General medical evaluation of the tests.

This paper proposes the use of artificial intelligence techniques, specifically the nnU-Net convolutional neural network, to improve the identification of left ventricular walls in images of myocardial perfusion scintigraphy, with the objective of improving the diagnosis and treatment of coronary artery disease. The methodology included data collection in a clinical environment, followed by data preparation and analysis using the 3D Slicer Platform for manual segmentation, and subsequently, the application of artificial intelligence models for automated segmentation, focusing on the efficiency of identifying the walls of the left ventricular. A total of 83 clinical routine exams were collected, each exam containing 50 slices, which is 4,150 images. The results demonstrate the efficiency of the proposed artificial intelligence model, with a Dice coefficient of 87% and an average Intersection over Union of 0.8, reflecting high agreement with the manual segmentations produced by experts and surpassing traditional interpretation methods. The internal and external validation of the model corroborates its future applicability in real clinical scenarios, offering a new perspective in the analysis of myocardial perfusion scintigraphy images. The integration of artificial intelligence into the process of analyzing myocardial perfusion scintigraphy images represents a significant advancement in diagnostic accuracy, promoting substantial improvements in the interpretation of medical images, and establishing a foundation for future research and clinical applications, such as artifact correction.