Home

Deep Reinforcement Learning for the Active Extraction and Visualisation of Optimal Biomarkers in Medical Images

This bioengineering project will develop novel methods for discovering and visualising optimal biomarkers from chest computed tomography images based on extensions of recently developed deep reinforcement learning techniques. The extensions proposed in this project will advance the state of the art in medical image analysis given that it will allow an efficient analysis of large dimensionality inputs in their original high resolution. In addition, our project will be the first approach capable of discovering previously unknown biomarkers associated with important clinical outcomes.

July 2022 - 2 papers accepted to ECCV 2022
July 2022 - 6 papers accepted to MICCAI 2022
February 2022 - 2 papers accepted to CVPR 2022
January 2022 - Gustavo Carneiro invited to be an Area Chair for MICCAI 2022.
January 2022 - 1 paper accepted at ISBI 2022 on polyp tracking from videos
October 2021 - Hossein finished his MPhil -- congrats Hossein!
June 2021 - Prof Carneiro awarded an MRFF Primary Health Care Infrastructure
June 2021 - 4 papers accepted to MICCAI 2021
May 2021 - Gustavo Carneiro's invited presentation at SEED 2021
January 2021 - Gustavo Carneiro invited to be an Area Chair for MICCAI 2021.
January 2021 - Renato has had a paper on Survival analysis accepted to ISBI 2021.
November 2020 - Research on Endometriosis appeared in a local newspaper (article at AdelaideNow)
October 2020 - Renato Hermoza invited to speak at the 16th International Symposium on Medical Information Processing and Analysis (SIPAIM'20)
August 2020 - Renato Hermoza awarded a MICCAI Student Travel Award -- Congrats Renato!
July 2020 - Prof. Carneiro awarded an MRFF - AI grant
July 2020 - 3 papers accepted to MICCAI 2020 -- congrats to Renato, Yu and Fengbei.
July 2020 - Yu Tian passed major review -- congrats Yu!
July 2020 - invited article written by Gustavo Carneiro at Hospital + Healthcare Makazine -- link (see pages 62-64)
April 2020 - Interview about our polyp classification paper, The Lead.

February 2020 - Prof. Carneiro awarded with Cooperative Research Centres Projects (CRC-P) on AI diagnostic tool to improve optometry accuracy
March 2020 - Gabriel Maicas is interviewed by The Lead
March 2020 - 1 IEEE Acess and 1 GIE paper accepted
February 2020 - Prof. Carneiro has a paper accepted to MedIA
January 2020 - 3 papers accepted to ISBI 2020
December 2019 - Prof. Carneiro has a paper accepted to MedIA
December 2019 - Intelligent machines to support, not replace, doctors, The University of Adelaide.
November 2019 - Prof. Carneiro was awarded an ARC Future Fellowship!
November 2019 - PhD student Renato Hermoza Aragones passed major review - Congrats Renato!
October 2019 - Two Ultrasound in Medicine & Biology papers published, and Gabriel has been interviewed by The Advertiser about his work!
October 2019 - Gustavo and Gabriel are part of a group selected as a finalist for the Minister's Research and Innovation Award with the project Computer Aided Diagnosis using Artificial Intelligence in Colorectal Polyps, as part of the 2019 SA Health Awards.
September 2019 Gabriel Maicas et al. have a paper accepted to MedIA
June 2019 Prof. Nascimento and Prof. Carneiro have a paper accepted to PAMI
May 2019 - Prof. Carneiro has a paper accepted to ICML'19
February 2019 - Prof. Carneiro has a paper accepted to CVPR'19
February 2019: Welcome Research Assistant Dr. Gabriel Maicas
February - June 2019: Prof. Gustavo Carneiro spend SSP leave at IST (Portugal) and TUM (Germany), as a Humboldt Fellow
December 2018: Welcome PhD student Hossein Askari
December 2018: Congrats Gabriel Maicas for PhD and Dean’s Commendation for Doctoral Thesis Excellence!
October 2018: Workshop DLMIA @ MICCAI 2018
October 2018: Workshop BIA @ MICCAI 2018
October 2018: Oral presentation by Gabriel Maicas @ MICCAI 2018
October 2018: Welcome PhD student Renato Hermoza Aragones
October 2018: Prof. Carneiro visited IST-Lisbon and TUM on an Epic grant

Deep Reinforcement Learning for the Active Extraction and Visualisation of Optimal Biomarkers in Medical Images

Workshops

Publications

In Defense of Kalman Filtering for Polyp Tracking from Colonoscopy Videos

NVUM: Non-Volatile Unbiased Memory for Robust Medical Image Classification

Contrastive Transformer-based Multiple Instance Learning for Weakly Supervised Polyp Frame Detection

Censor-aware Semi-supervised Learning for Survival Time Prediction from Medical Images

Test Time Transform Prediction for Open Set Histopathological Image Recognition

Post-hoc Overall Survival Time Prediction from Brain MRI.

Artificial intelligence for the diagnosis of lymph node metastases in patients with abdominopelvic malignancy: a systematic review and meta-analysis

3D Semantic Mapping from Arthroscopy using Out-of-distribution Pose and Depth and In-distribution Segmentation Training

Self-supervised Lesion Change Detection and Localisation in Longitudinal Multiple Sclerosis Brain Imaging

Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Images

Balanced-MixUp for highly imbalanced medical image classification

Region Proposals for Saliency Map Refinement for Weakly-supervised Disease Localisation and Classification

Few-Shot Anomaly Detection for Polyp Frames from Colonoscopy

Self-supervised Depth Estimation to Regularise Semantic Segmentation in Knee Arthroscopy

Semi-supervised Multi-domain Multi-task Training for Metastatic Colon Lymph Node Diagnosis From Abdominal CT

Photoshopping Colonoscopy Video Frames

Unsupervised Task Design to Meta-Train Medical Image Classifiers

Deep Learning Uncertainty and Confidence Calibration for the Five-class Polyp Classification from Colonoscopy

Automatic Segmentation of Multiple Structures in Knee Arthroscopy Using Deep Learning

Computer-aided diagnosis for characterization of colorectal lesions: a comprehensive software including serrated lesions.

Pre and Post-hoc Diagnosis and Interpretation ofMalignancy from Breast DCE-MRI

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

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

Siam-U-Net: encoder-decoder siamese network for knee cartilage tracking in ultrasound images

Producing radiologist quality reports for interpretable deep learning

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

Bayesian Generative Active Deep Learning

A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning

One-stage Five-class Polyp Detection and Classification

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

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

Approximate Fisher Information Matrix to Characterise the Training of Deep Neural Networks

Multi-modal Cycle-consistent Generalized Zero-Shot Learning

Bayesian Instance Segmentation in Open Set World

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

Training Medical Image Analysis Systems like Radiologists

Invited Talks

O(N) Training of Triplet Nets for Distance Metric Learning

Pre and post-hoc Diagnosis and Interpretation of Malignancy from Breast DCE-MRI

Safety is the Foundation of Medical ML

Machine learning capability at AIML with examples of projects that identify organs from MRI and ultra-sound

Machine Learning (ML) for Medical Image Computing (MIC) and Computer Assisted Intervention (CAI)

Podcast hosted by the University of Adelaide CS Club

AI and ML fundamentals for clinicians

Machine Learning Potential and Limitations in Medical Diagnostics

Awards

Mr. Hossein Askari Lyarjdameh

Mr. Fengbei Liu

Our Contacts

Address and email

Pre and Post-hoc Diagnosis and Interpretation of
Malignancy from Breast DCE-MRI

Machine Learning (ML) forMedical Image Computing (MIC) andComputer Assisted Intervention (CAI)

Mr.
Hossein Askari Lyarjdameh