AI-powered cancer-spotting kit

Google has contributed software to an AI-powered microscope the US Department of Defence (DoD) hopes will help pathologists spot cancerous cells in tissue samples much more quickly. The device, named the Augmented Reality Microscope (ARM), is in many regards a conventional ‘scope’ – users place samples on a glass tray and peer at them through an eyepiece. However, the ARM also employs computer vision algorithms that guides medics to focus on potentially problematic areas, and creates heatmaps labelling cells as benign or cancerous. Those images can be displayed on a monitor to allow more detailed study.

Researchers are already using ARMs to detect breast cancer, cervical cancer, prostate cancer and cell duplication using four different AI algorithms. The DoD’s Defense Innovation Unit (DIU) is investing in the technology to aid pathologists working at military hospitals that are often short-staffed. The Unit believes that the technology can speed the diagnosis process and provide experts with a second opinion when diagnosing diseases.

In all, 13 prototypes have been built so far; one of them is at the MITRE lab near Washington DC, one of the US government’s advanced science and technology R&D research groups. A team of researchers have tested the device’s abilities to detect breast cancer that has metastasised in lymph nodes. Results from early experiments showed that it was able to classify cancerous and benign cells with an accuracy level of about 94%.

Chemo via biodegradable brain implant 

Scientists have developed a biodegradable implant that helps chemotherapy drugs penetrate the blood-brain barrier and deliver a direct hit on brain tumours. It’s the latest advance in a rapidly growing field using ultrasound to fight cancer and other diseases. The team used paclitaxel in its study, a drug that generally struggles to break through the blood-brain barrier. This blood vessel lining keeps molecules from passing from blood to brain, but can also prohibit chemotherapy from reaching cancer cells. By implanting 5mm2 single-element US transducer into the skulls of mice, directly behind the tumour site, the researchers found a way to penetrate this. The implants generated ultrasound waves to loosen the barrier and allow the drugs to reach the tumour. Healthy tissue surrounding the area remained unharmed. According to the research, the tumours in the mice shrank, while the rodents doubled their lifetime compared to untreated mice. They also showed no poor effects on health at six months follow-up.

AI identifies cancers of unknown primary

Using machine learning, researchers at MIT and Dana-Farber Cancer Institute in the US have created a computational model that can analyse the sequence of about 400 genes and use that information to predict where a given tumour originated in the body. Using this model, the researchers showed that they could accurately classify at least 40% of tumours of unknown origin with high confidence, in a dataset of about 900 patients. This approach enabled a 2.2-fold increase in the number of patients who could have been eligible for a genomically guided, targeted treatment, based on where their cancer originated.

Wearable ultrasound scanner 

MIT researchers have designed a wearable ultrasound device that could allow people to detect tumours when they are still in early stages. In particular, it could be valuable for patients at high risk of developing breast cancer in between routine mammograms. 

The device is a flexible patch that can be attached to a bra, allowing the wearer to move an ultrasound tracker along the patch and image the breast tissue from different angles. In the new study, the researchers showed that they could obtain ultrasound images with resolution comparable to that of the ultrasound probes used in medical imaging centers.

“We changed the form factor of the ultrasound technology so that it can be used in your home. It’s portable and easy to use, and provides real-time, user-friendly monitoring of breast tissue,” said Canan Dagdeviren, an associate professor in MIT’s Media Lab and the senior author of the study. “My goal is to target the people who are most likely to develop interval cancer,” says Dagdeviren, whose research group specialises in developing wearable electronic devices that conform to the body. “With more frequent screening, our goal to increase the survival rate to up to 98%.”

Cancer ‘sense-and-respond’ implant 

Cancer cells are constantly evolving and becoming resistant to treatment. Despite this, current diagnostic methods, such as imaging tests, blood tests, and tissue samples, offer only infrequent and limited views of these changes. Therefore, existing treatments often approach cancer as if it’s a static disease. Now, a new miniature implant capable of continuously monitoring a patient’s cancer and adjusting their immunotherapy dose in real-time could become a game-changer. This device could supply real-time data from the tumour site, which could then be used to tailor more effective, tumour-specific therapies.

A team of researchers led by Rice University in Houston, Texas, US, has been awarded a $45 million grant by the Advanced Research Projects Agency for Health (ARPA-H) to speed up the development of a sense-and-respond implant technology (prototype pictured below) that could reduce cancer-related fatalities in the US by more than half. The research group is comprised of engineers, physicians, and multidisciplinary specialists in synthetic biology, materials science, immunology, oncology, electrical engineering, artificial intelligence, and other fields spanning 20 different research labs. The grant is set to fast-track the development and testing of this novel approach, focusing on significantly enhancing immunotherapy results in patients suffering from hard-to-treat cancers such as ovarian and pancreatic types.