lookiposter.blogg.se

1. #Osirix lite length tool shows 0 pixels update
2. #Osirix lite length tool shows 0 pixels manual
3. #Osirix lite length tool shows 0 pixels free

#Osirix lite length tool shows 0 pixels update

Therefore, we have presented herein an update to the DeepImageTranslator software by including a tool for multimodal medical image segmentation analysis based on semantic segmentation maps generated using a deep convolutional neural network. In particular, measurements of volume and radiotracer uptake of adipose tissues of different regions may prove to be important for future studies on the metabolic syndrome, as hypertrophic obesity is related to changes in adipose tissue distribution and alterations in metabolic endpoints. Nonetheless, selection of ROIs is an important aspect of in vivo metabolic studies involving PET/CT imaging.

#Osirix lite length tool shows 0 pixels free

Nevertheless, most deep learning pipelines for semantic image segmentation generate color-coded segmentation maps stored as image files, while most free software programs for medical image analysis cannot use these files to generate ROI statistics of multimodal images stored as DICOM files. One growing area of development is the popularization of deep learning methods through the creation of user-friendly tools with a graphical interface. In recent years, numerous open-source software tools have been reported in the field of medical image processing. Similar results were obtained for the measurement of FDG uptake in the lungs ( Fig.4C-D).

#Osirix lite length tool shows 0 pixels manual

Nevertheless, the P-value of the correlation between manual measurement and that using segmentation maps continued to decrease when more ROIs were used ( Fig.4B). Increase in measurement accuracy (determined by the correlation coefficient) through increasing numbers of manually selected ROIs plateaued after more than 8 ROIs were used. For subcutaneous adipose tissue FDG uptake, the correlation coefficient and the -log of the P-value increased sharply once values from more than 4 ROIs were combined ( Fig.4A). In general, regardless the number of ROIs used, manually measured FDG uptake in the lungs and subcutaneous adipose tissue was well correlated with that calculated with segmentation maps using the MMMISA program ( Fig.4). Next, we tested the concordance of organ-specific FDG uptake measured using multiple manually selected ROIs versus FDG uptake determined using deep learning-generated segmentation maps. Increase in number of manually selected ROIs increases accuracy of organ-specific FDG uptake approximations compared to true organ-specific FDG uptake measured using deep learning-generated segmentation maps Furthermore, we also compare measurements performed using the MMMISA and those made with manually selected ROIs. We then demonstrate the use of the program for the measurement of 2-deoxy-2-fluoroglucose (-FDG) uptake by the lungs and subcutaneous adipose tissue using whole-body -FDG-PET/CT scans from the ACRIN-HNSCC-FDG-PET/CT database. Therefore, we present herein an update to the DeepImageTranslator software with the addiction of a tool for multimodal medical image segmentation analysis (hereby referred to as the MMMISA). We have previously developed a user-friendly software tool for image-to-image translation using deep learning (DeepImageTranslator, described in, released at: ). Nevertheless, most deep learning pipelines for semantic image segmentation generate color-coded segmentation maps stored as image files, while most free software programs for medical image analysis ( e.g., 3D-Slicer, OsiriX Lite, and AMIDE) cannot use these files to generate ROI statistics of multimodal images stored as DICOM files. One possible method is the use of deep learning for automated segmentation. However, for organs/tissues with complex shapes ( e.g., the intestines and adipose tissues), manual ROI segmentation is not a scalable approach. The use of spherical or ellipsoid ROIs may be sufficient for large organs such as the liver and large muscle groups. Analysis of multimodal medical images ( e.g., position emission tomography/magnetic resonance imaging and PET/computed tomography ) often requires the selection of one or many anatomical regions of interest (ROIs) for extraction of useful statistics.