DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation
By Guotai Wang, Maria A. Zuluaga, Wenqi Li, Rosalind Pratt, Premal A. Patel, Michael Aertsen, Tom Doel, Anna L. David, Jan Deprest, Sébastien Ourselin and 1 more. 2017
476 citations recorded by the source corpus.
Accurate medical image segmentation is essential for diagnosis, surgical planning and many other applications. Convolutional Neural Networks (CNNs) have become the state-of-the-art automatic segmentation methods. However, fully automatic results may still need to be refined to become accurate and robust enough for clinical use. We propose a deep learning-based interactive segmentation method to improve the results obtained by an automatic CNN and to reduce user interactions during refinement for higher accuracy. We use one CNN to obtain an initial automatic segmentation, on which user interactions are added to indicate mis-segmentations. Another CNN takes as input the user interactions with the initial segmentation and gives a refined result. We propose to combine user interactions with CNNs through geodesic distance transforms, and propose a resolution-preserving network that gives a better dense prediction. In addition, we integrate user interactions as hard constraints into a back-propagatable Conditional Random Field. We validated the proposed framework in the context of 2D placenta segmentation from fetal MRI and 3D brain tumor segmentation from FLAIR images. Experimental results show our method achieves a large improvement from automatic CNNs, and obtains comparable and even higher accuracy with fewer user interventions and less time compared with traditional interactive methods.
Subfields: Computer Vision and Pattern Recognition, Pediatrics, Perinatology and Child Health, Medical Imaging
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Ming-Hsuan Yang
- Dacheng Tao
- Jiashi Feng
- Xiaogang Wang
- Trevor Darrell
- Chunhua Shen
- Andrew Zisserman
In Medical Imaging
Citations in the corpus
- Iterative Interaction Training for Segmentation Editing Networks (2018, positive): “Different than [20], we investigate training in an iterative interaction fashion on simulated user inputs and we also focus on multi-label segmentation problems as well as binary ones.”
- Guide Me: Interacting with Deep Networks (2018, background): “In the field of medical imaging, [2] proposes to interactively improve segmentation by updating a seedmap given by the user and [57] uses a second network operating both on the previous prediction and human feedback.”
- Deep Interactive Thin Object Selection (2021, methodology): “…in which user clicks first go through Euclidean distance transformation before concatenated with the image for training an FCN. Recent methods focus on better exploiting useful context from user-provided inputs [23, 15, 27] or deriving better representation for user clicks [32, 45, 19, 31].”
- Content-Aware Multi-Level Guidance for Interactive Instance Segmentation (2019, unknown): “The segmented results are useful for downstream applications such as image/video editing [6, 30], image-based medical diagnosis [50, 51], human-machine collaborative annotation [2], etc .”
- Segment Anything in Medical Images (2023, unknown): “In addition to the bounding box, scribble is another commonly used user interaction in medical image segmentation [50][49], which was not supported in the current SAM.”
- Medical Image Segmentation Using Deep Learning: A Survey (2020, methodology): “[121] proposed the DeepIGeoS using the cascade of two CNNs for interactive segmentation of 2D and 3D medical images.”
- Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformer (2021, methodology): “Medical image segmentation is a very basic and important step for computer-assisted diagnosis, treatment planning, and intervention (Wang et al., 2018; Luo et al., 2021d).”
- Interactive Image Segmentation With First Click Attention (2020, background): “It directly ben-efits many applications, e.g . image editing [ 8, 11, 29] and medical imaging analysis [46].”
- Segment anything in medical images (2023, unknown): “However, their application to medical image segmentation has been challenging due to the substantial domain gap [6] (Supplementary Related work).”
- A Continual Learning Framework for Uncertainty-Aware Interactive Image Segmentation (2021, methodology): “After user annotations are collected, a majority of the models re-fine segmentation through spatial regularization using post-processing techniques such as conditional random fields and graph cuts (Wang et al. 2018; Dhara et al. 2018; Zhou, Chen, and Wang 2019).”
- A Fully Convolutional Two-Stream Fusion Network for Interactive Image Segmentation (2018, background): “Essentially, all these networks [15, 17, 16, 18, 19, 21, 28] adopt early fusion structures.”
- FocusCut: Diving into a Focus View in Interactive Segmentation (2022, methodology): “The Average Symmetric Surface Distance (ASSD), which is used to evaluate the similarity of the boundaries of the prediction and ground truth, has also been used in interactive medical image segmentation [45].”