Transatlantic partners Cambridge Consultants in the UK and Exact Imaging in Toronto, Canada are leveraging Artificial Intelligence to improve the way in which prostate cancer is visualised and detected.

Cambridge Consultants says it is applying deep learning to high-resolution micro-ultrasound imaging to identify potential suspicious regions of tissue and inform urologists who may want to consider this additional data in their biopsy protocol. The technology product design consultancy says that early results “show real promise.”

Prostate cancer is the second most common cause of cancer death in men in both the US and the UK. There is an urgent need for improved accuracy in the detection and diagnosis of aggressive prostate cancers.

The current standard-of-care ultrasound, which guides prostatic needle biopsies that help to diagnose prostate cancer, yields a 30 per cent false negative rate as the resolution of the ultrasound systems is insufficient to differentiate suspicious regions. As such, the prostate biopsies are usually delivered in a systematic, ‘blind pattern.

Exact Imaging’s ExactVu™ micro-ultrasound platform is a significant new imaging tool to allow urologists to harness micro ultrasound’s near microscopic resolution to visualise suspicious regions and actually target their biopsies to those regions. 

Operating at 29 MHz, the micro-ultrasound provides a 300 per cent improvement in resolution over conventional ultrasound.

Cambridge Consultants aims to harness higher resolution micro-ultrasound images from the ExactVu™ platform, in combination with decades of medical technology expertise and cutting-edge machine learning techniques, to provide new information to urologists to help them to improve their targeting of prostate biopsies. 

In recent years Cambridge Consultants has been at the forefront of advances in machine learning and deep learning, applying this transformative technology to a wide range of industries and disciplines.

With its AI tools able to interrogate the full ultrasound data set correlated to pathology, the analysis should deliver improved accuracy and better characterisation of suspicious regions. 

The machine learning approach being applied is faster and less computationally intensive than traditional statistical approaches and may ultimately form the backbone of a commercially-viable software application. 
Early results from proof of concept testing show significant promise, even with relatively limited data sets.

Shweta Gupta, head of Urology and Women’s Health at Cambridge Consultants said: “The need for effective management of prostate cancer is as pressing as ever. We are proud to have the opportunity to try and improve the detection pathway and excited by the opportunity to apply deep learning to this significant clinical problem.”

The current work on prostate cancer is the latest output from Cambridge Consultants’ Digital Greenhouse  – a unique experimental environment where data scientists and engineers explore and develop cutting edge machine learning and deep learning techniques. 

Recent work has focused on applying deep learning in areas where massive datasets are unavailable. In this case, data was available on hundreds of patients – aiming to ensure that deep learning is potent beyond the huge online datasets that have powered advances to date.