Evaluating Interpretability in Deep Learning using Breast Cancer Histopathological Images

Macedo, Daniel C.; S., De Lima John W.; Santos, Vinicius D.; O., Moraes Tasso L.; P., Neto Fernando M.; Arrais, Nicksson; Vinuto, Tiago; Lucena, Joao

doi:10.1109/sibgrapi55357.2022.9991797

Cited by 2 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Actually, MobileNetV2, NASNetLarge, EfficientNetB0 (DL models), ViT, and DenseNet201 are all advanced DL models. The advantage of the method is that it provides a way to not only evaluate the accuracy of the models but their capacity to recognize the proper districts where the tumor cores are found as well, which can aid pathologists with tumour diagnoses [12].…”

Section: Results Comparisonmentioning

confidence: 99%

“…The methodology consisted primarily of training on the BreakHis dataset using five DL models, then evaluating the BreCaHAD dataset and using Grad-CAM to assess the interpretability of each DL model. The number of annotations matched to the JSON file was then validated to assess the accuracy of the interpretable regions of the models [12].…”

Section: Dnnsmentioning

confidence: 99%

“…This article aims to compare several methods of machine learning in diagnosing breast cancer, including supervised learning-based cancer detection, automated nuclear section segmentation model, BCRecommender, DL models (including five neural networks), and Computer-aided diagnosis [9][10][11][12][13]. All of the methods used are based on BreCaHAD which is used for detecting breast cancer and histopathological diagnosis [14].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Comparison of machine learning models on breast cancer risk prediction challenge

Chen

2023

ACE

View full text Add to dashboard Cite

Breast cancer is a malignant tumor that poses a serious risk to women's life and wellbeing. To make matters worse, this cancer is less symptomatic in its early stages. It is not easily diagnosed through traditional means. The topic of this essay is to investigate machine learning for the determination of breast cancer.. The methods based on machine learning are as followed: automated nuclear section segmentation model, BCRecommender System, DNNs, and computer-aided diagnosis model (CADM). The methods studied are all based on the BreCaHad dataset and use a comparative metric.To measure the performance of each model, the accuracy, F1-score, specificity, and precision are used. The result shows that the approaches based on machine learning work well in diagnosing breast carcinoma, with high accuracy. Most of them have a percentage over 90% in accuracy and some of them are even higher than 95%. However, some of the models work poorly, such as layer 1 of BCRecommender with 61.06% accuracy and EfficientNetB0 with 72.96%. With every aspect taken into consideration, computer-aided diagnosis (CADM: Using combined features of HOG, WPD, ResNet as well as PCA + SVM) has the greatest advantage in diagnosing BC.

show abstract

Section: Results Comparisonmentioning

confidence: 99%

Section: Dnnsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of machine learning models on breast cancer risk prediction challenge

Chen

2023

ACE

View full text Add to dashboard Cite

show abstract

Use of Autoencoders for Improving the Performance of Classification and Interpretation of Convolutional Neural Networks in Histopathological Images

Macedo,

de Paula Neto,

Moraes

et al. 2024

Int. J. Comp. Intel. Appl.

View full text Add to dashboard Cite

Breast cancer is one of the most common types of cancer and it presents itself as being the leading cause of death among women. If its diagnosis occur soon enough, the probability to achieve the cure of the patient can be increased. Recently, it has been more common the use of deep neural network techniques to aid pathologists in their prognosis, but they still do not fully trust them because they lack interpretability. In light of that, this work investigates if previous training of the models as encoders could enhance their accuracy in both classification and interpretability. There were implemented three models to the BreakHis and BreCaHAD dataset: NASNet Mobile, DenseNET201, and MobileNetV2. The experiments have shown that the three models increased the classification performance and two models improved their interpretability using the proposed strategy. DenseNet201 encoder has performed almost 23% better than its vanilla version in classifying a tumor and the NASNet Mobile encoder has improved 28.5% in its tumor interpretation.

show abstract

Evaluating Interpretability in Deep Learning using Breast Cancer Histopathological Images

Cited by 2 publications

References 31 publications

Comparison of machine learning models on breast cancer risk prediction challenge

Comparison of machine learning models on breast cancer risk prediction challenge

Use of Autoencoders for Improving the Performance of Classification and Interpretation of Convolutional Neural Networks in Histopathological Images

Contact Info

Product

Resources

About