Polyps represent an early sign of the development of Colorectal Cancer. The standard procedure for their detection consists of colonoscopic examination of the gastrointestinal tract. However, the wide range of polyp shapes and visual appearances, as well as the reduced quality of this image modality, turn their automatic identification and segmentation with computational tools into a challenging computer vision task. In this work, we present a new strategy for the delineation of gastrointestinal polyps from endoscopic images based on a direct extension of common encoder-decoder networks for semantic segmentation. In our approach, two pretrained encoder-decoder networks are sequentially stacked: the second network takes as input the concatenation of the original frame and the initial prediction generated by the first network, which acts as an attention mechanism enabling the second network to focus on interesting areas within the image, thereby improving the quality of its predictions. Quantitative evaluation carried out on several polyp segmentation databases shows that double encoder-decoder networks clearly outperform their single encoder-decoder counterparts in all cases. In addition, our best double encoder-decoder combination attains excellent segmentation accuracy and reaches state-of-the-art performance results in all the considered datasets, with a remarkable boost of accuracy on images extracted from datasets not used for training.
Highly imbalanced datasets are ubiquitous in medical image classification problems. In such problems, it is often the case that rare classes associated to less prevalent diseases are severely under-represented in labeled databases, typically resulting in poor performance of machine learning algorithms due to overfitting in the learning process. In this paper, we propose a novel mechanism for sampling training data based on the popular MixUp regularization technique, which we refer to as Balanced-MixUp. In short, Balanced-MixUp simultaneously performs regular (i.e., instance-based) and balanced (i.e., class-based) sampling of the training data. The resulting two sets of samples are then mixed-up to create a more balanced training distribution from which a neural network can effectively learn without incurring in heavily under-fitting the minority classes. We experiment with a highly imbalanced dataset of retinal images (55K samples, 5 classes) and a long-tail dataset of gastro-intestinal video frames (10K images, 23 classes), using two CNNs of varying representation capabilities. Experimental results demonstrate that applying Balanced-MixUp outperforms other conventional sampling schemes and loss functions specifically designed to deal with imbalanced data. Code is released at https://github.com/agaldran/balanced_mixup .
The scarcity of high quality medical image annotations hinders the implementation of accurate clinical applications for detecting and segmenting abnormal lesions. To mitigate this issue, the scientific community is working on the development of unsupervised anomaly detection (UAD) systems that learn from a training set containing only normal (i.e., healthy) images, where abnormal samples (i.e., unhealthy) are detected and segmented based on how much they deviate from the learned distribution of normal samples. One significant challenge faced by UAD methods is how to learn effective low-dimensional image representations that are sensitive enough to detect and segment abnormal lesions of varying size, appearance and shape. To address this challenge, we propose a novel self-supervised UAD pre-training algorithm, named Multi-centred Strong Augmentation via Contrastive Learning (MSACL). MSACL learns representations by separating several types of strong and weak augmentations of normal image samples, where the weak augmentations represent normal images and strong augmentations denote synthetic abnormal images. To produce such strong augmentations, we introduce MedMix, a novel data augmentation strategy that creates new training images with realistic looking lesions (i.e., anomalies) in normal images. The pre-trained representations from MSACL are generic and can be used to improve the efficacy of different types of off-the-shelf state-of-the-art (SOTA) UAD models. Comprehensive experimental results show that the use of MSACL largely improves these SOTA UAD models on four medical imaging datasets from diverse organs, namely colonoscopy, fundus screening and covid-19 chest-ray datasets.
Minimally invasive surgery (MIS) has many documented advantages, but the surgeon's limited visual contact with the scene can be problematic. Hence, systems that can help surgeons navigate, such as a method that can produce a 3D semantic map, can compensate for the limitation above. In theory, we can borrow 3D semantic mapping techniques developed for robotics, but this requires finding solutions to the following challenges in MIS: 1) semantic segmentation, 2) depth estimation, and 3) pose estimation. In this paper, we propose the first 3D semantic mapping system from knee arthroscopy that solves the three challenges above. Using out-of-distribution non-human datasets, where pose could be labeled, we jointly train depth+pose estimators using selfsupervised and supervised losses. Using an in-distribution human knee dataset, we train a fully-supervised semantic segmentation system to label arthroscopic image pixels into femur, ACL, and meniscus. Taking testing images from human knees, we combine the results from these two systems to automatically create 3D semantic maps of the human knee. The result of this work opens the pathway to the generation of intraoperative 3D semantic mapping, registration with pre-operative data, and robotic-assisted arthroscopy
We propose probabilistic task modelling -- a generative probabilistic model for collections of tasks used in meta-learning. The proposed model combines variational auto-encoding and latent Dirichlet allocation to model each task as a mixture of Gaussian distribution in an embedding space. Such modelling provides an explicit representation of a task through its task-theme mixture. We present an efficient approximation inference technique based on variational inference method for empirical Bayes parameter estimation. We perform empirical evaluations to validate the task uncertainty and task distance produced by the proposed method through correlation diagrams of the prediction accuracy on testing tasks. We also carry out experiments of task selection in meta-learning to demonstrate how the task relatedness inferred from the proposed model help to facilitate meta-learning algorithms.
Longitudinal imaging forms an essential component in the management and follow-up of many medical conditions. The presence of lesion changes on serial imaging can have significant impact on clinical decision making, highlighting the important role for automated change detection. Lesion changes can represent anomalies in serial imaging, which implies a limited availability of annotations and a wide variety of possible changes that need to be considered. Hence, we introduce a new unsupervised anomaly detection and localisation method trained exclusively with serial images that do not contain any lesion changes. Our training automatically synthesises lesion changes in serial images, introducing detection and localisation pseudo-labels that are used to self-supervise the training of our model. Given the rarity of these lesion changes in the synthesised images, we train the model with the imbalance robust focal Tversky loss. When compared to supervised models trained on different datasets, our method shows competitive performance in the detection and localisation of new demyelinating lesions on longitudinal magnetic resonance imaging in multiple sclerosis patients. Code for the models will be made available on GitHub.
In this paper, we address the problem of training deep neural networks in the presence of severe label noise. Our proposed training algorithm ScanMix, combines semantic clustering with semi-supervised learning (SSL) to improve the feature representations and enable an accurate identification of noisy samples, even in severe label noise scenarios. To be specific, ScanMix is designed based on the expectation maximisation (EM) framework, where the E-step estimates the value of a latent variable to cluster the training images based on their appearance representations and classification results, and the M-step optimises the SSL classification and learns effective feature representations via semantic clustering. In our evaluations, we show state-of-the-art results on standard benchmarks for symmetric, asymmetric and semantic label noise on CIFAR-10 and CIFAR-100, as well as large scale real label noise on WebVision. Most notably, for the benchmarks contaminated with large noise rates (80% and above), our results are up to 27% better than the related work. The code is available at https://github.com/ragavsachdeva/ScanMix.
Deep neural network models are robust to a limited amount of label noise, but their ability to memorise noisy labels in high noise rate problems is still an open issue. The most competitive noisy-label learning algorithms rely on a 2-stage process comprising an unsupervised learning to classify training samples as clean or noisy, followed by a semi-supervised learning that minimises the empirical vicinal risk (EVR) using a labelled set formed by samples classified as clean, and an unlabelled set with samples classified as noisy. In this paper, we hypothesise that the generalisation of such 2-stage noisy-label learning methods depends on the precision of the unsupervised classifier and the size of the training set to minimise the EVR. We empirically validate these two hypotheses and propose the new 2-stage noisy-label training algorithm LongReMix. We test LongReMix on the noisy-label benchmarks CIFAR-10, CIFAR-100, WebVision, Clothing1M, and Food101-N. The results show that our LongReMix generalises better than competing approaches, particularly in high label noise problems. Furthermore, our approach achieves state-of-the-art performance in most datasets. The code will be available upon paper acceptance.
The classification accuracy of deep learning models depends not only on the size of their training sets, but also on the quality of their labels. In medical image classification, large-scale datasets are becoming abundant, but their labels will be noisy when they are automatically extracted from radiology reports using natural language processing tools. Given that deep learning models can easily overfit these noisy-label samples, it is important to study training approaches that can handle label noise. In this paper, we adapt a state-of-the-art (SOTA) noisy-label multi-class training approach to learn a multi-label classifier for the dataset Chest X-ray14, which is a large scale dataset known to contain label noise in the training set. Given that this dataset also has label noise in the testing set, we propose a new theoretically sound method to estimate the performance of the model on a hidden clean testing data, given the result on the noisy testing data. Using our clean data performance estimation, we notice that the majority of label noise on Chest X-ray14 is present in the class 'No Finding', which is intuitively correct because this is the most likely class to contain one or more of the 14 diseases due to labelling mistakes.
The training of deep learning models generally requires a large amount of annotated data for effective convergence and generalisation. However, obtaining high-quality annotations is a laboursome and expensive process due to the need of expert radiologists for the labelling task. The study of semi-supervised learning in medical image analysis is then of crucial importance given that it is much less expensive to obtain unlabelled images than to acquire images labelled by expert radiologists.Essentially, semi-supervised methods leverage large sets of unlabelled data to enable better training convergence and generalisation than if we use only the small set of labelled images.In this paper, we propose the Self-supervised Mean Teacher for Semi-supervised (S$^2$MTS$^2$) learning that combines self-supervised mean-teacher pre-training with semi-supervised fine-tuning. The main innovation of S$^2$MTS$^2$ is the self-supervised mean-teacher pre-training based on the joint contrastive learning, which uses an infinite number of pairs of positive query and key features to improve the mean-teacher representation. The model is then fine-tuned using the exponential moving average teacher framework trained with semi-supervised learning.We validate S$^2$MTS$^2$ on the thorax disease multi-label classification problem from the dataset Chest X-ray14, where we show that it outperforms the previous SOTA semi-supervised learning methods by a large margin.