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.
In this paper, we propose a novel self-supervised representation learning method, called Constrained Contrastive Distribution learning for anomaly detection (CCD), which learns fine-grained feature representations by simultaneously predicting the distribution of augmented data and image contexts using contrastive learning with pretext constraints.
In this paper, we propose a novel mechanism for sampling training databased 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.
we introduce a new post-hoc method for OS time prediction that does not require segmentation map annotation for training. Our model uses medical image and patient demographics (represented by age) as inputs to estimate the OS time and to estimate a saliency map that localizes the tumor as a way to explain the OS time prediction in a post-hoc manner.
The main methods designed for weakly supervised disease classification and localisation rely on saliency or attention maps that are not specifically trained for localisation, or on region proposals that can not be refined to produce accurate detections. In this paper, we introduce a new model that combines region proposal and saliency detection to overcome both limitations for weakly supervised disease classification and localisation
We propose a novel self-supervised monocular depth estimation to regularise the training of the semantic segmentation in knee arthroscopy. To further regularise the depth estimation, we propose the use of clean training images captured by the stereo arthroscope of routine objects (presenting none of the poor imaging conditions and with rich texture information) to pre-train the model.
We propose a new few-shot anomaly detection method based on an encoder trained to maximise the mutual information between feature embeddings and normal images, followed by a few-shot score inference network, trained with a large set of inliers and a substantially smaller set of outliers
In this paper, we study the roles of conﬁdence calibration (via post-process temperature scaling) and classiﬁcation uncertainty (computed either from classiﬁcation entropy or the predicted variance produced by Bayesian methods) in deep learning models. Results suggest that calibration and uncertainty improve classiﬁcation interpretation and accuracy.
In this study, CAD software developed at the University of Adelaide (Australia) that includes serrated polyp differentiation was validated with Japanese images on narrow-band imaging (NBI) and blue-laser imaging (BLI).
We propose a new method for the automatic segmentation of multiple tissue structures for knee arthroscopy.
We propose a new method to unsupervisedly design a large number of classification tasks to meta-train medical image classifiers.
We introduce a new system that detects frames containing polyps as anomalies from a distribution of frames from exams that do not contain any polyps. The system is trained using a one-class training set consisting of colonoscopy frames without polyps--such training set is considerably less expensive to obtain, compared to the 2-class data set mentioned above.
We introduce a new training strategy from two data sets: one containing the global annotations, and another (publicly available) containing only the lymph node ROI localisation. We term our new strategy semi-supervised multi-domain multi-task training, where the goal is to improve the diagnosis accuracy on the globally annotated data set by incorporating the ROI annotations from a different domain.
We propose a new deep learning method to track, accurately and eﬃciently, the femoral condyle cartilage in ultrasound sequences, which were acquired under several clinical conditions, mimicking realistic surgical setups. Our solution, that we name Siam-U-Net, requires minimal user initialization and combines a deep learning segmentation method with a siamese framework for tracking the cartilage in temporal and spatio-temporal sequences of 2D ultrasound images.
We propose a new method for breast cancer screening from DCE-MRI based on a post-hoc approach that is trained using weakly annotated data (i.e., labels are available only at the image level without any lesion delineation). The advertiser interviewed Gabriel about this project.
This paper proposes a novel approach for the non-rigid segmentation of deformable objects in image sequences, which is based on one-shot segmentation that uniﬁes rigid detection and non-rigid segmentation using elastic regularization.
In this work, we studied the feasibility of using a state-of-the-art deep neural network (UNet) to automatically segment femoral cartilage imaged with dynamic volumetric US (at the refresh rate of 1 Hz), under simulated surgical conditions.
We propose a one-class classifier deep learning algorithm to discriminate among US images acquired in a simulated surgical scenario where the femoral cartilage could/could not be outlined.
We propose a one stage detection and classification model for a new 5-class polyp classification problem.
We propose a new model agnostic paradigm to interpret deep learning model classification decisions supported by a novel definition of saliency that incorporates the following conditions: 1) for images with lesions, all salient regions should represent lesions, 2) for images containing no lesions, no salient region should be produced,and 3) lesions are generally small with relatively smooth borders.
We propose a learning method to train diagnosis models, where our approach is designed to work with relatively small datasets. In particular, the optimisation loss is based on multi-task learning that jointly trains forthe tasks of segmentation and diagnosis classification.
We propose a model-agnostic interpretability method that involves training a simple recurrent neural network model to produce descriptive sentences to clarify the decision of deep learning classifiers.
We propose a novel training approach inspired by how radiologists are trained. In particular, we explore the use of meta-training that models a classifier based on a series of tasks. Tasks are selected using teacher-student curriculum learning, where each task consists of simple classification problems containing small training sets
We propose a novel one-class deep Gaussian process that assesses the quality of ultrasound images.