The categorization of medical photographs poses considerable difficulties owing to noise, uncertainty, and ambiguous information. Conventional deep learning models frequently encounter difficulties in addressing this issue, resulting in diminished diagnostic precision, particularly in the context of low-quality or ambiguous situations. This work presents a hybrid methodology that combines Neutrosophic Set (NS) theory with deep learning models to improvemagnetic resonance imaging(MRI)picture classification in uncertain settings. NS theory delineates three domains: True (T), Indeterminate (I)and False (F) to address picture uncertainty and noise, hence enhancing deep learning models' capacity to analyze complex, ambiguous visual data. To assess the methodology, four advanced deep learning models MobileNet, VGG16, DenseNet121and InceptionV3 were employed, and their efficacy was analyzed on brain tumormedical image datasets. The findings demonstrate that models trained on NS-transformed data, especially DenseNet and inception, produce enhanced results relative to those trained on the originaldata, attaining notably higher accuracy, precision, and recall. This illustrates that integratingNS theory into deep learning models markedly improves their capacity to categorize uncertain and noisy MRIpictures, offering a reliable method for enhancing diagnostic accuracy in medical imaging.