# HFSOF: A Hierarchical Feature Selection and Optimization Framework for Ultrasound-Based Diagnosis of Endometrial Lesions

## TL;DR

This paper introduces a new framework to improve the accuracy of diagnosing endometrial lesions using ultrasound images by combining advanced data analysis techniques.

## Contribution

A novel hierarchical framework combining KPCA, filter-based feature fusion, and WMA optimization for robust ultrasound-based diagnosis of endometrial lesions.

## Key findings

- The framework effectively balances nonlinear structure preservation and feature redundancy control.
- The proposed pipeline achieves robust classification with high generalization on medical imaging datasets.
- The method provides interpretable and reproducible results for intelligent diagnosis.

## Abstract

Endometrial lesions are common in gynecology, exhibiting considerable clinical heterogeneity across different subtypes. Although ultrasound imaging is the preferred diagnostic modality due to its noninvasive, accessible, and cost-effective nature, its diagnostic performance remains highly operator-dependent, leading to subjectivity and inconsistent results. To address these limitations, this study proposes a hierarchical feature selection and optimization framework for endometrial lesions, aiming to enhance the objectivity and robustness of ultrasound-based diagnosis. Firstly, Kernel Principal Component Analysis (KPCA) is employed for nonlinear dimensionality reduction, retaining the top 1000 principal components. Secondly, an ensemble of three filter-based methods—information gain, chi-square test, and symmetrical uncertainty—is integrated to rank and fuse features, followed by thresholding with Maximum Scatter Difference Linear Discriminant Analysis (MSDLDA) for preliminary feature selection. Finally, the Whale Migration Algorithm (WMA) is applied to population-based feature optimization and classifier training under the constraints of a Support Vector Machine (SVM) and a macro-averaged F1 score. Experimental results demonstrate that the proposed closed-loop pipeline of “kernel reduction—filter fusion—threshold pruning—intelligent optimization—robust classification” effectively balances nonlinear structure preservation, feature redundancy control, and model generalization, providing an interpretable, reproducible, and efficient solution for intelligent diagnosis in small- to medium-scale medical imaging datasets.