Deep Learning Nuclei Detection in Digitized Histology Images by Superpixels

Abstract

Background:Advances in image analysis and computational techniques have facilitated automatic detection of critical features in histopathology images. Detection of nuclei is critical for squamous epithelium cervical intraepithelial neoplasia (CIN) classification into normal, CIN1, CIN2, and CIN3 grades.Methods:In this study, a deep learning (DL)-based nuclei segmentation approach is investigated based on gathering localized information through the generation of superpixels using a simple linear iterative clustering algorithm and training with a convolutional neural network.Results:The proposed approach was evaluated on a dataset of 133 digitized histology images and achieved an overall nuclei detection (object-based) accuracy of 95.97%, with demonstrated improvement over imaging-based and clustering-based benchmark techniques.Conclusions:The proposed DL-based nuclei segmentation Method with superpixel analysis has shown improved segmentation results in comparison to state-of-the-art methods.

Artificial intelligence in digital pathology — new tools for diagnosis and precision oncology

“…The CNN thus works by hierarchically deconstructing the image into low-level cues, such as edges, curves or shapes, which are then aggregated to form high-order structural relationships in order to identify features of interest. CNN DL-based approaches have been used for image-based detection and segmentation tasks to identify and quantify cells 32,33,82,87 (such as neutrophils, lymphocytes and blast cells), histological features (for example, nuclei 34,35,88,89 , mitotic figures, stroma 90 and glandular structures 38,39 ) or regions of interest (such as the tumoural 54 or peritumoural areas). In addition, Senaras et al 91 have developed the CNN-based DeepFocus system to automatically detect and segment out-of-focus and blurry areas in digitized WSIs, with an average accuracy of 93.2% (±9.6%).…”

Artificial intelligence in digital breast pathology: Techniques and applications

“…Convolutional neural networks (CNN) with hierarchical layers of pattern detectors has shown great success for image recognition problems. CNN-based approaches have been used for image-based detection and segmentation tasks to identify and quantify cells [ [22] , [23] , [24] , [25] ] and histological features [ [26] , [27] , [28] , [29] ]. Finally, recurrent neural networks (RNN) use self-connecting pattern detectors for sequence processing.…”

A Comprehensive Review for Breast Histopathology Image Analysis Using Classical and Deep Neural Networks

“…In addition, this review discussed the deep ANNs method not only can be applied in the field of breast histopathological image analysis, but also in the field of other closed microscopic image analysis, such as: Cervical histopathological analysis [167], [168], [169], cervical cytopathological analysis [170], [171], [172], stem cell analysis [173], [174], microbiological image analysis [175], [176], [177], sperm quality analysis [178], [179], [178], web-based platform for computer assisted diagnosis [180], [181], and rock microstructural analysis [182], [183]. No matter from the aspects of image pre-processing, feature extraction and selection, segmentation, and classification, or from the aspects of deep ANN model design and proposed framework idea, the methods of deep ANN summarized in this review can bring a new perspective to the research in other fields.…”