Medical Success: AI Could Be The Future Of Breast Cancer Detection

Medical Success: AI Could Be The Future Of Breast Cancer Detection

It has been revealed that AI could be the future of breast cancer detection. Check out the latest reports about this below and find out new details on medical breakthroughs.

AI could be the future of breast cancer detection

Artificial intelligence (AI) has the potential to revolutionize breast cancer detection and risk assessment. A recent study conducted in Sweden revealed that AI technology could identify 20% more breast cancer cases than experienced radiologists.

Additionally, AI can reduce the workload of radiologists by over 40%, making their jobs more efficient.

The study, which was published in The Lancet Oncology, involved a randomized, controlled, population-based trial that analyzed 80,033 mammograms of women in Sweden.

The participants, aged between 40 and 80, were divided into two groups. One group had their mammograms read by AI before being analyzed by a radiologist, while the second group had their mammograms read by two radiologists without AI assistance.

The study conducted by Kristina Lang, an associate professor in diagnostic radiology at Lund University and a consultant at Skane University Hospital, found that using AI to identify screening examinations with a high risk of breast cancer, which underwent double reading by radiologists, led to a 20% increase in the number of cancers detected compared to mammograms read by two radiologists alone.

In the screening process, radiologists used AI as detection support, which highlighted suspicious findings on images.

The remaining examinations were classified as low-risk and were read only by one radiologist.

The research found that 75% of cancers detected in the AI group were invasive, while 25% were in situ.

Among those who had their mammograms analyzed by two radiologists (the control group), 81% of cancers detected were invasive, and 19% were in situ.

Carcinoma in Situ

Carcinoma in situ refers to the presence of abnormal cells in their original location that may appear cancerous under a microscope but have not spread beyond their source. It is a noninvasive cancer known as stage zero. While the in situ cells themselves are not cancerous, they can potentially develop into cancer and spread from their original location.

This type of cancer can occur anywhere in the body, but there are two types specifically associated with the breast: ductal carcinoma in situ (DCIS) and lobular carcinoma in situ (LCIS). DCIS occurs when abnormal cells are found in the milk ducts of the breast, while LCIS refers to abnormal cell growth in the lobules of the glands that produce milk.

In only about 20 percent of cases, DCIS develops into cancer, and approximately 60,000 individuals are diagnosed with DCIS each year in the United States.

It is crucial for women to understand the significance of carcinoma in situ, especially DCIS and LCIS that relate to the breast, so that they can make informed decisions about whether or not to receive treatment.

Unfortunately, some doctors may not explain these types of cancer thoroughly, which can result in women receiving unnecessary treatments.

The use of mammography to detect these types of cancer enables doctors and oncologists to closely monitor them and prevent the cells from spreading and developing into breast cancer in the future.
Helped to Decrease Workload
A recent study found that AI reduced mammogram-reading workload by 44 percent. The group supported by AI had a total of 46,345 mammograms, with radiologists reading an average of 50 screening examinations per hour. The researchers estimated that AI saved five months of time that would have been required if radiologists had read all screenings.

In Sweden, each breast screening examination is double-read by two radiologists to ensure accuracy. However, the shortage of breast radiologists in Sweden and other countries makes this process difficult. AI could potentially help alleviate some of the workload involved in reading breast screening examination

results in the future.

No effect on false positives

“According to recent findings, incorporating AI into cancer screening has resulted in a 20% increase (41) in the detection of cancers when compared to traditional screening methods, without any increase in false positives. False positives are when a woman is recalled for further testing but is ultimately cleared of cancer suspicion.

This is a common concern in mammography screening programs, with a false positive rate of 7% to 12% after a single mammogram.

This rate is higher in younger women and those with dense breasts, which affects around 40% of women. The likelihood of receiving a false positive result increases over time, rising to 50% – 60% after 10 years of annual mammograms.

Given that breast cancer incidence rates are increasing by 0.5% annually, doctors and scientists are urgently exploring more effective ways to detect and predict breast cancer risk.

Breast cancer is currently responsible for around 30% of all new cancers diagnosed in women in the United States each year, and is the most common cancer globally, accounting for 12.5% of all new cancer cases annually.

Using AI to detect breast cancer

Other studies have also explored ways that AI can help to identify breast cancer.
Breast cancer prediction is an area where AI excels. A study conducted on mammograms assessed by five AI algorithms revealed that all five were better at predicting breast cancer risk than traditional clinical risk models. The AI algorithms identified not only previously missed cancers but also features in breast tissue that could predict future cancers further.

When the AI algorithms were combined with the standard risk models, the prediction accuracy improved significantly.

MIT’s computer science and artificial intelligence lab developed an AI prediction model that can predict the development of breast cancer up to five years in advance using a patient’s mammogram.

The algorithm was trained using more than 200,000 exams, and it outperformed previous methods in predicting cancer risk and identifying high-risk groups.

The model used deep learning techniques to identify patterns in mammograms that doctors might miss, enabling it to detect cancer early.

The study on the model published in Science Translational Medicine found that the model was effective in predicting cancer risk among women with dense breast tissue, a group that is at higher risk of developing breast cancer.

Post Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.