Hybrid deep autoencoder with Curvature Gaussian for detection of various types of cells in bone marrow trephine biopsy images

  title={Hybrid deep autoencoder with Curvature Gaussian for detection of various types of cells in bone marrow trephine biopsy images},
  author={Tzu-Hsi Song and Victor Sanchez and Hesham EIDaly and Nasir M. Rajpoot},
  journal={2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)},
Automated cell detection is a critical step for a number of computer-assisted pathology related image analysis algorithm. However, automated cell detection is complicated due to the variable cytomorphological and histological factors associated with each cell. In order to efficiently resolve the challenge of automated cell detection, deep learning strategies are widely applied and have recently been shown to be successful in histopathological images. In this paper, we concentrate on bone marrow… 

Figures and Tables from this paper

Simultaneous Cell Detection and Classification with an Asymmetric Deep Autoencoder in Bone Marrow Histology Images
This novel network uses one deep autoencoder to detect the positions of cells and classify types of cells simultaneously, and can efficiently detect the cells with irregular shape.
Simultaneous Cell Detection and Classification in Bone Marrow Histology Images
This paper proposes a synchronized deep autoencoder network for simultaneous detection and classification of cells in bone marrow histology images that uses a curve-support Gaussian model to compute probability maps that allow detecting irregularly shape cells precisely.
Surrounding Cell Suppression For Unsupervised Representation Learning In Hematological Cell Classification
This work proposes and analyzes several techniques for reducing their influence and shows that this improves classification results of unsupervisedly learned cell representations.
Circular Anchors for the Detection of Hematopoietic Cells Using Retinanet
Experiments on hematopoietic cells in bone marrow images show that these methods reduce the number of false positive predictions and increase detection accuracy, and an extension to the Non-maximum Suppression algorithm that copes with predictions that differ in size is introduced.
State of the Art Cell Detection in Bone Marrow Whole Slide Images
U-Net-based cell detection methods and state-of-the-art detection methods for the localization of hematopoietic cells in high-resolution bone marrow images show that even with weak annotations and cell-like artifacts, cells can be localized with high precision.
Semi-Supervised Nests of Melanocytes Segmentation Method Using Convolutional Autoencoders
An effective computer-vision based deep learning tool is proposed that can perform the nests segmentation based on an autoencoder architecture with two learning steps and its ability to segment nests areas with Dice similarity coefficient 0.81, sensitivity 0.76, and specificity 0.94 is a state-of-the-art result.
Cell detection in pathology and microscopy images with multi-scale fully convolutional neural networks
A novel multi-scale fully convolutional neural networks approach for regression of a density map to robustly detect the nuclei of pathology and microscopy images and achieves a promising detection performance that equates and sometimes exceeds the recently published leading detection approaches with the same benchmark datasets.
Modern convolutional object detectors for nuclei detection on pleural effusion cytology images
This work proposes the first implementation of the faster region-based convolutional neural network (Faster R-CNN), the region- based fully Convolutional network (R-FCN), and the single shot multibox detector (SSD) methods for nuclei detection on pathology images.
Deep Learning Models for Digital Pathology
The different challenges facing computational systems for digital pathology are summarized and a review of state-of-the-art works that developed deep learning-based solutions for the predictive modeling of histopathology images from a detection, stain normalization, segmentation, and tissue classification perspective are provided.
A New Generalized Deep Learning Framework Combining Sparse Autoencoder and Taguchi Method for Novel Data Classification and Processing
A novel framework, which primarily integrates the Taguchi Method to a deep autoencoder based system without considering to modify the overall structure of the network, is presented and the results are quite encouraging and verified the overall performance of the proposed framework.


Stacked Sparse Autoencoder (SSAE) for Nuclei Detection on Breast Cancer Histopathology Images
A Stacked Sparse Autoencoder, an instance of a deep learning strategy, is presented for efficient nuclei detection on high-resolution histopathological images of breast cancer and out-performed nine other state of the art nuclear detection strategies.
Locality Sensitive Deep Learning for Detection and Classification of Nuclei in Routine Colon Cancer Histology Images
A Spatially Constrained Convolutional Neural Network (SC-CNN) to perform nucleus detection and a novel Neighboring Ensemble Predictor (NEP) coupled with CNN to more accurately predict the class label of detected cell nuclei are proposed.
Methods for Nuclei Detection, Segmentation, and Classification in Digital Histopathology: A Review—Current Status and Future Potential
This study presents, discusses, and extracts the major trends from an exhaustive overview of various nuclei detection, segmentation, feature computation, and classification techniques used in histopathology imagery, specifically in hematoxylin-eosin and immunohistochemical staining protocols.
Local isotropic phase symmetry measure for detection of beta cells and lymphocytes
Experimental results show that the algorithm performs better than human experts for detection of two types of specific cells in histology images, cells in mouse pancreatic sections and lymphocytes in human breast tissue, and outperforms the best reported results for the latter.
A Nonlinear Mapping Approach to Stain Normalization in Digital Histopathology Images Using Image-Specific Color Deconvolution
The experimental results suggest that the paradigm of color normalization, as a preprocessing step, can significantly help histological image analysis algorithms to demonstrate stable performance which is insensitive to imaging conditions in general and scanner variations in particular.
A Non-Linear Mapping Approach to Stain Normalisation in Digital Histopathology Images using Image-Specific Colour Deconvolution
The experimental results suggest that the paradigm of colour normalisation, as a preprocessing step, can significantly help histological image analysis algorithms to demonstrate stable performance which is insensitive to imaging conditions in general and scanner variations in particular.
Scale and Curvature Invariant Ridge Detector for Tortuous and Fragmented Structures
A novel ridge detector is proposed, SCIRD, which is simultaneously rotation, scale and curvature invariant, and relaxes shape assumptions to achieve enhancement of target image structures inSegmenting dendritic trees and corneal nerve fibres.
Bone marrow pathology in essential thrombocythemia: interobserver reliability and utility for identifying disease subtypes.
The results show that histologic criteria described in the WHO classification are difficult to apply reproducibly and question the validity of distinguishing true ET from prefibrotic myelofibrosis on the basis of subjective morphologic criteria.
Coupled Deep Autoencoder for Single Image Super-Resolution
A data-driven model coupled deep autoencoder (CDA) that simultaneously learns the intrinsic representations of LR and HR image patches and a big-data-driven function that precisely maps these LR representations to their corresponding HR representations is developed.
Autoencoders, Unsupervised Learning, and Deep Architectures
  • P. Baldi
  • Computer Science
    ICML Unsupervised and Transfer Learning
  • 2012
The framework sheds light on the different kinds of autoencoders, their learning complexity, their horizontal and vertical composability in deep architectures, their critical points, and their fundamental connections to clustering, Hebbian learning, and information theory.