It’s well known that #mammography alone is considered an ineffective method for #breast #cancer #surveillance and diagnosing cancer recurrence, but from now on this statement is #outdated.
#Radiodiagnosis Department at Kasr AlAiny School of Medicine, Cairo University, in collaboration with Baheya Foundation for early breast cancer and treatment, performed a #pioneer study in the field of #breast #imaging that aimed to evaluate the ability to use #artificial #intelligence (AI) for reading digital mammograms to #exclude #recurrence in the #operative bed of known breast cancer following the different surgical procedures: #lumpectomy, #quadrantectomy, #oncoplastic_surgery, and #reconstructive_surgeries (post-mastectomy) presented by #autologous_tissue_flaps or #prosthetic_implants.
The AI scoring percentage for a clear operative bed ranged from 0% to 26%, with a mean of 15%. Operative bed benign changes displayed a score range from 10% to 88%, mean 48.2%, and malignancy recurrence range from 65% to 99%, mean 87.7%. The optimum cut-off #value to distinguish between benign postoperative changes and malignancy recurrence was 56.5% (95%, CI 0.824–1.060, p value <0.001).
#Reconstructive surgeries with autologous #implants showed a range AI scoring of 19.6% to 14.7%, for intact implants.
Implants that showed #intracapsular_rupture -confirmed by MR imaging- displayed a score range of 45% to 67%, and a mean of 58.7% + 11.9%.
Further investigations yet to come involving AI and integrity of silicone implants.
Methods:
Lunit Cancer Screening AI-MMG, on digital mammography.
Dual-energy contrast-enhanced mammography unit;
*Amulet Innovality (FUJIFILM Healthcare Middle East & Africa Global Company, Japan) and
*Senographe Pristina 3D machine (GE HealthCare, United Kingdom).
#digitalmammography, #artificialintelligence #breastcancer #suspiciouslesions, #cancer_recurrance
#post_operative_changes, #reconstructive_breast_surgeries
