| Jia et al. [43] |
Detection of cervical cancer cells in a complex situation based on an improved YOLOv3 network |
MAP of 78.87%, 8.02%, 8.22% and 4.83% higher than SSD (Single Shot Multi-Box Detector), YOLOv3 (You Only Look Once) and ResNet50. |
| Ali et al. [44] |
Machine learning-based statistical analysis for early-stage detection of cervical cancer |
A Random Tree (RT) accuracy biopsy (98.33%), cytology (98.65%) |
| Random Forest (RF) and Instance-Based K-nearest neighbor (IBk) provided the best performance for Hinselmann (99.16%) and Schiller (98.58%), respectively. |
| Zhang et al. [45] |
Quantitative detection of cervical cancer based on time series information from smear images |
Accuracy 98.3% |
| Sensitivity 98.1% |
| Specificity 97.9%. |
| Chitra et al. [46] |
An optimized deep learning model using a Mutation-based Atom Search Optimization algorithm for cervical cancer detection |
Accuracy 98.38% |
| Sensitivity 98.83% |
| Specificity 98.5%. |
| Precision 98.58% |
| Recall 99.3% |
| F-score 98.25% |
| Cao et al. [33] |
A novel attention-guided convolutional network for the detection of abnormal cervical cells in cervical cancer screening |
Online Database |
| Sensitivity = 95.83% |
| Specificity = 94.81% |
| Accuracy = 95.08% |
| AUC = 0.991 |
| External Dataset (110 cases and 35,013 images) |
| Sensitivity = 91.30% |
| Specificity = 90.62% |
| Accuracy = 90.91% |
| AUC = 0.934 |
| Diagnostic time is 0.04s/image compare to average time of pathologist 14.83s/image. |
| Devi, et al. [47] |
Cervical Cancer Classification from Pap Smear Images Using Modified Fuzzy C Means, PCA, and KNN |
Minimum accuracy 94.15%, Maximum accuracy 96.28%, Average accuracy 94.86%, Sensitivity 97.96%, |
| Specificity 83.65% |
| F1-score 96.87%, |
| Precision 96.31% |
| Bhatt et al. [48] |
Cervical cancer detection in pap smear whole slide images using convNet with transfer learning and progressive resizing |
Accuracy (99.70%) |
| Precision (99.70%) |
| Recall (99.72%) |
| F-Beta (99.63%) |
| Kappa scores (99.31%) |
| Desiani et al. [49] |
Bi-path Architecture of CNN Segmentation and Classification Method for Cervical Cancer Disorders Based on Pap-smear Images |
Accuracy = 90% |
| Sensitivity (SN) |
| Specificity (SP) |
| F1-score |
|
