skip to main content


Title: Rotation equivariant and invariant neural networks for microscopy image analysis
Abstract Motivation

Neural networks have been widely used to analyze high-throughput microscopy images. However, the performance of neural networks can be significantly improved by encoding known invariance for particular tasks. Highly relevant to the goal of automated cell phenotyping from microscopy image data is rotation invariance. Here we consider the application of two schemes for encoding rotation equivariance and invariance in a convolutional neural network, namely, the group-equivariant CNN (G-CNN), and a new architecture with simple, efficient conic convolution, for classifying microscopy images. We additionally integrate the 2D-discrete-Fourier transform (2D-DFT) as an effective means for encoding global rotational invariance. We call our new method the Conic Convolution and DFT Network (CFNet).

Results

We evaluated the efficacy of CFNet and G-CNN as compared to a standard CNN for several different image classification tasks, including simulated and real microscopy images of subcellular protein localization, and demonstrated improved performance. We believe CFNet has the potential to improve many high-throughput microscopy image analysis applications.

Availability and implementation

Source code of CFNet is available at: https://github.com/bchidest/CFNet.

Supplementary information

Supplementary data are available at Bioinformatics online.

 
more » « less
Award ID(s):
1717205
NSF-PAR ID:
10425987
Author(s) / Creator(s):
; ; ;
Publisher / Repository:
Oxford University Press
Date Published:
Journal Name:
Bioinformatics
Volume:
35
Issue:
14
ISSN:
1367-4803
Page Range / eLocation ID:
p. i530-i537
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    After graphene was first exfoliated in 2004, research worldwide has focused on discovering and exploiting its distinctive electronic, mechanical, and structural properties. Application of the efficacious methodology used to fabricate graphene, mechanical exfoliation followed by optical microscopy inspection, to other analogous bulk materials has resulted in many more two-dimensional (2D) atomic crystals. Despite their fascinating physical properties, manual identification of 2D atomic crystals has the clear drawback of low-throughput and hence is impractical for any scale-up applications of 2D samples. To combat this, recent integration of high-performance machine-learning techniques, usually deep learning algorithms because of their impressive object recognition abilities, with optical microscopy have been used to accelerate and automate this traditional flake identification process. However, deep learning methods require immense datasets and rely on uninterpretable and complicated algorithms for predictions. Conversely, tree-based machine-learning algorithms represent highly transparent and accessible models. We investigate these tree-based algorithms, with features that mimic color contrast, for automating the manual inspection process of exfoliated 2D materials (e.g., MoSe2). We examine their performance in comparison to ResNet, a famous Convolutional Neural Network (CNN), in terms of accuracy and the physical nature of their decision-making process. We find that the decision trees, gradient boosted decision trees, and random forests utilize physical aspects of the images to successfully identify 2D atomic crystals without suffering from extreme overfitting and high training dataset demands. We also employ a post-hoc study that identifies the sub-regions CNNs rely on for classification and find that they regularly utilize physically insignificant image attributes when correctly identifying thin materials.

     
    more » « less
  2. Abstract Motivation

    Accurately predicting drug–target interactions (DTIs) in silico can guide the drug discovery process and thus facilitate drug development. Computational approaches for DTI prediction that adopt the systems biology perspective generally exploit the rationale that the properties of drugs and targets can be characterized by their functional roles in biological networks.

    Results

    Inspired by recent advance of information passing and aggregation techniques that generalize the convolution neural networks to mine large-scale graph data and greatly improve the performance of many network-related prediction tasks, we develop a new nonlinear end-to-end learning model, called NeoDTI, that integrates diverse information from heterogeneous network data and automatically learns topology-preserving representations of drugs and targets to facilitate DTI prediction. The substantial prediction performance improvement over other state-of-the-art DTI prediction methods as well as several novel predicted DTIs with evidence supports from previous studies have demonstrated the superior predictive power of NeoDTI. In addition, NeoDTI is robust against a wide range of choices of hyperparameters and is ready to integrate more drug and target related information (e.g. compound–protein binding affinity data). All these results suggest that NeoDTI can offer a powerful and robust tool for drug development and drug repositioning.

    Availability and implementation

    The source code and data used in NeoDTI are available at: https://github.com/FangpingWan/NeoDTI.

    Supplementary information

    Supplementary data are available at Bioinformatics online.

     
    more » « less
  3. Abstract Motivation

    Best performing named entity recognition (NER) methods for biomedical literature are based on hand-crafted features or task-specific rules, which are costly to produce and difficult to generalize to other corpora. End-to-end neural networks achieve state-of-the-art performance without hand-crafted features and task-specific knowledge in non-biomedical NER tasks. However, in the biomedical domain, using the same architecture does not yield competitive performance compared with conventional machine learning models.

    Results

    We propose a novel end-to-end deep learning approach for biomedical NER tasks that leverages the local contexts based on n-gram character and word embeddings via Convolutional Neural Network (CNN). We call this approach GRAM-CNN. To automatically label a word, this method uses the local information around a word. Therefore, the GRAM-CNN method does not require any specific knowledge or feature engineering and can be theoretically applied to a wide range of existing NER problems. The GRAM-CNN approach was evaluated on three well-known biomedical datasets containing different BioNER entities. It obtained an F1-score of 87.26% on the Biocreative II dataset, 87.26% on the NCBI dataset and 72.57% on the JNLPBA dataset. Those results put GRAM-CNN in the lead of the biological NER methods. To the best of our knowledge, we are the first to apply CNN based structures to BioNER problems.

    Availability and implementation

    The GRAM-CNN source code, datasets and pre-trained model are available online at: https://github.com/valdersoul/GRAM-CNN.

    Supplementary information

    Supplementary data are available at Bioinformatics online.

     
    more » « less
  4. Traditionally, a high-performance microscope with a large numerical aperture is required to acquire high-resolution images. However, the images’ size is typically tremendous. Therefore, they are not conveniently managed and transferred across a computer network or stored in a limited computer storage system. As a result, image compression is commonly used to reduce image size resulting in poor image resolution. Here, we demonstrate custom convolution neural networks (CNNs) for both super-resolution image enhancement from low-resolution images and characterization of both cells and nuclei from hematoxylin and eosin (H&E) stained breast cancer histopathological images by using a combination of generator and discriminator networks so-called super-resolution generative adversarial network-based on aggregated residual transformation (SRGAN-ResNeXt) to facilitate cancer diagnosis in low resource settings. The results provide high enhancement in image quality where the peak signal-to-noise ratio and structural similarity of our network results are over 30 dB and 0.93, respectively. The derived performance is superior to the results obtained from both the bicubic interpolation and the well-known SRGAN deep-learning methods. In addition, another custom CNN is used to perform image segmentation from the generated high-resolution breast cancer images derived with our model with an average Intersection over Union of 0.869 and an average dice similarity coefficient of 0.893 for the H&E image segmentation results. Finally, we propose the jointly trained SRGAN-ResNeXt and Inception U-net Models, which applied the weights from the individually trained SRGAN-ResNeXt and inception U-net models as the pre-trained weights for transfer learning. The jointly trained model’s results are progressively improved and promising. We anticipate these custom CNNs can help resolve the inaccessibility of advanced microscopes or whole slide imaging (WSI) systems to acquire high-resolution images from low-performance microscopes located in remote-constraint settings. 
    more » « less
  5. Background

    Quantitative analysis of mitochondrial morphology plays important roles in studies of mitochondrial biology. The analysis depends critically on segmentation of mitochondria, the image analysis process of extracting mitochondrial morphology from images. The main goal of this study is to characterize the performance of convolutional neural networks (CNNs) in segmentation of mitochondria from fluorescence microscopy images. Recently, CNNs have achieved remarkable success in challenging image segmentation tasks in several disciplines. So far, however, our knowledge of their performance in segmenting biological images remains limited. In particular, we know little about their robustness, which defines their capability of segmenting biological images of different conditions, and their sensitivity, which defines their capability of detecting subtle morphological changes of biological objects.

    Methods

    We have developed a method that uses realistic synthetic images of different conditions to characterize the robustness and sensitivity of CNNs in segmentation of mitochondria. Using this method, we compared performance of two widely adopted CNNs: the fully convolutional network (FCN) and the U‐Net. We further compared the two networks against the adaptive active‐mask (AAM) algorithm, a representative of high‐performance conventional segmentation algorithms.

    Results

    The FCN and the U‐Net consistently outperformed the AAM in accuracy, robustness, and sensitivity, often by a significant margin. The U‐Net provided overall the best performance.

    Conclusions

    Our study demonstrates superior performance of the U‐Net and the FCN in segmentation of mitochondria. It also provides quantitative measurements of the robustness and sensitivity of these networks that are essential to their applications in quantitative analysis of mitochondrial morphology.

     
    more » « less