Stand-alone AI can reduce radiologists’ screening mammography workloads by 90%
Stand-alone AI technology could help ease radiologist workloads by interpreting screening mammograms. Research published in Radiology this week proved the technology’s sensitivity is non-inferior when applied to digital mammography.
Screening mammograms, the majority of which are truly negative, account for a significant portion of radiologists’ workload. These mountainous lists, unfortunately, have become more burdensome with the staffing shortages many radiology departments now face. Consequently, screening mammograms, which are indispensable for women, could take a back seat to more acutely urgent exams.
One possible solution for this issue is the implementation of artificial intelligence. As technology has advanced, research has demonstrated AI’s comparability to radiologists’ readings in many exams. It has produced particularly noteworthy findings in studies pertaining to digital mammography (DM) and digital breast tomosynthesis (DBT), which could prove to be valuable in alleviating workload burdens.
“Use of AI as the only stand-alone reader of screening studies could be a cost-effective approach by removing all the workload of reading screening findings, allowing radiologists to focus on only the AI-recalled findings,” corresponding author, Sara Romero-Martin, from the Department of Radiology at Hospital Universitario Reina Sofía, and co-authors explained.
In their retrospective examination of 15,999 DM and DBT exams, AI achieved non-inferior sensitivity compared to radiologists for both DM and DBT. In DM exams, the recall rate was reduced by 2%, though it did increase for DBT exams by up to 12%.
Though the recall rates for DBT exams increased with stand-alone AI, the authors note that the technology could still be utilized as an initial reading tool if radiologists circle back to the exams that AI flags for recall. This would still result in a reduction of workload.
“AI could be used as a pre-selection tool to determine which examinations are likely normal and could be read by fewer radiologists, leading to a screening workload reduction of between 70% and 90%,” the authors suggested.
The results of the study are promising, however, the authors cautioned that additional prospective studies containing more heterogeneous data are needed to substantiate the findings.
You can view the full results in Radiology.
Related Breast Imaging Technology Content:
DBT plus synthesized mammography drops patients’ dosage without losing imaging quality
3D mammography approaching 50% of breast imaging systems in the US
Ultrasound alone detects 92% of breast cancers recalled on DBT exams
Breast MRI screening cuts cancer mortality rates in half for women with lesser-known gene mutations
DBT spot compression views increase reader accuracy
Digital breast tomosynthesis outperforms DM at detecting malignancy in developing asymmetries
AI drops DBT workloads for radiologists by 40% while also reducing recalls
Less experienced radiologists are more susceptible to fatigue when reading DBT exams
Imaging center has credentials revoked following ‘severe’ issues with mammography screening
Q&A: Should COVID vaccinated patients delay getting breast imaging — new study says no
In addition to her background in journalism, Hannah also has patient-facing experience in clinical settings, having spent more than 12 years working as a registered rad tech. She joined Innovate Healthcare in 2021 and has since put her unique expertise to use in her editorial role with Health Imaging.