Journal of nuclear medicine : official publication, Society of Nuclear Medicine
-
Despite the great media attention for artificial intelligence (AI), for many health care professionals the term and the functioning of AI remain a "black box," leading to exaggerated expectations on the one hand and unfounded fears on the other. In this review, we provide a conceptual classification and a brief summary of the technical fundamentals of AI. ⋯ The main limitations of current AI techniques, such as issues with interpretability or the need for large amounts of annotated data, are briefly addressed. Finally, we highlight the possible impact of AI on the nuclear medicine profession, the associated challenges and, last but not least, the opportunities.
-
Our purpose was to assess whether the addition of data from multiparametric pelvic MRI (mpMR) and whole-body MRI (wbMR) to the interpretation of 18F-fluoromethylcholine (18F-FCH) or 68Ga-HBED-CC PSMA-11 (68Ga-PSMA) PET/CT (=PET) improves the detection of local tumor recurrence or of nodal and distant metastases in patients after radical prostatectomy with biochemical failure. Methods: The current analysis was performed as part of a prospective, multicenter trial on 18F-FCH or 68Ga-PSMA PET, mpMR, and wbMR. Eligible men had an elevated level of prostate-specific antigen (PSA) (>0.2 ng/mL) and high-risk features (Gleason score > 7, PSA doubling time < 10 mo, or PSA > 1.0 ng/mL) with negative or equivocal conventional imaging results. ⋯ Compared with the composite reference standard for the detection of disease beyond the prostatic fossa, PET/wbMR, PET, and wbMR had sensitivity of 50%, 50%, and 8.3%, respectively, and specificity of 97.1%, 97.1%, and 94.1%, respectively. Conclusion: Interpretation of PET/mpMR resulted in a higher detection rate for local tumor recurrence in the prostatic bed in men with biochemical failure after radical prostatectomy. However, the addition of wbMR to 18F-FCH or 68Ga-PSMA PET did not improve detection of regional or distant metastases.