Fiji is a distribution of the popular open-source software ImageJ focused on biological-image analysis. Fiji uses modern software engineering practices to combine powerful software libraries with a broad range of scripting languages to enable rapid prototyping of image-processing algorithms. Fiji facilitates the transformation of new algorithms into ImageJ plugins that can be shared with end users through an integrated update system. We propose Fiji as a platform for productive collaboration between computer science and biology research communities.

/pdf/fiji-an-open-source-platform-for-biological-image-analysis-1v529iu3cx.pdf

Fiji: an open-source platform for biological-image analysis

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Feature selection is an important problem for pattern classification systems. We study how to select good features according to the maximal statistical dependency criterion based on mutual information. Because of the difficulty in directly implementing the maximal dependency condition, we first derive an equivalent form, called minimal-redundancy-maximal-relevance criterion (mRMR), for first-order incremental feature selection. Then, we present a two-stage feature selection algorithm by combining mRMR and other more sophisticated feature selectors (e.g., wrappers). This allows us to select a compact set of superior features at very low cost. We perform extensive experimental comparison of our algorithm and other methods using three different classifiers (naive Bayes, support vector machine, and linear discriminate analysis) and four different data sets (handwritten digits, arrhythmia, NCI cancer cell lines, and lymphoma tissues). The results confirm that mRMR leads to promising improvement on feature selection and classification accuracy.

Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy

Feature selection based on mutual information: criteria ofmax-dependency, max-relevance, and min-redundancy

The automatic analysis of the 3D optical microscopic images containing neuron cells remains one of the central challenges in the modern computational neuroscience. The varying image qualities make the accurate detection of the curvilinear neuronal arbours elusive. The high computational cost raised by large 3D image volumes also makes the conventional filter-bank learning methods impractical. We present a novel Triple-Crossing (TC) 2.5D convolutional neural network to detect the neuronal arbours in large 3D microscopic volumes with a reasonable computational cost. The network is trained to output a regression map that indicates the presence of the neuronal arbours. The proposed methods can be used as a pre-processing step in an automated neuronal circuit reconstruction pipeline, which enables the collection of large-scale neuron morphological datasets. In our experiments, we show that the proposed methods could effectively eliminate dense background noises and fix the gaps along neuronal arbours. The proposed methods could also outperform the original 2.5D neural network regarding the training efficiency as well as the generalisation performance.

Triple-Crossing 2.5D Convolutional Neural Network for Detecting Neuronal Arbours in 3D Microscopic Images

The registration, segmentation, and annotation of microscopy images and respective biological objects (e.g., cells) are distinct challenges often encountered in bioimage informatics. Here we present several studies in widely used model systems of the fruit fly, zebrafish, and C. elegans to demonstrate how registration methods have been employed to align three-dimensional (3-D) brain images at a very large scale and to solve challenging segmentation and annotation problems for 3-D cellular images. Specifically, we consider two types of registration between images and models: image-to-image registration and model-to-image registration, where a model consists of a description of the geometrical shape or the spatial layout of biological objects in the respective images.

3-D Registration of Biological Images and Models: Registration of microscopic images and its uses in segmentation and annotation

The development of high-resolution microscopy makes possible the high-throughput screening of cellular information, such as gene expression at single cell resolution. One of the critical enabling techniques yet to be developed is the automatic recognition or annotation of specific cells in a 3D image stack. In this paper, we present a novel graph-based algorithm, ARC, that determines cell identities in a 3D confocal image of C. elegans based on their highly stereotyped arrangement. This is an essential step in our work on gene expression analysis of C. elegans at the resolution of single cells. Our ARC method integrates both the absolute and relative spatial locations of cells in a C. elegans body. It uses a marker-guided, spatially-constrained, two-stage bipartite matching to find the optimal match between cells in a subject image and cells in 15 template images that have been manually annotated and vetted. We applied ARC to the recognition of cells in 3D confocal images of the first larval stage (L1) of C. elegans hermaphrodites, and achieved an average accuracy of 94.91%.

/pdf/automatic-recognition-of-cells-arc-for-3d-images-of-c-4ltj7sdcwk.pdf

Automatic recognition of cells (ARC) for 3D images of C. elegans

Automatic 3D neuron reconstruction for very large 3D light microscopy images remains to be a challenge in neuroscience. Few existing neuron tracing algorithms can be used with commonly available computers (laptops, desktops, or workstations) to efficiently and accurately reconstruct a neuron in image stacks that are tens of gigabytes or greater. We introduce a new automatic tracing algorithm called Neuron Crawler, which works by first tracing a region of interest (e.g., around the soma), and then iteratively tracing in adjacent image tiles to grow the neuron structure in 3D to its termination point within the image. Our experimental results show that Neuron Crawler can achieve reconstruction accuracy that is comparable to several state-of-the-art algorithms, but with much less computational cost.

/pdf/neuron-crawler-an-automatic-tracing-algorithm-for-very-large-4n0erfy1cv.pdf

Neuron crawler: An automatic tracing algorithm for very large neuron images

A new energy function is proposed for forming self-adapting ordered representations of input samples in a multilayer perceptron. Simulation results on unconstrained handwritten digit recognition give a better invariance extraction for this model than for several other models.

Hanchuan Peng

Papers

Triple-Crossing 2.5D Convolutional Neural Network for Detecting Neuronal Arbours in 3D Microscopic Images

3-D Registration of Biological Images and Models: Registration of microscopic images and its uses in segmentation and annotation

Automatic recognition of cells (ARC) for 3D images of C. elegans

Neuron crawler: An automatic tracing algorithm for very large neuron images

Energy function for learning invariance in multilayer perceptron