Interpretable classification of colon histological images using attention-based residual network model
- Author:
- No author available
- Journal Title:
- Chinese Journal of Biomedical Engineering
- Issue:
- 5
- DOI:
- 10.3760/cma.j.cn115668-20210729-00063
- Key Word:
- 注意力机制;注意力热图;残差网络;病理学图像;可解释性;Attention mechanism;Attention heatmap;Residual network;Pathological image;Interpretability
Abstract： Objective:To establish a residual network model based on attention mechanism for multi-category diagnosis of eight commonly-seen "image patches" in colorectal pathology.Methods:Attention mechanism based residual neural network learning was used for label prediction of eight colon histological images. Meanwhile, the characteristics of interpretable classifications were obtained by decoding the network-learned patterns based on attention heatmaps generated by gradient-weighted class activation mapping (Grad-CAM) .Results:The proposed method achieved a 98.78% accuracy and an AUC area of 0.998 3 in classification of 8 colon histological image patches including colon cancer. The attention heatmaps generated generally coincided with classifications by professional pathologists.Conclusion:The residual network model based on the attention mechanism can achieve high accuracy in the multi-classification of pathological images. This helps physicians in determining on symptomatic treatment in response to real-time, objective and accurate diagnostic findings, and also offers interpretability for classification of histological images.
- [1]Evgeny A. Smirnov,Denis M. Timoshenko,Serge N. Andrianov.Comparison of Regularization Methods for ImageNet Classification with Deep Convolutional Neural Networks[J].2014,6(1).
- [2]Copa, L.,Volpi, M.,Munoz-Mari, J.,etc.A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification[J].2011,5(3).
- [3]Pradeep Kumar Mallick,Seuc Ho Ryu,Sandeep Kumar Satapathy,etc.Brain MRI Image Classification for Cancer Detection Using Deep Wavelet Autoencoder-Based Deep Neural Network[J].2019,7.
- [4]Hao,Sun,Xianxu,Zeng,Tao,Xu,etc.Computer-Aided Diagnosis in Histopathological Images of the Endometrium Using a Convolutional Neural Network and Attention Mechanisms.[J].2019.
- [5]Dawoon Jung,Mau Dung Nguyen,Mina Park,etc.Multiple Classification of Gait Using Time-Frequency Representations and Deep Convolutional Neural Networks[J].2020,28(4).
- [6]A. Sáez,J. Sánchez-Monedero,P. A. Gutiérrez,etc.Machine Learning Methods for Binary and Multiclass Classification of Melanoma Thickness From Dermoscopic Images[J].2015,35(4).
- [7]SanaUllah Khan,Naveed Islam,Zahoor Jan,etc.A novel deep learning based framework for the detection and classification of breast cancer using transfer learning[J].2019,125.
- [8]D'Agostino RB Sr,Pencina MJ,D'Agostino RB Jr.Evaluating the added predictive ability of a new marker: from area under the ROC curve to reclassification and beyond.[J].2008,27(2).
- [9]LeCun Yann,Bengio Yoshua,Hinton Geoffrey.Deep learning[J].2015,521(7553).
- [10]Tarabalka, Y.,Benediktsson, J. A.,Chanussot, J..Segmentation and Classification of Hyperspectral Images Using Minimum Spanning Forest Grown From Automatically Selected Markers[J].2010,40(5).
- [11]Qiangchang, Wang,Yuanjie, Zheng,Gongping, Yang,etc.Multi-Scale Rotation-Invariant Convolutional Neural Networks for Lung Texture Classification.[J].2017,(Spec ).
- [12]Hai Tang,Zhihui Hu.Research on Medical Image Classification Based on Machine Learning[J].2020,8.
- [13]van der Maaten, Laurens,Hinton, Geoffrey.Visualizing Data using t-SNE.[J].2008,9(11).
- [14]Bolei,Xu,Jingxin,Liu,Xianxu,Hou,etc.Attention by Selection: A Deep Selective Attention Approach to Breast Cancer Classification.[J].2019.
- [15]Geert Litjens,Thijs Kooi,Babak Ehteshami Bejnordi,etc.A survey on deep learning in medical image analysis[J].2017,42.
- [16]Su Yeon Kim,James Diggans,Dan Pankratz,etc.Classification of usual interstitial pneumonia in patients with interstitial lung disease: assessment of a machine learning approach using high-dimensional transcriptional data[J].2015,3(6).
- [17]Hyungtae Lee,Heesung Kwon.Going Deeper With Contextual CNN for Hyperspectral Image Classification[J].2017,26(10).
- [18]Rathore,S.,Hussain,M.,AksamIftikhar,M.,etc.Ensemble classification of colon biopsy images based on information rich hybrid features[J].2014,47.
- [19]Ozdemir, E.,Gunduz-Demir, C..A Hybrid Classification Model for Digital Pathology Using Structural and Statistical Pattern Recognition[J].2013,32(2).
- [20]Kim, Incheol,Rajaraman, Sivaramakrishnan,Antani, Sameer.Visual Interpretation of Convolutional Neural Network Predictions in Classifying Medical Image Modalities[J].2019,9(2).
- [21]Xiang Li,Wei Li,Ran Tao.Staged Detection–Identification Framework for Cell Nuclei in Histopathology Images[J].2019,69(1).
- [22]Moosmann Frank,Jurie Frederic,Nowak Eric.Randomized Clustering Forests for Image Classification[J].2008,30(9).
- [23]Gongning Luo,Wangmeng Zuo,Henggui Zhang,etc.Multi-Views Fusion CNN for Left Ventricular Volumes Estimation on Cardiac MR Images[J].2018,65(9).
- [24].Deep Features Learning for Medical Image Analysis with Convolutional Autoencoder Neural Network[J].2017.
- [25]Ying Wang,Ting Peng,Jiajia Duan,etc.Pathological Image Classification Based on Hard Example Guided CNN[J].2020,8.