Introduction: The interpretation of total volume of disease in PET may help with decision-making in mCRPC? AI could quantify all the lesions, measuring the total tumor volume and the percentage of increase or response. Human specialists have a subjective interpretation
The objective of this study its to compare the PET interpretation by AI vs Human Specialists
Methods: A survey on QUESTIONPRO platform was released through various digital channels. The survey gathered the following parameters:
Specialists’ year of experience ( < 5 , 5 -10, 10-20, > 20 ) interpretation of 3 clinical cases of real mCRPC patients (BASAL PET and FOLLOW-UP PET after a treatment) The human expert had to identify the response percentage (0-100%).
The participants were consulted the following: If the quantification of basal and follow-up tumor volume, would impact their decision-making? If would they consider referring the patient to an organization which is able to prepare their patient’s tumor response?
The platform MIM Software Encore was used for the quantification of tumor volume through AI. The programming staff developed a workflow that divides the skeletal system, recognizing the structures to be analyzed in PET Coline studies.
Results: The virtual survey were completed by 134 to specialists of multiple LATAM countries (Argentina, Mexico, Brazil, Guatemala, Honduras, Nicaragua, Panama, Cuba, Dominican Republic, Venezuela, Colombia, Ecuador, Peru, Bolivia, Chile, Paraguay ,Uruguay) USA and Spain.
As for the years of experience, the participants were divided as follows: ( < 5: 13.97%; 5-10: 24.58%; 10-20: 30.73 %; > 20: 30.73 %)
The analysis of the statistical significance shows superiority of AI (Case 1: p < 0.001 Case 2: p < 0.001 Case 3: p < 0.005) 83% of the participants considered that AI does contribute to their decision-making.
Conclusions: Measuring the total tumor volume with the AI model generated significantly greater results than the ones provided by experts interpretation, regardless of their years of experience. Specialists consider that the implementation of the AI model in the PET/CT is essential and generates impact on their decision-making.
.jpg)
.jpg)
