Construction and Evaluation of Robust Interpretation Models for Breast Cancer Metastasis Prediction

Adnan, Nahim; Zand, Maryam; Huang, Tim H.M.; Ruan, Jianhua

doi:10.1109/tcbb.2021.3120673

Cited by 5 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Default parameters were used in all experiments, except that for LR, the L1 penalty was set to true to achieve sparse solutions due to a large number of gene features present in the dataset. Previous studies in the same dataset and similar datasets have shown that RF has consistently outperformed other classifiers in predicting breast cancer metastasis, and its performance is robust concerning parameter variations, making it a preferred choice for benchmarking [ 24 , 27 ]. The area under the receiver-operating characteristics curve (AUC) score was used to determine the prediction accuracy of the prediction models.…”

Section: Methodsmentioning

confidence: 99%

A Robust Personalized Classification Method for Breast Cancer Metastasis Prediction

Adnan

Najnin

Ruan

2022

Cancers

View full text Add to dashboard Cite

Accurate prediction of breast cancer metastasis in the early stages of cancer diagnosis is crucial to reduce cancer-related deaths. With the availability of gene expression datasets, many machine-learning models have been proposed to predict breast cancer metastasis using thousands of genes simultaneously. However, the prediction accuracy of the models using gene expression often suffers from the diverse molecular characteristics across different datasets. Additionally, breast cancer is known to have many subtypes, which hinders the performance of the models aimed at all subtypes. To overcome the heterogeneous nature of breast cancer, we propose a method to obtain personalized classifiers that are trained on subsets of patients selected using the similarities between training and testing patients. Results on multiple independent datasets showed that our proposed approach significantly improved prediction accuracy compared to the models trained on the complete training dataset and models trained on specific cancer subtypes. Our results also showed that personalized classifiers trained on positively and negatively correlated patients outperformed classifiers trained only on positively correlated patients, highlighting the importance of selecting proper patient subsets for constructing personalized classifiers. Additionally, our proposed approach obtained more robust features than the other models and identified different features for different patients, making it a promising tool for designing personalized medicine for cancer patients.

show abstract

Section: Methodsmentioning

confidence: 99%

A Robust Personalized Classification Method for Breast Cancer Metastasis Prediction

Adnan

Najnin

Ruan

2022

Cancers

View full text Add to dashboard Cite

show abstract

“…In Adnan et al [93], the authors have implemented SHAP in conjunction with LIME to explain that a small number of highly compact and biological gene cluster features resulted in similar or better performance than classifiers built with many more individual genes. With training on smaller gene clusters, LIME proved that the classifiers have better AUC than the original classifiers except in RF and rSVM.…”

Section: Local Interpretable Model Agnostic Explanations (Lime)mentioning

confidence: 99%

Explainable artificial intelligence in breast cancer detection and risk prediction: A systematic scoping review

Ghasemi,

Hashtarkhani,

Schwartz

et al. 2024

Cancer Innovation

View full text Add to dashboard Cite

With the advances in artificial intelligence (AI), data‐driven algorithms are becoming increasingly popular in the medical domain. However, due to the nonlinear and complex behavior of many of these algorithms, decision‐making by such algorithms is not trustworthy for clinicians and is considered a black‐box process. Hence, the scientific community has introduced explainable artificial intelligence (XAI) to remedy the problem. This systematic scoping review investigates the application of XAI in breast cancer detection and risk prediction. We conducted a comprehensive search on Scopus, IEEE Explore, PubMed, and Google Scholar (first 50 citations) using a systematic search strategy. The search spanned from January 2017 to July 2023, focusing on peer‐reviewed studies implementing XAI methods in breast cancer datasets. Thirty studies met our inclusion criteria and were included in the analysis. The results revealed that SHapley Additive exPlanations (SHAP) is the top model‐agnostic XAI technique in breast cancer research in terms of usage, explaining the model prediction results, diagnosis and classification of biomarkers, and prognosis and survival analysis. Additionally, the SHAP model primarily explained tree‐based ensemble machine learning models. The most common reason is that SHAP is model agnostic, which makes it both popular and useful for explaining any model prediction. Additionally, it is relatively easy to implement effectively and completely suits performant models, such as tree‐based models. Explainable AI improves the transparency, interpretability, fairness, and trustworthiness of AI‐enabled health systems and medical devices and, ultimately, the quality of care and outcomes.

show abstract

“…DL algorithms have been successfully applied in medical imaging and disease detection, identification, and diagnosis. For example, in breast cancer, several studies have reported the utilisation, or the potential application, of automation in improving early detection and diagnosis with subsequent classification of cancer subtypes [14][15][16][17][18][19][20][21][22][23][24][25]. DL models have also been studied in creating treatment plans for locally advanced breast cancers and predicting survival rates [26,27].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-Based Artificial Intelligence to Investigate Targeted Nanoparticles’ Uptake in TNBC Cells

Ali

Balamurali

Varamini

2022

IJMS

View full text Add to dashboard Cite

Triple negative breast cancer (TNBC) is the most aggressive subtype of breast cancer in women. It has the poorest prognosis along with limited therapeutic options. Smart nano-based carriers are emerging as promising approaches in treating TNBC due to their favourable characteristics such as specifically delivering different cargos to cancer cells. However, nanoparticles’ tumour cell uptake, and subsequent drug release, are essential factors considered during the drug development process. Contemporary qualitative analyses based on imaging are cumbersome and prone to human biases. Deep learning-based algorithms have been well-established in various healthcare settings with promising scope in drug discovery and development. In this study, the performance of five different convolutional neural network models was evaluated. In this research, we investigated two sequential models from scratch and three pre-trained models, VGG16, ResNet50, and Inception V3. These models were trained using confocal images of nanoparticle-treated cells loaded with a fluorescent anticancer agent. Comparative and cross-validation analyses were further conducted across all models to obtain more meaningful results. Our models showed high accuracy in predicting either high or low drug uptake and release into TNBC cells, indicating great translational potential into practice to aid in determining cellular uptake at the early stages of drug development in any area of research.

show abstract

Construction and Evaluation of Robust Interpretation Models for Breast Cancer Metastasis Prediction

Cited by 5 publications

References 36 publications

A Robust Personalized Classification Method for Breast Cancer Metastasis Prediction

A Robust Personalized Classification Method for Breast Cancer Metastasis Prediction

Explainable artificial intelligence in breast cancer detection and risk prediction: A systematic scoping review

Deep Learning-Based Artificial Intelligence to Investigate Targeted Nanoparticles’ Uptake in TNBC Cells

Contact Info

Product

Resources

About