The artificial intelligence (AI)-powered module provides a prostate segmentation tool for MRI-guided transurethral ultrasound ablation (TULSA) procedures in patients with prostate cancer.
Reportedly built on over 24 million parameters drawn from nearly 7,500 training images, the artificial intelligence (AI) module Contouring Assistant has garnered 510(k) clearance from the Food and Drug Administration (FDA) for use in MRI-guided transurethral ultrasound ablation (TULSA) procedures in patients with prostate cancer.
Utilized in conjunction with Profound Medical’s TULSA-PRO system, the Contouring Assistant module offers machine learning-based segmentation of the prostate to facilitate targeted ablation of diseased tissue.
Utilized in conjunction with Profound Medical’s TULSA-PRO system (shown above), the recently FDA-cleared Contouring Assistant module provides machine-learning based prostate segmentation, which was found to be non-inferior to contouring done by leading prostate radiologists, according to Profound Medical, the manufacturer of the Contouring Assistant module. (Image courtesy of Profound Medical.)
Profound Medical noted that the Contouring Assistant module was developed with a reference standard that combined contours from leading prostate radiologists Steven Raman, M.D., Robert Princethal, M.D., and Edward Steiner, M.D. Subsequent research evaluating the stand-alone capability of Contouring Assistant in 100 prostate cancer cases found it was non-inferior to the aforementioned reference standard, according to Profound Medical.
The company also noted that additional testing of the Contouring Assistant module by three urologists demonstrated a 32 percent reduction in the time it took to complete prostate segmentation.
“ … (Contouring) Assistant not only allowed my esteemed urologist colleagues and I to approach the accuracy of an expert radiologist reader in our TULSA treatment designs, but also enabled us to reduce overall procedure times by one-third,” noted Preston Sprenkle, M.D., an associate professor of urology at the Yale School of Medicine in New Haven, Ct.
MRI-Based AI Radiomics Model Offers 'Robust' Prediction of Perineural Invasion in Prostate Cancer
July 26th 2024A model that combines MRI-based deep learning radiomics and clinical factors demonstrated an 84.8 percent ROC AUC and a 92.6 percent precision-recall AUC for predicting perineural invasion in prostate cancer cases.
Systematic Review: PET/MRI May be More Advantageous than PET/CT in Cancer Imaging
July 18th 2024While PET/MRI and PET/CT had comparable sensitivity for patient-level regional nodal metastases and lesion-level recurrence, the authors of a systematic review noted that PET/MRI had significantly higher accuracy in breast cancer and colorectal cancer staging.