Potential of deep learning segmentation for the extraction of archaeological features from historical map series.

Historical maps present a unique depiction of past landscapes, providing evidence for a wide range of information such as settlement distribution, past land use, natural resources, transport networks, toponymy and other natural and cultural data within an explicitly spatial context. Maps produced before the expansion of large-scale mechanized agriculture reflect a landscape that is lost today. Of particular interest to us is the great quantity of archaeologically relevant information that these maps recorded, both deliberately and incidentally. Despite the importance of the information they contain, researchers have only recently begun to automatically digitize and extract data from such maps as coherent information, rather than manually examine a raster image. However, these new approaches have focused on specific types of information that cannot be used directly for archaeological or heritage purposes. This paper provides a proof of concept of the application of deep learning techniques to extract archaeological information from historical maps in an automated manner. Early twentieth century colonial map series have been chosen, as they provide enough time depth to avoid many recent large-scale landscape modifications and cover very large areas (comprising several countries). The use of common symbology and conventions enhance the applicability of the method. The results show deep learning to be an efficient tool for the recovery of georeferenced, archaeologically relevant information that is represented as conventional signs, line-drawings and text in historical maps. The method can provide excellent results when an adequate training dataset has been gathered and is therefore at its best when applied to the large map series that can supply such information. The deep learning approaches described here open up the possibility to map sites and features across entire map series much more quickly and coherently than other available methods, opening up the potential to reconstruct archaeological landscapes at continental scales.

TSC1 Promotes B Cell Maturation but Is Dispensable for Germinal Center Formation.

Accumulating evidence indicates that the tuberous sclerosis complex 1 (TSC1), a tumor suppressor that acts by inhibiting mTOR signaling, plays an important role in the immune system. We report here that TSC1 differentially regulates mTOR complex 1 (mTORC1) and mTORC2/Akt signaling in B cells. TSC1 deficiency results in the accumulation of transitional-1 (T1) B cells and progressive losses of B cells as they mature beyond the T1 stage. Moreover, TSC1KO mice exhibit a mild defect in the serum antibody responses or rate of Ig class-switch recombination after immunization with a T-cell-dependent antigen. In contrast to a previous report, we demonstrate that both constitutive Peyer's patch germinal centers (GCs) and immunization-induced splenic GCs are unimpaired in TSC1-deficient (TSC1KO) mice and that the ratio of GC B cells to total B cells is comparable in WT and TSC1KO mice. Together, our data demonstrate that TSC1 plays important roles for B cell development, but it is dispensable for GC formation and serum antibody responses.

Identification of a tissue-specific, C/EBPß-dependent pathway of differentiation for murine peritoneal macrophages.

Macrophages and dendritic cells (DC) are distributed throughout the body and play important roles in pathogen detection and tissue homeostasis. In tissues, resident macrophages exhibit distinct phenotypes and activities, yet the transcriptional pathways that specify tissue-specific macrophages are largely unknown. We investigated the functions and origins of two peritoneal macrophage populations in mice: small and large peritoneal macrophages (SPM and LPM, respectively). SPM and LPM differ in their ability to phagocytose apoptotic cells, as well as in the production of cytokines in response to LPS. In steady-state conditions, SPM are sustained by circulating precursors, whereas LPM are maintained independently of hematopoiesis; however, both populations are replenished by bone marrow precursors following radiation injury. Transcription factor analysis revealed that SPM and LPM express abundant CCAAT/enhancer binding protein (C/EBP)-ß. Cebpb(-/-) mice exhibit elevated numbers of SPM-like cells but lack functional LPM. Alveolar macrophages are also missing in Cebpb(-/-) mice, although macrophage populations in the spleen, kidney, skin, mesenteric lymph nodes, and liver are normal. Adoptive transfer of SPM into Cebpb(-/-) mice results in SPM differentiation into LPM, yet donor SPM do not generate LPM after transfer into C/EBPß-sufficient mice, suggesting that endogenous LPM inhibit differentiation by SPM. We conclude that C/EBPß plays an intrinsic, tissue-restricted role in the generation of resident macrophages.