Active learning framework with iterative clustering for bioimage classification

Harnessing Deep Learning to Analyze Cryptic Morphological Variability of Marchantia polymorpha

Characterizing phenotypes is a fundamental aspect of biological sciences, although it can be challenging due to various factors. For instance, the liverwort Marchantia polymorpha is a model system for plant biology and exhibits morphological variability, making it difficult to identify and quantify distinct phenotypic features using objective measures. To address this issue, we utilized a deep-learning-based image classifier that can handle plant images directly without manual extraction of phenotypic features and analyzed pictures of M. polymorpha. This dioicous plant species exhibits morphological differences between male and female wild accessions at an early stage of gemmaling growth, although it remains elusive whether the differences are attributable to sex chromosomes. To isolate the effects of sex chromosomes from autosomal polymorphisms, we established a male and female set of recombinant inbred lines (RILs) from a set of male and female wild accessions. We then trained deep learning models to classify the sexes of the RILs and the wild accessions. Our results showed that the trained classifiers accurately classified male and female gemmalings of wild accessions in the first week of growth, confirming the intuition of researchers in a reproducible and objective manner. In contrast, the RILs were less distinguishable, indicating that the differences between the parental wild accessions arose from autosomal variations. Furthermore, we validated our trained models by an 'eXplainable AI' technique that highlights image regions relevant to the classification. Our findings demonstrate that the classifier-based approach provides a powerful tool for analyzing plant species that lack standardized phenotyping metrics.

Quantification of MR spectra by deep learning in an idealized setting: Investigation of forms of input, network architectures, optimization by ensembles of networks, and training bias

PURPOSE

The aims of this work are (1) to explore deep learning (DL) architectures, spectroscopic input types, and learning designs toward optimal quantification in MR spectroscopy of simulated pathological spectra; and (2) to demonstrate accuracy and precision of DL predictions in view of inherent bias toward the training distribution.

METHODS

Simulated 1D spectra and 2D spectrograms that mimic an extensive range of pathological in vivo conditions are used to train and test 24 different DL architectures. Active learning through altered training and testing data distributions is probed to optimize quantification performance. Ensembles of networks are explored to improve DL robustness and reduce the variance of estimates. A set of scores compares performances of DL predictions and traditional model fitting (MF).

RESULTS

Ensembles of heterogeneous networks that combine 1D frequency-domain and 2D time-frequency domain spectrograms as input perform best. Dataset augmentation with active learning can improve performance, but gains are limited. MF is more accurate, although DL appears to be more precise at low SNR. However, this overall improved precision originates from a strong bias for cases with high uncertainty toward the dataset the network has been trained with, tending toward its average value.

CONCLUSION

MF mostly performs better compared to the faster DL approach. Potential intrinsic biases on training sets are dangerous in a clinical context that requires the algorithm to be unbiased to outliers (i.e., pathological data). Active learning and ensemble of networks are good strategies to improve prediction performances. However, data quality (sufficient SNR) has proven as a bottleneck for adequate unbiased performance-like in the case of MF.

A stomata classification and detection system in microscope images of maize cultivars

Plant stomata are essential structures (pores) that control the exchange of gases between plant leaves and the atmosphere, and also they influence plant adaptation to climate through photosynthesis and transpiration stream. Many works in literature aim for a better understanding of these structures and their role in the evolution process and the behavior of plants. Although stomata studies in dicots species have advanced considerably in the past years, even there is not much knowledge about the stomata of cereal grasses. Due to the high morphological variation of stomata traits intra- and inter-species, detecting and classifying stomata automatically becomes challenging. For this reason, in this work, we propose a new system for automatic stomata classification and detection in microscope images for maize cultivars based on transfer learning strategy of different deep convolution neural netwoks (DCNN). Our performed experiments show that our system achieves an approximated accuracy of 97.1% in identifying stomata regions using classifiers based on deep learning features, which figures out as a nearly perfect classification system. As the stomata are responsible for several plant functionalities, this work represents an important advance for maize research, providing an accurate system in replacing the current manual task of categorizing these pores on microscope images. Furthermore, this system can also be a reference for studies using images from different cereal grasses.

Effectiveness of Create ML in microscopy image classifications: a simple and inexpensive deep learning pipeline for non-data scientists

Observing chromosomes is a time-consuming and labor-intensive process, and chromosomes have been analyzed manually for many years. In the last decade, automated acquisition systems for microscopic images have advanced dramatically due to advances in their controlling computer systems, and nowadays, it is possible to automatically acquire sets of tiling-images consisting of large number, more than 1000, of images from large areas of specimens. However, there has been no simple and inexpensive system to efficiently select images containing mitotic cells among these images. In this paper, a classification system of chromosomal images by deep learning artificial intelligence (AI) that can be easily handled by non-data scientists was applied. With this system, models suitable for our own samples could be easily built on a Macintosh computer with Create ML. As examples, models constructed by learning using chromosome images derived from various plant species were able to classify images containing mitotic cells among samples from plant species not used for learning in addition to samples from the species used. The system also worked for cells in tissue sections and tetrads. Since this system is inexpensive and can be easily trained via deep learning using scientists' own samples, it can be used not only for chromosomal image analysis but also for analysis of other biology-related images.

Machine learning approach for discrimination of genotypes based on bright-field cellular images

Morphological profiling is a combination of established optical microscopes and cutting-edge machine vision technologies, which stacks up successful applications in high-throughput phenotyping. One major question is how much information can be extracted from an image to identify genetic differences between cells. While fluorescent microscopy images of specific organelles have been broadly used for single-cell profiling, the potential ability of bright-field (BF) microscopy images of label-free cells remains to be tested. Here, we examine whether single-gene perturbation can be discriminated based on BF images of label-free cells using a machine learning approach. We acquired hundreds of BF images of single-gene mutant cells, quantified single-cell profiles consisting of texture features of cellular regions, and constructed a machine learning model to discriminate mutant cells from wild-type cells. Interestingly, the mutants were successfully discriminated from the wild type (area under the receiver operating characteristic curve = 0.773). The features that contributed to the discrimination were identified, and they included those related to the morphology of structures that appeared within cellular regions. Furthermore, functionally close gene pairs showed similar feature profiles of the mutant cells. Our study reveals that single-gene mutant cells can be discriminated from wild-type cells based on BF images, suggesting the potential as a useful tool for mutant cell profiling.

Thiazoline-related innate fear stimuli orchestrate hypothermia and anti-hypoxia via sensory TRPA1 activation

Thiazoline-related innate fear-eliciting compounds (tFOs) orchestrate hypothermia, hypometabolism, and anti-hypoxia, which enable survival in lethal hypoxic conditions. Here, we show that most of these effects are severely attenuated in transient receptor potential ankyrin 1 (Trpa1) knockout mice. TFO-induced hypothermia involves the Trpa1-mediated trigeminal/vagal pathways and non-Trpa1 olfactory pathway. TFOs activate Trpa1-positive sensory pathways projecting from trigeminal and vagal ganglia to the spinal trigeminal nucleus (Sp5) and nucleus of the solitary tract (NTS), and their artificial activation induces hypothermia. TFO presentation activates the NTS-Parabrachial nucleus pathway to induce hypothermia and hypometabolism; this activation was suppressed in Trpa1 knockout mice. TRPA1 activation is insufficient to trigger tFO-mediated anti-hypoxic effects; Sp5/NTS activation is also necessary. Accordingly, we find a novel molecule that enables mice to survive in a lethal hypoxic condition ten times longer than known tFOs. Combinations of appropriate tFOs and TRPA1 command intrinsic physiological responses relevant to survival fate.

Interactive Classification of Whole-Slide Imaging Data for Cancer Researchers

Whole-slide histology images contain information that is valuable for clinical and basic science investigations of cancer but extracting quantitative measurements from these images is challenging for researchers who are not image analysis specialists. In this article, we describe HistomicsML2, a software tool for learn-by-example training of machine learning classifiers for histologic patterns in whole-slide images. This tool improves training efficiency and classifier performance by guiding users to the most informative training examples for labeling and can be used to develop classifiers for prospective application or as a rapid annotation tool that is adaptable to different cancer types. HistomicsML2 runs as a containerized server application that provides web-based user interfaces for classifier training, validation, exporting inference results, and collaborative review, and that can be deployed on GPU servers or cloud platforms. We demonstrate the utility of this tool by using it to classify tumor-infiltrating lymphocytes in breast carcinoma and cutaneous melanoma. SIGNIFICANCE: An interactive machine learning tool for analyzing digital pathology images enables cancer researchers to apply this tool to measure histologic patterns for clinical and basic science studies.

Identification of sarcomatoid differentiation in renal cell carcinoma by machine learning on multiparametric MRI

Sarcomatoid differentiation in RCC (sRCC) is associated with a poor prognosis, necessitating more aggressive management than RCC without sarcomatoid components (nsRCC). Since suspected renal cell carcinoma (RCC) tumors are not routinely biopsied for histologic evaluation, there is a clinical need for a non-invasive method to detect sarcomatoid differentiation pre-operatively. We utilized unsupervised self-organizing map (SOM) and supervised Learning Vector Quantizer (LVQ) machine learning to classify RCC tumors on T2-weighted, non-contrast T1-weighted fat-saturated, contrast-enhanced arterial-phase T1-weighted fat-saturated, and contrast-enhanced venous-phase T1-weighted fat-saturated MRI images. The SOM was trained on 8 nsRCC and 8 sRCC tumors, and used to compute Activation Maps for each training, validation (3 nsRCC and 3 sRCC), and test (5 nsRCC and 5 sRCC) tumor. The LVQ classifier was trained and optimized on Activation Maps from the 22 training and validation cohort tumors, and tested on Activation Maps of the 10 unseen test tumors. In this preliminary study, the SOM-LVQ model achieved a hold-out testing accuracy of 70% in the task of identifying sarcomatoid differentiation in RCC on standard multiparameter MRI (mpMRI) images. We have demonstrated a combined SOM-LVQ machine learning approach that is suitable for analysis of limited mpMRI datasets for the task of differential diagnosis.

Artificial hibernation/life-protective state induced by thiazoline-related innate fear odors

Innate fear intimately connects to the life preservation in crises, although this relationships is not fully understood. Here, we report that presentation of a supernormal innate fear inducer 2-methyl-2-thiazoline (2MT), but not learned fear stimuli, induced robust systemic hypothermia/hypometabolism and suppressed aerobic metabolism via phosphorylation of pyruvate dehydrogenase, thereby enabling long-term survival in a lethal hypoxic environment. These responses exerted potent therapeutic effects in cutaneous and cerebral ischemia/reperfusion injury models. In contrast to hibernation, 2MT stimulation accelerated glucose uptake in the brain and suppressed oxygen saturation in the blood. Whole-brain mapping and chemogenetic activation revealed that the sensory representation of 2MT orchestrates physiological responses via brain stem Sp5/NST to midbrain PBN pathway. 2MT, as a supernormal stimulus of innate fear, induced exaggerated, latent life-protective effects in mice. If this system is preserved in humans, it may be utilized to give rise to a new field: "sensory medicine."

Machine learning identifies stroke features between species

Identification and localization of ischemic stroke (IS) lesions is routinely performed to confirm diagnosis, assess stroke severity, predict disability and plan rehabilitation strategies using magnetic resonance imaging (MRI). In basic research, stroke lesion segmentation is necessary to study complex peri-infarction tissue changes. Moreover, final stroke volume is a critical outcome evaluated in clinical and preclinical experiments to determine therapy or intervention success. Manual segmentations are performed but they require a specialized skill set, are prone to inter-observer variation, are not entirely objective and are often not supported by histology. The task is even more challenging when dealing with large multi-center datasets, multiple experimenters or large animal cohorts. On the other hand, current automatized segmentation approaches often lack histological validation, are not entirely user independent, are often based on single parameters, or in the case of complex machine learning methods, require vast training datasets and are prone to a lack of model interpretation.

Methods: We induced IS using the middle cerebral artery occlusion model on two rat cohorts. We acquired apparent diffusion coefficient (ADC) and T2-weighted (T2W) images at 24 h and 1-week after IS induction. Subsets of the animals at 24 h and 1-week post IS were evaluated using histology and immunohistochemistry. Using a Gaussian mixture model, we segmented voxel-wise interactions between ADC and T2W parameters at 24 h using one of the rat cohorts. We then used these segmentation results to train a random forest classifier, which we applied to the second rat cohort. The algorithms' stroke segmentations were compared to manual stroke delineations, T2W and ADC thresholding methods and the final stroke segmentation at 1-week. Volume correlations to histology were also performed for every segmentation method. Metrics of success were calculated with respect to the final stroke volume. Finally, the trained random forest classifier was tested on a human dataset with a similar temporal stroke on-set. Manual segmentations, ADC and T2W thresholds were again used to evaluate and perform comparisons with the proposed algorithms' output.

Results: In preclinical rat data our framework significantly outperformed commonly applied automatized thresholding approaches and segmented stroke regions similarly to manual delineation. The framework predicted the localization of final stroke regions in 1-week post-stroke MRI with a median Dice similarity coefficient of 0.86, Matthew's correlation coefficient of 0.80 and false positive rate of 0.04. The predicted stroke volumes also strongly correlated with final histological stroke regions (Pearson correlation = 0.88, P < 0.0001). Lastly, the stroke region characteristics identified by our framework in rats also identified stroke lesions in human brains, largely outperforming thresholding approaches in stroke volume prediction (P<0.01).

Conclusion: Our findings reveal that the segmentation produced by our proposed framework using 24 h MRI rat data strongly correlated with the final stroke volume, denoting a predictive effect. In addition, we show for the first time that the stroke imaging features can be directly translated between species, allowing identification of acute stroke in humans using the model trained on animal data. This discovery reduces the gap between the clinical and preclinical fields, unveiling a novel approach to directly co-analyze clinical and preclinical data. Such methods can provide further biological insights into human stroke and highlight the differences between species in order to help improve the experimental setups and animal models of the disease.

A stomata classification and detection system in microscope images of maize cultivars

Plant stomata are essential structures (pores) that control the exchange of gases between plant leaves and the atmosphere, and also they influence plant adaptation to climate through photosynthesis and transpiration stream. Many works in literature aim for a better understanding of these structures and their role in the evolution process and the behavior of plants. Although stomata studies in dicots species have advanced considerably in the past years, even there is not much knowledge about the stomata of cereal grasses. Due to the high morphological variation of stomata traits intra- and inter-species, detecting and classifying stomata automatically becomes challenging. For this reason, in this work, we propose a new system for automatic stomata classification and detection in microscope images for maize cultivars based on transfer learning strategy of different deep convolution neural netwoks (DCNN). Our performed experiments show that our system achieves an approximated accuracy of 97.1% in identifying stomata regions using classifiers based on deep learning features, which figures out as a nearly perfect classification system. As the stomata are responsible for several plant functionalities, this work represents an important advance for maize research, providing an accurate system in replacing the current manual task of categorizing these pores on microscope images. Furthermore, this system can also be a reference for studies using images from different cereal grasses.

Pyrenocine A induces monopolar spindle formation and suppresses proliferation of cancer cells

Pyrenocine A, a phytotoxin, was found to exhibit cytotoxicity against cancer cells with an IC₅₀ value of 2.6-12.9 μM. Live cell imaging analysis revealed that pyrenocine A arrested HeLa cells at the M phase with characteristic ring-shaped chromosomes. Furthermore, as a result of immunofluorescence staining analysis, we found that pyrenocine A resulted in the formation of monopolar spindles in HeLa cells. Monopolar spindles are known to be induced by inhibitors of the kinesin motor protein Eg5 such as monastrol and STLC. Monastrol and STLC induce monopolar spindle formation and M phase arrest via inhibition of the ATPase activity of Eg5. Interestingly, our data revealed that pyrenocine A had no effect on the ATPase activity of Eg5 in vitro, which suggested the compound induces a monopolar spindle by an unknown mechanism. Structure-activity relationship analysis indicates that the enone structure of pyrenocine A is likely to be important for its cytotoxicity. An alkyne-tagged analog of pyrenocine A was synthesized and suppressed proliferation of HeLa cells with an IC₅₀ value of 2.3 μM. We concluded that pyrenocine A induced monopolar spindle formation by a novel mechanism other than direct inhibition of Eg5 motor activity, and the activity of pyrenocine A may suggest a new anticancer mechanism.

IMACEL: A cloud-based bioimage analysis platform for morphological analysis and image classification

Automated quantitative image analysis is essential for all fields of life science research. Although several software programs and algorithms have been developed for bioimage processing, an advanced knowledge of image processing techniques and high-performance computing resources are required to use them. Hence, we developed a cloud-based image analysis platform called IMACEL, which comprises morphological analysis and machine learning-based image classification. The unique click-based user interface of IMACEL’s morphological analysis platform enables researchers with limited resources to evaluate particles rapidly and quantitatively without prior knowledge of image processing. Because all the image processing and machine learning algorithms are performed on high-performance virtual machines, users can access the same analytical environment from anywhere. A validation study of the morphological analysis and image classification of IMACEL was performed. The results indicate that this platform is an accessible and potentially powerful tool for the quantitative evaluation of bioimages that will lower the barriers to life science research.

A Weakly Supervised Deep Learning Framework for Sorghum Head Detection and Counting

The yield of cereal crops such as sorghum (Sorghum bicolor L. Moench) depends on the distribution of crop-heads in varying branching arrangements. Therefore, counting the head number per unit area is critical for plant breeders to correlate with the genotypic variation in a specific breeding field. However, measuring such phenotypic traits manually is an extremely labor-intensive process and suffers from low efficiency and human errors. Moreover, the process is almost infeasible for large-scale breeding plantations or experiments. Machine learning-based approaches like deep convolutional neural network (CNN) based object detectors are promising tools for efficient object detection and counting. However, a significant limitation of such deep learning-based approaches is that they typically require a massive amount of hand-labeled images for training, which is still a tedious process. Here, we propose an active learning inspired weakly supervised deep learning framework for sorghum head detection and counting from UAV-based images. We demonstrate that it is possible to significantly reduce human labeling effort without compromising final model performance (R ² between human count and machine count is 0.88) by using a semitrained CNN model (i.e., trained with limited labeled data) to perform synthetic annotation. In addition, we also visualize key features that the network learns. This improves trustworthiness by enabling users to better understand and trust the decisions that the trained deep learning model makes.

Comparison of Different Classifiers with Active Learning to Support Quality Control in Nucleus Segmentation in Pathology Images

Segmentation of nuclei in whole slide tissue images is a common methodology in pathology image analysis. Most segmentation algorithms are sensitive to input algorithm parameters and the characteristics of input images (tissue morphology, staining, etc.). Because there can be large variability in the color, texture, and morphology of tissues within and across cancer types (heterogeneity can exist even within a tissue specimen), it is likely that a set of input parameters will not perform well across multiple images. It is, therefore, highly desired, and necessary in some cases, to carry out a quality control of segmentation results. This work investigates the application of machine learning in this process. We report on the application of active learning for segmentation quality assessment for pathology images and compare three classification methods, Support Vector Machine (SVM), Random Forest (RF) and Convolutional Neural Network (CNN), for their performance improvement and efficiency.

Stemness and anti-cancer drug resistance in ATP-binding cassette subfamily G member 2 highly expressed pancreatic cancer is induced in 3D culture conditions

The expression of ATP-binding cassette subfamily G member 2 (ABCG2) is related to tumorigenic cancer stem cells (CSC) in several cancers. However, the effects of ABCG2 on CSC-related malignant characteristics in pancreatic ductal adenocarcinoma (PDAC) are not well elucidated. In this study, we compared the characteristics of low (ABCG2-) and high (ABCG2+)-ABCG2-expressing PDAC cells after cell sorting. In adherent culture condition, human PDAC cells, PANC-1, contained approximately 10% ABCG2+ cell populations, and ABCG2+ cells displayed more and longer microvilli compared with ABCG2- cells. Unexpectedly, ABCG2+ cells did not show significant drug resistance against fluorouracil, gemcitabine and vincristine, and ABCG2- cells exhibited higher sphere formation ability and stemness marker expression than those of ABCG2+ cells. Cell growth and motility was greater in ABCG2- cells compared with ABCG2+ cells. In contrast, epithelial-mesenchymal transition ability between ABCG2- and ABCG2+ cells was comparable. In 3D culture conditions, spheres derived from ABCG2- cells generated a large number of ABCG2+ cells, and the expression levels of stemness markers in these spheres were higher than spheres from ABCG2+ cells. Furthermore, spheres containing large populations of ABCG2+ cells exhibited high resistance against anti-cancer drugs presumably depending on ABCG2. ABCG2+ cells in PDAC in adherent culture are not correlated with stemness and malignant behaviors, but ABCG2+ cells derived from ABCG2- cells after sphere formation have stemness characteristics and anti-cancer drug resistance. These findings suggest that ABCG2- cells generate ABCG2+ cells and the malignant potential of ABCG2+ cells in PDAC varies depending on their environments.

Towards enhanced and interpretable clustering/classification in integrative genomics

High-throughput technologies have led to large collections of different types of biological data that provide unprecedented opportunities to unravel molecular heterogeneity of biological processes. Nevertheless, how to jointly explore data from multiple sources into a holistic, biologically meaningful interpretation remains challenging. In this work, we propose a scalable and tuning-free preprocessing framework, Heterogeneity Rescaling Pursuit (Hetero-RP), which weighs important features more highly than less important ones in accord with implicitly existing auxiliary knowledge. Finally, we demonstrate effectiveness of Hetero-RP in diverse clustering and classification applications. More importantly, Hetero-RP offers an interpretation of feature importance, shedding light on the driving forces of the underlying biology. In metagenomic contig binning, Hetero-RP automatically weighs abundance and composition profiles according to the varying number of samples, resulting in markedly improved performance of contig binning. In RNA-binding protein (RBP) binding site prediction, Hetero-RP not only improves the prediction performance measured by the area under the receiver operating characteristic curves (AUC), but also uncovers the evidence supported by independent studies, including the distribution of the binding sites of IGF2BP and PUM2, the binding competition between hnRNPC and U2AF2, and the intron–exon boundary of U2AF2 [availability: https://github.com/younglululu/Hetero-RP].

Interactive phenotyping of large-scale histology imaging data with HistomicsML

Whole-slide imaging of histologic sections captures tissue microenvironments and cytologic details in expansive high-resolution images. These images can be mined to extract quantitative features that describe tissues, yielding measurements for hundreds of millions of histologic objects. A central challenge in utilizing this data is enabling investigators to train and evaluate classification rules for identifying objects related to processes like angiogenesis or immune response. In this paper we describe HistomicsML, an interactive machine-learning system for digital pathology imaging datasets. This framework uses active learning to direct user feedback, making classifier training efficient and scalable in datasets containing 10⁸+ histologic objects. We demonstrate how this system can be used to phenotype microvascular structures in gliomas to predict survival, and to explore the molecular pathways associated with these phenotypes. Our approach enables researchers to unlock phenotypic information from digital pathology datasets to investigate prognostic image biomarkers and genotype-phenotype associations.

Improving labeling efficiency in automatic quality control of MRSI data

PURPOSE

To improve the efficiency of the labeling task in automatic quality control of MR spectroscopy imaging data.

METHODS

28'432 short and long echo time (TE) spectra (1.5 tesla; point resolved spectroscopy (PRESS); repetition time (TR)= 1,500 ms) from 18 different brain tumor patients were labeled by two experts as either accept or reject, depending on their quality. For each spectrum, 47 signal features were extracted. The data was then used to run several simulations and test an active learning approach using uncertainty sampling. The performance of the classifiers was evaluated as a function of the number of patients in the training set, number of spectra in the training set, and a parameter α used to control the level of classification uncertainty required for a new spectrum to be selected for labeling.

RESULTS

The results showed that the proposed strategy allows reductions of up to 72.97% for short TE and 62.09% for long TE in the amount of data that needs to be labeled, without significant impact in classification accuracy. Further reductions are possible with significant but minimal impact in performance.

CONCLUSION

Active learning using uncertainty sampling is an effective way to increase the labeling efficiency for training automatic quality control classifiers. Magn Reson Med 78:2399-2405, 2017. © 2017 International Society for Magnetic Resonance in Medicine.

Microfluidics for High-Throughput Quantitative Studies of Early Development

Developmental biology has traditionally relied on qualitative analyses; recently, however, as in other fields of biology, researchers have become increasingly interested in acquiring quantitative knowledge about embryogenesis. Advances in fluorescence microscopy are enabling high-content imaging in live specimens. At the same time, microfluidics and automation technologies are increasing experimental throughput for studies of multicellular models of development. Furthermore, computer vision methods for processing and analyzing bioimage data are now leading the way toward quantitative biology. Here, we review advances in the areas of fluorescence microscopy, microfluidics, and data analysis that are instrumental to performing high-content, high-throughput studies in biology and specifically in development. We discuss a case study of how these techniques have allowed quantitative analysis and modeling of pattern formation in the Drosophila embryo.

Bioimage Informatics for Big Data

Bioimage informatics is a field wherein high-throughput image informatics methods are used to solve challenging scientific problems related to biology and medicine. When the image datasets become larger and more complicated, many conventional image analysis approaches are no longer applicable. Here, we discuss two critical challenges of large-scale bioimage informatics applications, namely, data accessibility and adaptive data analysis. We highlight case studies to show that these challenges can be tackled based on distributed image computing as well as machine learning of image examples in a multidimensional environment.

An Interactive Learning Framework for Scalable Classification of Pathology Images

Recent advances in microscopy imaging and genomics have created an explosion of patient data in the pathology domain. Whole-slide images (WSIs) of tissues can now capture disease processes as they unfold in high resolution, recording the visual cues that have been the basis of pathologic diagnosis for over a century. Each WSI contains billions of pixels and up to a million or more microanatomic objects whose appearances hold important prognostic information. Computational image analysis enables the mining of massive WSI datasets to extract quantitative morphologic features describing the visual qualities of patient tissues. When combined with genomic and clinical variables, this quantitative information provides scientists and clinicians with insights into disease biology and patient outcomes. To facilitate interaction with this rich resource, we have developed a web-based machine-learning framework that enables users to rapidly build classifiers using an intuitive active learning process that minimizes data labeling effort. In this paper we describe the architecture and design of this system, and demonstrate its effectiveness through quantification of glioma brain tumors.

Trajectories of cell-cycle progression from fixed cell populations

An accurate dissection of sources of cell-to-cell variability is crucial for quantitative biology at the single-cell level but has been challenging for the cell cycle. We present Cycler, a robust method that constructs a continuous trajectory of cell-cycle progression from images of fixed cells. Cycler handles heterogeneous microenvironments and does not require perturbations or genetic markers, making it generally applicable to quantifying multiple sources of cell-to-cell variability in mammalian cells.

Semi-automatic organelle detection on transmission electron microscopic images

Recent advances in the acquisition of large-scale datasets of transmission electron microscope images have allowed researchers to determine the number and the distribution of subcellular ultrastructures at both the cellular level and the tissue level. For this purpose, it would be very useful to have a computer-assisted system to detect the structures of interest, such as organelles. Using our original image recognition framework CARTA (Clustering-Aided Rapid Training Agent), combined with procedures to highlight and enlarge regions of interest on the image, we have developed a successful method for the semi-automatic detection of plant organelles including mitochondria, amyloplasts, chloroplasts, etioplasts, and Golgi stacks in transmission electron microscope images. Our proposed semi-automatic detection system will be helpful for labelling organelles in the interpretation and/or quantitative analysis of large-scale electron microscope imaging data.

BIOCAT: a pattern recognition platform for customizable biological image classification and annotation

Background

Pattern recognition algorithms are useful in bioimage informatics applications such as quantifying cellular and subcellular objects, annotating gene expressions, and classifying phenotypes. To provide effective and efficient image classification and annotation for the ever-increasing microscopic images, it is desirable to have tools that can combine and compare various algorithms, and build customizable solution for different biological problems. However, current tools often offer a limited solution in generating user-friendly and extensible tools for annotating higher dimensional images that correspond to multiple complicated categories.

Results

We develop the BIOimage Classification and Annotation Tool (BIOCAT). It is able to apply pattern recognition algorithms to two- and three-dimensional biological image sets as well as regions of interest (ROIs) in individual images for automatic classification and annotation. We also propose a 3D anisotropic wavelet feature extractor for extracting textural features from 3D images with xy-z resolution disparity. The extractor is one of the about 20 built-in algorithms of feature extractors, selectors and classifiers in BIOCAT. The algorithms are modularized so that they can be “chained” in a customizable way to form adaptive solution for various problems, and the plugin-based extensibility gives the tool an open architecture to incorporate future algorithms. We have applied BIOCAT to classification and annotation of images and ROIs of different properties with applications in cell biology and neuroscience.

Conclusions

BIOCAT provides a user-friendly, portable platform for pattern recognition based biological image classification of two- and three- dimensional images and ROIs. We show, via diverse case studies, that different algorithms and their combinations have different suitability for various problems. The customizability of BIOCAT is thus expected to be useful for providing effective and efficient solutions for a variety of biological problems involving image classification and annotation. We also demonstrate the effectiveness of 3D anisotropic wavelet in classifying both 3D image sets and ROIs.

LIPS database with LIPService: a microscopic image database of intracellular structures in Arabidopsis guard cells

BACKGROUND

Intracellular configuration is an important feature of cell status. Recent advances in microscopic imaging techniques allow us to easily obtain a large number of microscopic images of intracellular structures. In this circumstance, automated microscopic image recognition techniques are of extreme importance to future phenomics/visible screening approaches. However, there was no benchmark microscopic image dataset for intracellular organelles in a specified plant cell type. We previously established the Live Images of Plant Stomata (LIPS) database, a publicly available collection of optical-section images of various intracellular structures of plant guard cells, as a model system of environmental signal perception and transduction. Here we report recent updates to the LIPS database and the establishment of a database table, LIPService.

DESCRIPTION

We updated the LIPS dataset and established a new interface named LIPService to promote efficient inspection of intracellular structure configurations. Cell nuclei, microtubules, actin microfilaments, mitochondria, chloroplasts, endoplasmic reticulum, peroxisomes, endosomes, Golgi bodies, and vacuoles can be filtered using probe names or morphometric parameters such as stomatal aperture. In addition to the serial optical sectional images of the original LIPS database, new volume-rendering data for easy web browsing of three-dimensional intracellular structures have been released to allow easy inspection of their configurations or relationships with cell status/morphology. We also demonstrated the utility of the new LIPS image database for automated organelle recognition of images from another plant cell image database with image clustering analyses.

CONCLUSIONS

The updated LIPS database provides a benchmark image dataset for representative intracellular structures in Arabidopsis guard cells. The newly released LIPService allows users to inspect the relationship between organellar three-dimensional configurations and morphometrical parameters.

New insights into the dynamics of plant cell nuclei and chromosomes

The plant lamin-like protein NMCP/AtLINC and orthologues of the SUN-KASH complex across the nuclear envelope (NE) show the universality of nuclear structure in eukaryotes. However, depletion of components in the connection complex of the NE in plants does not induce severe defects, unlike in animals. Appearance of the Rabl configuration is not dependent on genome size in plant species. Topoisomerase II and condensin II are not essential for plant chromosome condensation. Plant endoreduplication shares several common characteristics with animals, including involvement of cyclin-dependent kinases and E2F transcription factors. Recent finding regarding endomitosis regulator GIG1 shed light on the suppression mechanism of endomitosis in plants. The robustness of plants, compared with animals, is reflected in their genome redundancy. Spatiotemporal functional analyses using chromophore-assisted light inactivation, super-resolution microscopy, and 4D (3D plus time) imaging will reveal new insights into plant nuclear and chromosomal dynamics.