Detection of Metastatic Breast Cancer from Whole-Slide Pathology Images Using an Ensemble Deep-Learning Method

Abstract

Background: Metastasis is the main cause of death toll among breast cancer patients. Since current approaches for diagnosis of lymph node metastases are time-consuming, deep learning (DL) algorithms with more speed and accuracy are explored for effective alternatives. Methods: A total of 220025 whole-slide pictures from patients’ lymph nodes were classified into two cohorts: testing and training. For metastatic cancer identification, we employed hybrid convolutional network models. The performance of our diagnostic system was verified using 57458 unlabeled images that utilized criteria that included accuracy, sensitivity, specificity, and P-value. Results: The DL-based system that was automatically and exclusively capable of quantifying and identifying metastatic lymph nodes was engineered. Quantification was made with 98.84% accuracy. Moreover, the precision of VGG16 and Recall was 92.42% and 91.25%, respectively. Further experiments demonstrated that metastatic cancer differentiation levels could influence the recognition performance. Conclusion: Our engineered diagnostic complex showed an elevated level of precision and efficiency for lymph node diagnosis. Our innovative DL-based system has a potential to simplify pathological screening for metastasis in breast cancer patients.

Classification and diagnostic prediction of breast cancer metastasis on clinical data using machine learning algorithms

“…Out of these three AlexNet GRU outperforms Kaggle PCam imaging dataset 99.5% Choudhury 34 To diagnose and predict the cancer prognosis of Malignant Pleural Mesothelioma as early as possible (MPM) 8 different algorithms are used Clinical data collected by Dicle University 79.29% Bejnordi et al 35 To investigate the predictive power of deep learning algorithms Vs 11 members of pathologists in a simulated time-constraint environment In a research challenge competition. 32 deep learning models have been submitted by the contestants out of which 7 models showed a greater performance Detecting lymph node metastases: A CAMELYON16 dataset Area Under the Curve (AUC) of 0.994 Abdollahiet al 36 To detect metastatic breast cancer using the whole-slide pathology images Ensemble model consisting of VGG16, Resnet50, Google net, and Mobile net CAMELYON16 dataset 98.84% Papandrianos et al 37 To identify bone metastasis of prostate cancer Convolutional Neural Network (CNN) Nuclear Medicine Department of Diagnostic Medical Center, Larisa, Greece 97.38% Gupta, and Gupta 38 Deep learning approaches for predicting breast cancer survivability Restricted Boltzmann Machine The Surveillance, Epidemiology, and End Results (SEER) database 97% Sharma and Mishra 39 Performance analysis of machine learning based optimized feature selection approaches for breast cancer diagnosis voting classifier Wisconsin Breast Cancer (WDBC) 99.41% Ak 40 A comparative analysis of breast cancer detection and diagnosis using data visualization and machine learning applications logistic regression model Dr. William H. Walberg of the University of Wisconsin Hospital 98.1% <...…”

The effects of process parameters on polydopamine coatings employed in tissue engineering applications

“…Since the pros of PDA outweigh its cons, various groups of scientists have modified the biomaterials’ surfaces by employing PDA with the aim of augmenting their surface performance. Therefore, within the last couple of years, PDA has been in the spotlight, with diverse applications in the field of biomedical engineering ( Lynge et al, 2011 ), including drug delivery ( Huang et al, 2018 ), implants ( Jia et al, 2019 ), surface engineering ( Yang et al, 2015 ), cancer therapy ( Abdollahi et al, 2022 ; Honmane et al, 2022 ), TE (bone ( Huang et al, 2016 ; Kaushik et al, 2020 ), cartilage ( Huang et al, 2021 ), muscle ( Zhou et al, 2021 ), skin ( Yazdi et al, 2022 ), tendon ( Lin et al, 2019 ), and neuron ( Qian et al, 2018 ; Yan et al, 2020 )), and microfluidic systems ( Niculescu et al, 2021 ).…”

Effect of porosity on mechanical and biological properties of bioprinted scaffolds

“…Tissue engineering (TE) which is an interdisciplinary field of medical and engineering sciences, aims to develop a biological mechanism for regenerating a damaged tissue or replacing it with natural and synthetic materials 5,6 . As a result, TE researchers have developed 3D printed body parts using natural and synthetic biomaterials to fulfill their theories 7–10 .…”

“…3,4 Tissue engineering (TE) which is an interdisciplinary field of medical and engineering sciences, aims to develop a biological mechanism for regenerating a damaged tissue or replacing it with natural and synthetic materials. 5,6 As a result, TE researchers have developed 3D printed body parts using natural and synthetic biomaterials to fulfill their theories. [7][8][9][10] Additive manufacturing (AM), often referred to as 3D printing or rapid prototyping, has been developed as a versatile and robust approach for advanced medical and industrial applications.…”