Objectification of evaluation criteria in microscopic agglutination test using deep learning.

We aim to objectify the evaluation criteria of agglutination rate estimation in the Microscopic Agglutination Test (MAT). This study proposes a deep learning method that extracts free leptospires from dark-field microscopic images and calculates the agglutination rate. The experiments show the effect of objectification with real pictures.

Pyrolysis-GC-MS analysis of ingested polystyrene microsphere content in individual Daphnia magna.

Microplastic (MP) pollution in the aquatic environment is a cause for increasing concern. However, analyzing MPs ingested by small organisms, such as zooplankton, is difficult because of the low content and small size of the ingested MPs. We attempted to determine the content of ingested MPs in individual zooplankton using pyrolysis-gas chromatography-mass spectrometry (Py-GC-MS). To establish zooplankton model of MP ingestion, individual Daphnia magna were cultivated separately in microplate cells with polystyrene (PS) microspheres (10 µm in diameter, 245,000 particles, 135 µg) under different conditions. To prepare calibration curves for determining ingested PS content, approximately 100-150 µg of commercially available Daphnia-based powdered fish food, roughly corresponding to the weight of a single D. magna organism, was mixed with PS microspheres (0.005-26 µg) and analyzed using Py-GC-MS at 600 °C. In the resulting pyrograms, peaks of the styrene monomer and trimer from PS were detected, and linear relationships were obtained between the relative peak area and the amount of added PS. Finally, the cultivated zooplankton were individually subjected to Py-GC-MS analysis, and the ingested PS content in each zooplankton was successfully determined. Individual zooplankton cultured with PS in the absence of food ingested 2.3-7.9 µg of PS particles, whereas that in the presence of food (Chlorella vulgaris) ingested only 0.1-0.2 µg of PS particles. This result suggests that zooplankton might preferentially ingest ordinary food when both food and MPs are present, although further systematic studies are necessary to validate this observation.

Automated approach for segmenting gross tumor volumes for lung cancer stereotactic body radiation therapy using CT-based dense V-networks.

The aim of this study was to develop an automated segmentation approach for small gross tumor volumes (GTVs) in 3D planning computed tomography (CT) images using dense V-networks (DVNs) that offer more advantages in segmenting smaller structures than conventional V-networks. Regions of interest (ROI) with dimensions of 50 × 50 × 6-72 pixels in the planning CT images were cropped based on the GTV centroids when applying stereotactic body radiotherapy (SBRT) to patients. Segmentation accuracy of GTV contours for 192 lung cancer patients [with the following tumor types: 118 solid, 53 part-solid types and 21 pure ground-glass opacity (pure GGO)], who underwent SBRT, were evaluated based on a 10-fold cross-validation test using Dice's similarity coefficient (DSC) and Hausdorff distance (HD). For each case, 11 segmented GTVs consisting of three single outputs, four logical AND outputs, and four logical OR outputs from combinations of two or three outputs from DVNs were obtained by three runs with different initial weights. The AND output (combination of three outputs) achieved the highest values of average 3D-DSC (0.832 ± 0.074) and HD (4.57 ± 2.44 mm). The average 3D DSCs from the AND output for solid, part-solid and pure GGO types were 0.838 ± 0.074, 0.822 ± 0.078 and 0.819 ± 0.059, respectively. This study suggests that the proposed approach could be useful in segmenting GTVs for planning lung cancer SBRT.

Automated classification of urinary stones based on microcomputed tomography images using convolutional neural network.

PURPOSE: The classification of urinary stones is important prior to treatment because the treatments depend on three types of urinary stones, i.e., calcium, uric acid, and mixture stones. We have developed an automatic approach for the classification of urinary stones into the three types based on microcomputed tomography (micro-CT) images using a convolutional neural network (CNN). MATERIALS AND METHODS: Thirty urinary stones from different patients were scanned in vitro using micro-CT (pixel size: 14.96 µm; slice thickness: 15 µm); a total of 2,430 images (micro-CT slices) were produced. The slices (227 × 227 pixels) were classified into the three categories based on their energy dispersive X-ray (EDX) spectra obtained via scanning electron microscopy (SEM). The images of urinary stones from each category were divided into three parts; 66%, 17%, and 17% of the dataset were assigned to the training, validation, and test datasets, respectively. The CNN model with 15 layers was assessed based on validation accuracy for the optimization of hyperparameters such as batch size, learning rate, and number of epochs with different optimizers. Then, the model with the optimized hyperparameters was evaluated for the test dataset to obtain classification accuracy and error. RESULTS: The validation accuracy of the developed approach with CNN with optimized hyperparameters was 0.9852. The trained CNN model achieved a test accuracy of 0.9959 with a classification error of 1.2%. CONCLUSIONS: The proposed automated CNN-based approach could successfully classify urinary stones into three types, namely calcium, uric acid, and mixture stones, using micro-CT images.

TIPE2 (Tumor Necrosis Factor α-induced Protein 8-like 2) Is a Novel Negative Regulator of TAK1 Signal.

TIPE2 (TNF-α-induced protein 8-like 2) is a novel death effector domain protein and is a negative regulator of the innate and adaptive immune response. Although it has been demonstrated that caspase-8 contributes to the negative regulation of TIPE2, the negative regulatory mechanism is not entirely understood. Here, we demonstrate that TIPE2 interacts with TGF-ß-activated kinase 1 (TAK1), a crucial regulatory molecule of inflammatory and immune signals, and consequently acts as a powerful negative regulator of TAK1. The interaction between endogenous TIPE2 and TAK1 was observed in RAW264.7 macrophage-like cells and mouse primary cells derived from spleen and thymus. The TIPE2 amino acid 101-140 region interacted with TAK1 by binding to the amino acid 200-291 region of the internal kinase domain of TAK1. TIPE2 interfered with the formation of the TAK1-TAB1-TAB2 complex and subsequently inhibited activation of TAK1 and its downstream molecules. Importantly, silencing TIPE2 through RNA interference attenuated the inhibitory action of TIPE2 on LPS- and TNF-α-stimulated TAK1 activity. Exogenous TIPE2 101-140, the region that interacts with TAK1, also inhibited LPS- and TNF-α-stimulated NF-κB reporter activity. Interestingly, cell-permeable TIPE2 protein maintained its binding ability with TAK1 and exhibited the same inhibitory action of native TIPE2 on TLR4 signaling in vitro Thus, cell-permeable TIPE2 protein is a potential candidate for intracellular protein therapy for TAK1-related diseases. The present study demonstrates that TIPE2 acts as a novel negative regulator of inflammatory and immune responses through TAK1 signaling.