Can Deep Learning Provide a CT-Less Alternative for Attenuation Compensation with SPECT MPI?
In a recent interview, Abhinav K. Jha, Ph.D., discussed key challenges with the use of SPECT MRI and how an emerging deep learning model may facilitate attenuation compensation without the need for an additional computed tomography (CT) scan.
While single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) is well validated for the detection of coronary artery disease (CAD) and other cardiovascular abnormalities, there is a degrading effect with attenuation that requires an additional computed tomography (CT) scan to address attenuation compensation.
However, in a recent interview, Abhinav Kumar Jha, Ph.D, noted there are a large number of SPECT scanners that do not have the CT component and this issue is particularly prevalent in community hospitals and rural facilities. Dr. Jha says this problem is compounded as studies have demonstrated a higher prevalence of heart disease in rural health-care settings.
Dr. Jha pointed out that 75 percent of SPECT MPI exams are performed without attenuation compensation and cites a survey of nuclear cardiology providers that found only 5.6 percent provided CT-based attenuation correction.
“Therefore, you can imagine there's a very important need for a large segment of the patient population to have access to this technology of attenuation correction without being able to take a CT scan,” noted Dr. Jha, an associate professor of biomedical engineering and radiology at the Washington University School of Medicine in St. Louis.
However, in recently published research, Dr. Jha and other researchers developed a deep learning technique that provides CT-less (dubbed CTLESS) attenuation compensation. With this research and other studies, Dr. Jha said the CTLESS approach has provided consistent performance across scanner models and patients with different degrees of heart disease.
While acknowledging that more studies are needed to validate the technology, Dr. Jha noted the CTLESS approach has potential to bolster access to SPECT MPI.
“I'm excited about the CTLESS technology (and) making the process of attenuation compensation more accessible, affordable as well as safe,” emphasized Dr. Jha.
(Editor’s note: For related content, see “Assessing MACE Risk in Women: Can an Emerging Model with SPECT MPI Imaging Have an Impact?,” “Radiology ‘Game-Changer’: FDA Approves PET Agent for Enhanced Detection of Coronary Artery Disease” and “Study Shows Merits of CTA-Derived Quantitative Flow Ratio in Predicting MACE.”)
For more insights from Dr. Jha, watch the video below.
Can CT-Based Deep Learning Bolster Prognostic Assessments of Ground-Glass Nodules?
June 19th 2025Emerging research shows that a multiple time-series deep learning model assessment of CT images provides 20 percent higher sensitivity than a delta radiomic model and 56 percent higher sensitivity than a clinical model for prognostic evaluation of ground-glass nodules.
Multinational Study Reaffirms Value of Adjunctive AI for Prostate MRI
June 16th 2025The use of adjunctive AI in biparametric prostate MRI exams led to 3.3 percent and 3.4 percent increases in the AUC and specificity, respectively, for clinically significant prostate cancer (csPCa) in a 360-person cohort drawn from 53 facilities.
