Integrating Transformer and Bidirectional Long Short-Term Memory for Intelligent Breast Cancer Detection from Histopathology Biopsy Images

Breast cancer is a significant threat to the global population,affecting not only women but also a threat to the entire population.With recent advancements in digital pathology,Eosin and hematoxylin images provide enhanced clarity in examiningmicroscopic features of breast tissues based on their staining properties.Early cancer detection facilitates the quickening of the therapeutic process,thereby increasing survival rates.The analysis made by medical professionals,especially pathologists,is time-consuming and challenging,and there arises a need for automated breast cancer detection systems.The upcoming artificial intelligence platforms,especially deep learning models,play an important role in image diagnosis and prediction.Initially,the histopathology biopsy images are taken from standard data sources.Further,the gathered images are given as input to the Multi-Scale Dilated Vision Transformer,where the essential features are acquired.Subsequently,the features are subjected to the Bidirectional Long Short-Term Memory(Bi-LSTM)for classifying the breast cancer disorder.The efficacy of the model is evaluated using divergent metrics.When compared with other methods,the proposed work reveals that it offers impressive results for detection.

A double constrained robust capon beamforming based imaging method for early breast cancer detection

Ultra-wideband （UWB） microwave images are proposed for detecting small malignant breast tumors based on the large contrast of electric parameters between a malignant tumor and normal breast tissue. In this study, an antenna array composed of 9 antennas is applied to the detection. The double constrained robust capon beamforming （DCRCB） algorithm is used for reconstructing the breast image due to its better stability and high signal-to-interference-plus-noise ratio （SINR）. The successful detection of a tumor of 2 mm in diameter shown in the reconstruction demonstrates the robustness of the DCRCB beamforming algorithm. This study verifies the feasibility of detecting small breast tumors by using the DCRCB imaging algorithm.

A progressive processing method for breast cancer detection via UWB based on an MRI-derived model

Ultra-wideband （UWB） microwave imaging is a promising method for breast cancer detection based on the large contrast of electric parameters between the malignant tumor and its surrounded normal breast organisms. In the case of multiple tumors being present, the conventional imaging approaches may be ineffective to detect all the tumors clearly. In this paper, a progressive processing method is proposed for detecting more than one tumor. The method is divided into three stages： primary detection, refocusing and image optimization. To test the feasibility of the approach, a numerical breast model is developed based on the realistic magnetic resonance image （MRI）. Two tumors are assumed embedded in different positions. Successful detection of a 3.6 mm-diameter tumor at a depth of 42 mm is achieved. The correct information of both tumors is shown in the reconstructed image, suggesting that the progressive processing method is promising for multi-tumor detection.

Gaussian Optimized Deep Learning-based Belief Classification Model for Breast Cancer Detection

With the rapid increase of new cases with an increased mortality rate,cancer is considered the second and most deadly disease globally.Breast cancer is the most widely affected cancer worldwide,with an increased death rate percentage.Due to radiologists’processing of mammogram images,many computer-aided diagnoses have been developed to detect breast cancer.Early detection of breast cancer will reduce the death rate worldwide.The early diagnosis of breast cancer using the developed computer-aided diagnosis(CAD)systems still needed to be enhanced by incorporating innovative deep learning technologies to improve the accuracy and sensitivity of the detection system with a reduced false positive rate.This paper proposed an efficient and optimized deep learning-based feature selection approach with this consideration.This model selects the relevant features from the mammogram images that can improve the accuracy of malignant detection and reduce the false alarm rate.Transfer learning is used in the extraction of features initially.Na ext,a convolution neural network,is used to extract the features.The two feature vectors are fused and optimized with enhanced Butterfly Optimization with Gaussian function(TL-CNN-EBOG)to select the final most relevant features.The optimized features are applied to the classifier called Deep belief network(DBN)to classify the benign and malignant images.The feature extraction and classification process used two datasets,breast,and MIAS.Compared to the existing methods,the optimized deep learning-based model secured 98.6%of improved accuracy on the breast dataset and 98.85%of improved accuracy on the MIAS dataset.

Design and Analysis of Antipodal Vivaldi Antennas for Breast Cancer Detection

This paper presents the design and analysis of antipodal Vivaldi antennas(AVAs)for breast cancer detection.In order to enhance the antenna gain,different techniques such as using the uniform and non-uniform corrugation,expanding the dielectric substrate and adding the parasitic patch are applied to original AVA.The design procedure of two developed AVA structures i.e.,AVA with non-uniform corrugation and AVA with parasitic patch are presented.The proposed AVAs are designed on inexpensive FR4 substrate.The AVA with non-uniform corrugation has compact dimension of 50×50 mm2 or 0.28λL×0.28λL,whereλL is wavelength of the lowest operating frequency.The antenna can operate within the frequency range from 1.63 GHz to over 8 GHz.For the AVA with parasitic patch and uniform corrugation,the overall size of antenna is 50×86 mm2 or 0.24λL×0.41λL.It can operate within the frequency range from 1.4 GHz to over 8 GHz.The maximum gain for AVA with non-uniform corrugation and AVA with parasitic patch and uniform corrugation are 9.03 and 11.31 dBi,respectively.The corrugation profile and parasitic patch of the proposed antenna are optimized to achieve the desired properties for breast cancer detection.In addition,the proposed AVAs are measured with breast phantom to detect cancerous cell inside the breast and the performance in detecting cancerous cell are discussed.The measured result can confirm that the proposed AVAs can detect unwanted cell inside the breast while maintaining the compact size,simple structure and low complexity in design.

Breast Calcifications and Histopathological Analysis on Tumour Detection by CNN

The most salient argument that needs to be addressed universally is Early Breast Cancer Detection(EBCD),which helps people live longer lives.The Computer-Aided Detection(CADs)/Computer-Aided Diagnosis(CADx)sys-tem is indeed a software automation tool developed to assist the health profes-sions in Breast Cancer Detection and Diagnosis(BCDD)and minimise mortality by the use of medical histopathological image classification in much less time.This paper purposes of examining the accuracy of the Convolutional Neural Network(CNN),which can be used to perceive breast malignancies for initial breast cancer detection to determine which strategy is efficient for the early iden-tification of breast cell malignancies formation of masses and Breast microcalci-fications on the mammogram.When we have insufficient data for a new domain that is desired to be handled by a pre-trained Convolutional Neural Network of Residual Network(ResNet50)for Breast Cancer Detection and Diagnosis,to obtain the Discriminative Localization,Convolutional Neural Network with Class Activation Map(CAM)has also been used to perform breast microcalcifications detection tofind a specific class in the Histopathological image.The test results indicate that this method performed almost 225.15%better at determining the exact location of disease(Discriminative Localization)through breast microcalci-fications images.ResNet50 seems to have the highest level of accuracy for images of Benign Tumour(BT)/Malignant Tumour(MT)cases at 97.11%.ResNet50’s average accuracy for pre-trained Convolutional Neural Network is 94.17%.

Detection of Malignant and Benign Breast Cancer Using the ANOVA-BOOTSTRAP-SVM

Purpose:The aim of this research is to propose a modification of the ANOVA-SVM method that can increase accuracy when detecting benign and malignant breast cancer.Methodology:We proposed a new method ANOVA-BOOTSTRAP-SVM.It involves applying the analysis of variance(ANOVA)to support vector machines(SVM)but we use the bootstrap instead of cross validation as a train/test splitting procedure.We have tuned the kernel and the C parameter and tested our algorithm on a set of breast cancer datasets.Findings:By using the new method proposed,we succeeded in improving accuracy ranging from 4.5 percentage points to 8 percentage points depending on the dataset.Research limitations:The algorithm is sensitive to the type of kernel and value of the optimization parameter C.Practical implications:We believe that the ANOVA-BOOTSTRAP-SVM can be used not only to recognize the type of breast cancer but also for broader research in all types of cancer.Originality/value:Our findings are important as the algorithm can detect various types of cancer with higher accuracy compared to standard versions of the Support Vector Machines.

Improved region growing segmentation for breast cancer detection:progression of optimized fuzzy classifier

Purpose-Breast cancer is one of the most common malignant tumors in women,which badly have an effect on women’s physical and psychological health and even danger to life.Nowadays,mammography is considered as a fundamental criterion for medical practitioners to recognize breast cancer.Though,due to the intricate formation of mammogram images,it is reasonably hard for practitioners to spot breast cancer features.Design/methodology/approach-Breast cancer is one of the most common malignant tumors in women,which badly have an effect on women’s physical and psychological health and even danger to life.Nowadays,mammography is considered as a fundamental criterion for medical practitioners to recognize breast cancer.Though,due to the intricate formation of mammogram images,it is reasonably hard for practitioners to spot breast cancer features.Findings-The performance analysis was done for both segmentation and classification.From the analysis,the accuracy of the proposed IAP-CSA-based fuzzy was 41.9%improved than the fuzzy classifier,2.80%improved than PSO,WOA,and CSA,and 2.32%improved than GWO-based fuzzy classifiers.Additionally,the accuracy of the developed IAP-CSA-fuzzy was 9.54%better than NN,35.8%better than SVM,and 41.9%better than the existing fuzzy classifier.Hence,it is concluded that the implemented breast cancer detection model was efficient in determining the normal,benign and malignant images.Originality/value-This paper adopts the latest Improved Awareness Probability-based Crow Search Algorithm(IAP-CSA)-based Region growing and fuzzy classifier for enhancing the breast cancer detection of mammogram images,and this is the first work that utilizes this method.

Large Scale Analysis of Complex Permittivity of Breast Cancer in Microwave Band

To obtain some prior knowledge of breast cancer detection by microwave imaging, we have measured and analyzed the complex permittivity of tissues extracted from over 140 breast cancer surgeries. The relative permittivity and conductivity of tumor at 1.6 GHz were 17.5% and 16.2% higher than those of mammary gland tissue, respectively. In invasive ductal carcinoma of scirrhous type, 8 out of 64 had higher relative permittivity and conductivity of mammary gland than those of tumor. However, when evaluated by the Debye parameter considering the frequency dependence of the tissue, it is rare that ε∞ and Δε of cancer are simultaneously lower than those of mammary gland. The relative permittivity and conductivity of fibroadenoma are almost the same as those of mammary glands. The relative permittivity and conductivity of each tissue showed strong linearity. Microwave imaging requires accurate reconstruction of ε∞ and Δε to distinguish cancer from normal tissue.

Detection of breast cancer based on novel porous silicon Bragg reflector surface-enhanced Raman spectroscopy-active structure

In this Letter, the surface-enhanced Raman scattering(SERS) signal of early breast cancer(BRC) patient serum is obtained by a composite silver nanoparticles(Ag NPs) PSi Bragg reflector SERS substrate. Based on these advantages, the serum SERS signals of 30 normal people and 30 early BRC patients were detected by this substrate. After a baseline correction of the experimental data, principal component analysis and linear discriminant analysis were used to complete the data processing. The results showed that the diagnostic accuracy, specificity,and sensitivity of the composite Ag NPs PSi Bragg reflector SERS substrate were 95%, 96.7%, and 93.3%, respectively. The results of this exploratory study prove that the detection of early BRC serum based on a composite Ag NPs PSi Bragg reflector SERS substrate is with a stable strong SERS signal, and an unmarked and noninvasive BRC diagnosis technology. In the future, this technology can serve as a noninvasive clinical tool to detect cancer diseases and have a considerable impact on clinical medical detection.

QUANTITATIVE DETECTION OF AMPLIFICATION OF PROTO-ONCOGENES IN BREAST CANCER

In the present study, dot-blot hybridization, serial dilution analysis and densitomctric scanning were used to detect amplification of proto- oncogenes including c-erbB2, c-myc, int-2 and c-Ha-ras in 104 paraffin-embedded breast cancers. Expression of c-erbB2 was also examined by immunohistochemistry. Amplification of c-erbB2. c-myc and int-2 genes was found in 34.7%, 17.8% and 11.9% of breast cancers respectively. However amplification of c-Ha-ras was not detected in all cases. In 11.9% of cases co-amplification of two or more oncogenes was observed. Positive immunostain-ing of c-erbB2 was seen in 23.8% of the cases and it was significantly associated, but not always corresponding to the amplification of the gene. There was no difference between primary and metastatic breast cancer in the alterations of proto-oncogenes examined in this study, which suggested that the amplification and overexpression of these proto-oncogenes occured prior to and maintained in the process of metastasis of breast cancer. Statistical analysis showed that high-scale of immunopositive staining of c-erbB2 and high-fold co-amplification of proto-oncogenes were significantly correlated with large size of the tumour and the number of involved lymph nodes. Our results indicate that the alterations of multiple oncogenes are involved in the development of breats cancer and some of them may have prognostic importance for breast cancer patients.

Pulse Generation and Compression Techniques for Microwave Electronics and Ultrafast Systems

Ultrabroadband systems and ultrafast electronics require the generation,transmission,and processing of high-quality ultrashort pulses rang-ing from nanoseconds(ns)to picoseconds(ps),which include well-established and emerging applications of time-domain reflectometry,arbitrary wave-form generation,sampling oscilloscopes,frequency synthesis,through-wall radar imaging,indoor communication,radar surveillance,and medical radar detection.Impulse radar advancements in industrial,scientific,and medical(ISM)domains are,for example,driven by ns-scale-defined ultrawideband(UWB)technologies.Nevertheless,the generation of ultrashort ps-scale pulses is highly desired to achieve unprecedented performances in all these ap-plications and future systems.However,due to the variety and applicability of different pulse generation and compression techniques,the selection of optimum or appropriate pulse generators and compressors is difficult for practitioners and users.To this end,this article aims to provide a comprehen-sive overview of ultrashort ns and ps pulse generation and compression techniques.The proposed and developed pulse generators available in the litera-ture and on the market,which are characterized by their corresponding pros and cons,are also explored.The theoretical analysis of pulse generation us-ing a nonlinear transmission line(NLTL)presented in the literature is briefly explained as well.Additionally,a holistic overview of these pulse genera-tors from the perspective of applications is given to describe their utilization in practical systems.All of these techniques are well summarized and com-pared in terms of fundamental pulse parameters,and research gaps in specified areas are highlighted.A thorough discussion of previous research work on various topologies and techniques is presented,and potential future directions for technical advancement are examined.