In a newly published study, an algorithm developed at NIH shows promise for improving early detection of cervical cancer in low-resource areas, where 80 percent of cases occur.
The Clinical Treatment Score post-5-years tool helps clinicians identify which patients are at high risk of their cancers recurring after completing five years of adjuvant hormone therapy.
The firm's algorithm rapidly identifies skin irregularities by comparing the image to data from its cloud-based database, acting as a diagnostic aid for pathologists.
A study led by Johns Hopkins describes a method for automating slow, inaccurate manual chart review when searching for signs of misdiagnosis.
Clinical validation work suggests that the firm's DCISionRT test could be used to stratify patients who may benefit from radiation, in addition to being used as a diagnostic tool.
The funding will go toward bringing the BA100 test to clinicians. The test can identify patients most likely to respond to the standard of care chemotherapy treatment.
The commercial future of the test is uncertain, but one of its developers said that work to develop it demonstrates even mature technologies can have new clinical value.
Google researchers said their technology was able to detect 89 percent of tumors compared to 73 percent for pathologists analyzing slides.
Following validation, the approach, which uses a deep convolutional neural network trained with almost 130,000 clinical images, could be developed into a smartphone app to detect skin cancer early.
The company said that it can distinguish patients suffering from lupus from those with other autoimmune diseases using its antibody array platform.