Machine Learning Algorithms for Breast Cancer Diagnosis: Challenges, Prospects and Future Research Directions

Abstract

Early diagnosis of breast cancer does not only increase the chances of survival but also control the diffusion of cancerous cells in the body. Previously, researchers have developed machine learning algorithms in breast cancer diagnosis such as Support Vector Machine, K-Nearest Neighbor, Convolutional Neural Network, K-means, Fuzzy C-means, Neural Network, Principle Component Analysis (PCA) and Naive Bayes. Unfortunately these algorithms fall short in one way or another due to high levels of computational complexities. For instance, support vector machine employs feature elimination scheme for eradicating data ambiguity and detecting tumors at initial stage. However this scheme is expensive in terms of execution time. On its part, k-means algorithm employs Euclidean distance to determine the distance between cluster centers and data points. However this scheme does not guarantee high accuracy when executed in different iterations. Although the K-nearest Neighbor algorithm employs feature reduction, principle component analysis and 10 fold cross validation methods for enhancing classification accuracy, it is not efficient in terms of processing time. On the other hand, fuzzy c-means algorithm employs fuzziness value and termination criteria to determine the execution time on datasets. However, it proves to be extensive in terms of computational time due to several iterations and fuzzy measure calculations involved. Similarly, convolutional neural network employed back propagation and classification method but the scheme proves to be slow due to frequent retraining. In addition, the neural network achieves low accuracy in its predictions. Since all these algorithms seem to be expensive and time consuming, it necessary to integrate quantum computing principles with conventional machine learning algorithms. This is because quantum computing has the potential to accelerate computations by simultaneously carrying out calculation on many inputs. In this paper, a review of the current machine learning algorithms for breast cancer prediction is provided. Based on the observed shortcomings, a quantum machine learning based classifier is recommended. The proposed working mechanisms of this classifier are elaborated towards the end of this paper.

Breast cancer: A comparative review for breast cancer detection using machine learning techniques

“…It starts with a collection of points that have been labeled and then utilizes them to teach itself how to classify more points. To assign a label to a new point, the system polls the labeled points located in the immediate vicinity, also known as the point's nearest neighbors 52 Decision tree C4.5 is a predictive modeling technique that has the potential to be used in a wide variety of contexts.…”

“…To assign a label to a new point, the system polls the labeled points located in the immediate vicinity, also known as the point's nearest neighbors. 52 (d) Decision tree C4.5 is a predictive modeling technique that has the potential to be used in a wide variety of contexts. It is possible to design it using an algorithmic method that may divide the data set in various ways according to the present conditions.…”

Decoding breast cancer Histopathology: Machine Learning-Enhanced Advanced Mathematical Models in Multi-B-Value MR Diffusion Imaging

“…These computational approaches offer advantages in speed, scalability, and the ability to analyze complex, high-dimensional data 13 . However, the utility of ML is not without challenges; issues related to data quality, model interpretability, and clinical integration remain areas of active research and discussion 14 . While machine learning algorithms have shown promise, they often require large datasets and may not be generalizable across different populations or healthcare settings 15 .…”