Understanding metric-related pitfalls in image analysis validation.

Validation metrics are key for tracking scientific progress and bridging the current chasm between artificial intelligence research and its translation into practice. However, increasing evidence shows that, particularly in image analysis, metrics are often chosen inadequately. Although taking into account the individual strengths, weaknesses and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multistage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides a reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. Although focused on biomedical image analysis, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. The work serves to enhance global comprehension of a key topic in image analysis validation.

Metrics reloaded: recommendations for image analysis validation.

Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. In biomedical image analysis, chosen performance metrics often do not reflect the domain interest, and thus fail to adequately measure scientific progress and hinder translation of ML techniques into practice. To overcome this, we created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. Developed by a large international consortium in a multistage Delphi process, it is based on the novel concept of a problem fingerprint-a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), dataset and algorithm output. On the basis of the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as classification tasks at image, object or pixel level, namely image-level classification, object detection, semantic segmentation and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. Its applicability is demonstrated for various biomedical use cases.

Automated detection and quantification of single RNAs at cellular resolution in zebrafish embryos.

Analysis of differential gene expression is crucial for the study of cell fate and behavior during embryonic development. However, automated methods for the sensitive detection and quantification of RNAs at cellular resolution in embryos are lacking. With the advent of single-molecule fluorescence in situ hybridization (smFISH), gene expression can be analyzed at single-molecule resolution. However, the limited availability of protocols for smFISH in embryos and the lack of efficient image analysis pipelines have hampered quantification at the (sub)cellular level in complex samples such as tissues and embryos. Here, we present a protocol for smFISH on zebrafish embryo sections in combination with an image analysis pipeline for automated transcript detection and cell segmentation. We use this strategy to quantify gene expression differences between different cell types and identify differences in subcellular transcript localization between genes. The combination of our smFISH protocol and custom-made, freely available, analysis pipeline will enable researchers to fully exploit the benefits of quantitative transcript analysis at cellular and subcellular resolution in tissues and embryos.

Automated classification of cellular expression in multiplexed imaging data with Nimbus.

Multiplexed imaging offers a powerful approach to characterize the spatial topography of tissues in both health and disease. To analyze such data, the specific combination of markers that are present in each cell must be enumerated to enable accurate phenotyping, a process that often relies on unsupervised clustering. We constructed the Pan-Multiplex (Pan-M) dataset containing 197 million distinct annotations of marker expression across 15 different cell types. We used Pan-M to create Nimbus, a deep learning model to predict marker positivity from multiplexed image data. Nimbus is a pre-trained model that uses the underlying images to classify marker expression across distinct cell types, from different tissues, acquired using different microscope platforms, without requiring any retraining. We demonstrate that Nimbus predictions capture the underlying staining patterns of the full diversity of markers present in Pan-M. We then show how Nimbus predictions can be integrated with downstream clustering algorithms to robustly identify cell subtypes in image data. We have open-sourced Nimbus and Pan-M to enable community use at https://github.com/angelolab/Nimbus-Inference.

Understanding metric-related pitfalls in image analysis validation.

Validation metrics are key for the reliable tracking of scientific progress and for bridging the current chasm between artificial intelligence (AI) research and its translation into practice. However, increasing evidence shows that particularly in image analysis, metrics are often chosen inadequately in relation to the underlying research problem. This could be attributed to a lack of accessibility of metric-related knowledge: While taking into account the individual strengths, weaknesses, and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multi-stage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides the first reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. Focusing on biomedical image analysis but with the potential of transfer to other fields, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. To facilitate comprehension, illustrations and specific examples accompany each pitfall. As a structured body of information accessible to researchers of all levels of expertise, this work enhances global comprehension of a key topic in image analysis validation.

Automated reconstruction of whole-embryo cell lineages by learning from sparse annotations.

We present a method to automatically identify and track nuclei in time-lapse microscopy recordings of entire developing embryos. The method combines deep learning and global optimization. On a mouse dataset, it reconstructs 75.8% of cell lineages spanning 1 h, as compared to 31.8% for the competing method. Our approach improves understanding of where and when cell fate decisions are made in developing embryos, tissues, and organs.

A searchable image resource of Drosophila GAL4 driver expression patterns with single neuron resolution.

Precise, repeatable genetic access to specific neurons via GAL4/UAS and related methods is a key advantage of Drosophila neuroscience. Neuronal targeting is typically documented using light microscopy of full GAL4 expression patterns, which generally lack the single-cell resolution required for reliable cell type identification. Here, we use stochastic GAL4 labeling with the MultiColor FlpOut approach to generate cellular resolution confocal images at large scale. We are releasing aligned images of 74,000 such adult central nervous systems. An anticipated use of this resource is to bridge the gap between neurons identified by electron or light microscopy. Identifying individual neurons that make up each GAL4 expression pattern improves the prediction of split-GAL4 combinations targeting particular neurons. To this end, we have made the images searchable on the NeuronBridge website. We demonstrate the potential of NeuronBridge to rapidly and effectively identify neuron matches based on morphology across imaging modalities and datasets.

A connectome and analysis of the adult Drosophila central brain.

The neural circuits responsible for animal behavior remain largely unknown. We summarize new methods and present the circuitry of a large fraction of the brain of the fruit fly Drosophila melanogaster. Improved methods include new procedures to prepare, image, align, segment, find synapses in, and proofread such large data sets. We define cell types, refine computational compartments, and provide an exhaustive atlas of cell examples and types, many of them novel. We provide detailed circuits consisting of neurons and their chemical synapses for most of the central brain. We make the data public and simplify access, reducing the effort needed to answer circuit questions, and provide procedures linking the neurons defined by our analysis with genetic reagents. Biologically, we examine distributions of connection strengths, neural motifs on different scales, electrical consequences of compartmentalization, and evidence that maximizing packing density is an important criterion in the evolution of the fly's brain.

Animal brains of all sizes, from the smallest to the largest, work in broadly similar ways. Studying the brain of any one animal in depth can thus reveal the general principles behind the workings of all brains. The fruit fly Drosophila is a popular choice for such research. With about 100,000 neurons ­ compared to some 86 billion in humans ­ the fly brain is small enough to study at the level of individual cells. But it nevertheless supports a range of complex behaviors, including navigation, courtship and learning. Thanks to decades of research, scientists now have a good understanding of which parts of the fruit fly brain support particular behaviors. But exactly how they do this is often unclear. This is because previous studies showing the connections between cells only covered small areas of the brain. This is like trying to understand a novel when all you can see is a few isolated paragraphs. To solve this problem, Scheffer, Xu, Januszewski, Lu, Takemura, Hayworth, Huang, Shinomiya et al. prepared the first complete map of the entire central region of the fruit fly brain. The central brain consists of approximately 25,000 neurons and around 20 million connections. To prepare the map ­ or connectome ­ the brain was cut into very thin 8nm slices and photographed with an electron microscope. A three-dimensional map of the neurons and connections in the brain was then reconstructed from these images using machine learning algorithms. Finally, Scheffer et al. used the new connectome to obtain further insights into the circuits that support specific fruit fly behaviors. The central brain connectome is freely available online for anyone to access. When used in combination with existing methods, the map will make it easier to understand how the fly brain works, and how and why it can fail to work correctly. Many of these findings will likely apply to larger brains, including our own. In the long run, studying the fly connectome may therefore lead to a better understanding of the human brain and its disorders. Performing a similar analysis on the brain of a small mammal, by scaling up the methods here, will be a likely next step along this path.

The cell adhesion protein CAR is a negative regulator of synaptic transmission.

The Coxsackievirus and adenovirus receptor (CAR) is essential for normal electrical conductance in the heart, but its role in the postnatal brain is largely unknown. Using brain specific CAR knockout mice (KO), we discovered an unexpected role of CAR in neuronal communication. This includes increased basic synaptic transmission at hippocampal Schaffer collaterals, resistance to fatigue, and enhanced long-term potentiation. Spontaneous neurotransmitter release and speed of endocytosis are increased in KOs, accompanied by increased expression of the exocytosis associated calcium sensor synaptotagmin 2. Using proximity proteomics and binding studies, we link CAR to the exocytosis machinery as it associates with syntenin and synaptobrevin/VAMP2 at the synapse. Increased synaptic function does not cause adverse effects in KO mice, as behavior and learning are unaffected. Thus, unlike the connexin-dependent suppression of atrioventricular conduction in the cardiac knockout, communication in the CAR deficient brain is improved, suggesting a role for CAR in presynaptic processes.

Active graph matching for automatic joint segmentation and annotation of C. elegans.

In this work we present a novel technique we term active graph matching, which integrates the popular active shape model into a sparse graph matching problem. This way we are able to combine the benefits of a global, statistical deformation model with the benefits of a local deformation model in form of a second-order random field. We present a new iterative energy minimization technique which achieves empirically good results. This enables us to exceed state-of-the art results for the task of annotating nuclei in 3D microscopic images of C. elegans. Furthermore with the help of the generalized Hough transform we are able to jointly segment and annotate a large set of nuclei in a fully automatic fashion for the first time.

Omnidirectional displacements for deformable surfaces.

Deformable surface models are often represented as triangular meshes in image segmentation applications. For a fast and easily regularized deformation onto the target object boundary, the vertices of the mesh are commonly moved along line segments (typically surface normals). However, in case of high mesh curvature, these lines may not intersect with the target boundary at all. Consequently, certain deformations cannot be achieved. We propose omnidirectional displacements for deformable surfaces (ODDS) to overcome this limitation. ODDS allow each vertex to move not only along a line segment but within the volumetric inside of a surrounding sphere, and achieve globally optimal deformations subject to local regularization constraints. However, allowing a ball-shaped instead of a linear range of motion per vertex significantly increases runtime and memory. To alleviate this drawback, we propose a hybrid approach, fastODDS, with improved runtime and reduced memory requirements. Furthermore, fastODDS can also cope with simultaneous segmentation of multiple objects. We show the theoretical benefits of ODDS with experiments on synthetic data, and evaluate ODDS and fastODDS quantitatively on clinical image data of the mandible and the hip bones. There, we assess both the global segmentation accuracy as well as local accuracy in high curvature regions, such as the tip-shaped mandibular coronoid processes and the ridge-shaped acetabular rims of the hip bones.

Automatic detection and classification of teeth in CT data.

We propose a fully automatic method for tooth detection and classification in CT or cone-beam CT image data. First we compute an accurate segmentation of the maxilla bone. Based on this segmentation, our method computes a complete and optimal separation of the row of teeth into 16 subregions and classifies the resulting regions as existing or missing teeth. This serves as a prerequisite for further individual tooth segmentation. We show the robustness of our approach by providing extensive validation on 43 clinical head CT scans.

An articulated statistical shape model for accurate hip joint segmentation.

In this paper we propose a framework for fully automatic, robust and accurate segmentation of the human pelvis and proximal femur in CT data. We propose a composite statistical shape model of femur and pelvis with a flexible hip joint, for which we extend the common definition of statistical shape models as well as the common strategy for their adaptation. We do not analyze the joint flexibility statistically, but model it explicitly by rotational parameters describing the bent in a ball-and-socket joint. A leave-one-out evaluation on 50 CT volumes shows that image driven adaptation of our composite shape model robustly produces accurate segmentations of both proximal femur and pelvis. As a second contribution, we evaluate a fine grain multi-object segmentation method based on graph optimization. It relies on accurate initializations of femur and pelvis, which our composite shape model can generate. Simultaneous optimization of both femur and pelvis yields more accurate results than separate optimizations of each structure. Shape model adaptation and graph based optimization are embedded in a fully automatic framework.

Automatic extraction of mandibular nerve and bone from cone-beam CT data.

The exact localization of the mandibular nerve with respect to the bone is important for applications in dental implantology and maxillofacial surgery. Cone beam computed tomography (CBCT), often also called digital volume tomography (DVT), is increasingly utilized in maxillofacial or dental imaging. Compared to conventional CT, however, soft tissue discrimination is worse due to a reduced dose. Thus, small structures like the alveolar nerves are even harder recognizable within the image data. We show that it is nonetheless possible to accurately reconstruct the 3D bone surface and the course of the nerve in a fully automatic fashion, with a method that is based on a combined statistical shape model of the nerve and the bone and a Dijkstra-based optimization procedure. Our method has been validated on 106 clinical datasets: the average reconstruction error for the bone is 0.5 +/- 0.1 mm, and the nerve can be detected with an average error of 1.0 +/- 0.6 mm.