International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 04 | Apr2022
www.irjet.net
p-ISSN: 2395-0072
A Review on Breast Cancer Detection Anija J Anilkumar1, Dr. Deepesh Edwin.2 1PG
Student, Dept. of Electronics & Communication Engineering, LBSITW, Kerala, India Professor, Dept. of Electronics & Communication Engineering, LBSITW, Kerala, India ---------------------------------------------------------------------***--------------------------------------------------------------------2Assistant
Abstract -Breast Cancer is a disease in which cells in the
Data mining algorithms used in the healthcare industry plays an important role due to its advanced performance in prediction, diagnosis and making real time decisions to save people’s lives. Classification and prediction are the most common data mining modeling goals, which uses several algorithms for the prediction of breast cancer. Data mining is an important part of machine learning, and it is used to find valuable patterns and trends hidden within vast volumes of data. Data mining and Machine Learning both employ advanced algorithms to uncover relevant data patterns. Machine learning process is based on three main strategies that consist of preprocessing, feature extraction and classification. This paper presents a machine learning strategy for breast cancer detection. Various study strategies are suggested for detection of breast cancer.
breast grow out of control. It is the most common type of cancer found in women around the world and it is among the leading causes of deaths in women. For the early detection process of cancer, machine learning techniques make a huge contribution. This paper presents a comparative analysis of machine learning and data mining techniques used to predict breast cancer. Many researchers have made their own efforts in the diagnosis and prediction of breast cancer, and each technique has a different accuracy rate, which varies in different situations. The main focus of this paper is to make a comparative analysis of existing machine learning and data mining techniques to find the most suitable method that supports with good accuracy of prediction. The main purpose of this review is to highlight some of the previous studies of machine learning used to predict breast cancer. Key Words: Machine prediction, data mining.
2. REVIEW ON DIFFERENT PAPERS
learning, Breast Cancer
Jayanthi et al. breast cancer detection using KNN algorithm. The initial step of the KNN is to calculate the distance of the input test sample with all the dataset entries of training samples. KNN gives an accuracy of 96.49%.[1]
1. INTRODUCTION The second most common cancer diagnosed in women in the world is Breast Cancer. Breast cancer occurs when some breast cells begin to grow abnormally. Due to early detection, the survival rates have increased and the number of deaths associated with this disease is steadily declining. It is important to understand that most breast lumps are benign (non-cancerous) and malignant (cancerous). Benign tumors grow slowly and do not spread, where malignant tumors grow expeditiously, occupy and demolish nearby normal tissues and Unfurl throughout the body. There are multiple tests for diagnosing breast cancer, including mammogram, ultrasound, MRI and biopsy. Mammogram is an X-ray of the breast. If an abnormality is detected on a screening mammogram, the doctor may recommend a diagnostic mammogram to further evaluate that abnormality.
Sengar et al. Breast cancer prediction using 2 machine learning algorithms namely Decision Tree classifier and Logistic Regression. The best algorithm for prediction is the decision tree. It has pinpoint prediction accuracy. Decision Tree gives an accuracy of 95.10%.[2] Lin et al. Breast cancer prediction using a algorithm of K-means and SOM neural network Compared with the K-means model and SOM network model, hybrid algorithm can accurately the datasets. Hybrid algorithm model gives accuracy and computing time.[3]
Kathale et al. proposed a method for detecting the cancer region and classifying cancerous or normal patients. Here, Random Forest algorithm is being used for detection and classification of breast cancer. It gives an accuracy of 95.3%.[4]
Ultrasound is used after a mammogram. It is used to determine whether a new breast lump is a solid mass or a fluid-filled cyst. Biopsy is the only sure way to diagnose most cancers. It is the main symptomatic system that can decide whether the suspicious region is carcinogenic. There are different types of breast cancer. The most common types are invasive ductal carcinoma and invasive lobular carcinoma.
© 2022, IRJET
|
Impact Factor value: 7.529
hybrid model. neural cluster better
Bayrak et al. proposed two most popular machine learning techniques including SVM and ANN. The classification performance of SVM and ANN are done through performance metrics such as accuracy, precision,
|
ISO 9001:2008 Certified Journal
|
Page 3897