DINs: Deep Interactive Networks for Neurofibroma Segmentation in Neurofibromatosis Type 1 on Whole-Body MRI
This work addresses the need for accurate tumor burden assessment in NF1 patients, offering an incremental improvement over existing interactive segmentation methods.
The authors tackled the problem of segmenting neurofibromas in whole-body MRI scans for Neurofibromatosis Type 1 patients, proposing deep interactive networks (DINs) that improved segmentation accuracy by 44% over automated methods and 14% over other interactive methods in Dice Similarity Coefficient (DSC).
Neurofibromatosis type 1 (NF1) is an autosomal dominant tumor predisposition syndrome that involves the central and peripheral nervous systems. Accurate detection and segmentation of neurofibromas are essential for assessing tumor burden and longitudinal tumor size changes. Automatic convolutional neural networks (CNNs) are sensitive and vulnerable as tumors' variable anatomical location and heterogeneous appearance on MRI. In this study, we propose deep interactive networks (DINs) to address the above limitations. User interactions guide the model to recognize complicated tumors and quickly adapt to heterogeneous tumors. We introduce a simple but effective Exponential Distance Transform (ExpDT) that converts user interactions into guide maps regarded as the spatial and appearance prior. Comparing with popular Euclidean and geodesic distances, ExpDT is more robust to various image sizes, which reserves the distribution of interactive inputs. Furthermore, to enhance the tumor-related features, we design a deep interactive module to propagate the guides into deeper layers. We train and evaluate DINs on three MRI data sets from NF1 patients. The experiment results yield significant improvements of 44% and 14% in DSC comparing with automated and other interactive methods, respectively. We also experimentally demonstrate the efficiency of DINs in reducing user burden when comparing with conventional interactive methods. The source code of our method is available at \url{https://github.com/Jarvis73/DINs}.