Breast density assessment combined with AI system detects more interval cancers: Study
Netherlands: Assessment using the combination of artificial intelligence (AI) algorithm and breast density measurements versus either method alone can enable the detection of a larger proportion of women who would develop interval cancer (IC), claims a recent study. Incorporating mammographic breast density (BD) in breast cancer risk models betters accuracy, but accuracy remains modest,...
Netherlands: Assessment using the combination of artificial intelligence (AI) algorithm and breast density measurements versus either method alone can enable the detection of a larger proportion of women who would develop interval cancer (IC), claims a recent study.
Incorporating mammographic breast density (BD) in breast cancer risk models betters accuracy, but accuracy remains modest, Alexander J. T. Wanders and the team from Netherland note in their study published in the journal Radiology. By combining assessments of BD and AI cancer detection systems, the prediction of interval cancer risk may be improved. Considering this, the authors conducted the study with an objective to evaluate the performance of a neural network (NN)-based model that combines the assessments of BD and an AI system in the prediction of risk of developing IC among women with negative screening mammography results.
The retrospective nested case-control study performed with screening examinations consisted of women who developed IC and women with normal follow-up findings (from January 2011 to January 2015). An AI cancer detection system analyzed all studies that yielded a score of 1–10, representing an increased likelihood of malignancy.
Using publicly available software, BD was computed automatically. By combining the AI score and BD using 10-fold cross-validation, an NN model was trained. Bootstrap analysis was used to calculate the area under the receiver operating characteristic curve (AUC).
The study included a total of 2222 women with IC and 4661 women in the control group (mean age, 61 years).
The study revealed the following findings:
· AUC of the NN model was 0.79, which was higher than the AUC of the AI cancer detection system or BD alone (AUC, 0.73 and 0.69).
· At 90% specificity, the NN model had a sensitivity of 50.9% (339 of 666 women) for prediction of IC, which was higher than that of the AI system (37.5%; 250 of 666 women) or BD percentage alone (22.4%; 149 of 666 women).
"In the study, we present a risk model that combines the assessments of an AI algorithm and breast density measurements for identifying women at risk for developing interval cancer. This combination model yielded higher performance in predicting compared with either of the methods alone," wrote the authors.
"The risk model has the potential to personalize current breast cancer screening programs by defining which women benefit from an additional evaluation, aiming to reduce interval cancer rates," they concluded.
The study titled, "Interval Cancer Detection Using a Neural Network and Breast Density in Women with Negative Screening Mammograms," was published in the journal Radiology.
Medha Baranwal joined Medical Dialogues as an Editor in 2018 for Speciality Medical Dialogues. She covers several medical specialties including Cardiac Sciences, Dentistry, Diabetes and Endo, Diagnostics, ENT, Gastroenterology, Neurosciences, and Radiology. She has completed her Bachelors in Biomedical Sciences from DU and then pursued Masters in Biotechnology from Amity University. She has a working experience of 5 years in the field of medical research writing, scientific writing, content writing, and content management. She can be contacted at firstname.lastname@example.org. Contact no. 011-43720751