Brain Tumor Image Retrieval via Multitask Learning
This work addresses the need for more informative image retrieval in medical imaging, specifically for brain tumor analysis, but it is incremental as it builds on existing classification-based methods.
The authors tackled the problem of brain tumor image retrieval by extending classification-based systems with multitask learning to incorporate multiple data aspects like tumor type and localization, resulting in representations that contain more relevant information than single-task approaches.
Classification-based image retrieval systems are built by training convolutional neural networks (CNNs) on a relevant classification problem and using the distance in the resulting feature space as a similarity metric. However, in practical applications, it is often desirable to have representations which take into account several aspects of the data (e.g., brain tumor type and its localization). In our work, we extend the classification-based approach with multitask learning: we train a CNN on brain MRI scans with heterogeneous labels and implement a corresponding tumor image retrieval system. We validate our approach on brain tumor data which contains information about tumor types, shapes and localization. We show that our method allows us to build representations that contain more relevant information about tumors than single-task classification-based approaches.