Large scale tissue histopathology image classification, segmentation, and visualization via deep convolutional activation features

By Yan Xu, Zhipeng Jia, Liang Wang, Yuqing Ai, Fang Zhang, Maode Lai, Eric I-Chao Chang. BMC Bioinformatics, 2017

407 citations recorded by the source corpus.

Histopathology image analysis is a gold standard for cancer recognition and diagnosis. Automatic analysis of histopathology images can help pathologists diagnose tumor and cancer subtypes, alleviating the workload of pathologists. There are two basic types of tasks in digital histopathology image analysis: image classification and image segmentation. Typical problems with histopathology images that hamper automatic analysis include complex clinical representations, limited quantities of training images in a dataset, and the extremely large size of singular images (usually up to gigapixels). The property of extremely large size for a single image also makes a histopathology image dataset be considered large-scale, even if the number of images in the dataset is limited. In this paper, we propose leveraging deep convolutional neural network (CNN) activation features to perform classification, segmentation and visualization in large-scale tissue histopathology images. Our framework transfers features extracted from CNNs trained by a large natural image database, ImageNet, to histopathology images. We also explore the characteristics of CNN features by visualizing the response of individual neuron components in the last hidden layer. Some of these characteristics reveal biological insights that have been verified by pathologists. According to our experiments, the framework proposed has shown state-of-the-art performance on a brain tumor dataset from the MICCAI 2014 Brain Tumor Digital Pathology Challenge and a colon cancer histopathology image dataset. The framework proposed is a simple, efficient and effective system for histopathology image automatic analysis. We successfully transfer ImageNet knowledge as deep convolutional activation features to the classification and segmentation of histopathology images with little training data. CNN features are significantly more powerful than expert-designed features.

Subfields: Artificial Intelligence, Biophysics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/fe9e72d0c01775036f09a857adcbc88b6228590e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biophysics

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep Convolutional Neural Networks Enable Discrimination of Heterogeneous Digital Pathology Images (2017, background): “There are two basic subjects in analysis of digital histopathology images including classiﬁcation and segmentation (Xu et al., 2017).”
What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentation (2020, neutral): “, medical lesions segmentation [3, 7, 16,31,42].”
Artificial Intelligence and Digital Pathology: Challenges and Opportunities (2018, neutral): “The training set had 22 LGG images and 23 GBM images, and the testing (validation) set had 40 images.[12] Another example is the Camelyon dataset that contains many digital slides (i.”
A Review on a Deep Learning Perspective in Brain Cancer Classification (2019, background): “The computerized image analysis can partially overcome these shortcomings [56].”
Adaptive Weighting Multi-Field-Of-View CNN for Semantic Segmentation in Pathology (2019, background): “The state-of-the-art methods accurately distinguish regions (normal and tumor) in digital pathology images [7][42][43].”
Machine Learning Methods for Histopathological Image Analysis (2017, methodology): “, performed classification and segmentation tasks on brain and colon pathological images using features extracted from CNN trained on ImageNet, and achieved state-of-the-art performance [54].”
Segmentation of Nuclei in Histopathology Images by Deep Regression of the Distance Map (2019, background): “states, such as mitoses [8], [9] or the classification of tissue regions, such as glands [10] and necrotic or metastatic regions [11], [12] and prediction of tumor type and grade [13]–[15].”