Using the Internet as part of an image-based lung cancer screening program could facilitate the process by increasing the number of radiologists who can read the images, according to an exhibit at last year's RSNA meeting. One of the problems in using
Using the Internet as part of an image-based lung cancer screening program could facilitate the process by increasing the number of radiologists who can read the images, according to an exhibit at last year's RSNA meeting.
One of the problems in using spiral CT for lung cancer screening is a shortage of radiologists to read the images, said Kaori Fujimura of NTT Cyber Solutions Laboratories in Tokyo. Fujimura presented a solution in an infoRAD exhibit.
"We developed a client-server system for reading lung cancer screening images over the Internet," Fujimura said.
The system consists of data entry terminals, database server, computer-aided detection systems, and reading terminals. Interview data and medical images are registered by the operator of the data entry terminal and sent to the DB server, which distributes them to the CAD systems and the reading terminals.
If opinions differ among radiologists interpreting the images, a conference is held to resolve the issue before reports are completed. The DB server collects the doctors' reports and returns them to the entry terminal.
A five-point protocol maintains security of data transmitted over the Internet:
1.Virtual private network is employed
2.Patient information is anonymous
3.DICOM data are encrypted separately
4.Data are decrypted only after user authentication
5.Data are saved only in the main memory of the reading terminals
The reading system also features collaboration and videoconferencing functions. During a collaborative reading, images delivered beforehand are synchronously displayed at different terminals.
"We developed a collaborative function," Fujimura said. "In conjunction with a videoconference facility, this function enables radiologists are different locations to perform collaborative diagnoses by reading exactly the same images."
MRI-Based AI Radiomics Model Offers 'Robust' Prediction of Perineural Invasion in Prostate Cancer
July 26th 2024A model that combines MRI-based deep learning radiomics and clinical factors demonstrated an 84.8 percent ROC AUC and a 92.6 percent precision-recall AUC for predicting perineural invasion in prostate cancer cases.
Breast MRI Study Examines Common Factors with False Negatives and False Positives
July 24th 2024The absence of ipsilateral breast hypervascularity is three times more likely to be associated with false-negative findings on breast MRI and non-mass enhancement lesions have a 4.5-fold likelihood of being linked to false-positive results, according to new research.
Can Polyenergetic Reconstruction Help Resolve Streak Artifacts in Photon Counting CT?
July 22nd 2024New research looking at photon-counting computed tomography (PCCT) demonstrated significantly reduced variation and tracheal air density attenuation with polyenergetic reconstruction in contrast to monoenergetic reconstruction on chest CT.