A New Pes Planus Automatic Diagnosis Method: ViT-OELM Hybrid Modeling

Abstract

Background/Objectives: Pes planus (flat feet) is a condition characterized by flatter than normal soles of the foot. In this study, a Vision Transformer (ViT)-based deep learning architecture is proposed to automate the diagnosis of pes planus. The model analyzes foot images and classifies them into two classes, as "pes planus" and "not pes planus". In the literature, models based on Convolutional neural networks (CNNs) can automatically perform such classification, regression, and prediction processes, but these models cannot capture long-term addictions and general conditions. Methods: In this study, the pes planus dataset, which is openly available on the Kaggle database, was used. This paper suggests a ViT-OELM hybrid model for automatic diagnosis from the obtained pes planus images. The suggested ViT-OELM hybrid model includes an attention mechanism for feature extraction from the pes planus images. A total of 1000 features obtained for each sample image from this attention mechanism are used as inputs for an Optimum Extreme Learning Machine (OELM) classifier using various activation functions, and are classified. Results: In this study, the performance of this suggested ViT-OELM hybrid model is compared with some other studies, which used the same pes planus database. These comparison results are given. The suggested ViT-OELM hybrid model was trained for binary classification. The performance metrics were computed in testing phase. The model showed 98.04% accuracy, 98.04% recall, 98.05% precision, and an F-1 score of 98.03%. Conclusions: Our suggested ViT-OELM hybrid model demonstrates superior performance compared to those of other studies, which used the same dataset, in the literature.

Keywords: ViT-OELM modeling; automatic diagnosis; optimum extreme learning machine (OELM); pes planus; vision transformer (ViT).

Figure 1

Block diagram of our suggested approach using the ViT-OELM for pes planus diagnosis. In here, numbers and * represent patch and position respectively.

Figure 2

Example images from both pes planus and not pes planus classes in the dataset.

Figure 3

Block diagram of the Transformer encoder–decoder.

Figure 4

Block diagram of the MHA mechanism.

Figure 5

Block diagram of the attention mechanism used in this paper.

Figure 6

The hyperparameter selection and optimization process of the suggested ViT-OELM hybrid model.

Figure 7

The training process for the suggested VİT-OELM hybrid model.

Figure 8

Confusion matrix for binary-class scenario.

Figure 9

The ViT-OELM hybrid model’s performance curves. (a) Accuracy values. (b) Loss values.

Figure 10

(a) ROC Curve, (b) Precision–Recall Curve.