Generalized nucleus segmentation techniques can contribute greatly to reducing the time to develop and validate visual biomarkers for new digital pathology datasets. We summarize the results of MoNuSeg 2018 Challenge whose objective was to develop generalizable nuclei segmentation techniques in digital pathology. The challenge was an official satellite event of the MICCAI 2018 conference in which 32 teams with more than 80 participants from geographically diverse institutes participated. Contestants were given a training set with 30 images from seven organs with annotations of 21,623 individual nuclei. A test dataset with 14 images taken from seven organs, including two organs that did not appear in the training set was released without annotations. Entries were evaluated based on average aggregated Jaccard index (AJI) on the test set to prioritize accurate instance segmentation as opposed to mere semantic segmentation. More than half the teams that completed the challenge outperformed a previous baseline. Among the trends observed that contributed to increased accuracy were the use of color normalization as well as heavy data augmentation. Additionally, fully convolutional networks inspired by variants of U-Net, FCN, and Mask-RCNN were popularly used, typically based on ResNet or VGG base architectures. Watershed segmentation on predicted semantic segmentation maps was a popular post-processing strategy. Several of the top techniques compared favorably to an individual human annotator and can be used with confidence for nuclear morphometrics.

Detecting various types of cells in and around the tumor matrix holds a special significance in characterizing the tumor micro-environment for cancer prognostication and research. Automating the tasks of detecting, segmenting, and classifying nuclei can free up the pathologists’ time for higher value tasks and reduce errors due to fatigue and subjectivity. To encourage the computer vision research community to develop and test algorithms for these tasks, we prepared a large and diverse dataset of nucleus boundary annotations and class labels. The dataset has over 46,000 nuclei from 37 hospitals, 71 patients, four organs, and four nucleus types. We also organized a challenge around this dataset as a satellite event at the International Symposium on Biomedical Imaging (ISBI) in April 2020. The challenge saw a wide participation from across the world, and the top methods were able to match inter-human concordance for the challenge metric. In this paper, we summarize the dataset and the key findings of the challenge, including the commonalities and differences between the methods developed by various participants. We have released the MoNuSAC2020 dataset to the public.

Osteoporosis is a major cause of fractures and associated morbidity in the aged population. The pathogenesis of osteoporosis is multifactorial; whereas traditional pathophysiological concepts emphasize endocrine mechanisms, it has been recognized that also components of the immune system have a significant impact on bone. Since 2000, when the term ‘osteoimmunology' was coined, novel insights into the role of inflammatory cytokines by influencing the fine-tuned balance between bone resorption and bone formation have helped to explain the occurrence of osteoporosis in conjunction with chronic inflammatory reactions. Moreover, the phenomenon of a low-grade, chronic, systemic inflammatory state associated with aging has been defined as ‘inflamm-aging' by Claudio Franceschi and has been linked to age-related diseases such as osteoporosis. Given the tight anatomical and physiological coexistence of B cells and the bone-forming units in the bone marrow, a role of B cells in osteoimmunological interactions has long been suspected. Recent findings of B cells as active regulators of the RANK/RANKL/OPG axis, of altered RANKL/OPG production by B cells in HIV-associated bone loss or of a modulated expression of genes linked to B-cell biology in response to estrogen deficiency support this assumption. Furthermore, oxidative stress and the generation of advanced glycation end products have emerged as links between inflammation and bone destruction.

The steroid hormones progestagens, estrogens, androgens, and glucocorticoids as well as their precursor cholesterol are required for successful establishment and maintenance of pregnancy and proper development of the fetus. The human placenta forms at the interface of maternal and fetal circulation. It participates in biosynthesis and metabolism of steroids as well as their regulated exchange between maternal and fetal compartment. This review outlines the mechanisms of human placental handling of steroid compounds. Cholesterol is transported from mother to offspring involving lipoprotein receptors such as low-density lipoprotein receptor (LDLR) and scavenger receptor class B type I (SRB1) as well as ATP-binding cassette (ABC)-transporters, ABCA1 and ABCG1. Additionally, cholesterol is also a precursor for placental progesterone and estrogen synthesis. Hormone synthesis is predominantly performed by members of the cytochrome P-450 (CYP) enzyme family including CYP11A1 or CYP19A1 and hydroxysteroid dehydrogenases (HSDs) such as 3β-HSD and 17β-HSD. Placental estrogen synthesis requires delivery of sulfate-conjugated precursor molecules from fetal and maternal serum. Placental uptake of these precursors is mediated by members of the solute carrier (SLC) family including sodium-dependent organic anion transporter (SOAT), organic anion transporter 4 (OAT4), and organic anion transporting polypeptide 2B1 (OATP2B1). Maternal–fetal glucocorticoid transport has to be tightly regulated in order to ensure healthy fetal growth and development. For that purpose, the placenta expresses the enzymes 11β-HSD 1 and 2 as well as the transporter ABCB1. This article also summarizes the impact of diverse compounds and diseases on the expression level and activity of the involved transporters, receptors, and metabolizing enzymes and concludes that the regulatory mechanisms changing the physiological to a pathophysiological state are barely explored. The structure and the cellular composition of the human placental barrier are introduced. While steroid production, metabolism and transport in the placental syncytiotrophoblast have been explored for decades, few information is available for the role of placental-fetal endothelial cells in these processes. With regard to placental structure and function, significant differences exist between species. To further decipher physiologic pathways and their pathologic alterations in placental steroid handling, proper model systems are mandatory.

Malignant melanoma is one of the most aggressive forms of skin cancer. Early detection is important as it significantly improves survival rates. Consequently, accurate discrimination of malignant skin lesions from benign lesions such as seborrheic keratoses or benign nevi is crucial, while accurate computerised classification of skin lesion images is of great interest to support diagnosis. In this paper, we propose a fully automatic computerised method to classify skin lesions from dermoscopic images. Our approach is based on a novel ensemble scheme for convolutional neural networks (CNNs) that combines intra-architecture and inter-architecture network fusion. The proposed method consists of multiple sets of CNNs of different architecture that represent different feature abstraction levels. Each set of CNNs consists of a number of pre-trained networks that have identical architecture but are fine-tuned on dermoscopic skin lesion images with different settings. The deep features of each network were used to train different support vector machine classifiers. Finally, the average prediction probability classification vectors from different sets are fused to provide the final prediction. Evaluated on the 600 test images of the ISIC 2017 skin lesion classification challenge, the proposed algorithm yields an area under receiver operating characteristic curve of 87.3% for melanoma classification and an area under receiver operating characteristic curve of 95.5% for seborrheic keratosis classification, outperforming the top-ranked methods of the challenge while being simpler compared to them. The obtained results convincingly demonstrate our proposed approach to represent a reliable and robust method for feature extraction, model fusion and classification of dermoscopic skin lesion images.