1. Deep convolutional activation features for large scale Brain Tumor histopathology image classification and segmentation
- Author
-
Zhipeng Jia, Yuqing Ai, Fang Zhang, Eric Chang, Maode Lai, and Yan Xu
- Subjects
Contextual image classification ,Computer science ,business.industry ,Segmentation-based object categorization ,Feature extraction ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Brain tumor ,Scale-space segmentation ,Pattern recognition ,Feature selection ,Image segmentation ,medicine.disease ,Feature (computer vision) ,medicine ,Computer vision ,Segmentation ,Artificial intelligence ,business - Abstract
We propose a simple, efficient and effective method using deep convolutional activation features (CNNs) to achieve stat- of-the-art classification and segmentation for the MICCAI 2014 Brain Tumor Digital Pathology Challenge. Common traits of such medical image challenges are characterized by large image dimensions (up to the gigabyte size of an image), a limited amount of training data, and significant clinical feature representations. To tackle these challenges, we transfer the features extracted from CNNs trained with a very large general image database to the medical image challenge. In this paper, we used CNN activations trained by ImageNet to extract features (4096 neurons, 13.3% active). In addition, feature selection, feature pooling, and data augmentation are used in our work. Our system obtained 97.5% accuracy on classification and 84% accuracy on segmentation, demonstrating a significant performance gain over other participating teams.
- Published
- 2015