Stacked Sparse Autoencoder (SSAE) for Nuclei Detection on Breast Cancer Histopathology Images
By Jun Xu, Lei Xiang, Qingshan Liu, Hannah Gilmore, Jianzhong Wu, Jinghai Tang, Anant Madabhushi. 2015
815 citations recorded by the source corpus.
Automated nuclear detection is a critical step for a number of computer assisted pathology related image analysis algorithms such as for automated grading of breast cancer tissue specimens. The Nottingham Histologic Score system is highly correlated with the shape and appearance of breast cancer nuclei in histopathological images. However, automated nucleus detection is complicated by 1) the large number of nuclei and the size of high resolution digitized pathology images, and 2) the variability in size, shape, appearance, and texture of the individual nuclei. Recently there has been interest in the application of “Deep Learning” strategies for classification and analysis of big image data. Histopathology, given its size and complexity, represents an excellent use case for application of deep learning strategies. In this paper, a Stacked Sparse Autoencoder (SSAE), an instance of a deep learning strategy, is presented for efficient nuclei detection on high-resolution histopathological images of breast cancer. The SSAE learns high-level features from just pixel intensities alone in order to identify distinguishing features of nuclei. A sliding window operation is applied to each image in order to represent image patches via high-level features obtained via the auto-encoder, which are then subsequently fed to a classifier which categorizes each image patch as nuclear or non-nuclear. Across a cohort of 500 histopathological images (2200 × 2200) and approximately 3500 manually segmented individual nuclei serving as the groundtruth, SSAE was shown to have an improved F-measure 84.49% and an average area under Precision-Recall curve (AveP) 78.83%. The SSAE approach also out-performed nine other state of the art nuclear detection strategies.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging, Medical Imaging
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
- Francisco Herrera
- Salvador Garcia
- Anant Madabhushi
- M. J. Jesús
- B. van Ginneken
- Francisco Charte
- Anne L. Martel
- Ozan Ciga
In Computer Vision and Pattern Recognition
- Dinggang Shen
- Anant Madabhushi
- Heung-Il Suk
- B. van Ginneken
- Christos Davatzikos
- Guorong Wu
- Amir Hussain
- Daniel Rueckert
In Radiology, Nuclear Medicine and Imaging
- Anant Madabhushi
- Dinggang Shen
- Heung-Il Suk
- B. van Ginneken
- Daniel Rueckert
- Ronald M. Summers
- Hayit Greenspan
- Anne L. Martel
In Medical Imaging
- Anant Madabhushi
- Thippa Reddy Gadekallu
- Ozan Ciga
- Heung-Il Suk
- Amir Hussain
- Mufti Mahmud
- Dinggang Shen
- Quoc-Viet Pham
Citations in the corpus
- Multi-class texture analysis in colorectal cancer histology (2016, methodology): “This approach has been successfully used by various groups (see Xu et al. 3 for an overview) and has led to new candidate biomarkers 4–6 .”
- A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines (2018, methodology): “The authors of [111] introduce a method, based on stacked DAEs to produce higher level and more compact features, which eases this task.”
- Deep Learning and Medical Diagnosis: A Review of Literature (2018, neutral): “[62] SSAE Digital pathology images Nuclei detection of breast cancer; the stacked sparse autoencoder (SSAE) approach can outperform state of the art nuclear detection strategies.”
- Applications of Deep Learning and Reinforcement Learning to Biological Data (2017, methodology): “used Stacked Sparse DA architecture to identify nuclei in the histopathology images of the breast cancer [105].”
- Deep Learning Applications in Medical Image Analysis (2018, methodology): “[73], although he used a Stacked Sparse Autoencoder (SSAE) instead.”
- Locality Sensitive Deep Learning for Detection and Classification of Nuclei in Routine Colon Cancer Histology Images (2016, methodology): “As opposed to other approaches [7], [8] that do not enforce the pixels close to the center of a nucleus to have a higher probability value than those further away, the predicted probability values produced by SC-CNN are topologically constrained such that high probability values are concentrated in…”
- LEARN: Learned Experts’ Assessment-Based Reconstruction Network for Sparse-Data CT (2017, neutral): “Until now, machine learning especially deep learning were mainly utilized for medical image analysis, such as organ segmentation [31], nodule detection [32], nuclei classification [33].”
- Deep learning in bioinformatics (2016, methodology): “In terms of biomedical imaging, DNNs have been applied in several research areas, including anomaly classification [122–124], segmentation [133], recognition [142, 143] and brain decoding [149, 150].”
- Transfer Learning for Molecular Cancer Classification Using Deep Neural Networks (2019, methodology): “Therefore, following [46], the computation time of various algorithms have been comparedw.”
- A Deep Convolutional Neural Network for segmenting and classifying epithelial and stromal regions in histopathological images (2016, methodology): “In [28,29], we presented a Stacked Sparse Autoencoder (SSAE) framework for automated nuclear detection from high resolution breast histopathological images.”