Voxel-level Importance Maps for Interpretable Brain Age Estimation

Brain aging, and more specifically the difference between the chronological and the biological age of a person, may be a promising biomarker for identifying neurodegenerative diseases. For this purpose accurate prediction is important but the localisation of the areas that play a significant role in the prediction is also crucial, in order to gain clinicians' trust and reassurance about the performance of a prediction model. Most interpretability methods are focused on classification tasks and cannot be directly transferred to regression tasks. In this study, we focus on the task of brain age regression from 3D brain Magnetic Resonance (MR) images using a Convolutional Neural Network, termed prediction model. We interpret its predictions by extracting importance maps, which discover the parts of the brain that are the most important for brain age. In order to do so, we assume that voxels that are not useful for the regression are resilient to noise addition. We implement a noise model which aims to add as much noise as possible to the input without harming the performance of the prediction model. We average the importance maps of the subjects and end up with a population-based importance map, which displays the regions of the brain that are influential for the task. We test our method on 13,750 3D brain MR images from the UK Biobank, and our findings are consistent with the existing neuropathology literature, highlighting that the hippocampus and the ventricles are the most relevant regions for brain aging.

NeuralDP Differentially private neural networks by design

The application of differential privacy to the training of deep neural networks holds the promise of allowing large-scale (decentralized) use of sensitive data while providing rigorous privacy guarantees to the individual. The predominant approach to differentially private training of neural networks is DP-SGD, which relies on norm-based gradient clipping as a method for bounding sensitivity, followed by the addition of appropriately calibrated Gaussian noise. In this work we propose NeuralDP, a technique for privatising activations of some layer within a neural network, which by the post-processing properties of differential privacy yields a differentially private network. We experimentally demonstrate on two datasets (MNIST and Pediatric Pneumonia Dataset (PPD)) that our method offers substantially improved privacy-utility trade-offs compared to DP-SGD.

Enhancing MR Image Segmentation with Realistic Adversarial Data Augmentation

The success of neural networks on medical image segmentation tasks typically relies on large labeled datasets for model training. However, acquiring and manually labeling a large medical image set is resource-intensive, expensive, and sometimes impractical due to data sharing and privacy issues. To address this challenge, we propose an adversarial data augmentation approach to improve the efficiency in utilizing training data and to enlarge the dataset via simulated but realistic transformations. Specifically, we present a generic task-driven learning framework, which jointly optimizes a data augmentation model and a segmentation network during training, generating informative examples to enhance network generalizability for the downstream task. The data augmentation model utilizes a set of photometric and geometric image transformations and chains them to simulate realistic complex imaging variations that could exist in magnetic resonance (MR) imaging. The proposed adversarial data augmentation does not rely on generative networks and can be used as a plug-in module in general segmentation networks. It is computationally efficient and applicable for both supervised and semi-supervised learning. We analyze and evaluate the method on two MR image segmentation tasks: cardiac segmentation and prostate segmentation. Results show that the proposed approach can alleviate the need for labeled data while improving model generalization ability, indicating its practical value in medical imaging applications.

Differentially private training of neural networks with Langevin dynamics for calibrated predictive uncertainty

We show that differentially private stochastic gradient descent (DP-SGD) can yield poorly calibrated, overconfident deep learning models. This represents a serious issue for safety-critical applications, e.g. in medical diagnosis. We highlight and exploit parallels between stochastic gradient Langevin dynamics, a scalable Bayesian inference technique for training deep neural networks, and DP-SGD, in order to train differentially private, Bayesian neural networks with minor adjustments to the original (DP-SGD) algorithm. Our approach provides considerably more reliable uncertainty estimates than DP-SGD, as demonstrated empirically by a reduction in expected calibration error (MNIST $\sim{5}$-fold, Pediatric Pneumonia Dataset $\sim{2}$-fold).

Transductive image segmentation: Self-training and effect of uncertainty estimation

Semi-supervised learning (SSL) uses unlabeled data during training to learn better models. Previous studies on SSL for medical image segmentation focused mostly on improving model generalization to unseen data. In some applications, however, our primary interest is not generalization but to obtain optimal predictions on a specific unlabeled database that is fully available during model development. Examples include population studies for extracting imaging phenotypes. This work investigates an often overlooked aspect of SSL, transduction. It focuses on the quality of predictions made on the unlabeled data of interest when they are included for optimization during training, rather than improving generalization. We focus on the self-training framework and explore its potential for transduction. We analyze it through the lens of Information Gain and reveal that learning benefits from the use of calibrated or under-confident models. Our extensive experiments on a large MRI database for multi-class segmentation of traumatic brain lesions shows promising results when comparing transductive with inductive predictions. We believe this study will inspire further research on transductive learning, a well-suited paradigm for medical image analysis.

Joint Semi-supervised 3D Super-Resolution and Segmentation with Mixed Adversarial Gaussian Domain Adaptation

Optimising the analysis of cardiac structure and function requires accurate 3D representations of shape and motion. However, techniques such as cardiac magnetic resonance imaging are conventionally limited to acquiring contiguous cross-sectional slices with low through-plane resolution and potential inter-slice spatial misalignment. Super-resolution in medical imaging aims to increase the resolution of images but is conventionally trained on features from low resolution datasets and does not super-resolve corresponding segmentations. Here we propose a semi-supervised multi-task generative adversarial network (Gemini-GAN) that performs joint super-resolution of the images and their labels using a ground truth of high resolution 3D cines and segmentations, while an unsupervised variational adversarial mixture autoencoder (V-AMA) is used for continuous domain adaptation. Our proposed approach is extensively evaluated on two transnational multi-ethnic populations of 1,331 and 205 adults respectively, delivering an improvement on state of the art methods in terms of Dice index, peak signal to noise ratio, and structural similarity index measure. This framework also exceeds the performance of state of the art generative domain adaptation models on external validation (Dice index 0.81 vs 0.74 for the left ventricle). This demonstrates how joint super-resolution and segmentation, trained on 3D ground-truth data with cross-domain generalization, enables robust precision phenotyping in diverse populations.

Differentially private training of neural networks with Langevin dynamics forcalibrated predictive uncertainty

We show that differentially private stochastic gradient descent (DP-SGD) can yield poorly calibrated, overconfident deep learning models. This represents a serious issue for safety-critical applications, e.g. in medical diagnosis. We highlight and exploit parallels between stochastic gradient Langevin dynamics, a scalable Bayesian inference technique for training deep neural networks, and DP-SGD, in order to train differentially private, Bayesian neural networks with minor adjustments to the original (DP-SGD) algorithm. Our approach provides considerably more reliable uncertainty estimates than DP-SGD, as demonstrated empirically by a reduction in expected calibration error (MNIST $\sim{5}$-fold, Pediatric Pneumonia Dataset $\sim{2}$-fold).