Early Recognition Of Breast Cancer Research Articles

Fusion of transfer learning models with LSTM for detection of breast cancer using ultrasound images

Breast Cancer (BC) is one of the top reasons for fatality in women worldwide. As a result, timely identification is critical for successful therapy and excellent survival rates. Transfer Learning (TL) approaches have recently shown promise in aiding in the early recognition of BC. In this work, three TL models, MobileNetV2, ResNet50, and VGG16, were combined with LSTM to extract the features from Ultrasound Images (USIs). Furthermore, the Synthetic Minority Over-sampling Technique (SMOTE) with Tomek (SMOTETomek) was employed to balance the extracted features. The proposed method with VGG16 achieved an F1 score of 99.0 %, Matthews Correlation Coefficient (MCC) and Kappa Coefficient of 98.9 % with an Area Under Curve (AUC) of 1.0. The K-fold method was applied for cross-validation and achieved an average F1 score of 96 %.Moreover, the Gradient-weighted Class Activation Mapping (Grad-CAM) method was applied for visualization, and the Local Interpretable Model-agnostic Explanations (LIME) method was applied for interpretability. The Normal Approximation Interval (NAI) and bootstrapping methods were used to calculate Confidence Intervals (CIs). The proposed method achieved a Lower CI (LCI), Upper CI (UCI), and Mean CI (MCI) of 96.50 %, 99.75 %, and 98.13 %, respectively, with the NAI, while 95 % LCI of 93.81 %, an UCI of 96.00 %, and a bootstrap mean of 94.90 % with the bootstrap method. Furthermore, the performance of the six state-of-the-art (SOTA) TL models, such as Xception, NASNetMobile, InceptionResNetV2, MobileNetV2, ResNet50, and VGG16, were compared with the proposed method.

An ensemble-based serial cascaded attention network and improved variational auto encoder for breast cancer prognosis prediction using data

Breast cancer is one of the most common types of cancer in women and it produces a huge amount of death rate in the world. Early recognition is lessening its impact. The early recognition of breast cancer could convince patients to receive surgical therapy, which will significantly improve the chance of restoration. This information is used by the machine learning technique to find links between them and appraise our forecasts of fresh occurrences. Later recognition of breast cancer can lead to death. An accurate prescient framework for breast cancer prediction is urgently needed in the current era. In order to accomplish the objective, an adaptive ensemble model is proposed for breast cancer prognosis prediction using data. At the initial stage, the raw data are fetched from benchmark datasets. It is then followed by data cleaning and preprocessing. Subsequently, the pre-processed data is fed into the Improved Variational Autoencoder (IVAE), where the deep features are extracted. Finally, the resultant features are given as input to the Ensemble-based Serial Cascaded Attention Network (ESCANet), which is built with Deep Temporal Convolution Network (DTCN), Bi-directional Long Short-Term Memory (BiLSTM), and Recurrent Neural Network (RNN). The effectiveness of the model is validated and compared with conventional methodologies. Therefore, the results elucidate that the proposed methodology achieves extensive results; thus, it increases the system’s efficiency.

StackBC: Deep learning and transfer learning techniques based stacking approach for accurate Invasive Ductal Carcinoma classification using histology images

Artificial intelligence (AI) based computer-aided diagnostic (CAD) systems can effectively diagnose critical disease. AI-based detection of breast cancer (BC) through images data is more efficient and accurate than professional radiologists. However, the existing AI-based BC diagnosis methods have complexity in low prediction accuracy and high computation time. Due to these reasons, medical professionals are not employing the current proposed techniques in E-Healthcare to effectively diagnose the BC. To diagnose the breast cancer effectively need to incorporate advanced AI techniques based methods in diagnosis process. In this work, we proposed a deep learning based diagnosis method (StackBC) to detect breast cancer in the early stage for effective treatment and recovery. In particular, we have incorporated deep learning models including Convolutional neural network (CNN), Long short term memory (LSTM), and Gated recurrent unit (GRU) for the classification of Invasive Ductal Carcinoma (IDC). Additionally, data augmentation and transfer learning techniques have been incorporated for data set balancing and for effective training the model. To further improve the predictive performance of model we used stacking technique. Among the three base classifiers (CNN, LSTM, GRU) the predictive performance of GRU are better as compared to individual model. The GRU is selected as a meta classifier to distinguish between Non-IDC and IDC breast images. The method Hold-Out has been incorporated and the data set is split into 90% and 10% for training and testing of the model, respectively. Model evaluation metrics have been computed for model performance evaluation. To analyze the efficacy of the model, we have used breast histology images data set. Our experimental results demonstrated that the proposed StackBC method achieved improved performance by gaining 99.02% accuracy and 100% area under the receiver operating characteristics curve (AUC-ROC) compared to state-of-the-art methods. Due to the high performance of the proposed method, we recommend it for early recognition of breast cancer in E-Healthcare.

End-to-end improved convolutional neural network model for breast cancer detection using mammographic data

Any disease is curable if it is diagnosed at the early stages with the help of a little human effort. The disease breast cancer is the second leading cause of death among women after lung cancer. Mammography is one of the most mainstream clinical imaging modalities that are utilized for early recognition of breast cancer. Early breast cancer detection helps to alleviate unnecessary treatments as well as saving women’s lives. The speedy development in deep learning and some of the strategies of machine learning have invigorated abundant enthusiasm for their application to clinical imaging issues. This paper presents an improved convolutional neural network (CNN) model that consists of three convolutional layers where the starting layer searches for low-level features and the ending layer searches for high-level features. Two activation functions, that is, the Rectified Linear Unit and sigmoid functions, are utilized for the detection of breast cancer using digitized film mammograms from the Digital Database for Screening Mammography. The proposed convolutional neural system for identifying breast malignancy on mammogram imaging achieved praiseworthy execution on examination with prior models. The experimentation found that the model achieved has a true positive rate of 99% (accuracy = 97.20%, precision = 99%, true negative rate = 96%, F-score = 0.99, balanced classification rate = 0.975, Youden’s index = 0.95). The proposed improved CNN model can be used as a second opinion of doctors to detect breast cancer.

Classification of Thermography Breast Images for Cancer Detection using Machine Learning

Breast cancer is presently the most well-known cancer in many urban communities in India, and the second generally normal in rural areas. Early recognition of breast cancer by orderly assessment of the individual may improve the endurance rate. Infrared thermography one of the imaging strategies that produce high goals infrared pictures shows the warmth design dependent on the temperature changes in breast regarding the movement of the cancer cells. Expanded metabolic movement and the bloodstream because of the augmentation of cancer cells instigates more warmth on the skin layer which are caught by the warm camera to deliver the thermal images. This paper talks about the picture handling calculation to recognize the nearness of cancer from the procured warm pictures. The approach incorporates the preprocessing the procured picture and fragmenting the area of enthusiasm, extricating the features from the divided picture followed by feature selection and classification.

A hybrid cost-sensitive ensemble for imbalanced breast thermogram classification.

Early recognition of breast cancer, the most commonly diagnosed form of cancer in women, is of crucial importance, given that it leads to significantly improved chances of survival. Medical thermography, which uses an infrared camera for thermal imaging, has been demonstrated as a particularly useful technique for early diagnosis, because it detects smaller tumors than the standard modality of mammography. In this paper, we analyse breast thermograms by extracting features describing bilateral symmetries between the two breast areas, and present a classification system for decision making. Clearly, the costs associated with missing a cancer case are much higher than those for mislabelling a benign case. At the same time, datasets contain significantly fewer malignant cases than benign ones. Standard classification approaches fail to consider either of these aspects. In this paper, we introduce a hybrid cost-sensitive classifier ensemble to address this challenging problem. Our approach entails a pool of cost-sensitive decision trees which assign a higher misclassification cost to the malignant class, thereby boosting its recognition rate. A genetic algorithm is employed for simultaneous feature selection and classifier fusion. As an optimisation criterion, we use a combination of misclassification cost and diversity to achieve both a high sensitivity and a heterogeneous ensemble. Furthermore, we prune our ensemble by discarding classifiers that contribute minimally to the decision making. For a challenging dataset of about 150 thermograms, our approach achieves an excellent sensitivity of 83.10%, while maintaining a high specificity of 89.44%. This not only signifies improved recognition of malignant cases, it also statistically outperforms other state-of-the-art algorithms designed for imbalanced classification, and hence provides an effective approach for analysing breast thermograms. Our proposed hybrid cost-sensitive ensemble can facilitate a highly accurate early diagnostic of breast cancer based on thermogram features. It overcomes the difficulties posed by the imbalanced distribution of patients in the two analysed groups.

Ganzkörper-MRT in der präoperativen Diagnostik des Mammakarzinoms – ein Vergleich mit den Stagingmethoden in der S 3-Leitlinie

The German Society of Senology (step-3 guidelines for the early recognition of breast cancer in Germany) recommends whole-body staging including chest X-ray, ultrasound of the liver and bone scintigraphy before systemic therapy in patients with breast cancer. The performance of these three examinations is time-consuming and involves radiation exposure. Whole-body MR imaging (WB-MRI) allows staging in a single examination without radiation exposure. The purpose of this study was to compare the diagnostic accuracy of WB-MRI with staging according to the guidelines. During 04/07 and 06/09, the initial staging in 51 patients (56 ± 12 yrs) with breast cancer (24 patients with lymph node metastases) was performed according to the S 3-guidelines. Additionally, all patients underwent contrast-enhanced WB-MRI (1.5-Tesla-Magnetom Avanto, Siemens, Erlangen). The findings of the different modalities were compared after correlation of the lesions by follow-up. The detection of suspicious findings and the accuracy of prediction of malignancy of the detected lesions were evaluated. Overall, 14 metastases were detected in 4 of 51 patients after completion of the follow-up. By means of WB-MRI, all 14 metastases could be detected, while just 4 of these metastases were identified by the conventional methods. The detection of distant metastases has an important impact on patient management. In this study WB-MRI in breast cancer staging has shown promising results in regard to possible clinical implementation as a matter of routine staging.

Primary and secondary breast cancer prevention. Knowledge, assessment and participation among the female population of Schleswig-Holstein

The intention was to find out to what extend women in Schleswig-Holstein were informed about primary and secondary preventive measures concerning breast cancer, how they assess their efficiency and in how far they are willing to take part in them. From June 1999 to April 2000 1 520 women in Schleswig-Holsteins were asked to complete a questionnaire about breast cancer prevention. There was a representative opinion poll of the market research company "Institut für Gesundheitsforschung München (Infratest)". Most of the women (90.6 %) believed in the efficiency of early recognition of breast cancer at the gynaecologist, only 79.3 % of them stated that they took the chance of taking part in the annual examination. According to the doctors Union "Kassenärztliche Vereinigung", only 50.4 % of the female members of health insurance schemes took part in examinations concerning the early recognition of breast cancer in 1999. The degree of knowledge about and participation in preventive measures depend on the age of the women. The gynaecologist was named as the most important source of information and counselling. In future the population needs more information and instruction concerning breast cancer preventive measures.