Structured crowdsourcing enables convolutional segmentation of histology images.

MOTIVATION: While deep-learning algorithms have demonstrated outstanding performance in semantic image segmentation tasks, large annotation datasets are needed to create accurate models. Annotation of histology images is challenging due to the effort and experience required to carefully delineate tissue structures, and difficulties related to sharing and markup of whole-slide images. RESULTS: We recruited 25 participants, ranging in experience from senior pathologists to medical students, to delineate tissue regions in 151 breast cancer slides using the Digital Slide Archive. Inter-participant discordance was systematically evaluated, revealing low discordance for tumor and stroma, and higher discordance for more subjectively defined or rare tissue classes. Feedback provided by senior participants enabled the generation and curation of 20 000+ annotated tissue regions. Fully convolutional networks trained using these annotations were highly accurate (mean AUC=0.945), and the scale of annotation data provided notable improvements in image classification accuracy. AVAILABILITY AND IMPLEMENTATION: Dataset is freely available at: https://goo.gl/cNM4EL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Review on electrically conductive smart nerve guide conduit for peripheral nerve regeneration.

At present, peripheral nerve injuries (PNIs) are one of the leading causes of substantial impairment around the globe. Complete recovery of nerve function after an injury is challenging. Currently, autologous nerve grafts are being used as a treatment; however, this has several downsides, for example, donor site morbidity, shortage of donor sites, loss of sensation, inflammation, and neuroma development. The most promising alternative is the development of a nerve guide conduit (NGC) to direct the restoration and renewal of neuronal axons from the proximal to the distal end to facilitate nerve regeneration and maximize sensory and functional recovery. Alternatively, the response of nerve cells to electrical stimulation (ES) has a substantial regenerative effect. The incorporation of electrically conductive biomaterials in the fabrication of smart NGCs facilitates the function of ES throughout the active proliferation state. This article overviews the potency of the various categories of electroactive smart biomaterials, including conductive and piezoelectric nanomaterials, piezoelectric polymers, and organic conductive polymers that researchers have employed latterly to fabricate smart NGCs and their potentiality in future clinical application. It also summarizes a comprehensive analysis of the recent research and advancements in the application of ES in the field of NGC.

A novel multi-phase treatment scheme for odorous rubber effluent.

Despite the great profits of rubber latex production, its preliminary processing releases a large amount of wastewater into the water bodies from several processing steps. This rubber effluent is rich in total Kjeldahl nitrogen (TKN), total dissolved solids (TDS), biological oxygen demand (BOD) and chemical oxygen demand (COD). Therefore, the study addressed a liquid phase treatment of the effluent using an Upflow Anaerobic Sludge Blanket (UASB) reactor followed by coagu-flocculation and aeration. In addition, the gas phase (containing odorous hydrogen sulphide of 10-12% by volume) from the UASB reactor was sent to a caustic scrubber where the H2S removal efficiency of 63 ± 5% was achieved. This integrated multi-phase treatment scheme proved to be an effective approach by reducing TKN, TDS, BOD and COD by 68-87%, 61-69%, 81-84% and 81-87% respectively in the final effluent.