Optimizing PSO-CNN Parameters to Enhance Radiologist Accuracy in Breast Cancer Screening

P. MalliKarjuna; G. Manasa

doi:10.32628/IJSRST

Authors

P. MalliKarjuna Assistant Professor, Department of ECE, K M M Institute of Technology & Science, Tirupati, Andhra Pradesh, India Author
G. Manasa M.Tech Student (DSCE), Department of ECE, K M M Institute of Technology & Science, Tirupati, Andhra Pradesh, India Author

DOI:

https://doi.org/10.32628/IJSRST

Keywords:

Breast Cancer, PSO Algorithm, CNN, Accuracy

Abstract

Breast cancer screening is a critical area of medical diagnostics, where the accuracy and performance of radiologists play a pivotal role in early detection and diagnosis. In this Project, we present a novel approach aimed at enhancing radiologists' performance in breast cancer screening through the optimization of parameters for a PSO with CNN. We compare the results of our proposed method against an existing approach based on Deep Neural Networks (DNN) in terms of accuracy, specificity, and the types of cancer detected, including both benign and malignant cases. The existing method employs DNN as the primary algorithm, achieving an accuracy rate of 92.8%. While this performance is commendable, our proposed method, leveraging the power of PSO-CNN with optimized parameters, surpasses it with an accuracy rate of 95.5%. This improvement is of paramount significance in the context of breast cancer screening, where even small increments in accuracy can have substantial positive impacts on patient outcomes. Furthermore, when considering specificity, the existing DNN-based method achieves a specificity rate of 87.4%. In contrast, our proposed method utilizing PSO-CNN parameters achieves a specificity rate of 90%. This enhancement in specificity is vital, as it minimizes false positives, reducing patient anxiety and unnecessary follow-up procedures. Our proposed method based approach maintains the capability to identify both types of cancer, aligning with the existing DNN-based method in this regard. Finally the potential of utilizing proposed method parameters to enhance radiologists' performance in breast cancer screening.

Downloads

Download data is not yet available.

References

Liu B., Cheng H. D., Huang J., Tian J., Tang X., Liu J. Fully automatic and segmentation-robust classification of breast tumors based on local texture analysis of ultrasound images. Pattern Recognition . 2010;43(1):280–298. doi: 10.1016/j.patcog.2009.06.002.

Girshick R., Donahue J., Darrell T., Malik J. Region-based convolutional networks for accurate object detection and segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2016 Jan;38(1):142–158.

Sathya M., Jeyaselvi M., Joshi S., Pandey E., Kumar Pareek P., Sajjad Shaukat jamal, vinay kumar, henry kwame atiglah, “cancer categorization using genetic algorithm to identify biomarker genes,” Journal of Healthcare Engineering . 2022;2022:12. doi: 10.1155/2022/5821938.5821938

Noura M., Abdel wahed A. Computer aided system for breast cancer diagnosis in ultrasound images. International Journal of Environmental Health Engineering . 2015;3(3):71–76. doi: 10.12785/jehe/030303.

Veta M., Pluim J. P. W., van Diest P. J., Viergever M. A. Breast cancer histopathology image analysis: a review. IEEE Transactions on Biomedical Engineering . 2014 May;61(5):1400–1411. doi: 10.1109/TBME.2014.2303852.

Motwani A., Shukla P. K., Pawar M. Smart predictive healthcare framework for remote patient monitoring and recommendation using deep learning with novel cost optimization. In: Senjyu T., Mahalle P. N., Perumal T., Joshi A., editors. Information and Communication Technology for Intelligent Systems . Vol. 195. Singapore: Springer; 2021.

Chan H. P. Computerized classification of malignant and benign micro calcifications on mammograms: consistency examination using an artificial neural network. Physics Medical Biology . 1996;42(3):549–567.

Varela C., Tahoces P. G., Méndez A. J., Souto M., Vidal J. J. Computerized detection of breast masses in digitized mammograms. Computers in Biology and Medicine . 2007;37(2):214–226. doi: 10.1016/j.compbiomed.2005.12.006

Shukla P. K., Shukla P. K., Bhatele M., et al. A novel machine learning model to predict the staying time of international migrants. The International Journal on Artificial Intelligence Tools . 2021;30(2) doi: 10.1142/S0218213021500020.2150002

Ciecholewski M. Malignant and benign mass segmentation in mammograms using active contour methods. Symmetry . 2017;9(277):1–22. doi: 10.3390/sym9110277.