Transformation Invariant Cancerous Tissue Classification Using Spatially Transformed DenseNet

Abstract

In this work, we introduce a spatially transformed DenseNet architecture for transformation invariant classification of cancer tissue. Our architecture increases the accuracy of the base DenseNet architecture while adding the ability to operate in a transformation invariant way while simultaneously being simpler than other models that try to provide some form of invariance.

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• A Survey on Visual Transformer
• TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
• Longformer: The Long-Document Transformer
• Is Space-Time Attention All You Need for Video Understanding?
• Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation
• Linformer: Self-Attention with Linear Complexity
• Deep Learning for Identifying Metastatic Breast Cancer
• ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
• Detecting Cancer Metastases on Gigapixel Pathology Images
• Axial Attention in Multidimensional Transformers
• Dermatologist Level Dermoscopy Skin Cancer Classification Using Different Deep Learning Convolutional Neural Networks Algorithms
• Recognition of Handwritten Digit using Convolutional Neural Network in Python with Tensorflow and Comparison of Performance for Various Hidden Layers
• Cancer image classification based on DenseNet model