Respond-CAM: Analyzing Deep Models for 3D Imaging Data by Visualizations

by   Guannan Zhao, et al.

The convolutional neural network (CNN) has become a powerful tool for various biomedical image analysis tasks, but there is a lack of visual explanation for the machinery of CNNs. In this paper, we present a novel algorithm, Respond-weighted Class Activation Mapping (Respond-CAM), for making CNN-based models interpretable by visualizing input regions that are important for predictions, especially for biomedical 3D imaging data inputs. Our method uses the gradients of any target concept (e.g. the score of target class) that flows into a convolutional layer. The weighted feature maps are combined to produce a heatmap that highlights the important regions in the image for predicting the target concept. We prove a preferable sum-to-score property of the Respond-CAM and verify its significant improvement on 3D images from the current state-of-the-art approach. Our tests on Cellular Electron Cryo-Tomography 3D images show that Respond-CAM achieves superior performance on visualizing the CNNs with 3D biomedical images inputs, and is able to get reasonably good results on visualizing the CNNs with natural image inputs. The Respond-CAM is an efficient and reliable approach for visualizing the CNN machinery, and is applicable to a wide variety of CNN model families and image analysis tasks.



There are no comments yet.


page 6

page 7

page 14


Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization

We propose a technique for producing "visual explanations" for decisions...

Grad-CAM: Why did you say that?

We propose a technique for making Convolutional Neural Network (CNN)-bas...

Grad-CAM++: Generalized Gradient-based Visual Explanations for Deep Convolutional Networks

Over the last decade, Convolutional Neural Network (CNN) models have bee...

Medical Image Segmentation Based on Multi-Modal Convolutional Neural Network: Study on Image Fusion Schemes

Image analysis using more than one modality (i.e. multi-modal) has been ...

Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks

Recently, increasing attention has been drawn to the internal mechani...

Improving Interpretability of CNN Models Using Non-Negative Concept Activation Vectors

Convolutional neural network (CNN) models for computer vision are powerf...

CNN Fixations: An unraveling approach to visualize the discriminative image regions

Deep convolutional neural networks (CNN) have revolutionized various fie...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.