Enhanced CNN-Based Decision Support Framework for Gastrointestinal Neuroendocrine Tumors using Inception-Resnet-V2

This research addresses the challenge of providing accurate decision support for Gastrointestinal Neuroendocrine Tumors (GI NETs) by introducing a novel Inception-ResNet-v2 enhanced CNN-based framework. There are currently no all-inclusive systems that successfully combine genetic, imaging, and clinical data. The Inception-ResNet-v2 model, which is well-known for its feature extraction capabilities, is used in our proposed system to bridge this gap by integrating various modalities into a single architecture. Due to GI NETs' intrinsic complexity, a nuanced approach is required, and our solution outperforms the current techniques. In terms of accuracy, precision, recall, and F1 score, our model routinely surpasses previous studies in comparison evaluations. The model outperforms previous research with impressive results: 92% accuracy, 94% precision, 91% recall, and 92% F1 score. The confusion matrix shows that the model can produce more accurate classifications, with less false positives and negatives. Not only does this study present a state-of-the-art decision support framework, but it also proven its worth by comparing it to existing standards in great detail. This model has the potential to be a game-changer in the field of precision medicine, according to the outcomes that have been shown. It will help us better understand and treat gastrointestinal NETs, which is a complex condition.