Imbalance-Effective Active Learning in Nucleus, Lymphocyte and Plasma Cell Detection

An Imbalance-Effective Active Learning (IEAL) based deep neural network algorithm is proposed for the automatic detection of nucleus, lymphocyte and plasma cells in hepatitis diagnosis. The active sampling approach reduces the training sample annotation cost and mitigates extreme imbalances among the nucleus, lymphocytes and plasma samples. A Bayesian U-net model is developed by incorporating IEAL with basic U-Net. The testing results obtained using an in-house dataset consisting of 43 whole slide images (300 256 * 256 images) show that the proposed method achieves an equal or better performance compared than a basic U-net classifier using less than half the number of annotated samples.

[1]  K. Ishak,et al.  Histological grading and staging of chronic hepatitis. , 1995 .

[2]  Lin Yang,et al.  Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation , 2017, MICCAI.

[3]  Burr Settles,et al.  Active Learning Literature Survey , 2009 .

[4]  C. Lee Giles,et al.  Learning on the border: active learning in imbalanced data classification , 2007, CIKM '07.

[5]  Lei Zhang,et al.  Fine-Tuning Convolutional Neural Networks for Biomedical Image Analysis: Actively and Incrementally , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Ching-Lung Lai,et al.  Epidemiology of Hepatocellular Carcinoma in the Asia-Pacific Region , 2016, Gut and liver.

[7]  Orcun Goksel,et al.  Active Learning for Segmentation by Optimizing Content Information for Maximal Entropy , 2018, DLMIA/ML-CDS@MICCAI.

[8]  C. E. SHANNON,et al.  A mathematical theory of communication , 1948, MOCO.

[9]  Tianbao Yang,et al.  Online Asymmetric Active Learning with Imbalanced Data , 2016, KDD.

[10]  Robert Sabourin,et al.  Improve the performance of transfer learning without fine-tuning using dissimilarity-based multi-view learning for breast cancer histology images , 2018, ICIAR.

[11]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[12]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[13]  Stefan Wrobel,et al.  Active Hidden Markov Models for Information Extraction , 2001, IDA.

[14]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.

[15]  Nassir Navab,et al.  Multiclass Deep Active Learning for Detecting Red Blood Cell Subtypes in Brightfield Microscopy , 2019, MICCAI.

[16]  Ruimao Zhang,et al.  Cost-Effective Active Learning for Deep Image Classification , 2017, IEEE Transactions on Circuits and Systems for Video Technology.

[17]  Qingyao Wu,et al.  Online Adaptive Asymmetric Active Learning for Budgeted Imbalanced Data , 2018, KDD.

[18]  Yupu Yang,et al.  Actively learning from mistakes in class imbalance problems , 2013 .

[19]  C. Sautès-Fridman,et al.  The immune contexture in human tumours: impact on clinical outcome , 2012, Nature Reviews Cancer.

[20]  Kaiming He,et al.  Rethinking ImageNet Pre-Training , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).