Preliminary study of AI-assisted diagnosis using FDG-PET/CT for axillary lymph node metastasis in patients with breast cancer

Abstract

Background To improve the diagnostic accuracy of axillary lymph node (LN) metastasis in breast cancer patients using 2-[18F]FDG-PET/CT, we constructed an artificial intelligence (AI)-assisted diagnosis system that uses deep-learning technologies. Materials and methods Two clinicians and the new AI system retrospectively analyzed and diagnosed 414 axillae of 407 patients with biopsy-proven breast cancer who had undergone 2-[18F]FDG-PET/CT before a mastectomy or breast-conserving surgery with a sentinel lymph node (LN) biopsy and/or axillary LN dissection. We designed and trained a deep 3D convolutional neural network (CNN) as the AI model. The diagnoses from the clinicians were blended with the diagnoses from the AI model to improve the diagnostic accuracy. Results Although the AI model did not outperform the clinicians, the diagnostic accuracies of the clinicians were considerably improved by collaborating with the AI model: the two clinicians' sensitivities of 59.8% and 57.4% increased to 68.6% and 64.2%, respectively, whereas the clinicians' specificities of 99.0% and 99.5% remained unchanged. Conclusions It is expected that AI using deep-learning technologies will be useful in diagnosing axillary LN metastasis using 2-[18F]FDG-PET/CT. Even if the diagnostic performance of AI is not better than that of clinicians, taking AI diagnoses into consideration may positively impact the overall diagnostic accuracy.

Diagnostic Performance of FDG-PET/CT Scan as Compared to US-Guided FNA in Prediction of Axillary Lymph Node Involvement in Breast Cancer Patients

“…Although the AI model, a designed and trained 3D convolutional neural network, did not overtake the clinicians, the accuracies were improved, with sensitivity values from 59.8% and 57.4% to 68.6% and 64.2%, but the specificities remained unchanged (29). Lastly, tumor markers have been recently utilized in asymptomatic breast cancer patients receiving adjuvant therapies.…”

Clinical Significance of Peritumoral Adipose Tissue PET/CT Imaging Features for Predicting Axillary Lymph Node Metastasis in Patients with Breast Cancer

“…Axillary lymph node dissection is recommended for breast cancer patients involving clinically and biopsy-proven positive axillary lymph nodes [ 2 ]. Meanwhile, sentinel lymph node biopsy is suggested as the gold standard for axillary lymph node staging of patients with clinically negative or suspicious lymph nodes but negative biopsy results [ 2 , 4 ]. However, sentinel lymph node biopsy showed a 9.8% false-negative rate in a previous clinical trial and, despite a lower morbidity than that of axillary lymph node dissection, surgical complications such as lymphedema were reported in 3.7–6.9% of patients undergoing sentinel lymph node sampling [ 5 , 6 , 7 ].…”

“…However, sentinel lymph node biopsy showed a 9.8% false-negative rate in a previous clinical trial and, despite a lower morbidity than that of axillary lymph node dissection, surgical complications such as lymphedema were reported in 3.7–6.9% of patients undergoing sentinel lymph node sampling [ 5 , 6 , 7 ]. Therefore, a noninvasive diagnostic method is highly desirable for accurate axillary lymph node staging [ 4 , 8 ]. F-18 fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) is notable for its exquisite diagnostic ability for detecting metastasis in various malignant diseases; therefore, it is one of the imaging examinations investigated for axillary lymph node staging [ 4 , 8 , 9 , 10 ].…”

“…Therefore, a noninvasive diagnostic method is highly desirable for accurate axillary lymph node staging [ 4 , 8 ]. F-18 fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) is notable for its exquisite diagnostic ability for detecting metastasis in various malignant diseases; therefore, it is one of the imaging examinations investigated for axillary lymph node staging [ 4 , 8 , 9 , 10 ]. Unfortunately, in a recent meta-analysis study, FDG PET/CT showed a sensitivity of only 52% for detecting axillary lymph node metastasis, whereas the specificity was 92%, suggesting the limited use of standalone FDG PET/CT in axillary nodal staging [ 9 ].…”

“…Unfortunately, in a recent meta-analysis study, FDG PET/CT showed a sensitivity of only 52% for detecting axillary lymph node metastasis, whereas the specificity was 92%, suggesting the limited use of standalone FDG PET/CT in axillary nodal staging [ 9 ]. Hence, a number of studies have attempted to develop diverse methods to improve the diagnostic accuracy of FDG PET/CT [ 4 , 11 ].…”