Researchers involved in a large multicenter trial have combined readily available technology with a customized data collection and reporting process that has enabled them to minimize costs while reading the studies in a timely manner. The technology and expertise used can be adapted to just about any clinical research study with digital imaging requirements, according to a scientific paper presented at the Society for Imaging Informatics in Medicine meeting in Providence.
Researchers involved in a large multicenter trial have combined readily available technology with a customized data collection and reporting process that has enabled them to minimize costs while reading the studies in a timely manner. The technology and expertise used can be adapted to just about any clinical research study with digital imaging requirements, according to a scientific paper presented at the Society for Imaging Informatics in Medicine meeting in Providence.
Bruce A. Vendt, MBA, and colleagues at the Electronic Radiology Laboratory of Mallinckrodt Institute of Radiology in St. Louis needed to implement an efficient and effective process to collect images for the Silent Cerebral Infarct Transfusion Trial (SITT), an intervention trial that randomized children with sickle cell anemia to receive blood transfusions or be observed for three years.
MRI studies from the more than 1800 children came from 28 participating clinical sites in the U.S., Canada, the U.K., and France. Three neuroradiologists at separate institutions reviewed the screening MR images to determine the presence of silent cerebral infarct-like lesions. Their findings were placed on web-based case report forms and sent to a statistical coordinating center as well as a neurology committee.
Two hundred children were ultimately accepted into the trial. Once accepted, patients will receive another MRI prior to randomization and another MRI three years later.
Results of the screening MRI studies had to be quickly disseminated in order to transition the eligible subjects into the randomization phase of the trial. The solution was to equip each site with two software programs to transmit the MRI images electronically back to the core processing site in St. Louis. The first program was Cisco Systems' commercially available VPN Client, which allows the images to be encrypted and sent over the Internet.
The second software program, the Clinical Studies Workstation (CSW) program, is Windows-based and was previously developed at Mallinckrodt to transmit images for clinical trials. It receives DICOM studies directly from a modality/PACS or a CD-ROM. It allows the user to remove protected health information and replace it with unique study identifiers and then transmit the study to a DICOM receiver over the Internet using a secure VPN connection.
Vendt emphasized that the CSW program is a well-tested and easy-to-use software package that has been successfully applied in three major clinical trials.
The image viewing requirement of the trial dictated a system that would allow the individual radiologists to view the studies and make precise measurements, allow the radiology panel to access each member's findings to help arrive at a consensus position, and allow the study neurologists and other study personnel to view the images and the neuroradiologists' findings.
The system also required that the neurologists be able to simultaneously view a patient study and previous studies for the same patient in order to determine possible changes in infarct-like lesions.
Because the trial was not using a RIS to enter patient information, the system also had to accept studies without the usual patient registration and processing.
Researchers chose the Philips iSite PACS, whose iSite/Radiology thin-client server module provided the radiology panel with a full-feature program to read studies, Vendt said. The iSite/Enterprise module allowed the neurology committee easy access to the studies over the Internet. The iSuite system administrator's module allowed Electronic Radiology Laboratory personnel to serve as PACS administrators with minimal training.
"Philips iSite has proven to be well suited to the clinical research environment with its limited patient demographics and high degree of measurement accuracy," he said.
The clinical sites can transmit the images to the lab in St. Louis almost immediately after the study is completed. The average time for the three neuroradiologists to review the image and send back their findings is two days. Turnaround time depends on radiologists completing the case report forms. Lab staff closely monitor the completion of case report forms and quickly notify the clinical sites when at least two of the radiologists have reached identical findings.
Collecting and viewing complex MRI studies of the brain from a large patient population is in itself a challenge, Vendt said. Using some available technologies and customizing others can significantly improve data collection, transmission, and processing.
Deep Learning Detection of Mammography Abnormalities: What a New Study Reveals
June 19th 2023In multiple mammography datasets with the original radiologist-detected abnormality removed, deep learning detection of breast cancer had an average area under the curve (AUC) of 87 percent and an accuracy rate of 83 percent, according to research presented at the recent Society for Imaging Informatics in Medicine (SIIM) conference.
Detecting Intracranial Hemorrhages: Can an Emerging AI Advance Have an Impact?
June 9th 2022A 3D whole brain convolutional neural network could provide enhanced sensitivity and specificity for diagnosing intracranial hemorrhages on computed tomography, according to new research presented at the Society for Imaging Informatics in Medicine (SIIM) conference in Kissimmee, Fla.