We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress hp
Sign In
Advertise with Us

Download Mobile App




AI Software Can Cut PET Scan Time in Half

By HospiMedica International staff writers
Posted on 27 May 2022

Recent research in PET has focused on decreasing noise and increasing signal-to-noise ratios (SNR). More...

Digital PET with silicon photomultipliers (SiPM) has led to improved timing, energy, spatial resolution, and effective time-of-flight (TOF) sensitivity. This has resulted in faster scanning with less injected activity. However, despite these advances, there is an ever-increasing demand for PET scans, which can contribute to significant delays in scheduling examinations and patient management. Deep learning (DL), a subdivision of artificial intelligence (AI), has many emerging applications in nuclear medicine. DL is able to increase PET resolution, decrease noise, and thus enhance image quality. It may allow for reducing injected activity, acquisition time, or a combination of both. Now, a new study that investigated whether AI-based denoising halves PET acquisition time in digital PET/CT has found that AI allows [18F]FDG PET duration in digital PET/CT to be halved, while restoring degraded ½-duration PET image quality.

The study by investigators at Baclesse Cancer Center (Caen, France) examined Subtle Medical, Inc.’s (Menlo Park, CA, USA) SubtlePET post-reconstruction PET denoising software that has been approved by the Food and Drug Administration and validated by the European Commission for [18F]FDG PET. The algorithm is based on deep convolutional neural networks (DCNN), the most common DL architecture. SubtlePET uses multi-slice 2.5D encoder-decoder U-Net DCNN. It takes the pixel’s neighborhood into account to reduce noise and increase image quality. Using a residual learning approach that is optimized for quantitative (L1 norm) and structural similarity (SSIM), it has learned to separate and suppress noise components while preserving non-noise components.

The software applies denoising to improve the image quality of low count PET (positron emission tomography) scans acquired in up to 25% of the original scan time, enabling centers to expedite patient care and improve patient comfort during PET exams. SubtlePET is FDA-cleared for use with 18F-FDG and 18F-Amyloid tracers and is CE-marked for use with 18F-FDG, 18F-Amyloid, 18F-Fluciclovine, 18F-DOPA, 18F-Choline, 18F-DCFPyL, Ga-68 Dotatate, and Ga-68 PSMA radiotracer PET images, expanding coverage for Prostate (PSMA) and Neuroendocrine tumors. The vendor-neutral software is a virtual upgrade to any brand of PET or PET/CT machine that boosts scanner performance across the entire fleet.

In the latest study, researchers aimed to evaluate the feasibility of halving PET acquisition time in a routine clinical setting by using SubtlePET while preserving visual and semi-quantitative PET performances in digital TOF PET/CT. The prospective study showed good visual and semi-quantitative performances of AI-denoised half-count PET compared to original PET in a digital PET/CT. The researchers simulated a two-fold reduction in the PET acquisition time and then applied SubtlePET. All PET series were successfully denoised within two minutes in an automatic workflow using a common GPU card. This makes it compatible with routine clinical use.

Visually, global image quality scores were similar between PET90 and PET45AI but lower and clinically insufficient in half-count PET45 due to high noise. The researchers obtained a few discordances (2.3%) between original PET90 and denoised PET45AI in the absolute detection of 856 lesions. The study findings support the routine use of Subtle PET combined with a two-fold faster PET acquisition. According to the researchers, the benefit of decreasing PET duration, thus reducing waiting time for appointments and helping patients who experience discomfort, outweighs the minor decrease in performance.

Related Links:
Baclesse Cancer Center 
Subtle Medical, Inc. 


Gold Member
SARS‑CoV‑2/Flu A/Flu B/RSV Sample-To-Answer Test
SARS‑CoV‑2/Flu A/Flu B/RSV Cartridge (CE-IVD)
Radiology Monitor
MDNC-6121 Barco Nio Color 5.8MP
Syringe Pump
SP50 Series
Fetal Monitor
BT-380
Read the full article by registering today, it's FREE! It's Free!
Register now for FREE to HospiMedica.com and get access to news and events that shape the world of Hospital Medicine.
  • Free digital version edition of HospiMedica International sent by email on regular basis
  • Free print version of HospiMedica International magazine (available only outside USA and Canada).
  • Free and unlimited access to back issues of HospiMedica International in digital format
  • Free HospiMedica International Newsletter sent every week containing the latest news
  • Free breaking news sent via email
  • Free access to Events Calendar
  • Free access to LinkXpress new product services
  • REGISTRATION IS FREE AND EASY!
Click here to Register








Channels

Artificial Intelligence

view channel
Image: Artificial intelligence (AI) standalone performance and reader performance with versus without AI assistance. (A) Receiver operating characteristics (ROC) curve for AI standalone performance in the US dataset (AUC 0.899, 95% CI 0.858 to 0.939). (B) ROC curve for AI standalone performance in the Korean dataset (AUC 0.963, 95% CI 0.946 to 0.975). (C) Pooled reader ROC without (AUC 0.718) versus with (AUC 0.852) AI assistance in the Korean dataset; P<0.001. AUC, area under the receiver operating characteristics curve. (Leonard Sunwoo et al., Journal of NeuroInterventional Surgery (2026). DOI: 10.1136/jnis-2026-025339)

AI Improves Non-Contrast CT Interpretation for Time-Sensitive Stroke Assessment

Acute ischemic stroke occurs when a blood vessel in the brain becomes blocked, requiring rapid diagnosis to enable timely reperfusion therapy. Emergency departments often use computed tomography angiography... Read more

Critical Care

view channel
Image Credit: Adobe Stock

Noninvasive Imaging Approach Aims to Detect Basal Cell Carcinoma Before It Becomes Visible

Basal cell carcinoma is the most common form of skin cancer and can damage nearby structures such as the nose or eyes when it develops on the face. Diagnosis typically depends on visible skin changes,... Read more

Surgical Techniques

view channel
Image: Associate Professor Menglin Chen studies how the light-sensitive nanoparticles affect living cells. The screen shows calcium being released inside a cell after nanoparticles taken up by the cell are exposed to blue light. Calcium plays an important role in cellular signaling, and the experiment helps the researchers understand how the nanoparticles can translate light into biological activity. (Photo courtesy of Aarhus University, Johanne Holm Jensen)

Light-Activated Nanoparticles May Offer New Approach to Retinal Prostheses

Retinitis pigmentosa is a degenerative retinal disorder in which photoreceptors progressively die, reducing visual signals to the brain while leaving surviving inner retinal circuits underused.... Read more

Point of Care

view channel
Image Credit: 123RF

Continuous Glucose Monitoring Identifies Cardiometabolic Risk in Adults Without Diabetes

Dysglycemia—abnormal blood glucose regulation—can fluctuate throughout the day and often escape conventional screening. Clinicians typically rely on fasting plasma glucose and hemoglobin A1c, which offer... Read more

Business

view channel
Image: LigaSure RAS Maryland, designed for the Valleylab FT10 platform on Hugo RAS, seals and cuts vessels, tissue, and lymphatics up to 7 mm in diameter (Photo courtesy of Medtronic)

Medtronic Receives FDA Clearance for Vessel-Sealing Instrument for Robotic Surgery

As robotic-assisted surgery expands across U.S. hospitals, teams increasingly seek energy instruments with the familiarity and performance of tools used in open and laparoscopic procedures.... Read more
Copyright © 2000-2026 Globetech Media. All rights reserved.