Ultrasound-Based Deep Learning Radiomics Nomogram for the Assessment of Lymphovascular Invasion in Invasive Breast Cancer: A Multicenter Study

Di Zhang; Wang Zhou; Wen-Wu Lu; Xia-Chuan Qin; Xian-Ya Zhang; Jun-Li Wang; Jun Wu; Yan-Hong Luo; Ya-Yang Duan; Chao-Xue Zhang

doi:10.1016/j.acra.2024.04.010

Ultrasound-Based Deep Learning Radiomics Nomogram for the Assessment of Lymphovascular Invasion in Invasive Breast Cancer: A Multicenter Study

Acad Radiol. 2024 Apr 23:S1076-6332(24)00217-4. doi: 10.1016/j.acra.2024.04.010. Online ahead of print.

Authors

Di Zhang¹, Wang Zhou¹, Wen-Wu Lu¹, Xia-Chuan Qin², Xian-Ya Zhang³, Jun-Li Wang⁴, Jun Wu⁵, Yan-Hong Luo⁶, Ya-Yang Duan¹, Chao-Xue Zhang⁷

Affiliations

¹ Department of Ultrasound, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui 230022, China (D.Z., W.Z., W.W.L., X.C.Q., Y.Y.D., C.X.Z.).
² Department of Ultrasound, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui 230022, China (D.Z., W.Z., W.W.L., X.C.Q., Y.Y.D., C.X.Z.); Department of Ultrasound, Beijing Anzhen Hospital Nanchong Hospital, Nanchong Central Hospital, The Second Clinical Medical College, North Sichuan Medical College (University), Nan Chong, Sichuan 637000, China (X.C.Q.).
³ Department of Medical Ultrasound, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei 430030, China (X.Y.Z.).
⁴ Department of Ultrasound, WuHu Hospital, East China Normal University (The Second People's Hospital, WuHu), Wuhu, Anhui 241001, China (J.L.W.).
⁵ Department of Ultrasound, The Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui 230601, China (J.W.).
⁶ The Third Affiliated Hospital of Anhui Medical University, Hefei First People's Hospital, Hefei, Anhui 230061, China (Y.H.L.).
⁷ Department of Ultrasound, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui 230022, China (D.Z., W.Z., W.W.L., X.C.Q., Y.Y.D., C.X.Z.). Electronic address: zcxay@163.com.

PMID: 38658211
DOI: 10.1016/j.acra.2024.04.010

Abstract

Rationale and objectives: The aim of this study was to develop a deep learning radiomics nomogram (DLRN) based on B-mode ultrasound (BMUS) and color doppler flow imaging (CDFI) images for preoperative assessment of lymphovascular invasion (LVI) status in invasive breast cancer (IBC).

Materials and methods: In this multicenter, retrospective study, 832 pathologically confirmed IBC patients were recruited from eight hospitals. The samples were divided into training, internal test, and external test sets. Deep learning and handcrafted radiomics features reflecting tumor phenotypes on BMUS and CDFI images were extracted. The BMUS score and CDFI score were calculated after radiomics feature selection. Subsequently, a DLRN was developed based on the scores and independent clinic-ultrasonic risk variables. The performance of the DLRN was evaluated for calibration, discrimination, and clinical usefulness.

Results: The DLRN predicted the LVI with accuracy, achieving an area under the receiver operating characteristic curve of 0.93 (95% CI 0.90-0.95), 0.91 (95% CI 0.87-0.95), and 0.91 (95% CI 0.86-0.94) in the training, internal test, and external test sets, respectively, with good calibration. The DLRN demonstrated superior performance compared to the clinical model and single scores across all three sets (p < 0.05). Decision curve analysis and clinical impact curve confirmed the clinical utility of the model. Furthermore, significant enhancements in net reclassification improvement (NRI) and integrated discrimination improvement (IDI) indicated that the two scores could serve as highly valuable biomarkers for assessing LVI.

Conclusion: The DLRN exhibited strong predictive value for LVI in IBC, providing valuable information for individualized treatment decisions.

Keywords: Deep learning; Invasive breast cancer; Lymphovascular invasion; Nomogram; Radiomics.