AI improves diagnosis, reduces false positives from mammo images
Radiologists getting an assist from artificial intelligence can detect more breast cancer—with a reduced rate of false positive incidents—from mammography images.
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 study found a significant improvement in the performance of radiologists before and after using AI. Researchers found that the AI alone showed 88.8 percent sensitivity in breast cancer detection—meaning the technology was able to identify breast cancer in about eight out of every nine sets of mammograms. By contrast radiologists’ sensitivity was 75.3 percent, but their performance increased to 84.8 percent when they got help from AI.
The survey also found that AI displayed better sensitivity in detecting cancer with mass, compared with the radiologists (90 percent vs. 78 percent). Artificial intelligence also was better in the detection of T1 cancers, which is considered early-stage invasive cancers. AI detected 91 percent of T1 cancers and 87 percent of node-negative cancers, while radiologists by themselves detected just 74 percent of both instances.
Breast density is also an important factor in diagnosing mammograms—dense breast tissues are more difficult to interpret because dense tissue is more likely to mask cancers in mammograms. The findings show that the diagnostic performance of AI was less affected by breast density, while radiologists' performance was prone to density, showing higher sensitivity for fatty breasts at 79.2 percent, compared with dense breasts at 73.8 percent. When aided by AI, the radiologist's sensitivity when interpreting dense breasts increased by 11 percent.
AI appears to have potential in helping radiologists limit the number of unnecessary biopsies, researchers say. To reduce the number of false negatives—missed cases—radiologists tend to seek biopsies for which they’re not certain of a diagnosis, says Eun Kyung Kim, a professor and radiologists at Yonsei University Severance Hospital.
"It requires extensive experience to correctly interpret breast images, and our study showed that AI can help find more breast cancer with lesser recalls, also detecting cancers in its early stage of development," he adds.
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 study found a significant improvement in the performance of radiologists before and after using AI. Researchers found that the AI alone showed 88.8 percent sensitivity in breast cancer detection—meaning the technology was able to identify breast cancer in about eight out of every nine sets of mammograms. By contrast radiologists’ sensitivity was 75.3 percent, but their performance increased to 84.8 percent when they got help from AI.
The survey also found that AI displayed better sensitivity in detecting cancer with mass, compared with the radiologists (90 percent vs. 78 percent). Artificial intelligence also was better in the detection of T1 cancers, which is considered early-stage invasive cancers. AI detected 91 percent of T1 cancers and 87 percent of node-negative cancers, while radiologists by themselves detected just 74 percent of both instances.
Breast density is also an important factor in diagnosing mammograms—dense breast tissues are more difficult to interpret because dense tissue is more likely to mask cancers in mammograms. The findings show that the diagnostic performance of AI was less affected by breast density, while radiologists' performance was prone to density, showing higher sensitivity for fatty breasts at 79.2 percent, compared with dense breasts at 73.8 percent. When aided by AI, the radiologist's sensitivity when interpreting dense breasts increased by 11 percent.
AI appears to have potential in helping radiologists limit the number of unnecessary biopsies, researchers say. To reduce the number of false negatives—missed cases—radiologists tend to seek biopsies for which they’re not certain of a diagnosis, says Eun Kyung Kim, a professor and radiologists at Yonsei University Severance Hospital.
"It requires extensive experience to correctly interpret breast images, and our study showed that AI can help find more breast cancer with lesser recalls, also detecting cancers in its early stage of development," he adds.
More for you
Loading data for hdm_tax_topic #better-outcomes...