Treating physicians need information about the molecular subtype of the tumor if they are to provide targeted therapy for colorectal carcinoma. A research team from University Hospital Zurich and the University of Oxford have now developed a method to predict the molecular classification of colorectal cancer from digital pathology slides.
Colorectal cancer is the third most common malignant tumor in men and women with approximately 1.8 million new cases globally per year, including around 4,000 in Switzerland. Surgery, radiation and chemotherapy as well as precision therapeutics are the established treatment options, but are associated with relevant side effects. Precise information about the molecular subtype of the tumor using RNA sequencing can support patient stratification for personalized therapy. Yet cancer classification through RNA sequencing remains a resource-intensive, costly process: examining a single sample costs over CHF 1,000. Further, up to 20 percent of samples cannot be conclusively classified due to insufficient availability of material or ambiguous results. 
{module In-article}
Research advances through image analysis and artificial intelligence
A research team led by Prof. Viktor Kölzer, Institute of Pathology and Molecular Pathology at University Hospital Zurich (UHZ), and Prof. Jens Rittscher, Institute of Biomedical Engineering at the University of Oxford, have now developed a much cheaper, faster method: they use artificial intelligence to analyze high-resolution images of histological slides. This allows the subclassification of colorectal tumors into one of four distinct transcriptional subtypes and gives an indication of optimal treatment strategies. Unlike RNA sequencing, which has been the gold standard thus far, this purely image-based procedure does not require any additional tissue material. It works even with very small tissue fragments and makes it possible to classify tissue samples that were previously inaccessible due to the technical limitations. The procedure also has the potential to lower costs considerably. Image-based procedures could therefore potentially revolutionize personalized therapy in colorectal cancer. Yet in order to use the new technology, the histological slides need to be appropriately prepared: “to use artificial intelligence for tumor analysis in daily diagnostic practice, we need to digitize pathology workflows,” says Prof. Kölzer.
Strategic importance for personalized medicine
In April this year, Prof. Kölzer accepted the post of Assistant Professor in Digital Pathology at UHZ. This professorship is the first of its kind in Switzerland with strategic importance for personalized medicine. Prof. Kölzer initialized this project on AI-supported cancer classification during his time at the University of Oxford, in a strong interdisciplinary collaboration with the pathologists, bioinformaticians, clinicians and statisticians of the multi-institutional Stratification in COloRecTal Cancer (S-CORT) Consortium. The study involved the analysis of 1,553 digital tissue slides with data on RNA expression, gene mutations and clinical progression using the latest machine vision and artificial intelligence technologies. This new technology was first published as a preprint in late May 2019 and is recommended for validation in prospective, randomized clinical trials. According to Prof. Kölzer, “After validation, we will be able to centralize the classification of colorectal tumors and release the technology for use.” Scans of histological slides could be sent to university centers, where they would be evaluated and the results returned electronically. In the long term, the method could also be used for other tumor types or even other diseases. Prof. Maughan, leader of the S:CORT consortium comments: “this research shows that, with the help of computer analysis, it is possible to detect complex biological patterns from the way the cancer looks under the microscope using routine ways to prepare tissue slides. This has great potential for providing information on how the cancer will behave in the individual and use this in the future to guide treatment decisions”.
Techniques developed by astronomers could help in the fight against breast and skin cancer. Charlie Jeynes at the University of Exeter will present his and Prof Tim Harries team's work today (3 July) at the RAS National Astronomy Meeting (NAM 2019) at the University of Lancaster.
A large part of astronomy depends on the detection and analysis of light. For example, scientists study the light scattered, absorbed and re-emitted in clouds of gas and dust, obtaining information on their interior.
Despite the vast differences in scale, the processes that light undergoes when travelling through the human body are very similar to those seen in space. And when things go wrong - when tissue becomes cancerous - that change should show up.
In the UK, nearly 60,000 women are diagnosed with breast cancer each year, and 12,000 die. Early diagnosis is key, with 90% of women diagnosed at the earliest stage surviving for at least five years, compared to 15% for women diagnosed with the most advanced stage. {module In-article}
Cancer creates tiny deposits of calcium in breasts, detected through a shift in the wavelength of light as it passes through the tissue. The Exeter team realised that the supercomputer codes developed to study the formation of stars and planets could be applied to find these deposits.
Charlie commented: "Light is fundamental to a diverse range of medical advances, like measuring blood oxygenation in premature babies, or treating port-wine stains with lasers. So there is a natural connection with astronomy, and we're delighted to use our work to take on cancer."
Working with biomedical scientist Nick Stone, also at Exeter, the team are refining supercomputer models to better understand how detected light is affected by human tissue. They eventually expect to develop a rapid diagnostic test that avoids unnecessary biopsies, improving the prospects for survival for thousands of women. Work is already underway with clinicians at Exeter's RD&E hospital to pilot the technology and pave the way for larger clinical trials
In a second project, the Exeter team are using supercomputer models for a potential new treatment for non-melanoma skin cancer (NMSC). This is the most common type of cancer, with more than 80,000 cases reported in England each year. NMSC is expected to cost the NHS £180 million a year by 2020, a figure set to rise as the disease becomes more prevalent.
In a partnership with Alison Curnow of the University of Exeter Medical School, the scientists are using their code to develop a simulated 'virtual laboratory' for studying skin cancer treatment. The two-pronged attack looks at light-activated drugs (photodynamic therapy) and light-heated nanoparticles (photothermal therapy).
The simulation looks at how gold nanoparticles in a virtual skin tumour are heated by exposure to near-infrared light. After 1 second of irradiation, the tumour heats up by 3 degrees Celsius. After 10 minutes, the same tumour is heated by 20 degrees - enough to kill its cells. So far, photothermal therapy with nanoparticles has been effective in rats, but with the team's code to narrow down experimental conditions, they are working towards translating the technology for humans.
Charlie said: "Advances in fundamental science should never be seen in isolation. Astronomy is no exception, and though impossible to predict at the outset, its discoveries and techniques often benefit society. Our work is a great example of that, and I'm really proud that we're helping our medical colleagues wage war on cancer."
The next steps include using 3D- rendered models taken from images of real tumours, and simulating how these would respond to different treatment regimes. Data exists on how these tumours responded to treatment, which gives excellent 'ground truth' data against which to compare the models. In this way the team will be able to predict whether different types of treatment would be more effective for a particular tumour type, and enable clinicians to have more options when it comes to choosing a treatment plan.
{module In-article}