Identifying pregnancy in cows using ovarian ultrasound images and convolutional neural networks - a proof-of-concept study

Andrade, André Cascalho; Silva, Luan Oliveira da; Souza, Victor Ferreira; Rufino, Luana Marta de Almeida; Silva, Tadeu Eder da; Santos, Adam; Gomes, Diego de Azevedo; Rodrigues, João Paulo Pacheco

doi:10.1016/j.compag.2023.107674

Cited by 1 publication

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed model integrates three different pre-trained models: (1) a combination of Customized CNN and EfficientNetV2B3 [ 29 ], (2) a combination of MobileNet [ 30 ] and Densenet121 [ 31 ], and (3) a combination of MobileNetV2 [ 32 ] and EfficientNetV2_b0 [ 33 ]. These models were chosen to leverage their pre-existing knowledge and weights that were previously trained for IDC detection.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Using hybrid pre-trained models for breast cancer detection

Zarif,

Abdulkader,

Elaraby

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Breast cancer is a prevalent and life-threatening disease that affects women globally. Early detection and access to top-notch treatment are crucial in preventing fatalities from this condition. However, manual breast histopathology image analysis is time-consuming and prone to errors. This study proposed a hybrid deep learning model (CNN+EfficientNetV2B3). The proposed approach utilizes convolutional neural networks (CNNs) for the identification of positive invasive ductal carcinoma (IDC) and negative (non-IDC) tissue using whole slide images (WSIs), which use pre-trained models to classify breast cancer in images, supporting pathologists in making more accurate diagnoses. The proposed model demonstrates outstanding performance with an accuracy of 96.3%, precision of 93.4%, recall of 86.4%, F1-score of 89.7%, Matthew’s correlation coefficient (MCC) of 87.6%, the Area Under the Curve (AUC) of a Receiver Operating Characteristic (ROC) curve of 97.5%, and the Area Under the Curve of the Precision-Recall Curve (AUPRC) of 96.8%, which outperforms the accuracy achieved by other models. The proposed model was also tested against MobileNet+DenseNet121, MobileNetV2+EfficientNetV2B0, and other deep learning models, proving more powerful than contemporary machine learning and deep learning approaches.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The proposed hybrid model uses transfer learning to combine the strengths of two pre-trained models, MobileNet [ 30 ] and DenseNet121 [ 31 ], for more robust breast cancer classification. The internal architecture of the model consists of two branches, with each branch, using a pre-trained model to extract features from the input image.…”

Section: Methodsmentioning

confidence: 99%