Convolutional neural networks for mammograph analysis

The main theme of this study is the application of advanced artificial intelligence techniques, especially Convolutional Neural Networks (CNN), for early detection of breast cancer. With the increasing importance of automated medical image analysis, this study aims to evaluate the effectiveness of CNN in the analysis of mammograms, focusing particularly on segmentation and anomaly detection. To achieve this objective, images from renowned public databases such as the Digital Database for Screening Mammography (DDSM) and INbreast were analyzed. The study also involves the preprocessing of these images to ensure the quality of the input data and the implementation of different CNN architectures, comparing their performance in terms of accuracy and reliability. The methodology adopted included a comprehensive literature review and the implementation of data augmentation and preprocessing techniques to optimize CNN performance. The data were collected from public databases and renowned scientific journals, ensuring the relevance and timeliness of the information. The analysis of the results showed that CNNs can outperform traditional methods, offering greater accuracy in the segmentation of tumors and other anomalies, promoting faster and more reliable diagnoses. The results show that CNN EfficientNet and InceptionResNetV2 achieved greater accuracy, while CNN MobileNet and MultiResUNet achieved satisfactory accuracy and with lower processing consumption than the other implemented networks.