online website builder

Pre and post-hoc diagnosis and interpretation of malignancy from breast dce-mri

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.

One shot segmentation: unifying rigid detection and non-rigid segmentation using elastic regularization

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 uniļ¬es rigid detection and non-rigid segmentation using elastic regularization.

One-stage Five-class Polyp Detection and Classification

We propose a one stage detection and classification model for a new 5-class polyp classification problem.

Model Agnostic Saliency for Weakly Supervised Lesion Detection from Breast DCE-MRI

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.

End-to-End Diagnosis and Segmentation Learning from Cardiac Magnetic Resonance Imaging

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.

Producing radiologist quality reports for interpretable deep learning

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.

Deep Learning based femoral cartilage automatic segmentation in ultrasound imaging for robotic knee arthroscopy

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.

Automatic quality assessment of transperineal ultrasound images of the male pelvic region using deep learning

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.

Training Medical Image Analysis Systems like Radiologists

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

One-class Gaussian process regressor for quality assessment of transperineal ultrasound images

We propose a novel one-class deep Gaussian process that assesses the quality of ultrasound images.