AI in Mammography: Improving Early Detection of Breast Cancer in India

In a significant development, a recent study published in The Lancet suggests that Artificial Intelligence (AI) could assist radiologists in diagnosing breast cancer more accurately and efficiently. This technology might prove invaluable in early detection, particularly for aggressive cancer types, while also reducing the heavy workload on medical professionals. Carried out in Sweden, where over one lakh women participated in a national screening program, the findings have significant implications for countries like India, where breast cancer accounts for 26.6% of all female cancer cases and faces a scarcity of skilled radiologists in many regions.

The Study Details

The study involved women aged between 40 to 74 who underwent breast cancer screening. Each mammogram was reviewed by at least two radiologists to confirm results. The AI system evaluated the mammograms and categorized them into three risk levels, with scores from 1 to 7 indicating low risk, 8 to 9 representing intermediate risk, and 10 signaling the highest risk. While women at low to intermediate risk had their mammograms reviewed by one radiologist, those classified at high risk by the AI system underwent a second review.

Remarkably, the AI-assisted screening method detected 6.4 cases per 1,000 women compared to the 5 cases per 1,000 detected using the standard method. This advanced technology also identified more invasive cancers, spotting 270 cases, compared to the 217 cases detected through conventional screening.

An additional significant benefit of AI-assisted screening is its efficiency in reducing the workload of radiologists, decreasing it by 44.2%, without increasing the number of false positives.

Why This Matters

Breast cancer is the most prevalent cancer among women worldwide. Mammography has been proven effective in decreasing mortality rates, although further studies are required to determine if AI-assisted mammography can reduce mortality rates even more. The study showcased that AI can identify cancers at an earlier stage, providing a critical benefit.

Dr. Abhishek Shankar, an oncologist at the All India Institute of Medical Sciences (AIIMS-Delhi), highlights the significant impact this technology could have in India: “Given the current disaggregated reporting system in our health care settings, this technology holds the potential to bring uniformity in how cancers are diagnosed and reported, even among doctors at different skill levels.”

Overcoming Challenges in India

Addressing breast cancer screening and treatment in India involves tackling several challenges. Firstly, the disease burden is substantial, with 98,000 deaths annually according to the Global Cancer Observatory. Additionally, Indian women develop breast cancer at a younger age compared to their Western counterparts. On average, the onset of breast cancer occurs in the early 40s to 50s in India, whereas it typically ranges from 40 to 50 in Western countries.

Secondly, detection remains challenging for younger women, who have denser breast tissue that complicates mammographic visualization, which is most effective in women over 50.

Finally, India experiences higher rates of aggressive breast cancer subtypes, such as triple-negative breast cancer, which does not respond to most standard treatments, and HER2-positive breast cancer, which is particularly aggressive.

Building Fit-for-Indian AI Models

For AI technologies to be truly effective in reducing breast cancer mortality rates in India, they need to be tailored to local conditions. One significant challenge is the development of an accurate Indian dataset for AI training. The patterns of breast cancer in India differ significantly from those observed in Western populations.

Creating such a dataset will require concerted efforts from the healthcare community, including医疗机构 and research institutions, to gather and share relevant data responsibly. By doing so, these AI models can become better suited to diagnose breast cancer in Indian women accurately and efficiently.

Current Availability of AI Technologies

The question arises regarding the current availability and adoption of AI technologies in breast cancer screening in India. While not widespread yet, these technologies hold significant promise for the future of cancer care. Partnerships between research institutions, private sector companies, and government bodies will be crucial in bringing these innovative solutions to the forefront of healthcare in India.

Investments in research, infrastructure, and training programs will help develop a skilled workforce capable of utilizing these advanced tools effectively, ultimately benefiting millions of women across the country.

While AI-assisted mammography represents a significant step forward in breast cancer screening, more work is needed to adapt these technologies to the unique needs and contexts of different countries, including India.

Discussing the potential and challenges of AI in breast cancer detection is a crucial step forward. Join the conversation by sharing your thoughts on how this technology can revolutionize breast cancer screening in India.

If this article resonated with you, please consider sharing it or subscribing to our newsletter to stay informed about the latest in medical advancements and healthcare innovations. Let us know your thoughts on the impact of AI in breast cancer detection in the comments section below.