RadiomixNet: Integrating Radiomics and Feature Extraction for Advanced Pneumonia Diagnosis
The research outlines a workflow for medical image analysis and disease diagnosis through radiomics feature extraction. The dataset, consisting of chest X-ray images, was pre-processed using techniques such as denoising, resizing, and enhancement to ensure uniformity and high image quality. Advanced...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10817104/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841563287126278144 |
|---|---|
| author | Rahul Gowtham Poola Siva Sankar Yellampalli |
| author_facet | Rahul Gowtham Poola Siva Sankar Yellampalli |
| author_sort | Rahul Gowtham Poola |
| collection | DOAJ |
| description | The research outlines a workflow for medical image analysis and disease diagnosis through radiomics feature extraction. The dataset, consisting of chest X-ray images, was pre-processed using techniques such as denoising, resizing, and enhancement to ensure uniformity and high image quality. Advanced texture analysis methods, including Gray Level Size Zone Matrix, Gray Level Co-Occurrence Matrix, Gray Level Dependence Matrix and, Gray Level Run Length Matrix were employed to extract radiomics features. Power Spectral Density analysis using Burg, Yule Walker, and Welch techniques further enriched the understanding of frequency characteristics within the radiomics feature matrices, uncovering patterns vital for precise predictions. Diverse classifiers, including Bernoulli Naïve Bayes, Random Subspace Boost, Quadratic Discriminant, and Gradient Boosting, were employed to classify test X-rays. The performance of these classifiers was evaluated using metrics such as Cohen’s Kappa, Accuracy, Matthews Correlation Coefficient, Sensitivity, Youden’s Index, Specificity, Log Loss, and Brier Score. Among these, Gradient Boosting demonstrated superior performance across all feature sets, achieving a Cohen’s Kappa of 0.93, MCC of 0.88, Youden’s Index of 0.82, and a Log Loss of 0.27. |
| format | Article |
| id | doaj-art-53eda181e8014aa09efeb4bfc35e8d7f |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-53eda181e8014aa09efeb4bfc35e8d7f2025-01-03T00:02:01ZengIEEEIEEE Access2169-35362025-01-011369571510.1109/ACCESS.2024.352290810817104RadiomixNet: Integrating Radiomics and Feature Extraction for Advanced Pneumonia DiagnosisRahul Gowtham Poola0https://orcid.org/0000-0002-0219-8159Siva Sankar Yellampalli1https://orcid.org/0000-0001-6774-1514Electronics and Communication Engineering Department, SRM University, Amaravathi, Andhra Pradesh, IndiaElectronics and Communication Engineering Department, SRM University, Amaravathi, Andhra Pradesh, IndiaThe research outlines a workflow for medical image analysis and disease diagnosis through radiomics feature extraction. The dataset, consisting of chest X-ray images, was pre-processed using techniques such as denoising, resizing, and enhancement to ensure uniformity and high image quality. Advanced texture analysis methods, including Gray Level Size Zone Matrix, Gray Level Co-Occurrence Matrix, Gray Level Dependence Matrix and, Gray Level Run Length Matrix were employed to extract radiomics features. Power Spectral Density analysis using Burg, Yule Walker, and Welch techniques further enriched the understanding of frequency characteristics within the radiomics feature matrices, uncovering patterns vital for precise predictions. Diverse classifiers, including Bernoulli Naïve Bayes, Random Subspace Boost, Quadratic Discriminant, and Gradient Boosting, were employed to classify test X-rays. The performance of these classifiers was evaluated using metrics such as Cohen’s Kappa, Accuracy, Matthews Correlation Coefficient, Sensitivity, Youden’s Index, Specificity, Log Loss, and Brier Score. Among these, Gradient Boosting demonstrated superior performance across all feature sets, achieving a Cohen’s Kappa of 0.93, MCC of 0.88, Youden’s Index of 0.82, and a Log Loss of 0.27.https://ieeexplore.ieee.org/document/10817104/Radiomicsdenoisingfeature extractionpower spectral density estimateclassification |
| spellingShingle | Rahul Gowtham Poola Siva Sankar Yellampalli RadiomixNet: Integrating Radiomics and Feature Extraction for Advanced Pneumonia Diagnosis IEEE Access Radiomics denoising feature extraction power spectral density estimate classification |
| title | RadiomixNet: Integrating Radiomics and Feature Extraction for Advanced Pneumonia Diagnosis |
| title_full | RadiomixNet: Integrating Radiomics and Feature Extraction for Advanced Pneumonia Diagnosis |
| title_fullStr | RadiomixNet: Integrating Radiomics and Feature Extraction for Advanced Pneumonia Diagnosis |
| title_full_unstemmed | RadiomixNet: Integrating Radiomics and Feature Extraction for Advanced Pneumonia Diagnosis |
| title_short | RadiomixNet: Integrating Radiomics and Feature Extraction for Advanced Pneumonia Diagnosis |
| title_sort | radiomixnet integrating radiomics and feature extraction for advanced pneumonia diagnosis |
| topic | Radiomics denoising feature extraction power spectral density estimate classification |
| url | https://ieeexplore.ieee.org/document/10817104/ |
| work_keys_str_mv | AT rahulgowthampoola radiomixnetintegratingradiomicsandfeatureextractionforadvancedpneumoniadiagnosis AT sivasankaryellampalli radiomixnetintegratingradiomicsandfeatureextractionforadvancedpneumoniadiagnosis |