The paper introduces an Adaptive Convolutional Autoencoder-based Snow Avalanches (ACAЕ-SA) algorithm for the detection and classification of brain tumors from MRI images. The authors address the limitations of manual detection by radiologists, such as errors and lack of accuracy, and propose an automated technique to enhance the diagnostic process. The ACAЕ-SA algorithm combines an Adaptive CNN component and an Autoencoder to improve detection and classification performance. The Snow Avalanches algorithm is integrated to optimize computational complexities. The effectiveness of the proposed technique is validated using two MRI datasets, figshare and BraTS 2018, demonstrating superior performance compared to state-of-the-art techniques. The paper also reviews existing methods and highlights the challenges in brain tumor detection, emphasizing the need for more efficient and accurate automated systems.The paper introduces an Adaptive Convolutional Autoencoder-based Snow Avalanches (ACAЕ-SA) algorithm for the detection and classification of brain tumors from MRI images. The authors address the limitations of manual detection by radiologists, such as errors and lack of accuracy, and propose an automated technique to enhance the diagnostic process. The ACAЕ-SA algorithm combines an Adaptive CNN component and an Autoencoder to improve detection and classification performance. The Snow Avalanches algorithm is integrated to optimize computational complexities. The effectiveness of the proposed technique is validated using two MRI datasets, figshare and BraTS 2018, demonstrating superior performance compared to state-of-the-art techniques. The paper also reviews existing methods and highlights the challenges in brain tumor detection, emphasizing the need for more efficient and accurate automated systems.