An organ transplant patient lies anesthetized on the operating table at the Istituto Mediterraneo per i Trapianti e Terapie ad Alta Specializzazione, or ISMETT (Mediterranean Institute of Transplantation and Advanced Specialized Therapies) in Palermo,
An organ transplant patient lies anesthetized on the operating table at the Istituto Mediterraneo per i Trapianti e Terapie ad Alta Specializzazione, or ISMETT (Mediterranean Institute of Transplantation and Advanced Specialized Therapies) in Palermo, Sicily. The transplant team waits for the pathologist's report, which will determine if and how organ rejection is to be treated by the team.
Working alone to make the sometimes tricky rejection diagnosis, ISMETT pathologist Dr. Marta Ida Minervini decides to enlist the aid of a telepathology system that provides real-time consultation from transplant pathologists located 4500 miles away at the University of Pittsburgh Medical Center (il Centro Medico dell'Universita di Pittsburgh).
The system, developed by UPMC, helps her avoid misdiagnoses, thus improving outcomes.
"Initially, I was skeptical, but the system has turned out to be much more useful than anticipated," said Dr. Anthony J. Demetris, director of transplant pathology at UPMC, who helped conceive and develop the system.
The client-server application uses a store-and-forward format with static images. A Java client on the Palermo pathologist's workstation works with the application server and database in Pittsburgh. Images and text are captured within the application, which manages all communications.
"We can render an opinion on cases anywhere in the world in a matter of minutes or hours," Demetris said.
The standard method of sending glass slides and/or tissue blocks can take days or weeks.
UPMC is an apt site for expert pathology consults. Surgeons there have performed more than 11,000 organ transplants, more than any other single center in the world. In the past two years, more than 150 cases have been reviewed using telepathology.
The system was developed in-house by UPMC to meet the specific requirements of transplant pathologists. Available 24/7, it allows for real-time chat. The system automatically pages Pittsburgh pathologists when a new case is submitted by ISMETT.
Since organ transplants can occur at any time of the day, it is not unusual for the five Pittsburgh pathologists to be paged in the middle of the night. The home of each pathologist is equipped with computers and monitors upgraded to display images at high resolution.
The system uses 640 x 480 (24-bit) color images. Cases typically generate between three and 20 images, each about 1 MB.
A private IP (Internet protocol) 33K bandwidth network is established between the ISMETT and UPMC firewalls, soon to be upgraded to a VPN (virtual private network). Secure DSL (digital subscriber line) or ISDN (integrated services digital network) lines link UPMC to pathologists' homes, said Dr. John R. Gilbertson, an assistant professor of pathology informatics at UPMC.
The principal disadvantages of static store-and-forward telepathology systems are thought to be field selection, interpretation, and image quality, Demetris said.
"We haven't encountered these problems to any serious extent, however, except for image quality, a problem that has been corrected by image editing software," he said.
UPMC has installed a similar telepathology link to the University of Kyushu in Fukuoka, Japan, to support the liver transplant program there. Plans to collaborate with another transplant center in India are in the works.
Can AI Bolster Breast Cancer Detection in DBT Screening?
January 16th 2025In sequential breast cancer screening with digital breast tomosynthesis (DBT), true positive examinations had more than double the AI case score of true negative examinations and the highest positive AI score changes from previous exams, according to new research.
CT Study Reveals Key Indicators for Angiolymphatic Invasion in Non-Small Cell Lung Cancer
January 15th 2025In computed tomography (CT) scans for patients with solid non-small cell lung cancer (NSCLC) < 30 mm, emerging research suggests the lollipop sign is associated with a greater than fourfold likelihood of angiolymphatic invasion.
Can MRI-Based AI Enhance Risk Stratification in Prostate Cancer?
January 13th 2025Employing baseline MRI and clinical data, an emerging deep learning model was 32 percent more likely to predict the progression of low-risk prostate cancer (PCa) to clinically significant prostate cancer (csPCa), according to new research.