Multi-Domain Feature Incorporation of Lightweight Convolutional Neural Networks and Handcrafted Features for Lung and Colon Cancer Diagnosis
This study presents a computer-aided diagnostic (CAD) framework that integrates multi-domain features through a hybrid methodology. The system uses several light deep networks (EfficientNetB0, MobileNet, and ResNet-18), which feature fewer layers and parameters, unlike traditional systems that depen...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Technologies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7080/13/5/173 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This study presents a computer-aided diagnostic (CAD) framework that integrates multi-domain features through a hybrid methodology. The system uses several light deep networks (EfficientNetB0, MobileNet, and ResNet-18), which feature fewer layers and parameters, unlike traditional systems that depend on a single, parameter-complex deep network. Additionally, it employs several handcrafted feature extraction techniques. It systematically assesses the diagnostic power of deep features only, handcrafted features alone, and both deep and handcrafted features combined. Furthermore, it examines the influence of combining deep features from multiple CNNs with distinct handcrafted features on diagnostic accuracy, providing insights into the effectiveness of this hybrid approach for classifying lung and colon cancer. To achieve this, the proposed CAD employs non-negative matrix factorization for lowering the dimension of the spatial deep feature sets. In addition, these deep features obtained from each network are distinctly integrated with handcrafted features sourced from temporal statistical attributes and texture-based techniques, including gray-level co-occurrence matrix and local binary patterns. Moreover, the CAD integrates the deep attributes of the three deep networks with the handcrafted attributes. It also applies feature selection based on minimum redundancy maximum relevance to the integrated deep and handcrafted features, guaranteeing optimal computational efficiency and high diagnostic accuracy. The results indicated that the suggested CAD system attained remarkable accuracy, reaching 99.7% using multi-modal features. The suggested methodology, when compared to present CAD systems, either surpassed or was closely aligned with state-of-the-art methods. These findings highlight the efficacy of incorporating multi-domain attributes of numerous lightweight deep learning architectures and multiple handcrafted features. |
|---|---|
| ISSN: | 2227-7080 |