Adaptive Smooth Activation for Improved Disease Diagnosis and Organ Segmentation from Radiology Scans
This work addresses the need for more accurate diagnostic tools in radiology, particularly for complex pathologies, though it is incremental as it builds on existing activation functions.
The authors tackled the problem of improving gradient propagation in convolutional networks for medical image analysis by proposing the Adaptive Smooth Activation Unit (ASAU), which achieved a 4.80% improvement in classification accuracy over ReLU for disease detection and 1%-3% gains in dice coefficient for liver tissue segmentation.
In this study, we propose a new activation function, called Adaptive Smooth Activation Unit (ASAU), tailored for optimized gradient propagation, thereby enhancing the proficiency of convolutional networks in medical image analysis. We apply this new activation function to two important and commonly used general tasks in medical image analysis: automatic disease diagnosis and organ segmentation in CT and MRI. Our rigorous evaluation on the RadImageNet abdominal/pelvis (CT and MRI) dataset and Liver Tumor Segmentation Benchmark (LiTS) 2017 demonstrates that our ASAU-integrated frameworks not only achieve a substantial (4.80\%) improvement over ReLU in classification accuracy (disease detection) on abdominal CT and MRI but also achieves 1\%-3\% improvement in dice coefficient compared to widely used activations for `healthy liver tissue' segmentation. These improvements offer new baselines for developing a diagnostic tool, particularly for complex, challenging pathologies. The superior performance and adaptability of ASAU highlight its potential for integration into a wide range of image classification and segmentation tasks.