Axillary lymph node metastasis status prediction of early-stage breast cancer using convolutional neural networks

Lee, Yan-Wei; Huang, Chiun‐Sheng; Shih, Chung-Chih; Chang, Ruey-Feng

doi:10.1016/j.compbiomed.2020.104206

Cited by 51 publications

(49 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth noting that DenseNet121 generated the highest results in terms of performance (Table 1) and average ranking (Figure 6) when compared to all other DL models. This coincides with recent work by Lee et al [8], where DenseNet121 (compared against machine learning models coupled with handcrafted features) also generated the highest performance results when assessed on predicting ALN metastasis of another dataset.…”

Section: Discussionsupporting

confidence: 89%

“…Because the treatment plan provided by oncologists and surgeons depends on the diagnosis and report obtained from pathologists, researchers have proposed computational methods using artificial intelligence to assist pathologists. For example, Lee et al [8] utilized convolutional neural networks to predict breast cancer metastases to axillary lymph 1 T. Turki and A. Al-Sharif are with the Department of Computer Science, King Abdulaziz University, Jeddah, 21589, Saudi Arabia.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Turki

Al-Sharif

Taguchi

2021

Preprint

View full text Add to dashboard Cite

Metastatic breast cancer is one of the attributed leading causes of women deaths worldwide. Accurate diagnosis to the spread of breast cancer to axillary lymph nodes (ALNs) is done by breast pathologist, utilizing the microscope to inspect and then providing the biopsy report. Because such a diagnosis process requires special expertise, there is a need for artificial intelligence-based tools to assist breast pathologists to automatically detect breast cancer metastases. This study aims to detect breast cancer metastasized to ALN with end-to-end deep learning (DL). Also, we utilize several DL architectures, including DenseNet121, ResNet50, VGG16, Xception as well as a customized lightweight convolutional neural network. We evaluate the DL models on NVIDIA GeForce RTX 2080Ti GPU using 114 processed microscopic images pertaining to ALN metastases in breast cancer patients. Compared to all DL models employed in this study, experimental results show that DenseNet121 generates the highest performance results (64-68%) based on AUC and accuracy.

show abstract

Section: Discussionsupporting

confidence: 89%

Section: Introductionmentioning

confidence: 99%

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

Turki

Al-Sharif

Taguchi

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…However, this approach required manual segmentation which is highly labor intensive. The deep learning-based computer-aided prediction developed by Lee et al 20 achieved sensitivity and specificity of 81.36% and 80.85% respectively, combining the tumor region and peritumoral tissue. This work demonstrates the potential of adding a variety of radiomic features from the primary tumor and may be applicable for models specific to imaging of the ALN.…”

Section: Discussionmentioning

confidence: 99%

“…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.…”

Section: Introductionmentioning

confidence: 99%

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

Tahmasebi

Sevrukov

et al. 2021

Ultrason Imaging

View full text Add to dashboard Cite

The purpose of this study was to evaluate an artificial intelligence (AI) system for the classification of axillary lymph nodes on ultrasound compared to radiologists. Ultrasound images of 317 axillary lymph nodes from patients referred for ultrasound guided fine needle aspiration or core needle biopsy and corresponding pathology findings were collected. Lymph nodes were classified into benign and malignant groups with histopathological result serving as the reference. Google Cloud AutoML Vision (Mountain View, CA) was used for AI image classification. Three experienced radiologists also classified the images and gave a level of suspicion score (1–5). To test the accuracy of AI, an external testing dataset of 64 images from 64 independent patients was evaluated by three AI models and the three readers. The diagnostic performance of AI and the humans were then quantified using receiver operating characteristics curves. In the complete set of 317 images, AutoML achieved a sensitivity of 77.1%, positive predictive value (PPV) of 77.1%, and an area under the precision recall curve of 0.78, while the three radiologists showed a sensitivity of 87.8% ± 8.5%, specificity of 50.3% ± 16.4%, PPV of 61.1% ± 5.4%, negative predictive value (NPV) of 84.1% ± 6.6%, and accuracy of 67.7% ± 5.7%. In the three external independent test sets, AI and human readers achieved sensitivity of 74.0% ± 0.14% versus 89.9% ± 0.06% ( p = .25), specificity of 64.4% ± 0.11% versus 50.1 ± 0.20% ( p = .22), PPV of 68.3% ± 0.04% versus 65.4 ± 0.07% ( p = .50), NPV of 72.6% ± 0.11% versus 82.1% ± 0.08% ( p = .33), and accuracy of 69.5% ± 0.06% versus 70.1% ± 0.07% ( p = .90), respectively. These preliminary results indicate AI has comparable performance to trained radiologists and could be used to predict the presence of metastasis in ultrasound images of axillary lymph nodes.

show abstract

“…The secondary endpoint is a false-negative rate of a maximum of 10% for the prediction of N0 vs. N+, compared with the histopathological assessment of excised sentinel lymph node(s). Many nomograms and ANN models have been developed for predicting nodal metastasis, or the lack thereof, with (23)(24)(25)(26)(27)(28)(29)(30)(31) or without imaging (32,33). The ANN model that this study aims to validate is a promising tool in the clinic because the input variables are routinely available, no extra imaging besides clinical work-up (mammography and axillary ultrasound) is necessary, and the web interface is user friendly.…”

Section: Secondary Endpointmentioning

confidence: 99%

The NILS study protocol - a retrospective validation study of a preoperative decision-making tool for non-invasive lymph node staging in women with primary breast cancer [ISRCTN14341750]

Skarping

Dihge

Bendahl

et al. 2022

Preprint

View full text Add to dashboard Cite

Background Routine preoperative axillary ultrasonography has proven insufficient for detecting low-burden nodal metastatic deposits. For the majority of newly diagnosed breast cancer patients presenting with clinical T1-T2 N0 disease, the standard axillary staging by sentinel lymph node biopsy is not therapeutic. The pilot non-invasive lymph node staging (NILS) artificial neural network (ANN) model to predict nodal status was published in 2019. The aim of the current study is to assess the performance measures of the model for the prediction of healthy lymph nodes in clinically N0 breast cancer patients at two breast cancer centers in Sweden. Methods This bicenter, observational, retrospective study has been designed to validate the NILS prediction model for nodal status using preoperatively collected clinicopathological and radiological data. A web-based implementation of the nodal status classifier has been developed and will be used in this study, resulting in an estimated probability of healthy lymph nodes for each study participant. Our primary endpoint is to report on the performance of the NILS prediction model to distinguish between healthy and metastatic lymph nodes (discrimination, N0 vs. N+) and compare the observed and predicted event rates of benign axillary nodal status (calibration). Discussion Internationally, there are numerous artificial intelligence projects involving non-invasive identification of N0 breast cancer. Here, we present a robust validation study based on external cohorts of our ANN model. Although validation is necessary to show generalizability, it is often overlooked. If the accuracy and discrimination reach a satisfactory level, our prediction tool can be implemented to assist medical professionals and breast cancer patients in shared decision-making on omitting sentinel node biopsy in patients predicted to be node-negative. In future, this may potentially save healthcare resources and reduce costs and adverse side effects. In addition, our study might prompt future studies of nodal metastases of malignancies in other organs, and thus might have implications beyond breast cancer. Trial registration This study has been prospectively registered in the ISRCTN registry, identification number: 14341750

show abstract

Axillary lymph node metastasis status prediction of early-stage breast cancer using convolutional neural networks

Cited by 51 publications

References 33 publications

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

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

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

The NILS study protocol - a retrospective validation study of a preoperative decision-making tool for non-invasive lymph node staging in women with primary breast cancer [ISRCTN14341750]

Contact Info

Product

Resources

About