- AI
- Molecular Imaging
- CT
- X-Ray
- Ultrasound
- MRI
- Facility Management
- Mammography
GE’s Centricity RIS gets smart
Radiology reporting on the GE Healthcare Centricity RIS just got smarter with an intelligent algorithm that senses when dictated cases don’t sound right. This “thought checker,” scheduled to begin routine shipment by the end of this year as an upgrade to the Centricity RIS-IC Reporting module, uses the context of reports to identify possible errors. The program, for example, might question whether the radiologist meant “left occipital lobe” rather than “right” by highlighting the directional term in blue. Or it might insert a red bar at a point where certain information needs to be added.
Radiology reporting on the GE Healthcare Centricity RIS just got smarter with an intelligent algorithm that senses when dictated cases don't sound right. This "thought checker," scheduled to begin routine shipment by the end of this year as an upgrade to the Centricity RIS-IC Reporting module, uses the context of reports to identify possible errors. The program, for example, might question whether the radiologist meant "left occipital lobe" rather than "right" by highlighting the directional term in blue. Or it might insert a red bar at a point where certain information needs to be added.
"It understands the concept of left and right and the need for certain measurements," said Michael Mast, GE senior manager of commercial marketing in the imaging integrated IT business unit. "It serves as an extra check in that it gives the radiologist a chance to clarify some points in a report."
GE showcased the advanced speech capability, and the partnership with M*Modal that made it possible, at the Society for Imaging Informatics in Medicine (SIIM) meeting. The new partner's AnyModal Conversational Documentation Services combines speech recognition and natural language to interpret the meaning of dictated reports and then identify possible errors. Among the other features included in the M*Modal technology are rules-based multiorganizational scheduling, patient and image tracking, multiple diagnostic reporting options, and outcome monitoring. An integrated mammography administration module further extends clinical utility.
GE is framing the availability of this new technology as accelerating the adoption of structured reporting in radiology by making automation a trusted part of the reporting workflow. M*Modal's technology first transforms spoken dictation into a draft report, then structures and encodes the recognized speech into a document format chosen by the user.
"The radiologist can send it to draft, to transcription, or to signature cue, based on [his or her] confidence in the report," Mast said.
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.
