Classification of static infrared images using pre-trained CNN for breast cancer detection

Goncalves, Cristiane Sales; Souza, Jefferson R.; Fernandes, Henrique

doi:10.1109/cbms52027.2021.00094

Cited by 8 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This indicates that the model is able to accurately classify breast cancer images into two classes (benign and malignant) with a high degree of certainty. The ROC 32 AUC 33 and F1-score are two metrics that are commonly used to evaluate the performance of classification models. The ROC AUC is a measure of the model's ability to distinguish between positive and negative cases.…”

Section: Performance Evaluationmentioning

confidence: 99%

“…This enables the effective training of the multi-task deep learning model, particularly when dealing with substantial datasets and computationally intensive tasks like data augmentation and custom loss computations. The advantages of the proposed model in utilizing CPU and GPU resources are as follows: 32 Receiver Operating Characteristics 33 Area Under Curve Figure 7 shows that the results of the model testing phase are promising. This model is able to identify and locate breast cancer with high accuracy.…”

Section: Performance Evaluationmentioning

confidence: 99%

“…While their model demonstrated competence, it falls short of the high accuracy level achieved in our model evaluation. Gonçalves et al[33] combined multiple CNN models and employed transfer learning to achieve a classification accuracy of 91.67%. Despite their efforts, their accuracy remains notably lower than the 99.14% accuracy reported in our model assessment.…”

mentioning

confidence: 99%

See 2 more Smart Citations

BreastCDNet: Breast Cancer Detection Neural Network, Classification and Localization

Mahichi,

Ghods,

Sohrabi

et al. 2023

Preprint

View full text Add to dashboard Cite

Breast cancer remains a significant health concern globally, necessitating advanced detection methods for improved patient outcomes. Convolutional neural networks, CNN, have revolutionized object detection by automating the feature extraction process and allowing for the efficient localization and classification of objects within images. BreastCDNet introduces a novel approach to breast cancer detection using CNN. This pioneering CNN method is tailored specifically for the task of ultrasound breast cancer detection and localization, offering a streamlined and effective approach that significantly enhances diagnostic accuracy. Multi-task learning is leveraged by the proposed model, with simultaneous consideration of breast ultrasound image classification and bounding box regression for lesion localization. Intricate features from medical images are extracted by BreastCDNet architecture, facilitating both classification (benign or malignant) and object localization. Separate data generators are employed for classification and bounding box labels to optimize model training. The model's effectiveness is demonstrated by experimental results on the BUSI dataset, where exceptional classification accuracy and precise bounding box predictions are achieved. Key components, including convolutional layers for feature extraction, max-pooling layers for spatial reduction, fully connected layers for predictions, and specific output layers for classification and bounding box regression, are encompassed by the model architecture. The BreastCDNet model is a high-performance breast cancer detection model that achieved 99.14% training accuracy, 97.70% validation accuracy, 0.99 ROC AUC, and 0.97 F1-score on the training set. It is also capable of accurately localizing breast cancer lesions with an IOU score of 0.95.

show abstract

Section: Performance Evaluationmentioning

confidence: 99%

Section: Performance Evaluationmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation