Constant scientific innovation and new technologies improve cancer detection and treatment worldwide. Imperial College London will lead, for at least 12 months, a consortium of clinicians and academics, which will collaborate with DeepMind Health and the Google AI health research team to develop more accurate breast cancer diagnosis thanks to artificial intelligence. Based at the Cancer Research UK Imperial Centre, the project will explore whether machine learning could make breast screening technologies more efficient than they are nowadays – mammograms, which are X-rays images of the breasts, miss thousands of cases every year, including an estimated 30% of interval cancers. The consortium will use machine learning technology on about 7,500 depersonalised mammography images from the OPTIMAM mammography database to train computer algorithms to better analyse screenings and identify cancerous tissue more accurately. This would lead to earlier detection and treatment. If successful, the technology could benefit millions of women: according to the last available data from the World Cancer Research Fund International, breast cancer is the most common cancer among women in the world, and the second most frequent cancer overall.
This is a guest post by Irma Rastegayeva, an innovation catalyst, entrepreneur, and consultant based in Boston. She left a successful 5-year tenure at Google in 2016 to pursue her passion for medical technology and healthcare innovation. Every 19 seconds, someone in the world is diagnosed with breast cancer "This changes everything!" said women's health nurse practitioner Barbara Dehn. And we desperately need a game-changer. Every 13 minutes, one woman dies of breast cancer in the US.
Radiologists getting an assist from artificial intelligence can detect more breast cancer--with a reduced rate of false positive incidents--from mammography images. A new study, published late last week in the Lancet Digital Health online journal, contends that AI can boost the accuracy of diagnosis by radiologists, compared with the results they achieve by just examining images from mammography exams. The study was conducted by Korean academic hospitals and Lunit, a Seoul-based medical AI company working in radiology and oncology. It draws on large-scale data of more than 170,000 mammogram examinations from five healthcare organizations in South Korea, the U.S. and the U.K. The set of data includes more than 36,000 cases found positive for cancer and verified by biopsies. That data trained the AI models, and the sensitivity of the model was compared with how radiologists perform without any technological assistance with diagnosis.
The global statistics for breast cancer are staggering: 1 in 8 women worldwide will be diagnosed at some point during their lifetime. Women who are diagnosed early have a 95 percent chance of living at least five years after diagnosis and it's estimated early breast cancer diagnosis could save 400,000 lives globally each year, according to the World Health Organization. Fine needle aspiration (FNA) is currently the least invasive technique to biopsy breast lumps, or masses. FNAs are less painful, less expensive to do, result in less complications for patients, and make results available more quickly than the current traditional core or open biopsies. FNAs are currently less reliable in conclusively diagnosing breast cancer than more invasive and painful techniques.
This allows much better resolution in seeing into breast tissue. Generally is a supplement for problem solving if there is a questionable finding on mammogram or ultrasound. Not used for general screening because it is not specific enough in finding breast cancer. Diagnosing breast cancer twenty to twenty-five years ago typically was done by a surgeon removing a section of breast tissue for evaluation by a pathologist. A core needle does exactly as the term suggests.