Tox_(R)CNN: Deep learning-based nuclei profiling tool for drug toxicity screening.

Toxicity is an important factor in failed drug development, and its efficient identification and prediction is a major challenge in drug discovery. We have explored the potential of microscopy images of fluorescently labeled nuclei for the prediction of toxicity based on nucleus pattern recognition. Deep learning algorithms obtain abstract representations of images through an automated process, allowing them to efficiently classify complex patterns, and have become the state-of-the art in machine learning for computer vision. Here, deep convolutional neural networks (CNN) were trained to predict toxicity from images of DAPI-stained cells pre-treated with a set of drugs with differing toxicity mechanisms. Different cropping strategies were used for training CNN models, the nuclei-cropping-based Tox_CNN model outperformed other models classifying cells according to health status. Tox_CNN allowed automated extraction of feature maps that clustered compounds according to mechanism of action. Moreover, fully automated region-based CNNs (RCNN) were implemented to detect and classify nuclei, providing per-cell toxicity prediction from raw screening images. We validated both Tox_(R)CNN models for detection of pre-lethal toxicity from nuclei images, which proved to be more sensitive and have broader specificity than established toxicity readouts. These models predicted toxicity of drugs with mechanisms of action other than those they had been trained for and were successfully transferred to other cell assays. The Tox_(R)CNN models thus provide robust, sensitive, and cost-effective tools for in vitro screening of drug-induced toxicity. These models can be adopted for compound prioritization in drug screening campaigns, and could thereby increase the efficiency of drug discovery.

Three-dimensional whole-heart T2 mapping at 3T.

PURPOSE: Detecting variations in myocardial water content with T2 mapping is superior to conventional T2 -weighted MRI since quantification enables direct observation of complicated pathology. Most commonly used T2 mapping techniques are limited in achievable spatial and/or temporal resolution, both of which reduce accuracy due to partial-volume averaging and misregistration between images. The goal of this study was to validate a novel free breathing T2 mapping sequence that overcomes these limitations. METHODS: The proposed technique was made insensitive to heart rate variability through the use of a saturation prepulse to reset magnetization every heartbeat. Respiratory navigator-gated, differentially T2 -weighted volumes were interleaved per heartbeat, guaranteeing registered images and robust voxel-by-voxel T2 maps. Free breathing acquisitions removed limits on spatial resolution and allowed short diastolic windows. Accuracy was quantified with simulations and phantoms. RESULTS: Homogeneous three-dimensional (3D) T2 maps were obtained from normal human subjects and swine. Normal human and swine left ventricular T2 values were 42.3 ± 4.0 and 43.5 ± 4.3 ms, respectively. The T2 value for edematous myocardium obtained from a swine model of acute myocardial infarction was 59.1 ± 7.1 ms. CONCLUSION: Free-breathing accurate 3D T2 mapping is feasible and may be applicable in myocardial assessment in lieu of current clinical black blood, T2 -weighted techniques.

Proximo-distal positional information encoded by an Fgf-regulated gradient of homeodomain transcription factors in the vertebrate limb.

The positional information theory proposes that a coordinate system provides information to embryonic cells about their position and orientation along a patterning axis. Cells interpret this information to produce the appropriate pattern. During development, morphogens and interpreter transcription factors provide this information. We report a gradient of Meis homeodomain transcription factors along the mouse limb bud proximo-distal (PD) axis antiparallel to and shaped by the inhibitory action of distal fibroblast growth factor (FGF). Elimination of Meis results in premature limb distalization and HoxA expression, proximalization of PD segmental borders, and phocomelia. Our results show that Meis transcription factors interpret FGF signaling to convey positional information along the limb bud PD axis. These findings establish a new model for the generation of PD identities in the vertebrate limb and provide a molecular basis for the interpretation of FGF signal gradients during axial patterning.

ESC-Track: A computer workflow for 4-D segmentation, tracking, lineage tracing and dynamic context analysis of ESCs.

Embryonic stem cells (ESCs) can be established as permanent cell lines, and their potential to differentiate into adult tissues has led to widespread use for studying the mechanisms and dynamics of stem cell differentiation and exploring strategies for tissue repair. Imaging live ESCs during development is now feasible due to advances in optical imaging and engineering of genetically encoded fluorescent reporters; however, a major limitation is the low spatio-temporal resolution of long-term 3-D imaging required for generational and neighboring reconstructions. Here, we present the ESC-Track (ESC-T) workflow, which includes an automated cell and nuclear segmentation and tracking tool for 4-D (3-D + time) confocal image data sets as well as a manual editing tool for visual inspection and error correction. ESC-T automatically identifies cell divisions and membrane contacts for lineage tree and neighborhood reconstruction and computes quantitative features from individual cell entities, enabling analysis of fluorescence signal dynamics and tracking of cell morphology and motion. We use ESC-T to examine Myc intensity fluctuations in the context of mouse ESC (mESC) lineage and neighborhood relationships. ESC-T is a powerful tool for evaluation of the genealogical and microenvironmental cues that maintain ESC fitness.

Pluripotency Surveillance by Myc-Driven Competitive Elimination of Differentiating Cells.

The mammalian epiblast is formed by pluripotent cells able to differentiate into all tissues of the new individual. In their progression to differentiation, epiblast cells and their in vitro counterparts, embryonic stem cells (ESCs), transit from naive pluripotency through a differentiation-primed pluripotent state. During these events, epiblast cells and ESCs are prone to death, driven by competition between Myc-high cells (winners) and Myc-low cells (losers). Using live tracking of Myc levels, we show that Myc-high ESCs approach the naive pluripotency state, whereas Myc-low ESCs are closer to the differentiation-primed state. In ESC colonies, naive cells eliminate differentiating cells by cell competition, which is determined by a limitation in the time losers are able to survive persistent contact with winners. In the mouse embryo, cell competition promotes pluripotency maintenance by elimination of primed lineages before gastrulation. The mechanism described here is relevant to mammalian embryo development and induced pluripotency.

Fast synthesis and bioconjugation of (68) Ga core-doped extremely small iron oxide nanoparticles for PET/MR imaging.

Combination of complementary imaging techniques, like hybrid PET/MRI, allows protocols to be developed that exploit the best features of both. In order to get the best of these combinations the use of dual probes is highly desirable. On this sense the combination of biocompatible iron oxide nanoparticles and 68Ga isotope is a powerful development for the new generation of hybrid systems and multimodality approaches. Our objective was the synthesis and application of a chelator-free 68Ga-iron oxide nanotracer with improved stability, radiolabeling yield and in vivo performance in dual PET/MRI. We carried out the core doping of iron oxide nanoparticles, without the use of any chelator, by a microwave-driven protocol. The synthesis allowed the production of extremely small (2.5 nm) 68Ga core-doped iron oxide nanoparticles. The microwave approach allowed an extremely fast synthesis with a 90% radiolabeling yield and T1 contrast in MRI. With the same microwave approach the nano-radiotracer was functionalized in a fast and efficient way. We finally evaluated these dual targeting nanoparticles in an angiogenesis murine model by PET/MR imaging. Copyright © 2016 John Wiley & Sons, Ltd.

Organ-focused mutual information for nonrigid multimodal registration of liver CT and Gd-EOB-DTPA-enhanced MRI.

Accurate detection of liver lesions is of great importance in hepatic surgery planning. Recent studies have shown that the detection rate of liver lesions is significantly higher in gadoxetic acid-enhanced magnetic resonance imaging (Gd-EOB-DTPA-enhanced MRI) than in contrast-enhanced portal-phase computed tomography (CT); however, the latter remains essential because of its high specificity, good performance in estimating liver volumes and better vessel visibility. To characterize liver lesions using both the above image modalities, we propose a multimodal nonrigid registration framework using organ-focused mutual information (OF-MI). This proposal tries to improve mutual information (MI) based registration by adding spatial information, benefiting from the availability of expert liver segmentation in clinical protocols. The incorporation of an additional information channel containing liver segmentation information was studied. A dataset of real clinical images and simulated images was used in the validation process. A Gd-EOB-DTPA-enhanced MRI simulation framework is presented. To evaluate results, warping index errors were calculated for the simulated data, and landmark-based and surface-based errors were calculated for the real data. An improvement of the registration accuracy for OF-MI as compared with MI was found for both simulated and real datasets. Statistical significance of the difference was tested and confirmed in the simulated dataset (p<0.01).

Optimal multiresolution 3D level-set method for liver segmentation incorporating local curvature constraints.

Advanced liver surgery requires a precise pre-operative planning, where liver segmentation and remnant liver volume are key elements to avoid post-operative liver failure. In that context, level-set algorithms have achieved better results than others, especially with altered liver parenchyma or in cases with previous surgery. In order to improve functional liver parenchyma volume measurements, in this work we propose two strategies to enhance previous level-set algorithms: an optimal multi-resolution strategy with fine details correction and adaptive curvature, as well as an additional semiautomatic step imposing local curvature constraints. Results show more accurate segmentations, especially in elongated structures, detecting internal lesions and avoiding leakages to close structures.

3D liver segmentation in preoperative CT images using a level-sets active surface method.

In this work we propose an active surface method to segment complete liver volumes from preoperative CT abdominal images. The method finds the surface that minimizes an energy function combining intensity inside and outside the surface, gradient information and curvature restrictions. The implementation is based on a level set technique following a multi-resolution strategy to reduce computing time. It requires only a single seed point inside the liver to initialize the active surface. The algorithm has been validated on a set of previously diagnosed livers. Resulting segmentations have been supervised by clinicians and radiologists, and numerically evaluated in terms of volume measurements with respect to those obtained from radiologists' manual segmentations. Additionally, radiologists analyzed the necessity of additional corrections on segmenting volumes.