Developing and validating deep learning-based heterogeneous model to improve diagnostic performance of ultrasound elastography for axillary lymph node metastasis of early breast cancer.

e12583 Background: To improve the performance of ultrasound (US) for diagnosing metastatic axillary lymph node (ALN), machine learning was used to reveal the inherently medical hints from ultrasonic images and assist pre-treatment evaluation of ALN for patients with early breast cancer. Methods: A total of 214 eligible patients with 220 breast lesions, from whom 220 target ALNs of ipsilateral axillae underwent ultrasound elastography (UE), were prospectively recruited. Based on feature extraction and fusion of B-mode and shear wave elastography (SWE) images of 140 target ALNs using radiomics and deep learning, with reference to the axillary pathological evaluation from training cohort, a proposed deep learning-based heterogeneous model (DLHM) was established and then validated by a collection of B-mode and SWE images of 80 target ALNs from testing cohort. Performance was compared between UE based on radiological criteria and DLHM in terms of areas under the receiver operating characteristics curve (AUC), sensitivity, specificity, accuracy, negative predictive value, and positive predictive value for diagnosing ALN metastasis. Results: DLHM achieved an excellent performance for both training and validation cohorts. In the prospectively testing cohort, DLHM demonstrated the best diagnostic performance with AUC of 0.911(95% confidence interval [CI]: 0.826, 0.963) in identifying metastatic ALN, which significantly outperformed UE in terms of AUC (0.707, 95% CI: 0.595, 0.804, P<0.001). Conclusions: DLHM provides an effective, accurate and non-invasive preoperative method for assisting the diagnosis of ALN metastasis in patients with early breast cancer.[Table: see text]

Download Full-text

Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides

10.1101/2021.10.10.21264721 ◽

2021 ◽

Author(s):

Feng Xu ◽

Chuang Zhu ◽

Wenqi Tang ◽

Ying Wang ◽

Yu Zhang ◽

...

Keyword(s):

Breast Cancer ◽

Deep Learning ◽

Lymph Node ◽

Receiver Operating Characteristic ◽

Early Breast Cancer ◽

Primary Tumor ◽

Axillary Lymph Node ◽

Operating Characteristic ◽

Axillary Lymph ◽

Tumor Biopsy

Objectives: To develop and validate a deep learning (DL) based primary tumor biopsy signature for predicting axillary lymph node (ALN) metastasis preoperatively in early breast cancer (EBC) patients with clinically negative ALN. Methods: A total of 1058 EBC patients with pathologically confirmed ALN status were enrolled from May 2010 to August 2020. A deep learning core-needle biopsy (DL-CNB) model was built on the attention based multiple instance learning (AMIL) framework to predict ALN status utilizing the deep learning features, which were extracted from the cancer areas of digitized whole-slide images (WSIs) of breast CNB specimens annotated by two pathologists. Accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curves, and areas under the receiver operating characteristic curve (AUCs) were analyzed to evaluate our model. Results: The best performing DL-CNB model with VGG16_BN as the feature extractor achieved an AUC of 0.816 (95% confidence interval (CI): 0.758, 0.865) in predicting positive ALN metastasis in the independent test cohort. Furthermore, our model incorporating the clinical data, which was called DL-CNB+C, yielded the best accuracy of 0.831 (95%CI: 0.775, 0.878), especially for patients younger than 50 years (AUC: 0.918, 95%CI: 0.825, 0.971). The interpretation of DL-CNB model showed that the top signatures most predictive of ALN metastasis were characterized by the nuclei features including density (p=0.015), circumference (p=0.009), circularity (p=0.010), and orientation (p=0.012). Conclusion: Our study provides a novel deep learning-based biomarker on primary tumor CNB slides to predict the metastatic status of ALN preoperatively for patients with early breast cancer.

Download Full-text

Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides

Frontiers in Oncology ◽

10.3389/fonc.2021.759007 ◽

2021 ◽

Vol 11 ◽

Author(s):

Feng Xu ◽

Chuang Zhu ◽

Wenqi Tang ◽

Ying Wang ◽

Yu Zhang ◽

...

Keyword(s):

Breast Cancer ◽

Deep Learning ◽

Lymph Node ◽

Early Breast Cancer ◽

Primary Tumor ◽

Axillary Lymph Node ◽

Axillary Lymph Node Metastasis ◽

Multiple Instance Learning ◽

Axillary Lymph ◽

Tumor Biopsy

ObjectivesTo develop and validate a deep learning (DL)-based primary tumor biopsy signature for predicting axillary lymph node (ALN) metastasis preoperatively in early breast cancer (EBC) patients with clinically negative ALN.MethodsA total of 1,058 EBC patients with pathologically confirmed ALN status were enrolled from May 2010 to August 2020. A DL core-needle biopsy (DL-CNB) model was built on the attention-based multiple instance-learning (AMIL) framework to predict ALN status utilizing the DL features, which were extracted from the cancer areas of digitized whole-slide images (WSIs) of breast CNB specimens annotated by two pathologists. Accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curves, and areas under the ROC curve (AUCs) were analyzed to evaluate our model.ResultsThe best-performing DL-CNB model with VGG16_BN as the feature extractor achieved an AUC of 0.816 (95% confidence interval (CI): 0.758, 0.865) in predicting positive ALN metastasis in the independent test cohort. Furthermore, our model incorporating the clinical data, which was called DL-CNB+C, yielded the best accuracy of 0.831 (95%CI: 0.775, 0.878), especially for patients younger than 50 years (AUC: 0.918, 95%CI: 0.825, 0.971). The interpretation of DL-CNB model showed that the top signatures most predictive of ALN metastasis were characterized by the nucleus features including density (p = 0.015), circumference (p = 0.009), circularity (p = 0.010), and orientation (p = 0.012).ConclusionOur study provides a novel DL-based biomarker on primary tumor CNB slides to predict the metastatic status of ALN preoperatively for patients with EBC.

Download Full-text

Clinical predictors of axillary lymph node metastasis in early breast cancer in Indian patients

International Journal of Research in Medical Sciences ◽

10.18203/2320-6012.ijrms20190463 ◽

2019 ◽

Vol 7 (3) ◽

pp. 739

Author(s):

Raghunandan Gorantlu Chowdappa ◽

Suhaildeen Kajamohideen

Keyword(s):

Breast Cancer ◽

Lymph Node ◽

Positive Predictive Value ◽

Early Breast Cancer ◽

Predictive Value ◽

Axillary Lymph Node ◽

Primary Objective ◽

Axillary Lymph Node Metastasis ◽

Axillary Lymph ◽

Clinical Predictors

Background: Surgical dissection is the accepted mode of staging the axilla in breast cancer. Proper prediction of axillary node positivity can help towards stratifying patients. The primary objective of the study was to assess the clinical factors influencing pathological axillary lymph node positivity in early carcinoma breast.Methods: This was a retrospective study, conducted at a tertiary cancer centre. Case records of all the patients with invasive breast cancer which are clinical T1 and T2 and either N0 or NI, from January 2011 to October 2014 were analysed. Clinical profile of the patient including age, BMI, comorbid, menstrual history, family history, symptoms, site of the lesion, size, single or multi centric origin were analysed.Results: Total of 608 patients of early breast cancer analysed of which 248 had pathological nodal positivity. The age group of 51 to 75 years, BMI ≥30, pre-menopausal patients had significant positive predictive value when compared to post-menopausal. Tumours in lower outer quadrant, central sector and multiple tumours also had positive predictive value. Clinical T2 when compared to clinical T1 stage and MRM when compared to BCS had significant positive predictive value.Conclusions: To conclude in present study age of the patient and clinical location of the tumour and surgery performed emerged as significant independent predictive factors of positive lymph node. Prospective studies are required to further prove the significance of these factors.

Download Full-text

Expression of CXCR4 is associated with axillary lymph node status in patients with early breast cancer

The Breast ◽

10.1016/j.breast.2005.08.034 ◽

2006 ◽

Vol 15 (4) ◽

pp. 533-539 ◽

Cited By ~ 27

Author(s):

Y.-C. Su ◽

M.-T. Wu ◽

C.-J. Huang ◽

M.-F. Hou ◽

S.-F. Yang ◽

...

Keyword(s):

Breast Cancer ◽

Lymph Node ◽

Early Breast Cancer ◽

Axillary Lymph Node ◽

Lymph Node Status ◽

Axillary Lymph ◽

Axillary Lymph Node Status ◽

Node Status

Download Full-text

BCIRG 005 main efficacy analysis: a phase III randomized trial comparing docetaxel in combination with doxorubicin and cyclophosphamide (TAC) versus doxorubicin and cyclophosphamide followed by docetaxel (AC→T) in women with Her-2/neu negative axillary lymph node positive early breast cancer.

10.1158/0008-5472.sabcs-77 ◽

2009 ◽

Cited By ~ 12

Author(s):

W Eiermann ◽

T Pienkowski ◽

J Crown ◽

L Chap ◽

M Pawlicki ◽

...

Keyword(s):

Breast Cancer ◽

Lymph Node ◽

Randomized Trial ◽

Early Breast Cancer ◽

Axillary Lymph Node ◽

Phase Iii ◽

Axillary Lymph ◽

Efficacy Analysis ◽

Her 2 ◽

Lymph Node Positive

Download Full-text

End-to-End Deep Learning for Detecting Metastatic Breast Cancer in Axillary Lymph Node from Digital Pathology Images

10.1007/978-3-030-91608-4_34 ◽

2021 ◽

pp. 343-353

Author(s):

Turki Turki ◽

Anmar Al-Sharif ◽

Y-h. Taguchi

Keyword(s):

Breast Cancer ◽

Deep Learning ◽

Metastatic Breast Cancer ◽

Lymph Node ◽

Axillary Lymph Node ◽

Digital Pathology ◽

Metastatic Breast ◽

Axillary Lymph ◽

End To End

Download Full-text

Practical consensus recommendations regarding the management of sentinel lymph node issues in early breast cancer

South Asian Journal of Cancer ◽

10.4103/sajc.sajc_120_18 ◽

2018 ◽

Vol 07 (02) ◽

pp. 132-136

Author(s):

Vedant Kabra ◽

R. Aggarwal ◽

S. Vardhan ◽

M. Singh ◽

R. Khandelwal ◽

...

Keyword(s):

Breast Cancer ◽

Lymph Node ◽

Sentinel Lymph Node ◽

Early Breast Cancer ◽

Axillary Lymph Node ◽

Clinical Staging ◽

Axillary Lymph Nodes ◽

Axillary Lymph ◽

Poor Prognostic Factor ◽

Consensus Recommendations

AbstractAxillary lymph node involvement is a very important poor prognostic factor in the clinical staging and management of breast cancer patients. Traditionally, axillary lymph node dissection (ALND) has been used for determining the status of the axillary lymph nodes. More recently the sentinel lymph node biopsy (SLNB) procedure has gained wider acceptance as the standard of care, having the advantage of being less invasivewhile providing good accuracy. This expert group used data from published literature, practical experience and opinion of a large group of academic oncologists to arrive at these practical consensus recommendations in regards with the use of the two different procedures and other issues in patients with early breast cancer for the benefit of community oncologists.

Download Full-text