Deep learning radiomics can predict axillary lymph node status in early-stage breast cancer

Zheng, Xueyi; Zhao, Yao; Huang, Yili; Yan, Yu; Wang, Yun; Liu, Yubo; Mao, Rushuang; Li, Fēi; Xiao, Yang; Wang, Yuanyuan; Hu, Yixin; Yu, Jinhua; Zhou, Jianhua

doi:10.1038/s41467-020-15027-z

Cited by 311 publications

(195 citation statements)

References 54 publications

Supporting

Mentioning

182

Contrasting

Unclassified

Order By: Relevance

“…Additionally, the two new imaging hallmarks, were superior to most of those clinical factors in the weighted ensemble model, suggesting their incremental role on PCa risk assessment. Our ndings are consistent with those of previous studies, which used the similar computational approaches for breast cancer assessment 33,34 .…”

Section: Discussionsupporting

confidence: 92%

An Artificial Intelligence-based Multimodality-Integration for Precise Prediction of Prostate Cancer Lymph Node Metastasis: A Retrospective Two-center Study

Hou¹,

Bao²,

Song³

et al. 2020

Preprint

View full text Add to dashboard Cite

BackgroundAccurate identification of pelvic lymph node metastasis (PLNM) in patients with prostate cancer (PCa) is crucial for determining appropriate treatment options. However, there is no clear consensus on the integration of clinicopathological and imaging findings available to predict PLNM. Therefore, we built a Prostate Cancer Risk (PRISK) tool using an artificial intelligence-based multimodality-integration to obtain a precisely informed decision about whether to perform extended pelvic lymph node dissection (ePLND). MethodsPRISK provides a novel precise risk assessment tool to reduce unnecessary ePLNDs while controlling PLNM missing rate. It was developed in 280 patients and verified in 71 patients internally and in 50 patients externally by integrating a set of radiologists’ interpretations, clinicopathological factors and newly refined imaging indicators from MR images with radiomics machine learning and deep learning algorithms. Its clinical applicability was compared with Briganti and Memorial Sloan Kettering Cancer Center (MSKCC) nomograms.ResultsPRISK yielded the best diagnostic performance with areas under the receiver operating characteristic curve (AUC) of 0.932 (95% CI, 0.895-0.958), 0.924 (95% CI, 0.837-0.974) and 0.758 (95% CI, 0.616-0.868) in the training/validation, internal test and external test cohorts. If the No. of ePLNDs missed for risk assessment is controlled at < 2%, PRISK can provide both higher No. of ePLNDs spared (PRISK 59.6% vs MSKCC 44.9% vs Briganti 37.7%) and lower No. of false-positives (PRISK 59.3% vs MSKCC 70.1% and Briganti 72.7%) as compared with MSKCC and Briganti score. In follow-up, patients stratified by PRISK showed significantly different biochemical recurrence rate after surgery.ConclusionsPRISK offers a noninvasive clinical biomarker to predict PLNM for patients with PCa. It shows improved accuracy of diagnosis support and reduced overtreatment burdens for patients with findings suggested of PCa.

show abstract

Section: Discussionsupporting

confidence: 92%

An Artificial Intelligence-based Multimodality-Integration for Precise Prediction of Prostate Cancer Lymph Node Metastasis: A Retrospective Two-center Study

Hou¹,

Bao²,

Song³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, deep learning based on the convolutional neural network has been considered as a stable, effective approach for the feature extraction, classification, detection, and segmentation tasks of radiologic images ( 17 – 20 ). It has been shown that a deep learning-based radiomics signature based on US and SWE could serve as a reliable and powerful tool for the prediction of axillary lymph node status in early-stage breast cancer ( 21 ). However, whether a deep learning-based radiomics signature can be used to improve the diagnostic performance of B-mode US and SWE for the classification of breast lesions remains unknown.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-Based Radiomics of B-Mode Ultrasonography and Shear-Wave Elastography: Improved Performance in Breast Mass Classification

et al. 2020

View full text Add to dashboard Cite

Objective Shear-wave elastography (SWE) can improve the diagnostic specificity of the B-model ultrasonography (US) in breast cancer. However, whether deep learning-based radiomics signatures based on the B-mode US (B-US-RS) or SWE (SWE-RS) could further improve the diagnostic performance remains to be investigated. We aimed to develop the B-US-RS and SWE-RS and determine their performances in classifying breast masses. Materials and Methods This retrospective study included 291 women (mean age ± standard deviation, 40.9 ± 12.3 years) from two centers who had US-visible solid breast masses and underwent biopsy and/or surgical resection between June 2015 and July 2017. B-mode US and SWE images of the 198 masses in 198 patients (training cohort) from center 1 were segmented, respectively, to construct B-US-RS and SWE-RS using the least absolute shrinkage and selection operator regression and tested in an independent validation cohort of 65 masses in 65 patients from center 1 and in an external validation cohort of 28 masses in 28 patients from center 2. The performances of B-US-RS and SWE-RS were assessed using receiver operating characteristic (ROC) analysis and compared with that of radiologist assessment [Breast Imaging Reporting and Data System (BI-RADS)] and quantitative SWE parameters [maximum elasticity ( E max ), mean elasticity ( E mean ), elasticity ratio ( E ratio ), and elastic modulus standard deviation ( E SD )] by using the McNemar test. Results The single best-performing quantitative SWE parameter, E max , had a higher specificity than BI-RADS assessment in the training and independent validation cohorts ( P < 0.001 for both). The areas under the ROC curves (AUCs) of B-US-RS and SWE-RS both were 0.99 (95% CI = 0.99–1.00) in the training cohort, 1.00 (95% CI = 1.00–1.00) in the independent validation cohort, and 1.00 (95% CI = 1.00–1.00) in the external validation cohort. The specificities of B-US-RS and SWE-RS were higher than that of E max in the training ( P < 0.001 for both) and independent validation cohorts ( P = 0.02 for both). Conclusion The B-US-RS and SWE-RS outperformed the quantitative SWE parameters and BI-RADS assessment for classifying breast masses. The integration of the deep learning-based radiomics approach would help improve the classification ability of B-mode US and SWE for breast masses.

show abstract

“…Nowadays, the development of radiomics in the aspects of tumor diagnosis, treatment decision and prognosis prediction is encouraging and breast cancer is one of the pioneers in the exploration. [7][8][9] Magnetic resonance imaging (MRI) radiomics-based approaches for predicting molecular subtype, recurrence risk and survival, pathologic complete responses of breast cancer patients showed powerful predictive ability and the prospect of extended application. [10][11][12][13] Moreover, the association between MRI radiomics with breast tumor microenvironment have been corroborated in previous studies.…”

Section: Introductionmentioning

confidence: 99%

Machine learning magnetic resonance imaging radiomics predicts axillary lymph node metastasis in invasive breast cancer

Yu¹,

He²,

Ouyang³

et al. 2020

Preprint

View full text Add to dashboard Cite

In current clinical practice, the standard evaluation for axillary lymph node (ALN) status in breast cancer is based on the invasive procedure and many patients will suffer from operative associated complications. Hence, a novel signature incorporated tumor and lymph node magnetic resonance imaging (MRI) radiomics, clinical and pathological characteristics, and molecular subtypes based on the machine learning approach was established to accurately identify ALN metastasis in early-stage invasive breast cancer patients. Although the misjudgment of ALN status by clinicians according to preoperative MRI are common during clinical practice and even the senior radiologists make mistakes sometimes, this multiomic radiomic signature showed the superiority over clinicians and could precisely discriminate ALN metastasis among different molecular subtype patients. Furthermore, the association between MRI radiomic features and tumor-microenvironment features including immune cells, long non-coding RNAs, and types of methylated sites were found, which revealed the potential biological underpinning of MRI radiomics.

show abstract

Deep learning radiomics can predict axillary lymph node status in early-stage breast cancer

Cited by 311 publications

References 54 publications

An Artificial Intelligence-based Multimodality-Integration for Precise Prediction of Prostate Cancer Lymph Node Metastasis: A Retrospective Two-center Study

An Artificial Intelligence-based Multimodality-Integration for Precise Prediction of Prostate Cancer Lymph Node Metastasis: A Retrospective Two-center Study

Deep Learning-Based Radiomics of B-Mode Ultrasonography and Shear-Wave Elastography: Improved Performance in Breast Mass Classification

Machine learning magnetic resonance imaging radiomics predicts axillary lymph node metastasis in invasive breast cancer

Contact Info

Product

Resources

About