High-Resolution Inflorescence Phenotyping Using a Novel Image-Analysis Pipeline, PANorama.

Variation in inflorescence development is an important target of selection for numerous crop species, including many members of the Poaceae (grasses). In Asian rice (Oryza sativa), inflorescence (panicle) architecture is correlated with yield and grain-quality traits. However, many rice breeders continue to use composite phenotypes in selection pipelines, because measuring complex, branched panicles requires a significant investment of resources. We developed an open-source phenotyping platform, PANorama, which measures multiple architectural and branching phenotypes from images simultaneously. PANorama automatically extracts skeletons from images, allows users to subdivide axes into individual internodes, and thresholds away structures, such as awns, that normally interfere with accurate panicle phenotyping. PANorama represents an improvement in both efficiency and accuracy over existing panicle imaging platforms, and flexible implementation makes PANorama capable of measuring a range of organs from other plant species. Using high-resolution phenotypes, a mapping population of recombinant inbred lines, and a dense single-nucleotide polymorphism data set, we identify, to our knowledge, the largest number of quantitative trait loci (QTLs) for panicle traits ever reported in a single study. Several areas of the genome show pleiotropic clusters of panicle QTLs, including a region near the rice Green Revolution gene SEMIDWARF1. We also confirm that multiple panicle phenotypes are distinctly different among a small collection of diverse rice varieties. Taken together, these results suggest that clusters of small-effect QTLs may be responsible for varietal or subpopulation-specific panicle traits, representing a significant opportunity for rice breeders selecting for yield performance across different genetic backgrounds.

Ultrack: pushing the limits of cell tracking across biological scales.

Tracking live cells across 2D, 3D, and multi-channel time-lapse recordings is crucial for understanding tissue-scale biological processes. Despite advancements in imaging technology, achieving accurate cell tracking remains challenging, particularly in complex and crowded tissues where cell segmentation is often ambiguous. We present Ultrack, a versatile and scalable cell-tracking method that tackles this challenge by considering candidate segmentations derived from multiple algorithms and parameter sets. Ultrack employs temporal consistency to select optimal segments, ensuring robust performance even under segmentation uncertainty. We validate our method on diverse datasets, including terabyte-scale developmental time-lapses of zebrafish, fruit fly, and nematode embryos, as well as multi-color and label-free cellular imaging. We show that Ultrack achieves state-of-the-art performance on the Cell Tracking Challenge and demonstrates superior accuracy in tracking densely packed embryonic cells over extended periods. Moreover, we propose an approach to tracking validation via dual-channel sparse labeling that enables high-fidelity ground truth generation, pushing the boundaries of long-term cell tracking assessment. Our method is freely available as a Python package with Fiji and napari plugins and can be deployed in a high-performance computing environment, facilitating widespread adoption by the research community.

Effects of hypertonic solutions on two species of human intestinal parasites during fecal examination.

Aim: Ova and parasite examination by flotation requires hypertonic solutions, which can damage the egg and cyst membranes, leading to false negatives. The authors investigated the harmful effects of ZnSO4 and C12H22O11 solutions on the ova and parasite examination. Materials & methods: The authors processed samples using the Three Fecal Test technique. Aliquots were floated in different pH levels, temperatures and solution densities. Results: Densities above 1.12 g/ml led structures to collapse after 6-10 min. pH neutralization of the ZnSO4 solution did not prevent the parasites from changing. Conclusion: All structures were altered when standard methods were performed. To delay collapse, the parasite floating under 5 °C is highly desirable.

Fecal exams require solutions that can damage the intestinal parasite's shape. This is bad for diagnosis. The authors investigated the harmful effects of these solutions on fecal exams. The authors processed samples using a technique called the Three Fecal Test. Fecal samples were floated in different conditions, including neutral and acidic solutions, high and low temperatures and varying densities of chemical solutions. Densities above 1.12 g/ml altered the structures of parasites. Neutral solutions did not prevent the structures from changing. The structures of all parasites were altered when the usual techniques were performed. Thus, the techniques for diagnosing intestinal parasites in feces must be improved. Temperatures under 5 °C are the best for preventing the destruction of parasite membranes.

CNN Filter Learning from Drawn Markers for the Detection of Suggestive Signs of COVID-19 in CT Images.

Early detection of COVID-19 is vital to control its spread. Deep learning methods have been presented to detect suggestive signs of COVID-19 from chest CT images. However, due to the novelty of the disease, annotated volumetric data are scarce. Here we propose a method that does not require either large annotated datasets or backpropagation to estimate the filters of a convolutional neural network (CNN). For a few CT images, the user draws markers at representative normal and abnormal regions. The method generates a feature extractor composed of a sequence of convolutional layers, whose kernels are specialized in enhancing regions similar to the marked ones, and the decision layer of our CNN is a support vector machine. As we have no control over the CT image acquisition, we also propose an intensity standardization approach. Our method can achieve mean accuracy and kappa values of 0.97 and 0.93, respectively, on a dataset with 117 CT images extracted from different sites, surpassing its counterpart in all scenarios.

Investigating the impact of supervoxel segmentation for unsupervised abnormal brain asymmetry detection.

Several brain disorders are associated with abnormal brain asymmetries (asymmetric anomalies). Several computer-based methods aim to detect such anomalies automatically. Recent advances in this area use automatic unsupervised techniques that extract pairs of symmetric supervoxels in the hemispheres, model normal brain asymmetries for each pair from healthy subjects, and treat outliers as anomalies. Yet, there is no deep understanding of the impact of the supervoxel segmentation quality for abnormal asymmetry detection, especially for small anomalies, nor of the added value of using a specialized model for each supervoxel pair instead of a single global appearance model. We aim to answer these questions by a detailed evaluation of different scenarios for supervoxel segmentation and classification for detecting abnormal brain asymmetries. Experimental results on 3D MR-T1 brain images of stroke patients confirm the importance of high-quality supervoxels fit anomalies and the use of a specific classifier for each supervoxel. Next, we present a refinement of the detection method that reduces the number of false-positive supervoxels, thereby making the detection method easier to use for visual inspection and analysis of the found anomalies.

Segmentation-Based Blood Flow Parameter Refinement in Cerebrovascular Structures Using 4-D Arterial Spin Labeling MRA.

OBJECTIVE: Cerebrovascular diseases are one of the main global causes of death and disability in the adult population. The preferred imaging modality for the diagnostic routine is digital subtraction angiography, an invasive modality. Time-resolved three-dimensional arterial spin labeling magnetic resonance angiography (4D ASL MRA) is an alternative non-invasive modality, which captures morphological and blood flow data of the cerebrovascular system, with high spatial and temporal resolution. This work proposes advanced medical image processing methods that extract the anatomical and hemodynamic information contained in 4D ASL MRA datasets. METHODS: A previously published segmentation method, which uses blood flow data to improve its accuracy, is extended to estimate blood flow parameters by fitting a mathematical model to the measured vascular signal. The estimated values are then refined using regression techniques within the cerebrovascular segmentation. The proposed method was evaluated using fifteen 4D ASL MRA phantoms, with ground-truth morphological and hemodynamic data, fifteen 4D ASL MRA datasets acquired from healthy volunteers, and two 4D ASL MRA datasets from patients with a stenosis. RESULTS: The proposed method reached an average Dice similarity coefficient of 0.957 and 0.938 in the phantom and real dataset segmentation evaluations, respectively. The estimated blood flow parameter values are more similar to the ground-truth values after the refinement step, when using phantoms. A qualitative analysis showed that the refined blood flow estimation is more realistic compared to the raw hemodynamic parameters. CONCLUSION: The proposed method can provide accurate segmentations and blood flow parameter estimations in the cerebrovascular system using 4D ASL MRA datasets. SIGNIFICANCE: The information obtained with the proposed method can help clinicians and researchers to study the cerebrovascular system non-invasively.

An Approach for Asbestos-related Pleural Plaque Detection.

Asbestos is a toxic ore widely used in construction and commercial products. Asbestos tends to dissolve into fibers and after years inhaling them, these fibers calcify and form plaques on the pleura. Despite being benign, pleural plaques may indicate an immunologic deficiency or dysfunctional lung areas. We propose a pipeline for asbestos-related pleural plaque detection in CT images of the human thorax based on the following operations: lung segmentation, 3D patch selection along the pleura, a convolutional neural network (CNN) for feature extraction, and classification by support vector machines (SVM). Due to the scarcity of publicly available and annotated datasets of pleural plaques, the proposed CNN relies on architecture learning with random weights obtained by a PCA-based approach instead of using traditional filter learning by backpropagation. Experiments show that the proposed CNN can outperform its counterparts based on backpropagation for small training sets.

Extending Supervoxel-based Abnormal Brain Asymmetry Detection to the Native Image Space.

Most neurological diseases are associated with abnormal brain asymmetries. Recent advances in automatic unsupervised techniques model normal brain asymmetries from healthy subjects only and treat anomalies as outliers. Outlier detection is usually done in a common standard coordinate space that limits its usability. To alleviate the problem, we extend a recent fully unsupervised supervoxel-based approach (SAAD) for abnormal asymmetry detection in the native image space of MR brain images. Experimental results using our new method, called N-SAAD, show that it can achieve higher accuracy in detection with considerably less false positives than a method based on unsupervised deep learning for a large set of MR-T1 images.

A methodology for generating four-dimensional arterial spin labeling MR angiography virtual phantoms.

Four-dimensional arterial spin labeling magnetic resonance angiography (4D ASL MRA) is a non-invasive medical imaging modality that can be used for anatomical and hemodynamic analysis of the cerebrovascular system. However, it generates a considerable amount of data, which is tedious to analyze visually. As an alternative, medical image processing methods can be used to process the data and present measurements of the geometry and blood flow in the cerebrovascular system to the user, such as vessel radius, tortuosity, blood flow volume, and transit time. Nevertheless, evaluating medical image processing methods developed for this modality requires annotated data, which can be time-consuming and expensive to obtain. Alternatively, virtual simulations are a faster and less expensive option that can be used for initial evaluation of image processing methods. The present work proposes a methodology for generating annotated 4D ASL MRA virtual phantoms, in different scenarios with different acquisition parameter settings. In each scenario, the phantoms are generated using real cerebrovascular geometries of healthy volunteers, where blood flow is simulated according to a mathematical model specifically designed to describe the signal observed in 4D ASL MRA images. Realistic noise is added using an homomorphic approach, designed to replicate noise characteristic of multi-coil acquisitions. In order to exemplify the utility of the phantoms, they are used to evaluate the accuracy of a method to estimate blood flow parameter values, such as relative blood volume and transit time, in different scenarios. The estimated values are then compared to its corresponding virtual ground-truth values. The accuracy of the results is ranked according to the average absolute error. The results of the experiments show that blood flow parameters can be more accurately estimated when blood is magnetically labeled for longer periods of time and when the datasets are acquired with higher temporal resolution. In summary, the present work describes a methodology to create annotated virtual phantoms, which represent a useful alternative for initial evaluation of medical image processing methods for 4D ASL MRA images.

ALTIS: A fast and automatic lung and trachea CT-image segmentation method.

PURPOSE: The automated segmentation of each lung and trachea in CT scans is commonly taken as a solved problem. Indeed, existing approaches may easily fail in the presence of some abnormalities caused by a disease, trauma, or previous surgery. For robustness, we present ALTIS (implementation is available at http://lids.ic.unicamp.br/downloads) - a fast automatic lung and trachea CT-image segmentation method that relies on image features and relative shape- and intensity-based characteristics less affected by most appearance variations of abnormal lungs and trachea. METHODS: ALTIS consists of a sequence of image foresting transforms (IFTs) organized in three main steps: (a) lung-and-trachea extraction, (b) seed estimation inside background, trachea, left lung, and right lung, and (c) their delineation such that each object is defined by an optimum-path forest rooted at its internal seeds. We compare ALTIS with two methods based on shape models (SOSM-S and MALF), and one algorithm based on seeded region growing (PTK). RESULTS: The experiments involve the highest number of scans found in literature - 1255 scans, from multiple public data sets containing many anomalous cases, being only 50 normal scans used for training and 1205 scans used for testing the methods. Quantitative experiments are based on two metrics, DICE and ASSD. Furthermore, we also demonstrate the robustness of ALTIS in seed estimation. Considering the test set, the proposed method achieves an average DICE of 0.987 for both lungs and 0.898 for the trachea, whereas an average ASSD of 0.938 for the right lung, 0.856 for the left lung, and 1.316 for the trachea. These results indicate that ALTIS is statistically more accurate and considerably faster than the compared methods, being able to complete segmentation in a few seconds on modern PCs. CONCLUSION: ALTIS is the most effective and efficient choice among the compared methods to segment left lung, right lung, and trachea in anomalous CT scans for subsequent detection, segmentation, and quantitative analysis of abnormal structures in the lung parenchyma and pleural space.

An Iterative Spanning Forest Framework for Superpixel Segmentation.

Superpixel segmentation has emerged as an important research problem in the areas of image processing and computer vision. In this paper, we propose a framework, namely Iterative Spanning Forest (ISF), in which improved sets of connected superpixels (supervoxels in 3D) can be generated by a sequence of image foresting transforms. In this framework, one can choose the most suitable combination of ISF components for a given application-i.e., 1) a seed sampling strategy; 2) a connectivity function; 3) an adjacency relation; and 4) a seed pixel recomputation procedure. The superpixels in ISF structurally correspond to spanning trees rooted at those seeds. We present five ISF-based methods to illustrate different choices for those components. These methods are compared with a number of state-of-the-art approaches with respect to effectiveness and efficiency. Experiments are carried out on several datasets containing 2D and 3D objects with distinct texture and shape properties, including a high-level application, named sky image segmentation. The theoretical properties of ISF are demonstrated in the supplementary material and the results show ISF-based methods rank consistently among the best for all datasets.

Projections as visual aids for classification system design.

Dimensionality reduction is a compelling alternative for high-dimensional data visualization. This method provides insight into high-dimensional feature spaces by mapping relationships between observations (high-dimensional vectors) to low (two or three) dimensional spaces. These low-dimensional representations support tasks such as outlier and group detection based on direct visualization. Supervised learning, a subfield of machine learning, is also concerned with observations. A key task in supervised learning consists of assigning class labels to observations based on generalization from previous experience. Effective development of such classification systems depends on many choices, including features descriptors, learning algorithms, and hyperparameters. These choices are not trivial, and there is no simple recipe to improve classification systems that perform poorly. In this context, we first propose the use of visual representations based on dimensionality reduction (projections) for predictive feedback on classification efficacy. Second, we propose a projection-based visual analytics methodology, and supportive tooling, that can be used to improve classification systems through feature selection. We evaluate our proposal through experiments involving four datasets and three representative learning algorithms.

Automatic Temporal Segmentation of Vessels of the Brain Using 4D ASL MRA Images.

OBJECTIVE: Automatic vessel segmentation can be used to process the considerable amount of data generated by four-dimensional arterial spin labeling magnetic resonance angiography (4D ASL MRA) images. Previous segmentation approaches for dynamic series of images propose either reducing the series to a temporal average (tAIP) or maximum intensity projection (tMIP) prior to vessel segmentation, or a separate segmentation of each image. This paper introduces a method that combines both approaches to overcome the specific drawbacks of each technique. METHODS: Vessels in the tAIP are enhanced by using the ranking orientation responses of path operators and multiscale vesselness enhancement filters. Then, tAIP segmentation is performed using a seed-based algorithm. In parallel, this algorithm is also used to segment each frame of the series and identify small vessels, which might have been lost in the tAIP segmentation. The results of each individual time frame segmentation are fused using an or boolean operation. Finally, small vessels found only in the fused segmentation are added to the tAIP segmentation. RESULTS: In a quantitative analysis using ten 4D ASL MRA image series from healthy volunteers, the proposed combined approach reached an average Dice coefficient of 0.931, being more accurate than the corresponding tMIP, tAIP, and single time frame segmentation methods with statistical significance. CONCLUSION: The novel combined vessel segmentation strategy can be used to obtain improved vessel segmentation results from 4D ASL MRA and other dynamic series of images. SIGNIFICANCE: Improved vessel segmentation of 4D ASL MRA allows a fast and accurate assessment of cerebrovascular structures.

Visualizing the Hidden Activity of Artificial Neural Networks.

In machine learning, pattern classification assigns high-dimensional vectors (observations) to classes based on generalization from examples. Artificial neural networks currently achieve state-of-the-art results in this task. Although such networks are typically used as black-boxes, they are also widely believed to learn (high-dimensional) higher-level representations of the original observations. In this paper, we propose using dimensionality reduction for two tasks: visualizing the relationships between learned representations of observations, and visualizing the relationships between artificial neurons. Through experiments conducted in three traditional image classification benchmark datasets, we show how visualization can provide highly valuable feedback for network designers. For instance, our discoveries in one of these datasets (SVHN) include the presence of interpretable clusters of learned representations, and the partitioning of artificial neurons into groups with apparently related discriminative roles.

Medical image segmentation via atlases and fuzzy object models: Improving efficacy through optimum object search and fewer models.

PURPOSE: Statistical object shape models (SOSMs), known as probabilistic atlases, are popular in medical image segmentation. They register an image into the atlas coordinate system, such that a desired object can be delineated from the constraints of its shape model. While this strategy facilitates segmenting objects with even weak-boundary contrast, it tends to require more models per object to cope with possible registration errors. Fuzzy object shape models (FOSMs) gain substantial speed by avoiding image registration and placing more relaxed model constraints with optimum object search. However, they tend to require stronger object boundary contrast for effective delineation. In this work, the authors show that optimum object search, the essential underpinning of FOSMs, can improve segmentation efficacy of SOSMs with fewer models per object. METHODS: For the sake of efficiency, the authors use three atlases per object (SOSM-3) as baseline for segmentation based on the best match with posterior probability maps. A novel strategy for SOSM with a single atlas and optimum object search (SOSM-S) is presented. When registering an image to the atlas system, one should expect that the object's boundary falls within the uncertainty region of the model-region wherein voxels show probabilities greater than 0 and less than 1 to be in the object. Since registration may fail, SOSM-S translates the atlas locally and, at each location, delineates and scores a candidate object in the uncertainty region. Segmentation is defined by the candidate with the highest score. The presented FOSM also uses a single model per object, but model construction uses only shape translations, building a fuzzy object model with larger uncertainty region. Optimum object search requires estimation of the object's location and/or optimization algorithms to speed-up segmentation. RESULTS: The authors evaluate SOSM-3, SOSM-S, and FOSM on 75 CT-images of the thorax and 35 MR T1-weighted images of the brain, with nine objects of interest. The results show that SOSM-S and FOSM can segment seven out of the nine objects with higher accuracy than SOSM-3, according to the average symmetric surface distance and statistical test. SOSM-S was consistently more accurate than FOSM, FOSM being 2-3 orders of magnitude faster than SOSM-S and SOSM-3 for model construction and hundreds of times faster than them for segmentation. CONCLUSIONS: Although multiple models per object can usually improve segmentation efficacy, the optimum object search has shown to reduce the number of required models. The efficiency gain of FOSM over SOSM-S motivates its use for interactive applications and studies with large image data sets. FOSM and SOSM impose different degrees of shape constraints from the model, making one approach more suitable than the other, depending on contrast. This suggests the use of hybrid models that can take advantage from the strengths of fuzzy and statistical models.

Choosing the Most Effective Pattern Classification Model under Learning-Time Constraint.

Nowadays, large datasets are common and demand faster and more effective pattern analysis techniques. However, methodologies to compare classifiers usually do not take into account the learning-time constraints required by applications. This work presents a methodology to compare classifiers with respect to their ability to learn from classification errors on a large learning set, within a given time limit. Faster techniques may acquire more training samples, but only when they are more effective will they achieve higher performance on unseen testing sets. We demonstrate this result using several techniques, multiple datasets, and typical learning-time limits required by applications.

Interactive volume segmentation with differential image foresting transforms.

The absence of object information very often asks for considerable human assistance in medical image segmentation. Many interactive two-dimensional and three-dimensional (3-D) segmentation methods have been proposed, but their response time to user's actions should be considerably reduced to make them viable from the practical point of view. We circumvent this problem in the framework of the image foresting transform (IFT)--a general tool for the design of image operators based on connectivity--by introducing a new algorithm (DIFT) to compute sequences of IFTs in a differential way. We instantiate the DIFT algorithm for watershed-based and fuzzy-connected segmentations under two paradigms (single-object and multiple-object) and evaluate the efficiency gains of both approaches with respect to their linear-time implementation based on the nondifferential IFT. We show that the DIFT algorithm provides efficiency gains from 10 to 17, reducing the user's waiting time for segmentation with 3-D visualization on a common PC from 19-36 s to 2-3 s. We also show that the multiple-object approach is more efficient than the single-object paradigm for both segmentation methods.

Iso-shaping rigid bodies for estimating their motion from image sequences.

In many medical imaging applications, due to the limited field of view of imaging devices, acquired images often include only a part of a structure. In such situations, it is impossible to guarantee that the images will contain exactly the same physical extent of the structure at different scans, which leads to difficulties in registration and in many other tasks, such as the analysis of the morphology, architecture, and kinematics of the structures. To facilitate such analysis, we developed a general method, referred to as iso-shaping, that generates structures of the same shape from segmented image sequences. The basis for this method is to automatically find a set of key points, called shape centers, in the segmented partial anatomic structure such that these points are present in all images and that they represent the same physical location in the object, and then trim the structure using these points as reference. The application area considered here is the analysis of the morphology, architecture, and kinematics of the joints of the foot from magnetic resonance images acquired at different joint positions and load conditions. The accuracy of the method is analyzed by utilizing ten data sets for iso-shaping the tibia and the fibula via four evaluative experiments. The analysis indicates that iso-shaping produces results as predicted by the theoretical framework.

The image foresting transform: theory, algorithms, and applications.

The image foresting transform (IFT) is a graph-based approach to the design of image processing operators based on connectivity. It naturally leads to correct and efficient implementations and to a better understanding of how different operators relate to each other. We give here a precise definition of the IFT, and a procedure to compute it-a generalization of Dijkstra's algorithm-with a proof of correctness. We also discuss implementation issues and illustrate the use of the IFT in a few applications.

Differential and relaxed image foresting transform for graph-cut segmentation of multiple 3D objects.

Graph-cut algorithms have been extensively investigated for interactive binary segmentation, when the simultaneous delineation of multiple objects can save considerable user's time. We present an algorithm (named DRIFT) for 3D multiple object segmentation based on seed voxels and Differential Image Foresting Transforms (DIFTs) with relaxation. DRIFT stands behind efficient implementations of some state-of-the-art methods. The user can add/remove markers (seed voxels) along a sequence of executions of the DRIFT algorithm to improve segmentation. Its first execution takes linear time with the image's size, while the subsequent executions for corrections take sublinear time in practice. At each execution, DRIFT first runs the DIFT algorithm, then it applies diffusion filtering to smooth boundaries between objects (and background) and, finally, it corrects possible objects' disconnection occurrences with respect to their seeds. We evaluate DRIFT in 3D CT-images of the thorax for segmenting the arterial system, esophagus, left pleural cavity, right pleural cavity, trachea and bronchi, and the venous system.