This paper presents the evaluation results of the methods submitted to Challenge US: Biometric Measurements from Fetal Ultrasound Images, a segmentation challenge held at the IEEE International Symposium on Biomedical Imaging 2012. The challenge was set to compare and evaluate current fetal ultrasound image segmentation methods. It consisted of automatically segmenting fetal anatomical structures to measure standard obstetric biometric parameters, from 2D fetal ultrasound images taken on fetuses at different gestational ages (21 weeks, 28 weeks, and 33 weeks) and with varying image quality to reflect data encountered in real clinical environments. Four independent sub-challenges were proposed, according to the objects of interest measured in clinical practice: abdomen, head, femur, and whole fetus. Five teams participated in the head sub-challenge and two teams in the femur sub-challenge, including one team who tackled both. Nobody attempted the abdomen and whole fetus sub-challenges. The challenge goals were two-fold and the participants were asked to submit the segmentation results as well as the measurements derived from the segmented objects. Extensive quantitative (region-based, distance-based, and Bland-Altman measurements) and qualitative evaluation was performed to compare the results from a representative selection of current methods submitted to the challenge. Several experts (three for the head sub-challenge and two for the femur sub-challenge), with different degrees of expertise, manually delineated the objects of interest to define the ground truth used within the evaluation framework. For the head sub-challenge, several groups produced results that could be potentially used in clinical settings, with comparable performance to manual delineations. The femur sub-challenge had inferior performance to the head sub-challenge due to the fact that it is a harder segmentation problem and that the techniques presented relied more on the femur's appearance.

Giant kelp (Macrocystis pyrifera) is the most widely distributed kelp species on the planet, constituting one of the richest and most productive ecosystems on Earth, but detailed information on its distribution is entirely missing in some marine ecoregions, especially in the high latitudes of the Southern Hemisphere. Here, we present an algorithm based on a series of filter thresholds to detect giant kelp employing Sentinel-2 imagery. Given the overlap between the reflectances of giant kelp and intertidal green algae (Ulvophyceae), the latter are also detected on shallow rocky intertidal areas. The kelp filter algorithm was applied separately to vegetation indices, the Floating Algae Index (FAI), the Normalised Difference Vegetation Index (NDVI), and a novel formula (the Kelp Difference, KD). Training data from previously surveyed kelp forests and other coastal and ocean features were used to identify reflectance threshold values. This procedure was validated with independent field data collected with UAV imagery at a high spatial resolution and point-georeferenced sites at a low spatial resolution. When comparing UAV with Sentinel data (high-resolution validation), an average overall accuracy ≥ 0.88 and Cohen’s kappa ≥ 0.64 coefficients were found in all three indices for canopies reaching the surface with extensions greater than 1 hectare, with the KD showing the highest average kappa score (0.66). Measurements between previously surveyed georeferenced points and remotely-sensed kelp grid cells (low-resolution validation) showed that 66% of the georeferenced points had grid cells indicating kelp presence within a linear distance of 300 m. We employed the KD in our kelp filter algorithm to estimate the global extent of giant kelp and intertidal green algae per marine ecoregion and province, producing a high-resolution global map of giant kelp and intertidal green algae, powered by Google Earth Engine.

Flower classification is a challenging task due to the wide range of flower species, which have a similar shape, appearance or surrounding objects such as leaves and grass. In this study, the authors propose a novel two‐step deep learning classifier to distinguish flowers of a wide range of species. First, the flower region is automatically segmented to allow localisation of the minimum bounding box around it. The proposed flower segmentation approach is modelled as a binary classifier in a fully convolutional network framework. Second, they build a robust convolutional neural network classifier to distinguish the different flower types. They propose novel steps during the training stage to ensure robust, accurate and real‐time classification. They evaluate their method on three well known flower datasets. Their classification results exceed 97% on all datasets, which are better than the state‐of‐the‐art in this domain.

Context: Vitamin D deficiency during pregnancy may be associated with suboptimal fetal growth, but direct evidence is lacking. Objectives: The aim of the study was to validate a method for fetal femur volume (FV) measurement using three-dimensional ultrasound and to detect correlations between FV and maternal vitamin D concentration. Design, Setting, and Participants: A novel method for assessing FV consists of three ultrasound measurements—femur length, proximal metaphyseal diameter (PMD), and midshaft diameter—and a volume equation; this was validated by comparing ultrasound to computed tomography measurements in six pregnancies after mid-trimester termination. This method was then applied in a cohort of healthy pregnant women participating in the Southampton Women Survey. Fetal three-dimensional ultrasound and maternal 25-hydroxyvitamin D [25(OH)D] levels were performed at 34 wk; dual-energy x-ray absorptiometry of the newborn was performed shortly after birth. Univariate and multiple linear regression analyses were performed between maternal characteristics and fetal outcomes. Main Outcome Measures: We performed ultrasound measurements of the fetal femur. Results: In 357 pregnant participants, serum 25(OH)D correlated significantly with FV (P = 0.006; r = 0.147) and PMD (P = 0.001; r = 0.176); FV also demonstrated positive univariate correlations with maternal height (P < 0.001; r = 0.246), weight (P = 0.003; r = 0.160), triceps skinfold thickness (P = 0.013; r = 0.134), and a borderline negative effect from smoking (P = 0.061). On multiple regression, independent predictors of FV were the maternal height and triceps skinfold thickness; the effect of 25(OH)D on FV was attenuated, but it remained significant for PMD. Conclusion: Using a novel method for assessing FV, independent predictors of femoral size were maternal height, adiposity, and serum vitamin D. Future trials should establish whether pregnancy supplementation with vitamin D is beneficial for the fetal skeleton, using FV and PMD as fetal outcome measures.

Nuclear detection, segmentation and morphometric profiling are essential in helping us further understand the relationship between histology and patient outcome. To drive innovation in this area, we setup a community-wide challenge using the largest available dataset of its kind to assess nuclear segmentation and cellular composition. Our challenge, named CoNIC, stimulated the development of reproducible algorithms for cellular recognition with real-time result inspection on public leaderboards. We conducted an extensive post-challenge analysis based on the top-performing models using 1,658 whole-slide images of colon tissue. With around 700 million detected nuclei per model, associated features were used for dysplasia grading and survival analysis, where we demonstrated that the challenge's improvement over the previous state-of-the-art led to significant boosts in downstream performance. Our findings also suggest that eosinophils and neutrophils play an important role in the tumour microevironment. We release challenge models and WSI-level results to foster the development of further methods for biomarker discovery.