Deep learning radiomics of ultrasonography: Identifying the risk of axillary non-sentinel lymph node involvement in primary breast cancer

Abstract

Background Completion axillary lymph node dissection is overtreatment for patients with sentinel lymph node (SLN) metastasis in whom the metastatic risk of residual non-SLN (NSLN) is low. However, the National Comprehensive Cancer Network panel posits that none of the previous studies has successfully identified such subset patients. Here, we develop a multicentre deep learning radiomics of ultrasonography model (DLRU) to predict the risk of SLN and NSLN metastasis. Methods In total, 937 eligible breast cancer patients with ultrasound images were enrolled from two hospitals as the training set ( n = 542) and independent test set ( n = 395) respectively. Using the images, we developed and validated a prediction model combined with deep learning radiomics and axillary ultrasound to sequentially identify the metastatic risk of SLN and NSLN, thereby, classifying patients to relevant axillary management groups. Findings In the test set, the DLRU yields the best performance in identifying patients with metastatic disease in SLNs (sensitivity=98.4%, 95% CI 96.6–100) and NSLNs (sensitivity=98.4%, 95% CI 95.6–99.9). The DLRU also accurately stratifies patients without metastasis in SLN or NSLN into the corresponding low-risk (LR)-SLN and high-risk (HR)-SLN&LR-NSLN category with the negative predictive value of 97% (95% CI 94.2–100) and 91.7% (95% CI 88.8–97.9), respectively. Moreover, compared with the current clinical management, DLRU appropriately assigned 51% (39.6%/77.4%) of overtreated patients in the entire study cohort into the LR group, perhaps avoiding overtreatment. Interpretation The performance of the DLRU indicates that it may offer a simple preoperative tool to promote personalized axillary management of breast cancer. Funding The National Nature Science Foundation of China; The National Outstanding Youth Science Fund Project of National Natural Science Foundation of China; The Scientific research project of Heilongjiang Health Committee; The Postgraduate Research &Practice Innovation Program of Harbin Medical University.

Assessment of Axillary Lymph Nodes for Metastasis on Ultrasound Using Artificial Intelligence

“…Additionally, many studies include ALNs on standard imaging without suspicion for biopsy for data augmentation, but this approach conflates the number of benign findings and does not mimic the clinical scenario of decision to biopsy suspicious nodes. Guo et al 19 developed a deep learning radiomics model of ultrasound images to identify the metastatic risk in sentinel and non-sentinel lymph nodes in primary breast cancer. Their proposed deep learning radiomics of ultrasonography model using both images of the primary tumor and ALN assigned 51% of the clinically over-treated patients to a low-risk group which could theoretically avoid LN biopsy.…”

“…15 Studies focused particularly on breast cancer metastasis prediction showed promising results for use as a second reader and assist in decision making. [16][17][18][19][20][21][22][23] However, this work to date has lacked standardization and relies on supervised machine learning models that require both high computational costs and extremely large datasets for algorithms training.…”

Staging of the Axilla in Breast Cancer and the Evolving Role of Axillary Ultrasound

“… 80 , 81 With the application of deep learning to ultrasound radiomics datasets, known as deep learning radiomics ultrasonography (DLRU), axillary lymph node status may be accurately predicted with AUC of >0.90. 82 , 83 Although radiomics is still in its infancy, it has great potential to pave the way for the personalization of surgical management of the axilla and “virtual biopsies.”…”

Deep decision support for lymph node metastatic risk evaluation

“…However, reliable methods for identifying SLN positive patients with low risk of NSLN metastasis have remained elusive. Given the recent progress of deep learning in a wide range of diagnostic tasks and the availability of electronic health records (EHRs) [4] , [5] , [6] , deep artificial neural networks may be well-suited for detecting lymph node metastases in breast cancer patients [7] .…”

“…In this issue of EBioMedicine, Guo et al. designed deep learning models based on the DenseNet architecture to determine patients’ SLN and NSLN metastasis status using axillary ultrasonography (AUS) images [7] . Prediction of SLN metastasis using a combined deep learning model and AUS report achieved an area under the receiver operating characteristic curve (AUC) of 0.848 (95% CI: 0.811–0.886) with a sensitivity of 0.984 (95% CI: 0.966–1) in the test set.…”