Automated cervical cancer screening using single-cell segmentation and deep learning: enhanced performance with liquid-based cytology

HIGHLIGHTS

• What: This study explored the potential of deep learning (DL) for cell classification using both Pap smears and LBC samples. In the model configuration phase, three hyper-parameters were used: (i) optimizer=‘Adam` (with a learning rate of 1 × 10-5 ); (ii) loss function: binary cross-entropy (loss=`binary-crossentropy`); and_(iii) the AUC metric, which was used for the evaluation of the model in training and validation. In the training phase of the model, the following hyper-parameters were used: Bach-size=512 and number of epochs: 100. This study investigated the performance of a ResNet . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.