2026-10-11T07:53:29Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34037940 2026-10-01T03:29:35Z category_29161 item_type_7 month_year_10_2026

Deep Learning with DenseNet121: Architecture and Application to Breast MRI Classification Saleh Ramezani (17846414) Deep learning artificial intelligence ai densenet121 model classifies deep learning <h3 dir="ltr">Description</h3><p dir="ltr">This presentation provides an accessible introduction to deep learning concepts and the DenseNet121 convolutional neural network architecture, using inflammatory breast cancer classification from MRI as a practical example. It reviews the fundamental components of neural networks, including neurons, weighted connections, activation functions, softmax classification, cross-entropy loss, gradient descent, backpropagation, learning rate, and optimization.</p><p dir="ltr">The presentation then provides a step-by-step examination of a 3D DenseNet121 architecture designed for volumetric breast MRI. It explains convolutional feature extraction, batch normalization, ReLU activation, pooling, dense connectivity, transition layers, feature-map growth and compression, and global average pooling. Particular emphasis is placed on how DenseNet reuses features by connecting each layer to preceding layers and progressively transforms a 3D MRI volume into a compact feature representation for classification.</p><p dir="ltr">The material uses the distinction between inflammatory breast cancer (IBC) and non-inflammatory locally advanced breast cancer (LABC) as the motivating clinical application, connecting fundamental deep learning concepts to a real-world medical imaging workflow.</p> 2026-10-01T03:29:35Z Text Presentation 10.6084/m9.figshare.34037940.v1 https://figshare.com/articles/presentation/Deep_Learning_with_DenseNet121_Architecture_and_Application_to_Breast_MRI_Classification/34037940 CC BY 4.0