# RadioGuide-DCN: A Radiomics-Guided Decorrelated Network for Medical Image Classification

## TL;DR

RadioGuide-DCN is a new medical image classification method that combines radiomics with deep learning to improve accuracy and reduce overfitting.

## Contribution

The novel integration of radiomics features with a decorrelation loss and anti-attention fusion module in a deep learning framework.

## Key findings

- RadioGuide-DCN achieves 93.63% accuracy in BUSI image classification.
- The model outperforms conventional methods in accuracy and AUC scores across multiple medical imaging tasks.

## Abstract

Medical imaging is an indispensable tool in clinical diagnosis and therapeutic decision-making, encompassing a wide range of modalities such as radiography, ultrasound, CT, and MRI. With the rapid advancement of deep learning technologies, significant progress has been made in medical image analysis. However, existing deep learning methods are often limited by dataset size, which can lead to overfitting, while traditional approaches relying on hand-crafted features lack specificity and fail to fully capture complex pathological information. To address these challenges, we propose RadioGuide-DCN, an innovative radiomics-guided decorrelated classification network. Our method integrates radiomics features as prior information into deep neural networks and employs a feature decorrelation loss mechanism combined with an anti-attention feature fusion module to effectively reduce feature redundancy and enhance the model’s capacity to capture both local details and global patterns. Specifically, we utilize a Kolmogorov–Arnold Network (KAN) classifier with learnable activation functions to further boost performance across various medical imaging datasets. Experimental results demonstrate that RadioGuide-DCN achieves an accuracy of 93.63% in BUSI image classification and consistently outperforms conventional radiomics and deep learning methods in multiple medical imaging classification tasks, significantly improving classification accuracy and AUC scores. Our study offers a novel paradigm for integrating deep learning with traditional imaging approaches and holds broad clinical application potential, particularly in tumor detection, image classification, and disease diagnosis.