The high cost of network infrastructure and high-power computing systems has prevented the benefits of medical informatics from reaching far into developing nations. A group of radiologists at the Indiana University School of Medicine is attempting to change that situation for one hospital in western Kenya.
The high cost of network infrastructure and high-power computing systems has prevented the benefits of medical informatics from reaching far into developing nations. A group of radiologists at the Indiana University School of Medicine is attempting to change that situation for one hospital in western Kenya.
In January, the second iteration of a special Indiana University PACS/RIS, called ReferralPACS, was installed at the Moi Teaching and Referral Hospital, the teaching arm of Moi University School of Medicine, in Eldoret. The archive includes comparison studies, a teaching file, and a research database.
Two years ago, the university installed the initial version of ReferralPACS in the Moi Teaching radiology department, said Dr. Marc Kohli, senior chief resident of IU's radiology department. Kohli's group began digitizing the hospital's film studies with a lightbox and digital camera mounted on a tripod. Photos were then combined with demographic data and entered into an Access database for later retrieval. During those two years, more than 4000 studies were archived. The Access database also gave the user the option of automatically sending an e-mail consult with the images attached for further review by IU faculty.
The new version of ReferralPACS is a client-server model written in Ruby-On-Rails (http://www.rubyonrails.org/), an open-source web framework language optimized for programmer productivity. The implementation is documented in the 2006 Proceedings of the American Medical Informatics Association (AMIA Annu Symp Proc 2006:988).
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.