Single-cell conventional pap smear image classification using pre-trained deep neural network architectures

Abstract

Background Automating cytology-based cervical cancer screening could alleviate the shortage of skilled pathologists in developing countries. Up until now, computer vision experts have attempted numerous semi and fully automated approaches to address the need. Yet, these days, leveraging the astonishing accuracy and reproducibility of deep neural networks has become common among computer vision experts. In this regard, the purpose of this study is to classify single-cell Pap smear (cytology) images using pre-trained deep convolutional neural network (DCNN) image classifiers. We have fine-tuned the top ten pre-trained DCNN image classifiers and evaluated them using five class single-cell Pap smear images from SIPaKMeD dataset. The pre-trained DCNN image classifiers were selected from Keras Applications based on their top 1% accuracy. Results Our experimental result demonstrated that from the selected top-ten pre-trained DCNN image classifiers DenseNet169 outperformed with an average accuracy, precision, recall, and F1-score of 0.990, 0.974, 0.974, and 0.974, respectively. Moreover, it dashed the benchmark accuracy proposed by the creators of the dataset with 3.70%. Conclusions Even though the size of DenseNet169 is small compared to the experimented pre-trained DCNN image classifiers, yet, it is not suitable for mobile or edge devices. Further experimentation with mobile or small-size DCNN image classifiers is required to extend the applicability of the models in real-world demands. In addition, since all experiments used the SIPaKMeD dataset, additional experiments will be needed using new datasets to enhance the generalizability of the models.

Deep learning model for tongue cancer diagnosis using endoscopic images

“…DenseNet169, which was evaluated as the most suitable algorithm in this study, was also effective in image evaluation conducted in previous studies. In a study to classify pathological images in which atypical images were used similar to this study, effective results were obtained even with a small number of images 34 . Similarly, DenseNet169 showed the best performance in the study of the AI model for classifying the quality of tongue images 35 .…”

Automated Detection and Classification of Cervical Cancer Using Pap Smear Microscopic Images: A Comprehensive Review and Future Perspectives

“…[96] Among the different pretrained classifiers used for the study, DenseNet169 outperforms with an average accuracy, precision, recall, and F1-score of 0.990, 0.974, 0.974, and 0.974, respectively. [96]…”

“…MA Mohammed et al work on pretrained deep neural network architecture. [96] Publicly available dataset, named SIPaKMeD are used in which a total number of 4049 single-cell images that are manually cropped from 966 full-slide Pap smear images. [96] Among the different pretrained classifiers used for the study, DenseNet169 outperforms with an average accuracy, precision, recall, and F1-score of 0.990, 0.974, 0.974, and 0.974, respectively.…”

“…Authors achieve a best kappa statistics value for biopsy images as 97% and for cytology images as 87%. [96]…”

“…[96--107] In this comparative study, the comparison is made among the SVM based work as well as the deep CNN model for cell image classification. The [58] Achieved an accuracy of 96 The relative nucleus area is used as a feature to identify the cancerous cells and achieves good differentiation between normal and cancerous cells, as cancer cells contain a larger distribution of darker pixels. [78] Alqahtani et al used ANN classification model to forecast the happening of cancer in the prostate and compared the result with SVM, Logistic regression model, and Decision tree.…”