Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{197301,
        author = {Megha Saha and Soni N and Thanu Shree M N and Swathi P},
        title = {Ultrasound-Based Breast Cancer Diagnosis with Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {6220-6236},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197301},
        abstract = {Breast cancer ranks among the leading causes of death from disease among women across the world and prompt detection is imperative to effective treatment. In this study, we proposed a deep learning approach aimed at automatically classifying breast ultrasound pictures into benign, malignant, and normal groups. The model was built using the DenseNet121 pretrained convolutional neural network, which was then intricately fine-tuned using additional layers to accomplish accurate classification outcomes. Modular image preprocessing was applied on the ultrasound images such as normalization, as well as data augmentations were implemented to benefit the training process. The model was trained using the Adam optimizer which was then evaluated on a test set using multiple accuracy and performance measurements. The proposed system achieved 94.94% test accuracy resulting in affirming the proposed approach as a possible reliable and efficient guide for radiologists in diagnosis of breast cancer cases.},
        keywords = {Breast Cancer, Breast Ultrasound, Deep Learning, DenseNet121, Transfer Learning, Computer-Aided Diagnosis.},
        month = {April},
        }