We present WeakSTIL, an interpretable two-stage weak label deep learning pipeline for scoring the percentage of stromal tumor infiltrating lymphocytes (sTIL%) in H&E-stained whole-slide images (WSIs) of breast cancer tissue. The sTIL% score is a prognostic and predictive biomarker for many solid tumor types. However, due to the high labeling efforts and high intra- and interobserver variability within and between expert annotators, this biomarker is currently not used in routine clinical decision making. WeakSTIL compresses tiles of a WSI using a feature extractor pre-trained with self-supervised learning on unlabeled histopathology data and learns to predict precise sTIL% scores for each tile in the tumor bed by using a multiple instance learning regressor that only requires a weak WSI-level label. By requiring only a weak label, we overcome the large annotation efforts required to train currently existing TIL detection methods. We show that WeakSTIL is at least as good as other TIL detection methods when predicting the WSI-level sTIL% score, reaching a coefficient of determination of $0.45\pm0.15$ when compared to scores generated by an expert pathologist, and an AUC of $0.89\pm0.05$ when treating it as the clinically interesting sTIL-high vs sTIL-low classification task. Additionally, we show that the intermediate tile-level predictions of WeakSTIL are highly interpretable, which suggests that WeakSTIL pays attention to latent features related to the number of TILs and the tissue type. In the future, WeakSTIL may be used to provide consistent and interpretable sTIL% predictions to stratify breast cancer patients into targeted therapy arms.
We propose a Deep learning-based weak label learning method for analysing whole slide images (WSIs) of Hematoxylin and Eosin (H&E) stained tumorcells not requiring pixel-level or tile-level annotations using Self-supervised pre-training and heterogeneity-aware deep Multiple Instance LEarning (DeepSMILE). We apply DeepSMILE to the task of Homologous recombination deficiency (HRD) and microsatellite instability (MSI) prediction. We utilize contrastive self-supervised learning to pre-train a feature extractor on histopathology tiles of cancer tissue. Additionally, we use variability-aware deep multiple instance learning to learn the tile feature aggregation function while modeling tumor heterogeneity. Compared to state-of-the-art genomic label classification methods, DeepSMILE improves classification performance for HRD from $70.43\pm4.10\%$ to $83.79\pm1.25\%$ AUC and MSI from $78.56\pm6.24\%$ to $90.32\pm3.58\%$ AUC in a multi-center breast and colorectal cancer dataset, respectively. These improvements suggest we can improve genomic label classification performance without collecting larger datasets. In the future, this may reduce the need for expensive genome sequencing techniques, provide personalized therapy recommendations based on widely available WSIs of cancer tissue, and improve patient care with quicker treatment decisions - also in medical centers without access to genome sequencing resources.
Learning the structure of a causal graphical model using both observational and interventional data is a fundamental problem in many scientific fields. A promising direction is continuous optimization for score-based methods, which efficiently learn the causal graph in a data-driven manner. However, to date, those methods require constrained optimization to enforce acyclicity or lack convergence guarantees. In this paper, we present ENCO, an efficient structure learning method for directed, acyclic causal graphs leveraging observational and interventional data. ENCO formulates the graph search as an optimization of independent edge likelihoods, with the edge orientation being modeled as a separate parameter. Consequently, we can provide convergence guarantees of ENCO under mild conditions without constraining the score function with respect to acyclicity. In experiments, we show that ENCO can efficiently recover graphs with hundreds of nodes, an order of magnitude larger than what was previously possible, while handling deterministic variables and latent confounders.
Federated learning (FL) has emerged as the predominant approach for collaborative training of neural network models across multiple users, without the need to gather the data at a central location. One of the important challenges in this setting is data heterogeneity, i.e. different users have different data characteristics. For this reason, training and using a single global model might be suboptimal when considering the performance of each of the individual user's data. In this work, we tackle this problem via Federated Mixture of Experts, FedMix, a framework that allows us to train an ensemble of specialized models. FedMix adaptively selects and trains a user-specific selection of the ensemble members. We show that users with similar data characteristics select the same members and therefore share statistical strength while mitigating the effect of non-i.i.d data. Empirically, we show through an extensive experimental evaluation that FedMix improves performance compared to using a single global model across a variety of different sources of non-i.i.d.-ness.
The goal of this paper is guided image filtering, which emphasizes the importance of structure transfer during filtering by means of an additional guidance image. Where classical guided filters transfer structures using hand-designed functions, recent guided filters have been considerably advanced through parametric learning of deep networks. The state-of-the-art leverages deep networks to estimate the two core coefficients of the guided filter. In this work, we posit that simultaneously estimating both coefficients is suboptimal, resulting in halo artifacts and structure inconsistencies. Inspired by unsharp masking, a classical technique for edge enhancement that requires only a single coefficient, we propose a new and simplified formulation of the guided filter. Our formulation enjoys a filtering prior from a low-pass filter and enables explicit structure transfer by estimating a single coefficient. Based on our proposed formulation, we introduce a successive guided filtering network, which provides multiple filtering results from a single network, allowing for a trade-off between accuracy and efficiency. Extensive ablations, comparisons and analysis show the effectiveness and efficiency of our formulation and network, resulting in state-of-the-art results across filtering tasks like upsampling, denoising, and cross-modality filtering. Code is available at \url{https://github.com/shizenglin/Unsharp-Mask-Guided-Filtering}.
Object localisation is typically considered in the context of regular images, for instance depicting objects like people or cars. In these images there is typically a relatively small number of instances per image per class, which usually is manageable to annotate. However, outside the realm of regular images we are often confronted with a different situation. In computational pathology digitised tissue sections are extremely large images, whose dimensions quickly exceed 250'000x250'000 pixels, where relevant objects, such as tumour cells or lymphocytes can quickly number in the millions. Annotating them all is practically impossible and annotating sparsely a few, out of many more, is the only possibility. Unfortunately, learning from sparse annotations, or sparse-shot learning, clashes with standard supervised learning because what is not annotated is treated as a negative. However, assigning negative labels to what are true positives leads to confusion in the gradients and biased learning. To this end, we present exclusive cross entropy, which slows down the biased learning by examining the second-order loss derivatives in order to drop the loss terms corresponding to likely biased terms. Experiments on nine datasets and two different localisation tasks, detection with YOLLO and segmentation with Unet, show that we obtain considerable improvements compared to cross entropy or focal loss, while often reaching the best possible performance for the model with only 10-40 of annotations.
In this work we propose a batch Bayesian optimization method for combinatorial problems on permutations, which is well suited for expensive cost functions on permutations. We introduce LAW, a new efficient batch acquisition method based on the determinantal point process, using an acquisition weighted kernel. Relying on multiple parallel evaluations, LAW accelerates the search for the optimal permutation. We provide a regret analysis for our method to gain insight in its theoretical properties. We then apply the framework to permutation problems, which have so far received little attention in the Bayesian Optimization literature, despite their practical importance. We call this method LAW2ORDER. We evaluate the method on several standard combinatorial problems involving permutations such as quadratic assignment, flowshop scheduling and the traveling salesman, as well as on a structure learning task.
The sample efficiency of Bayesian optimization(BO) is often boosted by Gaussian Process(GP) surrogate models. However, on mixed variable spaces, surrogate models other than GPs are prevalent, mainly due to the lack of kernels which can model complex dependencies across different types of variables. In this paper, we propose the frequency modulated (FM) kernel flexibly modeling dependencies among different types of variables, so that BO can enjoy the further improved sample efficiency. The FM kernel uses distances on continuous variables to modulate the graph Fourier spectrum derived from discrete variables. However, the frequency modulation does not always define a kernel with the similarity measure behavior which returns higher values for pairs of more similar points. Therefore, we specify and prove conditions for FM kernels to be positive definite and to exhibit the similarity measure behavior. In experiments, we demonstrate the improved sample efficiency of GP BO using FM kernels (BO-FM).On synthetic problems and hyperparameter optimization problems, BO-FM outperforms competitors consistently. Also, the importance of the frequency modulation principle is empirically demonstrated on the same problems. On joint optimization of neural architectures and SGD hyperparameters, BO-FM outperforms competitors including Regularized evolution(RE) and BOHB. Remarkably, BO-FM performs better even than RE and BOHB using three times as many evaluations.
Rotation is among the long prevailing, yet still unresolved, hard challenges encountered in visual object tracking. The existing deep learning-based tracking algorithms use regular CNNs that are inherently translation equivariant, but not designed to tackle rotations. In this paper, we first demonstrate that in the presence of rotation instances in videos, the performance of existing trackers is severely affected. To circumvent the adverse effect of rotations, we present rotation-equivariant Siamese networks (RE-SiamNets), built through the use of group-equivariant convolutional layers comprising steerable filters. SiamNets allow estimating the change in orientation of the object in an unsupervised manner, thereby facilitating its use in relative 2D pose estimation as well. We further show that this change in orientation can be used to impose an additional motion constraint in Siamese tracking through imposing restriction on the change in orientation between two consecutive frames. For benchmarking, we present Rotation Tracking Benchmark (RTB), a dataset comprising a set of videos with rotation instances. Through experiments on two popular Siamese architectures, we show that RE-SiamNets handle the problem of rotation very well and out-perform their regular counterparts. Further, RE-SiamNets can accurately estimate the relative change in pose of the target in an unsupervised fashion, namely the in-plane rotation the target has sustained with respect to the reference frame.