In a video interview, Hong Song, M.D., Ph.D., discussed retrospective research, presented at the recent Society for Nuclear Medicine and Molecular Imaging (SNMMI) conference, that evaluated the combination of artificial intelligence (AI)-based software and the PSMA agent piflufolastat F 18 to help quantify prostate cancer lesions and associations with biochemical progression-free survival.
Manual assessments of prostate specific membrane antigen (PSMA) scoring and measures such as standardized uptake value (SUV) mean and maximum SUV (SUVmax) on positron emission tomography (PET) scans can be tedious and are not always accurate, noted Hong Song, M.D., Ph.D., in a recent interview.
With this in mind, Dr. Song and colleagues recently evaluated the combination of aPROMISE software (PYLARIFY AI, Exini Diagnostics AB/Lantheus Holdings), an FDA-cleared deep learning platform for quantitative assessment of PSMA PET/CT images, and piflufostat F 18 (PYLARIFY®, Lantheus Holdings) to assess 69 patients with prostate cancer recurrence and the impact of quantitative measures upon subsequent biochemical progression-free survival.
In some of the findings from the study, presented at the recent Society for Nuclear Medicine and Molecular Imaging (SNMMI) conference, the researchers noted that higher PSMA-avid total tumor volume (PSMAAttv) and a higher aPSMA score for bone metastases were both associated with shorter biochemical progression-free survival in patients with prostate cancer.
(Editor’s note: For related content, see “Recurrent Prostate Cancer and Low PSA Levels: Can an Emerging PSMA PET Agent Have an Impact?,” “Emerging PET Radiotracer May Offer Multiple Advantages in Detecting Prostate Cancer” and “Can Pre-Op MRI Staging Help Predict Prostate Cancer Recurrence After a Prostatectomy?”)
“There are quantitative tools now that are readily available to help us have this prognostic evaluation of (patients) who may be at high risk for subsequent progression (of prostate cancer and) should be followed more closely. … There is more information than meets the eye in the scan that we can now quantify and extract,” emphasized Dr. Song, an assistant professor of radiology (nuclear medicine) at Stanford University.
For more insights from Dr. Song, watch the video below.
Study of Ofatumumab for Multiple Sclerosis Shows 'Profoundly Suppressed MRI Lesion Activity'
April 17th 2024The use of continuous ofatumumab in patients within three years of a relapsing multiple sclerosis diagnosis led to substantial reductions in associated lesions on brain MRI scans, according to research recently presented at the American Academy of Neurology (AAN) conference.
Could a Deep Learning Model for Mammography Improve Prediction of DCIS and Invasive Breast Cancer?
April 15th 2024Artificial intelligence (AI) assessment of mammography images may significantly enhance the prediction of invasive breast cancer and ductal carcinoma in situ (DCIS) in women with breast cancer, according to new research presented at the Society for Breast Imaging (SBI) conference.
Interventional Radiology Study Shows Low Breast Cancer Recurrence 16 Months After Cryoablation
March 29th 2024In a cohort of patients with invasive breast cancer and tumor sizes ranging between 0.3 to 9 cm, image-guided cryoablation was associated with a 10 percent recurrence rate at 16 months, according to research recently presented at the Society of Interventional Radiology (SIR) conference.
Emerging Insights on MRI-Guided Transurethral Ultrasound Ablation for Prostate Cancer
March 21st 2024For men with prostate cancer, the use of MRI-guided transurethral ultrasound ablation (TULSA) led to a 92 percent decrease in median prostate volume at one year, according to new research recently presented at Society of Interventional Radiology (SIR) conference.
Could Cloud-Based 'Progressive Loading' be a Boon for Radiology Workflows?
March 13th 2024The newly launched Progressive Loading feature, available through RamSoft’s OmegaAI software, reportedly offers radiologist rapid uploading of images that is faster than on-site networks and other cloud-based systems regardless of the network radiologists are using.
ECR Study Finds Mixed Results with AI on Breast Ultrasound
March 6th 2024While adjunctive use of AI led to significantly higher specificity and accuracy rates in detecting cancer on breast ultrasound exams in comparison to unassisted reading by breast radiologists, researchers noted that 12 of 13 BI-RADS 3 lesions upgraded by AI were ultimately benign, according to research presented at the European Congress of Radiology.