ABSTRACT
In order to alleviate the conflict between medical supply and demand, and to improve the efficiency of medical image transmission, this study proposes an intelligent method for large-volume medical image transmission. This method extracts and generates keyword pairs by analyzing medical diagnostic reports, and uses a 3D-UNet to segment original image data into various sub-area based on its anatomy structure. Then, the sub-areas are scored through keyword pairs and preset scoring criteria, and transmitted to user frontend in the order of prioritization score. Experiments show that this method can fulfill physicians' requirements of radiology reading and diagnosis with only ten percent of data transmitted, which efficiently optimized traditional transmission procedures.
ABSTRACT
Objective To analyze the differences between calculated and actual volumes of regions of interest ( ROIs) in three treatment planning systems ( TPSs):PrecisePlan, Xio, and Oncentra, to transfer different ROIs and compare their calculated volume between the three TPSs, and to provide a basis for clinical application. Methods Different sizes of ROIs were delineated on 5 sets of computed tomography ( CT) images with different slice thickness. Square and round regions with different slice numbers were contoured in a homogeneous phantom. Three groups of patients ( n=5) with head and neck tumor, chest and abdomen tumor, and pelvic tumor, respectively, were enrolled as subjects. All the ROIs were independently transferred back and forth between three TPSs and different workstations with the same system in DICOM RT format. The changes in actual and calculated ROI volumes were evaluated after back and forth transfer. Results There was a significant positive linear correlation between the calculated volume, slice thickness, slice number, and actual volume of ROI in each TPS ( PrecisePlan:R2=0. 994, P<0. 01;Xio:R2=0. 997, P<0. 01;Oncentra:R2=0. 995, P<0. 01) . There were significant differences in all calculated ROI volumes of the head, chest and abdomen between the three TPS ( P<0. 05) except for the calculated ROI volumes of the chest and abdomen between Oncentra and Xio ( P=0. 114 ) . Conclusions The variations in volume calculation algorithm and slice thickness are the main causes of differences in calculated ROI volume. Particularly, small?volume ROIs have the greatest variation in calculated volume. To avoid a secondary reconstruction of ROI volume, it is recommended to transfer ROI back and forth between dose calculation workstations with the same TPS.
ABSTRACT
Image guided surgery (IGS) requires an integrated environment for seamless acquisition, visualization,manipulation, display, registration and storage of complex data sets. The infrastructure to support IGS integrates image acquisition, networks, presurgical planning, surgical navigation, and archival storage elements. This paper describes the principal components of an integrated IGS environment and an implementation in a large academic medical center. The IGS infrastructure is illustrated for practical applications in neurosurgical case examples.
ABSTRACT
In clinical surgery, there are frequent needs for communication between the house staff and the attending physician in an emergency situation. It's often insufficient for the house staff to make a decision through the information which is delivered in the form of only voice through the telephone line. To overcome the limitation of voice communication, we have designed an emergency teleradiology system which can be used for emergency surgical and medical decision making. The system can transmit the high quality images of CT, MRI, and other X-ray data using a PC attached to a modem through the conventional telephone line. Progressive transmission adopted in the system enables us to efficiently utilize the band-width of telephone line which is typically very low. The iterative residual coding/decoding algorithm compresses various medical images effectively, and thus fast-transmission of images date helps the house staff to perceive the status of emergent patient and make a fast and correct decision about the patient. The system also satisfies design requirements such as low-cost, ease of operation and interactive image communication including voice. 'Teleradiology system' proposed in this paper has been installed and operated in the emergency care unit of Severance Hospital, and as a result, it is effective in the emergency situations.