Mammographic density is an important risk factor for breast cancer. Recent research has shown that percentage density assessed visually using visual analogue scales (VAS) showed stronger risk prediction than existing automated density measures, suggesting radiologists may recognise relevant image features not yet captured by hand-crafted algorithms. We show that a convolutional neural network is able to accurately predict the VAS scores provided by radiologists and provide an automated method for predicting breast cancer risk in a screening setting.
Speaker: Dr Martin Fergie
Martin Fergie is a computer science researcher at the University of Manchester in the Division of Informatics, Imaging and Data Sciences. After completing his PhD in 2012, he became the Chief Technology Officer of DigitalBridge, a start-up applying deep learning technology for performing image understanding for indoor scenes.
In March 2017 he moved to the University of Manchester to apply his experience in machine learning and computer vision to help develop novel imaging biomarkers. His current research is focused on developing models for predicting breast cancer risk from screening mammograms.
Breast cancer is the most common cancer among women in the world. It is estimated that one in eight women, all over the wide, would develop breast cancer during her life. Breast cancer is considered one of the first-leading causes of cancer deaths among women. The early detection of breast cancer could save many women's life. Mammogram is one of the most imaging technology used for diagnosing breast cancer. Although mammogram has recorded a high detection and classification accuracy, it is difficult in imaging dense breast tissues, its performance is poor in younger women, it is harmful, and it couldn’t detect breast tumor that less than 2 mm. To overcome these limitations, it was found that there is a relation between the temperature and the presence of breast cancer. Utilizing this fact, infrared thermography could be a good source of breast images to study and detect cancer at the early stages which is crucial for cancer patients for increasing the rate of breast cancer survival.
This talk aims to give an overview of the thermal imaging technology, its possible applications in the medical field, focusing on its opportunities and challenges for the early detection of breast cancer and highlighting the state-of-the-art of this point.
Speaker: Dr Tarek Gaber
Dr. Gaber is currently a lecturer of Compute Science and Software Engineering at Salford University. He received a PhD degree from the University of Manchester in Computer Science in 2012. He has significant experience with using image processing methods and machine learning technique. His research has been published in leading journals in these areas such as Signal, Image and Video Processing (Springer), Computer Networks (Elsevier), Computers & Electrical Engineering (Elsevier), and Computers and Electronics in Agriculture (Elsevier). He has published 40+ articles/papers and edited 4 books. Dr. Gaber has supervised 4 MSc (Research) students to successful completion and currently supervising PhD students.
Tarek was Programme Co-Chair of the International Conference on Advanced Intelligent Systems and Informatics (2015, 2016, and 2017) and the International Conference on Advanced Machine Learning Technologies and Applications (AMLTA2019). He is currently a Programme Co-Chair of the International Conference on Artificial Intelligence and Computer Vision (AICV’2020) which will be held in April 2020.
This is a joint event between the BCS Health Northern SG and the BCS Manchester Branch
Free parking: The nearest car park to the Business School is the John Dalton car park underneath the Mancunian Way. The carpark is accessed south off Chester Street, M1 5GD, and is located close to the back entrance of the Business School. Drive towards the south of the car park, park up, and enter the Business School via the rear entrance between buildings 5 and 6 on the campus map. There are 12 designated disabled parking spaces. The spaces are clearly marked and have sufficient width to allow wheelchair users to get in and out of their vehicles. All of the John Dalton car park is on one level smooth surface on the ground floor.
Travel Options to the Business School:
The Business School is situated just off Oxford Road on the Manchester Campus (All Saints). The closest railway station is Manchester Oxford Road, which is 0.3 miles away. Manchester Piccadilly Railway Station is 0.9 miles away and Manchester Victoria is 2 miles. Taxis can be pre-booked through Radio Cars, who also have wheelchair accessible taxis. Their contact number is 0161 236 8033. There are taxi ranks outside each railway station and the nearest drop off point at the Business School is either Ormond Street or Cambridge Street, close to the Business School entrance. Sat Nav postcode: M15 6FH
Claim the event and start manage its content.I am the organizer