C. elegans develops through four larval stages that are rhythmically terminated by molts, that is, the synthesis and shedding of a cuticular exoskeleton. Each larval cycle involves rhythmic accumulation of thousands of transcripts, which we show here relies on rhythmic transcription. To uncover the responsible gene regulatory networks (GRNs), we screened for transcription factors that promote progression through the larval stages and identified GRH-1, BLMP-1, NHR-23, NHR-25, MYRF-1, and BED-3. We further characterize GRH-1, a Grainyhead/LSF transcription factor, whose orthologues in other animals are key epithelial cell-fate regulators. We find that GRH-1 depletion extends molt durations, impairs cuticle integrity and shedding, and causes larval death. GRH-1 is required for, and accumulates prior to, each molt, and preferentially binds to the promoters of genes expressed during this time window. Binding to the promoters of additional genes identified in our screen furthermore suggests that we have identified components of a core molting-clock GRN. Since the mammalian orthologues of GRH-1, BLMP-1 and NHR-23, have been implicated in rhythmic homeostatic skin regeneration in mouse, the mechanisms underlying rhythmic C. elegans molting may apply beyond nematodes.

In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in http://medicaldecathlon.com/. In addition, both data and online evaluation are accessible via https://competitions.codalab.org/competitions/17094.

Intestinal organoids derived from single cells undergo complex crypt-villus patterning and morphogenesis. However, the nature and coordination of the underlying forces remains poorly characterized. Through light-sheet microscopy and mechanical perturbations, we demonstrate that organoid crypt formation coincides with stark lumen volume reduction, which works synergistically with actomyosin-generated crypt apical and villus basal tension to drive morphogenesis. We analyse these mechanical features in a quantitative 3D biophysical model and detect a critical point in actomyosin tensions, above which crypt becomes robust to volume changes. Finally, via single-cell RNA sequencing and pharmacological perturbations, we show that enterocyte-specific expressed sodium/glucose cotransporter modulates lumen volume reduction via promoting cell swelling. Altogether, our study reveals how cell fate-specific changes in osmotic and actomyosin forces coordinate robust organoid morphogenesis. One Sentence Summary Emergence of region-specific cell fates drive actomyosin patterns and luminal osmotic changes in organoid development

The MICCAI conference has encountered tremendous growth over the last years in terms of the size of the community, as well as the number of contributions and their technical success. With this growth, however, come new challenges for the community. Methods are more difficult to reproduce and the ever-increasing number of paper submissions to the MICCAI conference poses new questions regarding the selection process and the diversity of topics. To exchange, discuss, and find novel and creative solutions to these challenges, a new format of a hackathon was initiated as a satellite event at the MICCAI 2020 conference: The MICCAI Hackathon. The first edition of the MICCAI Hackathon covered the topics reproducibility, diversity, and selection of MICCAI papers. In the manner of a small think-tank, participants collaborated to find solutions to these challenges. In this report, we summarize the insights from the MICCAI Hackathon into immediate and long-term measures to address these challenges. The proposed measures can be seen as starting points and guidelines for discussions and actions to possibly improve the MICCAI conference with regards to reproducibility, diversity, and selection of papers.

Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision-support systems for diagnosis, surgery planning, and population-based analysis on spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms towards labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel-level by a human-machine hybrid algorithm (https://osf.io/nqjyw/, https://osf.io/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the the results of this evaluation and further investigate the performance-variation at vertebra-level, scan-level, and at different fields-of-view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The content and code concerning VerSe can be accessed at: https://github.com/anjany/verse.

Detection of diffraction-limited spots in single-molecule microscopy images is traditionally performed with mathematical operators designed for idealized spots. This process requires manual tuning of parameters that is time-consuming and not always reliable. We have developed deepBlink, a neural network-based method to detect and localize spots automatically. We demonstrate that deepBlink outperforms other state-of-the-art methods across six publicly available datasets containing synthetic and experimental data.

Instance segmentation is a key step for quantitative microscopy. While several machine learning based methods have been proposed for this problem, most of them rely on computationally complex models that are trained on surrogate tasks. Building on recent developments towards end-to-end trainable instance segmentation, we propose a minimalist recurrent network called recurrent dilated convolutional network (RDCNet), consisting of a shared stacked dilated convolution (sSDC) layer that iteratively refines its output and thereby generates interpretable intermediate predictions. It is light-weight and has few critical hyperparameters, which can be related to physical aspects such as object size or density.We perform a sensitivity analysis of its main parameters and we demonstrate its versatility on 3 tasks with different imaging modalities: nuclear segmentation of H&E slides, of 3D anisotropic stacks from light-sheet fluorescence microscopy and leaf segmentation of top-view images of plants. It achieves state-of-the-art on 2 of the 3 datasets.

Instance segmentation is a key step for quantitative microscopy. While several machine learning based methods have been proposed for this problem, most of them rely on computationally complex models that are trained on surrogate tasks. Building on recent developments towards end-to-end trainable instance segmentation, we propose a minimalist recurrent network called recurrent dilated convolutional network (RDCNet), consisting of a shared stacked dilated convolution (sSDC) layer that iteratively refines its output and thereby generates interpretable intermediate predictions. It is light-weight and has few critical hyperparameters, which can be related to physical aspects such as object size or density. We perform a sensitivity analysis of its main parameters and we demonstrate its versatility on 3 tasks with different imaging modalities: nuclear segmentation of H&E slides, of 3D anisotropic stacks from light-sheet fluorescence microscopy and leaf segmentation of top-view images of plants. It achieves state-of-the-art on 2 of the 3 datasets.

This work is a technical report concerning the Large Scale Vertebrae Segmentation Challenge (VerSe) organised in conjunction with the MICCAI 2019. The challenge set-up consisting of two tasks, vertebrae labelling and vertebrae segmentation, is detailed. A total of 160 multidetector CT scans closely resembling a typical spine-centreed clinical setting were prepared and annotated at voxel-level by a human-machine hybrid algorithm. Both the annotation protocol and the algorithm that aided the medical experts in this annotation process are presented. More importantly, eleven fully automated algorithms of the participating teams were submitted to be benchmarked on the VerSe data. This work presents a detailed performance analysis of these algorithms with the best performing algorithm achieving a vertebrae identification rate of 95% and a Dice coefficient of 90%. VerSe'19 is an open-call challenge and its image data along with the annotations and evaluation tools will continue to be publicly accessible through its online portal.

PURPOSE:To use and test a labeling algorithm that operates on two-dimensional reformations, rather than three-dimensional data to locate and identify vertebrae.MATERIALS AND METHODS:The authors improved the Btrfly Net, a fully convolutional network architecture described by Sekuboyina et al, which works on sagittal and coronal maximum intensity projections (MIPs) and augmented it with two additional components: spine localization and adversarial a priori learning. Furthermore, two variants of adversarial training schemes that incorporated the anatomic a priori knowledge into the Btrfly Net were explored. The superiority of the proposed approach for labeling vertebrae on three datasets was investigated: a public benchmarking dataset of 302 CT scans and two in-house datasets with a total of 238 CT scans. The Wilcoxon signed rank test was employed to compute the statistical significance of the improvement in performance observed with various architectural components in the authors' approach.RESULTS:On the public dataset, the authors' approach using the described Btrfly Net with energy-based prior encoding (Btrflype-eb) network performed as well as current state-of-the-art methods, achieving a statistically significant (P < .001) vertebrae identification rate of 88.5% ± 0.2 (standard deviation) and localization distances of less than 7 mm. On the in-house datasets that had a higher interscan data variability, an identification rate of 85.1% ± 1.2 was obtained.CONCLUSION:An identification performance comparable to existing three-dimensional approaches was achieved when labeling vertebrae on two-dimensional MIPs. The performance was further improved using the proposed adversarial training regimen that effectively enforced local spine a priori knowledge during training. Spine localization increased the generalizability of our approach by homogenizing the content in the MIPs.Supplemental material is available for this article.© RSNA, 2020.

Abstract Organoids recapitulate the self-organizing capacity of stem cells and the tissue organization of the original organ in a controlled and trackable environment. Intestinal organoids, in particular, can develop from a single cell into a fully-grown structure that contains most of the cell types, patterns, and morphogenetic properties of the adult intestine. Here we present a protocol for high-throughput organoid culture in multi-well plate format combined with high content immunofluorescence imaging and RNA extraction. Our protocol allows recording and analysis of thousands of organoids during several days of development.

Intestinal organoids are complex three-dimensional structures that mimic the cell-type composition and tissue organization of the intestine by recapitulating the self-organizing ability of cell populations derived from a single intestinal stem cell. Crucial in this process is a first symmetry-breaking event, in which only a fraction of identical cells in a symmetrical sphere differentiate into Paneth cells, which generate the stem-cell niche and lead to asymmetric structures such as the crypts and villi. Here we combine single-cell quantitative genomic and imaging approaches to characterize the development of intestinal organoids from single cells. We show that their development follows a regeneration process that is driven by transient activation of the transcriptional regulator YAP1. Cell-to-cell variability in YAP1, emerging in symmetrical spheres, initiates Notch and DLL1 activation, and drives the symmetry-breaking event and formation of the first Paneth cell. Our findings reveal how single cells exposed to a uniform growth-promoting environment have the intrinsic ability to generate emergent, self-organized behaviour that results in the formation of complex multicellular asymmetric structures.

We propose an auto-encoding network architecture for point clouds (PC) capable of extracting shape signatures without supervision. Building on this, we (i) design a loss function capable of modelling data variance on PCs which are unstructured, and (ii) regularise the latent space as in a variational auto-encoder, both of which increase the auto-encoders' descriptive capacity while making them probabilistic. Evaluating the reconstruction quality of our architectures, we employ them for detecting vertebral fractures without any supervision. By learning to efficiently reconstruct only healthy vertebrae, fractures are detected as anomalous reconstructions. Evaluating on a dataset containing $\sim$1500 vertebrae, we achieve area-under-ROC curve of $>$75%, without using intensity-based features.

Robust localisation and identification of vertebrae is essential for automated spine analysis. The contribution of this work to the task is two-fold: (1) Inspired by the human expert, we hypothesise that a sagittal and coronal reformation of the spine contain sufficient information for labelling the vertebrae. Thereby, we propose a butterfly-shaped network architecture (termed Btrfly Net) that efficiently combines the information across reformations. (2) Underpinning the Btrfly net, we present an energy-based adversarial training regime that encodes local spine structure as an anatomical prior into the network, thereby enabling it to achieve state-of-art performance in all standard metrics on a benchmark dataset of 302 scans without any post-processing during inference.

Analysis of entire transparent rodent bodies after clearing could provide holistic biological information in health and disease, but reliable imaging and quantification of fluorescent protein signals deep inside the tissues has remained a challenge. Here, we developed vDISCO, a pressure-driven, nanobody-based whole-body immunolabeling technology to enhance the signal of fluorescent proteins by up to two orders of magnitude. This allowed us to image and quantify subcellular details through bones, skin and highly autofluorescent tissues of intact transparent mice. For the first time, we visualized whole-body neuronal projections in adult mice. We assessed CNS trauma effects in the whole body and found degeneration of peripheral nerve terminals in the torso. Furthermore, vDISCO revealed short vascular connections between skull marrow and brain meninges, which were filled with immune cells upon stroke. Thus, our new approach enables unbiased comprehensive studies of the interactions between the nervous system and the rest of the body.

Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histologic sub-regions, i.e., peritumoral edematous/invaded tissue, necrotic core, active and non-enhancing core. This intrinsic heterogeneity is also portrayed in their radio-phenotype, as their sub-regions are depicted by varying intensity profiles disseminated across multi-parametric magnetic resonance imaging (mpMRI) scans, reflecting varying biological properties. Their heterogeneous shape, extent, and location are some of the factors that make these tumors difficult to resect, and in some cases inoperable. The amount of resected tumor is a factor also considered in longitudinal scans, when evaluating the apparent tumor for potential diagnosis of progression. Furthermore, there is mounting evidence that accurate segmentation of the various tumor sub-regions can offer the basis for quantitative image analysis towards prediction of patient overall survival. This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018. Specifically, we focus on i) evaluating segmentations of the various glioma sub-regions in pre-operative mpMRI scans, ii) assessing potential tumor progression by virtue of longitudinal growth of tumor sub-regions, beyond use of the RECIST/RANO criteria, and iii) predicting the overall survival from pre-operative mpMRI scans of patients that underwent gross total resection. Finally, we investigate the challenge of identifying the best ML algorithms for each of these tasks, considering that apart from being diverse on each instance of the challenge, the multi-institutional mpMRI BraTS dataset has also been a continuously evolving/growing dataset.

Analysis of entire transparent rodent bodies could provide holistic information on biological systems in health and disease. However, it has been challenging to reliably image and quantify signal from endogenously expressed fluorescent proteins in large cleared mouse bodies due to the low signal contrast. Here, we devised a pressure driven, nanobody based whole-body immunolabeling technology to enhance the signal of fluorescent proteins by up to two orders of magnitude. This allowed us to image subcellular details in transparent mouse bodies through bones and highly autofluorescent tissues, and perform quantifications. We visualized for the first-time whole-body neuronal connectivity of an entire adult mouse and discovered that brain trauma induces degeneration of peripheral axons. We also imaged meningeal lymphatic vessels and immune cells through the intact skull and vertebra in naive animals and trauma models. Thus, our new approach can provide an unbiased holistic view of biological events affecting the nervous system and the rest of the body.

Automatic segmentation of the liver and hepatic lesions is an important step towards deriving quantitative biomarkers for accurate clinical diagnosis and computer-aided decision support systems. This paper presents a method to automatically segment liver and lesions in CT and MRI abdomen images using cascaded fully convolutional neural networks (CFCNs) enabling the segmentation of a large-scale medical trial or quantitative image analysis. We train and cascade two FCNs for a combined segmentation of the liver and its lesions. In the first step, we train a FCN to segment the liver as ROI input for a second FCN. The second FCN solely segments lesions within the predicted liver ROIs of step 1. CFCN models were trained on an abdominal CT dataset comprising 100 hepatic tumor volumes. Validations on further datasets show that CFCN-based semantic liver and lesion segmentation achieves Dice scores over 94% for liver with computation times below 100s per volume. We further experimentally demonstrate the robustness of the proposed method on an 38 MRI liver tumor volumes and the public 3DIRCAD dataset.

In vitro experiments with cell cultures are essential for studying growth and migration behaviour and thus, for gaining a better understanding of cancer progression and its treatment. While recent progress in lens-free microscopy (LFM) has rendered it an inexpensive tool for continuous monitoring of these experiments, there is only little work on analysing such time-lapse sequences. We propose (1) a cell detector for LFM images based on residual learning, and (2) a probabilistic model based on moral lineage tracing that explicitly handles multiple detections and temporal successor hypotheses by clustering and tracking simultaneously. (3) We benchmark our method on several hours of LFM time-lapse sequences in terms of detection and tracking scores. Finally, (4) we demonstrate its effectiveness for quantifying cell population dynamics.

Reconstructing vascular networks is a challenging task in medical image processing as automated methods have to deal with large variations in vessel shape and image quality. Recent methods have addressed this problem as constrained maximum a posteriori (MAP) inference in a graphical model, formulated over an overcomplete network graph. Manual control and adjustments are often desired in practice and strongly benefit from indicating the uncertainties in the reconstruction or presenting alternative solutions. In this paper, we examine two different methods to sample vessel network graphs, a perturbation and a Gibbs sampler, and thereby estimate marginals. We quantitatively validate the accuracy of the approximated marginals using true marginals, computed by enumeration.