This paper proposes an Adaptive Convolutional Autoencoder-based Snow Avalanches (ACAE-SA) algorithm for the detection and classification of brain tumors from MRI images. The algorithm integrates an adaptive CNN and an autoencoder to detect and classify brain tumors. To address computational complexities, the Snow Avalanches algorithm is used as an optimization technique. The proposed method is validated using two MRI datasets: figshare and BraTS 2018. The ACAE-SA algorithm demonstrates superior performance in detecting and classifying brain tumors compared to existing techniques. Brain tumors are abnormal growths of brain cells that can lead to cancer. Gliomas are the most common type of brain tumor, arising from the transformation of glial cells in the brain and spinal cord. MRI is a commonly used technique for detecting brain tumors, as it provides detailed images of brain tissues. However, manual detection by radiologists is error-prone and less accurate. Therefore, computer-aided diagnostic techniques are needed to improve the accuracy of brain tumor detection. Deep learning has significantly advanced the detection and classification of brain tumors. Machine learning techniques, particularly deep learning, have enabled the identification of complex patterns in medical images. AI-based approaches have also been employed to enhance the diagnosis of brain tumors, including precise delineation of tumor volume and genotype. However, existing methods face challenges such as lack of rotational invariance and loss of high-range component linkages. The ACAE-SA algorithm addresses these challenges by combining adaptive CNN and autoencoder techniques with the Snow Avalanches algorithm for optimization. This novel architecture improves the detection and classification accuracy of brain tumors. The algorithm is evaluated using performance metrics, graphical representations, and comparative analysis. The results demonstrate the effectiveness of the ACAE-SA algorithm in detecting and classifying brain tumors from MRI images. The paper concludes with future work and recommendations for further research in this area.This paper proposes an Adaptive Convolutional Autoencoder-based Snow Avalanches (ACAE-SA) algorithm for the detection and classification of brain tumors from MRI images. The algorithm integrates an adaptive CNN and an autoencoder to detect and classify brain tumors. To address computational complexities, the Snow Avalanches algorithm is used as an optimization technique. The proposed method is validated using two MRI datasets: figshare and BraTS 2018. The ACAE-SA algorithm demonstrates superior performance in detecting and classifying brain tumors compared to existing techniques. Brain tumors are abnormal growths of brain cells that can lead to cancer. Gliomas are the most common type of brain tumor, arising from the transformation of glial cells in the brain and spinal cord. MRI is a commonly used technique for detecting brain tumors, as it provides detailed images of brain tissues. However, manual detection by radiologists is error-prone and less accurate. Therefore, computer-aided diagnostic techniques are needed to improve the accuracy of brain tumor detection. Deep learning has significantly advanced the detection and classification of brain tumors. Machine learning techniques, particularly deep learning, have enabled the identification of complex patterns in medical images. AI-based approaches have also been employed to enhance the diagnosis of brain tumors, including precise delineation of tumor volume and genotype. However, existing methods face challenges such as lack of rotational invariance and loss of high-range component linkages. The ACAE-SA algorithm addresses these challenges by combining adaptive CNN and autoencoder techniques with the Snow Avalanches algorithm for optimization. This novel architecture improves the detection and classification accuracy of brain tumors. The algorithm is evaluated using performance metrics, graphical representations, and comparative analysis. The results demonstrate the effectiveness of the ACAE-SA algorithm in detecting and classifying brain tumors from MRI images. The paper concludes with future work and recommendations for further research in this area.