A Novel Domain Adaptation Framework for Medical Image Segmentation

Gholami, Amir; Subramanian, Shashank; Shenoy, Varun; Himthani, Naveen; Yue, Xiangyu; Zhao, Sicheng; Jin, Peter H.; Biros, George; Keutzer, Kurt

doi:10.1007/978-3-030-11726-9_26

Cited by 42 publications

(32 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the method reported by Wang et al (2018), we analyzed the best-performing models. Note that Gholami et al (2018) and Lachinov et al (2018) did not present the Hausdorff distances obtained using their approaches. have been trained using a number of datasets with different preprocessing and augmentations.…”

Section: Brats 2018 Challengementioning

confidence: 91%

“…An interesting approach for generating phantom image data was exploited in Gholami et al (2018), where the authors utilized a multi-species partial differential equations (PDE) growth model of a tumor to generate synthetic lesions. However, such data does not necessarily follow the correct intensity distribution of a real MRI, hence it should be treated as a separate modality, because using the artificial data which is sampled from a very different distribution may adversely affect the overall segmentation performance by "tricking" the underlying deep model (Wei et al, 2018).…”

Section: Data Augmentation By Generating Artificial Datamentioning

confidence: 99%

“…Albeit data augmentation is introduced in order to improve the generalization capabilities of supervised learners, this impact was verified only in four BraTS 2018 papers (Benson et al, 2018;Gholami et al, 2018;Lachinov et al, 2018;Wang et al, 2018). Gholami et al (2018) showed that their PDE-based augmentation delivers very significant improvement in the DICE scores obtained for segmenting all parts of the tumors in the multi-class classification. The same performance boost (in the DICE values obtained for each class) was reported by Lachinov et al (2018).…”

Section: Brats 2018 Challengementioning

confidence: 99%

See 2 more Smart Citations

Data Augmentation for Brain-Tumor Segmentation: A Review

Nalepa

Marcinkiewicz²,

Kawulok

2019

Front. Comput. Neurosci.

261

127

View full text Add to dashboard Cite

Data augmentation is a popular technique which helps improve generalization capabilities of deep neural networks, and can be perceived as implicit regularization. It plays a pivotal role in scenarios in which the amount of high-quality ground-truth data is limited, and acquiring new examples is costly and time-consuming. This is a very common problem in medical image analysis, especially tumor delineation. In this paper, we review the current advances in data-augmentation techniques applied to magnetic resonance images of brain tumors. To better understand the practical aspects of such algorithms, we investigate the papers submitted to the Multimodal Brain Tumor Segmentation Challenge (BraTS 2018 edition), as the BraTS dataset became a standard benchmark for validating existent and emerging brain-tumor detection and segmentation techniques. We verify which data augmentation approaches were exploited and what was their impact on the abilities of underlying supervised learners. Finally, we highlight the most promising research directions to follow in order to synthesize high-quality artificial brain-tumor examples which can boost the generalization abilities of deep models.

show abstract

Section: Brats 2018 Challengementioning

confidence: 91%

Section: Data Augmentation By Generating Artificial Datamentioning

confidence: 99%

Section: Brats 2018 Challengementioning

confidence: 99%

See 1 more Smart Citation

Data Augmentation for Brain-Tumor Segmentation: A Review

Nalepa

Marcinkiewicz²,

Kawulok

2019

Front. Comput. Neurosci.

261

127

View full text Add to dashboard Cite

show abstract

“…These images are annotated with voxel-wise segmentation of tumor acquired through manual delineation performed by expert radiologists. For the healthy tissue segmentation, we refer to [17] where the brain is further segmented into gray matter, white matter and (a) L 2 (b) CS…”

Section: Real Tumor (Rt) Test-casementioning

confidence: 99%

Where did the tumor start? An inverse solver with sparse localization for tumor growth models

et al. 2020

Self Cite

View full text Add to dashboard Cite

We present a numerical scheme for solving an inverse problem for parameter estimation in tumor growth models for glioblastomas, a form of aggressive primary brain tumor. The growth model is a reaction-diffusion partial differential equation (PDE) for the tumor concentration. We use a PDE-constrained optimization formulation for the inverse problem. The unknown parameters are the reaction coefficient (proliferation), the diffusion coefficient (infiltration), and the initial condition field for the tumor PDE. Segmentation of Magnetic Resonance Imaging (MRI) scans drive the inverse problem where segmented tumor regions serve as partial observations of the tumor concentration. Like most cases in clinical practice, we use data from a single time snapshot. Moreover, the precise time relative to the initiation of the tumor is unknown, which poses an additional difficulty for inversion. We perform a frozen-coefficient spectral analysis and show that the inverse problem is severely ill-posed. We introduce a biophysically motivated regularization on the structure and magnitude of the tumor initial condition. In particular, we assume that the tumor starts at a few locations (enforced with a sparsity constraint on the initial condition of the tumor) and that the initial condition magnitude in the maximum norm is equal to one. We solve the resulting optimization problem using an inexact quasi-Newton method combined with a compressive sampling algorithm for the sparsity constraint. Our implementation uses PETSc and AccFFT libraries. We conduct numerical experiments on synthetic and clinical images to highlight the improved performance of our solver over a previously existing solver that uses standard two-norm regularization for the calibration parameters. The existing solver is unable to localize the initial condition. Our new solver can localize the initial condition and recover infiltration and proliferation. In clinical datasets (for which the ground truth is unknown), our solver results in qualitatively different solutions compared to the two-norm regularized solver. Related work.Although there has been a lot of work on forward problems for tumor growth, there has been less work on inverse problems. The latter has different aspects. The first is the underlying biophysical model. The second is the inverse problem setup, observation operators and the existence of scans at multiple points, the noise models, inversion parameters and constraints. And the third one is the solution algorithm.Regarding the underlying model, like us, most researchers focus on parameter calibration of a handful of model parameters using single-species reaction-diffusion equations [7,22,24,28,33,39,51,58,59]. While more complex models describing processes like mass effect, angiogenesis and chemotaxis [23,26,48,54,60] exist, they have not been considered for calibration due to theoretical and computational challenges. However, several groups, including ours, are working to address these challenges.Regarding the inverse problem setup, in most studies t...

show abstract

“…In the recent literature, adversarial techniques have become the de facto choice in adapting segmentation networks, for medical [5,9,11,24] and color [3,7,8,20] images. These techniques match the feature distribution across domains by alternating the training of two networks, one learning a discriminator between source and target features and the other generating segmentations.…”

Section: Introductionmentioning

confidence: 99%

Constrained Domain Adaptation for Segmentation

Bateson¹,

Kervadec²,

Dolz³

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We propose to adapt segmentation networks with a constrained formulation, which embeds domain-invariant prior knowledge about the segmentation regions. Such knowledge may take the form of simple anatomical information, e.g., structure size or shape, estimated from source samples or known a priori. Our method imposes domaininvariant inequality constraints on the network outputs of unlabeled target samples. It implicitly matches prediction statistics between target and source domains with permitted uncertainty of prior knowledge. We address our constrained problem with a differentiable penalty, fully suited for standard stochastic gradient descent approaches, removing the need for computationally expensive Lagrangian optimization with dual projections. Unlike current two-step adversarial training, our formulation is based on a single loss in a single network, which simplifies adaptation by avoiding extra adversarial steps, while improving convergence and quality of training. The comparison of our approach with stateof-the-art adversarial methods reveals substantially better performance on the challenging task of adapting spine segmentation across different MRI modalities. Our results also show a robustness to imprecision of size priors, approaching the accuracy of a fully supervised model trained directly in a target domain. Our method can be readily used for various constraints and segmentation problems.

show abstract

A Novel Domain Adaptation Framework for Medical Image Segmentation

Cited by 42 publications

References 23 publications

Data Augmentation for Brain-Tumor Segmentation: A Review

Data Augmentation for Brain-Tumor Segmentation: A Review

Where did the tumor start? An inverse solver with sparse localization for tumor growth models

Constrained Domain Adaptation for Segmentation

Contact Info

Product

Resources

About