Search

IntroductionAnalysis of multimodal medical images often requires the selection of one or many anatomical regions of interest (ROIs) for extraction of useful statistics. This task can prove laborious when a manual approach is used. We have previously developed a user-friendly software tool for image-to-image translation using deep learning. Therefore, we present herein an update to the DeepImageTranslator software with the addition of a tool for multimodal medical image segmentation analysis (hereby referred to as the MMMISA).MethodsThe MMMISA was implemented using the Tkinter library; backend computations were implemented using the Pydicom, Numpy, and OpenCV libraries. We tested our software using 4188 slices from whole-body axial 2-deoxy-2-[18F]-fluoroglucose-position emission tomography/computed tomography scans ([18F]-FDG-PET/CT) of 10 patients from the American College of Radiology Imaging Network-Head and Neck Squamous Cell Carcinoma (ACRIN-HNSCC) database. Using the deep learning software DeepImageTranslator, a model was trained with 36 randomly selected CT slices and manually labelled semantic segmentation maps. Utilizing the trained model, all the CT scans of the 10 HNSCC patients were segmented with high accuracy. Segmentation maps generated using the deep convolutional network were then used to measure organ specific [18F]-FDG uptake. We also compared measurements performed using the MMMISA and those made with manually selected ROIs.ResultsThe MMMISA is a tool that allows user to select ROIs based on deep learning-generated segmentation maps and to compute accurate statistics for these ROIs based on coregistered multimodal images. We found that organ-specific [18F]-FDG uptake measured using multiple manually selected ROIs is concordant with whole-tissue measurements made with segmentation maps using the MMMISA tool.

The development of shape memory polymers (SMPs) has gained remarkable attention due to their wide range of applications, from biomedical to electromechanical. In this work, we have developed and optimized an electroactive SMP based on polyvinyl alcohol/multi-walled carbon nanotubes (PVA/MWNTs) composites. When a constant voltage of 60 V was applied to the optimized sample, the polymer shape could be recovered to the original form within 35 s. Different weight fractions of MWNT/PVA composites were prepared by using a simple solution blending and transitional solution casting method, and their microstructures, electrical conductivities, thermal conductivities, and electroactive shape memory properties were investigated. According to our systematic analysis, the enhanced performance can be attributed to the reinforcement of MWNTs that led to the improved electrical and thermal conductivities of the PVA matrix.

Specimens of acidic multi-walled carbon nanotubes (AMWNTs) reinforced polyvinyl alcohol (PVA) nanocomposites (AMWNTs-PVA) were prepared using different amounts of AMWNTs by the traditional solution casting, involving ultrasonic wave agitation. The microstructures and tensile properties of AMWNTs-PVA were investigated by scanning electron microscopy, dynamic mechanical analysis, and quasi-static tensile testing. AMWNTs had good compatibility with PVA and dispersed evenly in the PVA matrix. The incorporation of AMWNTs improved the tensile modulus and strength of the PVA. The shape recovery testing revealed the shape recovery capacity of AMWNTs-PVA. It was observed that the recovery ratio increased, and the shape recovery rate slightly decrease with the increase of AMWNTs content. The results showed that the AMWNTs had strong interaction with the segments of the PVA and hence affected the shape recovery behavior of PVA. © 2012 Wiley Periodicals, Inc. J. Appl. Polym. Sci., 2013