Spotting cancer on smartphone photos

Researchers in the US have developed a new deep learning tool to more easily identify harmful skin lesions from photographs taken with a smartphone. The tool was devised using a branch of artificial intelligence called deep convolutional neural networks (DCNNs) and then ‘trained’ using more than 20,000 images. Importantly, the pictures were taken using different personal cameras, to ensure that it would work with real-life examples. Once the tool was trained using known examples, it demonstrated more than 90.3% sensitivity and 89.9% specificity in distinguishing suspicious pigmented lesions (SPLs) from nonsuspicious lesions, skin, and complex backgrounds.

“Electronic Nose” sniffs out cancer 

An odour-based test that sniffs out vapours emanating from blood samples was able to distinguish between benign and pancreatic and ovarian cancer cells with up to 95% accuracy, according to a new US study. The findings suggest that the new tool, which uses artificial intelligence and machine learning to decipher the mixture of volatile organic compounds (VOCs) emitting off cells in blood plasma samples, could serve as a non-invasive approach to screen for harder-to-detect cancers, such as pancreatic and ovarian. The electronic olfaction – ‘e-nose’ – system is equipped with nanosensors calibrated to detect the composition of VOCs, which all cells emanate. Among 93 patients, including 20 patients with ovarian cancer, 20 with benign ovarian tumours and 20 age-matched controls with no cancer, as well as 13 patients with pancreatic cancer, 10 patients with benign pancreatic disease, and 10 controls, the vapour sensors discriminated the VOCs from ovarian cancer with 95% accuracy and pancreatic cancer with 90% accuracy. The tool also correctly identified all patients (a total of eight) with early-stage cancers.

New prostate cancer urine test 

An experimental new test called ‘ExoGrail’ has the potential to revolutionise how patients with suspected prostate cancer are risk-assessed prior to an invasive biopsy. The researchers from the University of East Anglia, UK, said their new test could reduce the number of unnecessary prostate cancer biopsies by 35%. They developed the new ExoGrail urine test by combining two biomarker sources – measurements of a protein-marker called EN2 and the levels of gene expression of 10 genes related to prostate cancer risk. It builds on previously developed tests called PUR and ExoMeth. They then tested it using urine samples from 207 patients who had been undergone a biopsy for prostate cancer, successfully identifying patients who had prostate cancer and which did not. The ExoGrail test also provided risk scores for patients and highlighted those for which an invasive biopsy would have been beneficial.

New algorithm flags cancer’s weak spots

A new way to identify tumours that could be sensitive to particular immunotherapies has been developed using data from thousands of cancer patient samples sequenced through the 100,000 Genomes Project. The MMRDetect clinical algorithm makes it possible to identify tumours that have ‘mismatch repair deficiencies’ and then improve the personalisation of cancer therapies to exploit those weaknesses. 

The study, led by researchers from the University of Cambridge’s Department of Medical Genetics and MRC Cancer Unit, identified nine DNA repair genes that are critical guardians of the human genome from damage caused by oxygen and water, as well as errors during cell division. The team used a genome editing technology, CRISPR-Cas9, to ‘knock out’ (make inoperative) these repair genes in healthy human stem cells. In doing so, they observed strong mutation patterns, or mutational signatures, which offer useful markers of those genes and the repair pathways they are involved in, failing. The study suggested that these signatures of repair pathway defects are on-going and could therefore serve as crucial biomarkers in precision medicine.

Senior author, Dr Serena Nik-Zainal, a Cancer Research UK Advanced Clinician Scientist at Cambridge University’s MRC Cancer Unit, said: “When we knock out different DNA repair genes, we find a kind of fingerprint of that gene or pathway being erased. We can then use those fingerprints to figure out which repair pathways have stopped working in each person’s tumour, and what treatments should be used specifically to treat their cancer.”

New biomaterial from aquaculture waste

Scientists in Singapore have developed a new biomaterial made entirely from discarded bullfrog skin and fish scales that could help in bone repair. Such a biomaterial could be used to help with the regeneration of bone tissue lost to disease or injury, such as jaw defects from trauma or cancer surgery. 

The porous biomaterial, which contains the same compounds that are predominant in bones, acts as a scaffold for bone-forming cells to adhere to and multiply, leading to the formation of new bone. Through laboratory experiments, the Nanyang Technological University Singapore team found that human bone-forming cells seeded onto the biomaterial scaffold successfully attached themselves and started multiplying – a sign of growth. They also found that the risk of the biomaterial triggering an inflammatory response is low when compared to a control exposed to endotoxins, a compound known to stimulate immune response. The scientists believe the biomaterial is a promising alternative to the current standard practice of using a patient’s own tissues, which requires additional surgery for bone extraction.