Selected Publications

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). Our proposed post-hoc method automatically diagnosis the whole volume and, for positive cases, it localizes the malignant lesions that led to such diagnosis. Conversely, traditional approaches follow a pre-hoc approach that initially localises suspicious areas that are subsequently classified to establish the breast malignancy – this approach is trained using strongly annotated data (i.e., it needs a delineation and classification of all lesions in an image). Another goal of this paper is to establish the advantages and disadvantages of both approaches when applied to breast screening from DCE-MRI. Relying on experiments on a breast DCE-MRI dataset that contains scans of 117 patients, our results show that the post-hoc method is more accurate for diagnosing the whole volume per patient, achieving an AUC of 0.91, while the pre-hoc method achieves an AUC of 0.81. However, the performance for localising the malignant lesions remains challenging for the post-hoc method due to the weakly labelled dataset employed during training.
Preprint, 2018

The training of medical image analysis systems using machine learning approaches follows a common script: collect and annotate a large dataset, train the classifier on the training set, and test it on a hold-out test set. This process bears no direct resemblance with radiologist training, which is based on solving a series of tasks of increasing difficulty, where each task involves the use of significantly smaller datasets than those used in machine learning. In this paper, 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 hypothesize that our proposed meta-training approach can be used to pre-train medical image analysis models. This hypothesis is tested on the automatic breast screening classification from DCE-MRI trained with weakly labeled datasets. The classification performance achieved by our approach is shown to be the best in the field for that application, compared to state of art baseline approaches: DenseNet, multiple instance learning and multi-task learning.
In MICCAI, 2018

We present a novel methodology for the automated detection of breast lesions from dynamic contrast-enhanced magnetic resonance volumes (DCE-MRI). Our method, based on deep reinforcement learning, significantly reduces the inference time for lesion detection compared to an exhaustive search, while retaining state-of-art accuracy. This speed-up is achieved via an attention mechanism that progressively focuses the search for a lesion (or lesions) on the appropriate region(s) of the input volume. The attention mechanism is implemented by training an artificial agent to learn a search policy, which is then exploited during inference. Specifically, we extend the deep Q-network approach, previously demonstrated on simpler problems such as anatomical landmark detection, in order to detect lesions that have a significant variation in shape, appearance, location and size. We demonstrate our results on a dataset containing 117 DCE-MRI volumes, validating run-time and accuracy of lesion detection.
In MICCAI, 2017

Publications

. Pre and Post-hoc Diagnosis and Interpretation of Malignancy from Breast DCE-MRI. Preprint, 2018.

PDF

. Model Agnostic Saliency for Weakly Supervised Lesion Detection from Breast DCE-MRI. Preprint, 2018.

PDF

. Training Medical Image Analysis Systems like Radiologists. In MICCAI, 2018.

PDF

. Deep Reinforcement Learning for Active Breast Lesion Detection from DCE-MRI. In MICCAI, 2017.

PDF Video

. Spectral Shape Analysis of the Hippocampal Structure for Alzheimer’s Disease Diagnosis. Trends in Differential Equations and Applications, 2016.

PDF

Professional Activities

Reviewer: Medical Image Analysis MedIA

Program Commitee: Medical Imaging with Deep Learning MIDL 2018

Program Commitee: Workshop on Deep Learning in Medical Image Analysis. Miccai 2018

Program Commitee: Workshop on Deep Learning in Medical Image Analysis. Miccai 2017

Program Commitee. Miccai 2017

Program Commitee: VISART-Where Computer Vision Meets Art. ECCV 2016

Program Commitee: Workshop on Deep Learning in Medical Image Analysis. Miccai 2016

Volunteering: DICTA 2015 Conference

Teaching

The University of Adelaide

Introduction to Programming for Engineers - Semester 2 2017

Software Engineering & Project - Semester 2 2017

Software Engineering & Project - Semester 2 2016

Introduction to Programming for Engineers - Semester 1 2016

Contact