corresponding tumor sizes. Results: During the study period, the proportion of cases found by RBE increased ( p < 0.001), while median tumor size decreased (1990–1992: 22 mm; 2005/2006: 17 mm. Spearman rho = −0.12, p < 0.001). Nevertheless, SD remained the most frequent method of tumor identification (2005/2006: 48.9%). Carcinomas found by RBE were smaller (median size: 12 mm) than those found by the other two detection forms (SD: 21 mm, CBE: 21 mm; p < 0.001). Within the different methods, only in RBE was an appreciable decrease in the size of the detected tumors observed during the study period (Spearman rho = −0.14, p < 0.001; SD: Spearman rho = −0.05, p = 0.19; CBE: Spearman rho = −0.05, p = 0.43). Conclusion: Despite educational campaigns and high media coverage, the possibilities for improving the “classical” methods of tumor detection in breast cancer, self-detection and clinical breast examination, seem to be at their limit. The significant decrease in tumor size at time of detection observed in the last years is primarily only due to the increased use of breast imaging. Improved detection of smaller tumors may presumably be reached only by an increased use of radiological procedures.