Extravasation or partial extravasation of the radiopharmaceutical dose quality in positron emission tomography (PET) can undermine standard uptake value (SUV) and image quality. A topical sensor (Lara) has been validated using a number of metrics to characterise injection quality following manual injection. An assessment of the performance of these metrics for autoinjector administration has been undertaken. Methods: A single site, single PET/CT scanner was used to characterise injections using a KARL100 autoinjector with standardised apparatus, flush volume and infusion rate using Rad-inject pump (1 min infusion followed by 2 syringe flushes) for 18F-FDG, 68Ga-PSMA and 68Ga-DOTATATE. 296 patients with topical application of Lara sensors were retrospectively analysed using conventional statistical analysis and an artificial neural network. Results: Partial extravasation was noted in 1.1% of studies with 9.1% (inclusive of partial extravasation) identified to have an injection anomaly (eg. venous retention). Extravasation was independently predicted by the time elapsed as the counts recorded by the injection sensor fall from the maximum value to within 200% of the reference sensor counts (tc50) greater than 1200 seconds, the difference in counts for injection and reference sensors, normalized by dose, from 4 minutes post injection (ndAvgN) greater than 25, and the ratio of the average counts per second recorded by the injection sensor at the end of a monitoring period to those of the reference sensor (CEnd ratio) greater than 2. Conclusion: Extravasation and partial extravasation of PET doses are readily detected and differentiated using TAC metrics. The metrics can provide the insights that could inform image quality or SUV accuracy issues. Further validation of key metrics are recommended in a larger and more diverse cohort.