1. DINs: Deep Interactive Networks for Neurofibroma Segmentation in Neurofibromatosis Type 1 on Whole-Body MRI
- Author
-
Scott R. Plotkin, Fan Yan, Pengyi Hao, Xubin Zhang, Justin T. Jordan, Gordon J. Harris, Wei Chen, Jian-Wei Zhang, Wenli Cai, and Kien-Ninh Ina Ly
- Subjects
FOS: Computer and information sciences ,Neurofibromatosis 1 ,Computer science ,Computer Vision and Pattern Recognition (cs.CV) ,Whole body mri ,Computer Science - Computer Vision and Pattern Recognition ,Convolutional neural network ,Article ,Health Information Management ,Image Processing, Computer-Assisted ,medicine ,Humans ,Neurofibroma ,Segmentation ,Electrical and Electronic Engineering ,Neurofibromatosis ,Arthrogryposis ,Anatomical location ,Tumor size ,business.industry ,Pattern recognition ,medicine.disease ,Magnetic Resonance Imaging ,Tumor Burden ,3. Good health ,Computer Science Applications ,Neural Networks, Computer ,Artificial intelligence ,business ,Distance transform ,Biotechnology - Abstract
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}., Accepted by IEEE Journal of Biomedical and Health Informatics (JBHI)
- Published
- 2022
- Full Text
- View/download PDF