METHODS: This system extracted features from transfer learning of AlexNet, VGG19, and ResNet50 networks before reducing this problem into multiple binary sub-problems using error-correcting coding. The learners were trained using the support vector machine (SVM) method. The outputs of these classifiers were combined and compared to the true class codes for the final prediction.
RESULTS: Despite the superior performance of VGG19-SVM, with mean ± standard deviation accuracy and sensitivity of 80.68% ± 2.00% and 80.86% ± 0.45%, respectively, this model required a long training time. There were also false-negative cases using both the VGGNet-SVM and ResNet-SVM models. AlexNet-SVM was more efficient in terms of running speed and prediction consistency. Our findings also showed good diagnostic ability, with an area under the curve of approximately 0.95. Further investigation also showed good agreement between our research outcomes and that of the state-of-the-art methods, with specificity ranging from 93% to 100%.
CONCLUSIONS: We believe that the AlexNet-SVM model can be conveniently applied for clinical use. Further research could include the implementation of an optimization algorithm for hyperparameter tuning, as well as an appropriate selection of experimental design to improve the efficiency of Pap smear image classification.
METHODS: Manual segmentation involved selecting a region-of-interest (ROI) in images from the Bosphorus dataset to generate ground truth data. The HHM combined histogram equalization and morphological and thresholding-based algorithms to localize veins from hand images. The data were divided into training, validation, and testing sets with an 8:1:1 ratio before training AlexNet. We considered three image augmentation strategies to enlarge our training sets. The best training hyperparameters were found using the manually segmented dataset.
RESULTS: We obtained a good test accuracy (91.5%) using the model trained with manually segmented images. The HHM method showed slightly inferior performance (76.5%). Considerable improvement was observed in the test accuracy of the model trained with the inclusion of automatically segmented and augmented images (84%), with low false acceptance and false rejection rates (0.00035% and 0.095%, respectively). A comparison with past studies further demonstrated the competitiveness of our technique.
CONCLUSIONS: Our technique can be feasible for extracting the ROI in DHV images. This strategy provides higher consistency and greater efficiency than the manual approach.