Bevishjenila

Bio: Bevishjenila is an academic researcher from Sathyabama University. The author has contributed to research in topics: Cancer & Mammography. The author has an hindex of 1, co-authored 1 publications receiving 1 citations.

Breast Cancer Detection Using Machine Learning

Abstract: The most commonly diagnosed and second leading cause of cancer fatalities is breast cancer in women. AI and IoT integrated system that can help diagnose earlier breast cancer. The key tool for detecting breast cancer is mammograms. Yet cancer cells in breast tissue are difficult to identify. Since it has less fat and more muscle. To examine the irregular areas of density, mass and calcification that signify the presence of cancer, digitized mammography images are used. Several imaging techniques have been developed to detect and treat breast cancer early and to decrease the number of deaths, and many methods of diagnosis of breast cancer have been used to increase diagnostic accuracy. The current technique does not detect breast cancer reliably in the early stages, and most women have suffered from this.

An Effective Ensemble Machine Learning Approach to Classify Breast Cancer Based on Feature Selection and Lesion Segmentation Using Preprocessed Mammograms

Abstract: Simple Summary The screening of breast cancer in its earlier stages can play a crucial role in minimizing mortality rate by enabling clinicians to administer timely treatments and preventing the cancer from reaching the critical stage. With this view, the objective of this research is to develop an efficient automated approach for analyzing and classifying mammograms into four classes. Primarily, artefacts present in the mammograms are eliminated and the mammograms are enhanced utilizing image-processing techniques. When applying seven data augmentation methods, the volume of the mammography dataset is enlarged. Afterward, the region of interest (ROI) is extracted from the mammograms employing a region-growing algorithm with a dynamic intensity threshold calculated for each mammogram. From each ROI, a total of 16 geometrical features are extracted. These features are investigated with eleven state-of-the-art machine learning (ML) algorithms and depending on test accuracies, three ensemble models are developed. Among the ensemble models, the highest test accuracy of 96.03% is gained by stacking Random Forest and XGB classifier (RF-XGB). Furthermore, the performance of RF-XGB is boosted by utilizing various feature selection methods resulting in 98.05% accuracy. Moreover, the performance consistency of the best model is evaluated with the K-fold cross-validation experiment. This proposed approach of classifying mammograms may assist specialists in the precise and effective diagnosis of breast cancer. Abstract Background: Breast cancer, behind skin cancer, is the second most frequent malignancy among women, initiated by an unregulated cell division in breast tissues. Although early mammogram screening and treatment result in decreased mortality, differentiating cancer cells from surrounding tissues are often fallible, resulting in fallacious diagnosis. Method: The mammography dataset is used to categorize breast cancer into four classes with low computational complexity, introducing a feature extraction-based approach with machine learning (ML) algorithms. After artefact removal and the preprocessing of the mammograms, the dataset is augmented with seven augmentation techniques. The region of interest (ROI) is extracted by employing several algorithms including a dynamic thresholding method. Sixteen geometrical features are extracted from the ROI while eleven ML algorithms are investigated with these features. Three ensemble models are generated from these ML models employing the stacking method where the first ensemble model is built by stacking ML models with an accuracy of over 90% and the accuracy thresholds for generating the rest of the ensemble models are >95% and >96. Five feature selection methods with fourteen configurations are applied to notch up the performance. Results: The Random Forest Importance algorithm, with a threshold of 0.045, produces 10 features that acquired the highest performance with 98.05% test accuracy by stacking Random Forest and XGB classifier, having a higher than >96% accuracy. Furthermore, with K-fold cross-validation, consistent performance is observed across all K values ranging from 3–30. Moreover, the proposed strategy combining image processing, feature extraction and ML has a proven high accuracy in classifying breast cancer.

Lung Nodule Classification on Computed Tomography Using Neural Networks

Abstract: Lung cancer is a leading health issue and the major cause of death among all types of cancers. CT scanning is the popular method for lung cancer diagnosis detection. Manual processing of tomograms take long time for diagnosis. It is not an easy task. This complex work can also reduce the quality of diagnosis. Machine learning and neural network algorithm can be used to automatically process X-ray pictures, tomograms and PET images to detect diseases. The goal of the proposed work is to find any abnormal thing in lungs. Convolutional neural network is trained to classify abnormal area from the normal cells. The detection algorithm is designed to determine the existence of cancer in tomography images and validation, training and testing using CT images. The proposed work investigates the performance of classifier by training algorithm with morphological feature extraction. The performance results shows that proposed method achieves higher accuracy than existing methods.

Breast Cancer Detection in the Equivocal Mammograms by AMAN Method

Abstract: Breast cancer is a primary cause of human deaths among gynecological cancers around the globe. Though it can occur in both genders, it is far more common in women. It is a disease in which the patient’s body cells in the breast start growing abnormally. It has various kinds (e.g., invasive ductal carcinoma, invasive lobular carcinoma, medullary, and mucinous), which depend on which cells in the breast turn into cancer. Traditional manual methods used to detect breast cancer are not only time consuming but may also be expensive due to the shortage of experts, especially in developing countries. To contribute to this concern, this study proposed a cost-effective and efficient scheme called AMAN. It is based on deep learning techniques to diagnose breast cancer in its initial stages using X-ray mammograms. This system classifies breast cancer into two stages. In the first stage, it uses a well-trained deep learning model (Xception) while extracting the most crucial features from the patient’s X-ray mammographs. The Xception is a pertained model that is well retrained by this study on the new breast cancer data using the transfer learning approach. In the second stage, it involves the gradient boost scheme to classify the clinical data using a specified set of characteristics. Notably, the experimental results of the proposed scheme are satisfactory. It attained an accuracy, an area under the curve (AUC), and recall of 87%, 95%, and 86%, respectively, for the mammography classification. For the clinical data classification, it achieved an AUC of 97% and a balanced accuracy of 92%. Following these results, the proposed model can be utilized to detect and classify this disease in the relevant patients with high confidence.