An efficient strategy for weakly-supervised segmentation is to impose constraints or regularization priors on target regions. Recent efforts have focused on incorporating such constraints in the training of convolutional neural networks (CNN), however this has so far been done within a continuous optimization framework. Yet, various segmentation constraints and regularization can be modeled and optimized more efficiently in a discrete formulation. This paper proposes a method, based on the alternating direction method of multipliers (ADMM) algorithm, to train a CNN with discrete constraints and regularization priors. This method is applied to the segmentation of medical images with weak annotations, where both size constraints and boundary length regularization are enforced. Experiments on a benchmark cardiac segmentation dataset show our method to yield a performance near to full supervision.
Weakly supervised object localization (WSOL) models aim to locate objects of interest in an image after being trained only on data with coarse image level labels. Deep learning models for WSOL rely typically on convolutional attention maps with no constraints on the regions of interest which allows them to select any region, making them vulnerable to false positive regions. This issue occurs in many application domains, e.g., medical image analysis, where interpretability is central to the prediction. In order to improve the localization reliability, we propose a deep learning framework for WSOL with pixel level localization. It is composed of two sequential sub-networks: a localizer that localizes regions of interest; followed by a classifier that classifies them. Within its end-to-end training, we incorporate the prior knowledge stating that in an agnostic-class setup an image is more likely to contain relevant --object of interest-- and irrelevant regions --noise--. Based on the conditional entropy (CE) measured at the classifier, the localizer is driven to spot relevant regions (low CE), and irrelevant regions (high CE). Our framework is able to recover large discriminative regions using our recursive erasing algorithm that we incorporate within the backpropagation during training. Moreover, the framework handles intrinsically multi-instances. Experimental results on public datasets with medical images (GlaS colon cancer) and natural images (Caltech-UCSD Birds-200-2011, Oxford flower 102) show that, compared to state of the art WSOL methods, our framework can provide significant improvements in terms of image-level classification, pixel-level localization, and robustness to overfitting when dealing with few training samples. A public reproducible PyTorch implementation is provided in: https://github.com/sbelharbi/wsol-min-max-entropy-interpretability .
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 domain-invariant 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 state-of-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.
Even though convolutional neural networks (CNNs) are driving progress in medical image segmentation, standard models still have some drawbacks. First, the use of multi-scale approaches, i.e., encoder-decoder architectures, leads to a redundant use of information, where similar low-level features are extracted multiple times at multiple scales. Second, long-range feature dependencies are not efficiently modeled, resulting in non-optimal discriminative feature representations associated with each semantic class. In this paper we attempt to overcome these limitations with the proposed architecture, by capturing richer contextual dependencies based on the use of guided self-attention mechanisms. This approach is able to integrate local features with their corresponding global dependencies, as well as highlight interdependent channel maps in an adaptive manner. Further, the additional loss between different modules guides the attention mechanisms to remove the noise and focus on more discriminant regions of the image by emphasizing relevant feature associations. We evaluate the proposed model in the context of abdominal organ segmentation on magnetic resonance imaging (MRI). A series of ablation experiments support the importance of these attention modules in the proposed architecture. In addition, compared to other state-of-the-art segmentation networks our model yields better segmentation performance, increasing the accuracy of the predictions while reducing the standard deviation. This demonstrates the efficiency of our approach to generate precise and reliable automatic segmentations of medical images. Our code and the trained model are made publicly available at: https://github.com/sinAshish/Multi-Scale-Attention
This study investigates a curriculum-style strategy for semi-supervised CNN segmentation, which devises a regression network to learn image-level information such as the size of a target region. These regressions are used to effectively regularize the segmentation network, constraining softmax predictions of the unlabeled images to match the inferred label distributions. Our framework is based on inequality constraints that tolerate uncertainties with inferred knowledge, e.g., regressed region size, and can be employed for a large variety of region attributes. We evaluated our proposed strategy for left ventricle segmentation in magnetic resonance images (MRI), and compared it to standard proposal-based semi-supervision strategies. Our strategy leverages unlabeled data in more efficiently, and achieves very competitive results, approaching the performance of full-supervision.
This study investigates imposing inequality constraints on the outputs of CNNs for weakly supervised segmentation. In the general context of deep networks, constraints are commonly handled with penalty approaches for their simplicity, and despite their well-known limitations. Lagrangian optimization has well-established theoretical and practical advantages over penalty methods, but has been largely avoided for deep CNNs, mainly due to computational complexity and stability/convergence issues caused by alternating stochastic optimization and dual updates. Several recent studies showed that, in the context of deep CNNs, the theoretical advantages of Lagrangian optimization over simple penalties do not materialize in practice, with performances that are, surprisingly, worse. We leverage well-established concepts in interior-point methods, which approximate Lagrangian optimization with a sequence of unconstrained problems, while completely avoiding dual steps/projections. Specifically, we propose a sequence of unconstrained {\em log-barrier-extension} losses for approximating inequality-constrained CNN problems. The proposed extension has a duality-gap bound, which yields sub-optimality certificates for feasible solutions in the case of convex losses. While sub-optimality is not guaranteed for non-convex problems, the result shows that log-barrier extensions are a principled way to approximate Lagrangian optimization for constrained CNNs. Our approach addresses the well-known limitations of penalty methods and, at the same time, removes the explicit dual steps of Lagrangian optimization. We report comprehensive experiments showing that our formulation outperforms a recent penalty-based constrained CNN method, both in terms of accuracy and training stability.
Minimization of distribution matching losses is a principled approach to domain adaptation in the context of image classification. However, it is largely overlooked in adapting segmentation networks, which is currently dominated by adversarial models. We propose a class of loss functions, which encourage direct kernel density matching in the network-output space, up to some geometric transformations computed from unlabeled inputs. Rather than using an intermediate domain discriminator, our direct approach unifies distribution matching and segmentation in a single loss. Therefore, it simplifies segmentation adaptation by avoiding extra adversarial steps, while improving both the quality, stability and efficiency of training. We juxtapose our approach to state-of-the-art segmentation adaptation via adversarial training in the network-output space. In the challenging task of adapting brain segmentation across different magnetic resonance images (MRI) modalities, our approach achieves significantly better results both in terms of accuracy and stability.
Widely used loss functions for convolutional neural network (CNN) segmentation, e.g., Dice or cross-entropy, are based on integrals (summations) over the segmentation regions. Unfortunately, it is quite common in medical image analysis to have highly unbalanced segmentations, where standard losses contain regional terms with values that differ considerably --typically of several orders of magnitude-- across segmentation classes, which may affect training performance and stability. The purpose of this study is to build a boundary loss, which takes the form of a distance metric on the space of contours, not regions. We argue that a boundary loss can mitigate the difficulties of regional losses in the context of highly unbalanced segmentation problems because it uses integrals over the boundary between regions instead of unbalanced integrals over regions. Furthermore, a boundary loss provides information that is complementary to regional losses. Unfortunately, it is not straightforward to represent the boundary points corresponding to the regional softmax outputs of a CNN. Our boundary loss is inspired by discrete (graph-based) optimization techniques for computing gradient flows of curve evolution. Following an integral approach for computing boundary variations, we express a non-symmetric L2 distance on the space of shapes as a regional integral, which avoids completely local differential computations involving contour points. Our boundary loss is the sum of linear functions of the regional softmax probability outputs of the network. Therefore, it can easily be combined with standard regional losses and implemented with any existing deep network architecture for N-D segmentation. Our boundary loss has been validated on two benchmark datasets corresponding to difficult, highly unbalanced segmentation problems: the ischemic stroke lesion (ISLES) and white matter hyperintensities (WMH).
Accurate localization and segmentation of intervertebral disc (IVD) is crucial for the assessment of spine disease diagnosis. Despite the technological advances in medical imaging, IVD localization and segmentation are still manually performed, which is time-consuming and prone to errors. If, in addition, multi-modal imaging is considered, the burden imposed on disease assessments increases substantially. In this paper, we propose an architecture for IVD localization and segmentation in multi-modal MRI, which extends the well-known UNet. Compared to single images, multi-modal data brings complementary information, contributing to better data representation and discriminative power. Our contributions are three-fold. First, how to effectively integrate and fully leverage multi-modal data remains almost unexplored. In this work, each MRI modality is processed in a different path to better exploit their unique information. Second, inspired by HyperDenseNet, the network is densely-connected both within each path and across different paths, granting the model the freedom to learn where and how the different modalities should be processed and combined. Third, we improved standard U-Net modules by extending inception modules with two dilated convolutions blocks of different scale, which helps handling multi-scale context. We report experiments over the data set of the public MICCAI 2018 Challenge on Automatic Intervertebral Disc Localization and Segmentation, with 13 multi-modal MRI images used for training and 3 for validation. We trained IVD-Net on an NVidia TITAN XP GPU with 16 GBs RAM, using ADAM as optimizer and a learning rate of 10e-5 during 200 epochs. Training took about 5 hours, and segmentation of a whole volume about 2-3 seconds, on average. Several baselines, with different multi-modal fusion strategies, were used to demonstrate the effectiveness of the proposed architecture.