A novel framework for esophageal cancer grading: combining CT imaging, radiomics, reproducibility, and deep learning insights
Abstract Objective This study aims to create a reliable framework for grading esophageal cancer. The framework combines feature extraction, deep learning with attention mechanisms, and radiomics to ensure accuracy, interpretability, and practical use in tumor analysis. Materials and methods This ret...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-05-01
|
| Series: | BMC Gastroenterology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12876-025-03952-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849312057297469440 |
|---|---|
| author | Muna Alsallal Hanan Hassan Ahmed Radhwan Abdul Kareem Anupam Yadav Subbulakshmi Ganesan Aman Shankhyan Sofia Gupta Kamal Kant Joshi Hayder Naji Sameer Ahmed Yaseen Zainab H. Athab Mohaned Adil Bagher Farhood |
| author_facet | Muna Alsallal Hanan Hassan Ahmed Radhwan Abdul Kareem Anupam Yadav Subbulakshmi Ganesan Aman Shankhyan Sofia Gupta Kamal Kant Joshi Hayder Naji Sameer Ahmed Yaseen Zainab H. Athab Mohaned Adil Bagher Farhood |
| author_sort | Muna Alsallal |
| collection | DOAJ |
| description | Abstract Objective This study aims to create a reliable framework for grading esophageal cancer. The framework combines feature extraction, deep learning with attention mechanisms, and radiomics to ensure accuracy, interpretability, and practical use in tumor analysis. Materials and methods This retrospective study used data from 2,560 esophageal cancer patients across multiple clinical centers, collected from 2018 to 2023. The dataset included CT scan images and clinical information, representing a variety of cancer grades and types. Standardized CT imaging protocols were followed, and experienced radiologists manually segmented the tumor regions. Only high-quality data were used in the study. A total of 215 radiomic features were extracted using the SERA platform. The study used two deep learning models—DenseNet121 and EfficientNet-B0—enhanced with attention mechanisms to improve accuracy. A combined classification approach used both radiomic and deep learning features, and machine learning models like Random Forest, XGBoost, and CatBoost were applied. These models were validated with strict training and testing procedures to ensure effective cancer grading. Results This study analyzed the reliability and performance of radiomic and deep learning features for grading esophageal cancer. Radiomic features were classified into four reliability levels based on their ICC (Intraclass Correlation) values. Most of the features had excellent (ICC > 0.90) or good (0.75 < ICC ≤ 0.90) reliability. Deep learning features extracted from DenseNet121 and EfficientNet-B0 were also categorized, and some of them showed poor reliability. The machine learning models, including XGBoost and CatBoost, were tested for their ability to grade cancer. XGBoost with Recursive Feature Elimination (RFE) gave the best results for radiomic features, with an AUC (Area Under the Curve) of 91.36%. For deep learning features, XGBoost with Principal Component Analysis (PCA) gave the best results using DenseNet121, while CatBoost with RFE performed best with EfficientNet-B0, achieving an AUC of 94.20%. Combining radiomic and deep features led to significant improvements, with XGBoost achieving the highest AUC of 96.70%, accuracy of 96.71%, and sensitivity of 95.44%. The combination of both DenseNet121 and EfficientNet-B0 models in ensemble models achieved the best overall performance, with an AUC of 95.14% and accuracy of 94.88%. Conclusions This study improves esophageal cancer grading by combining radiomics and deep learning. It enhances diagnostic accuracy, reproducibility, and interpretability, while also helping in personalized treatment planning through better tumor characterization. Clinical trial number Not applicable. |
| format | Article |
| id | doaj-art-eacffb53d6ff400d9aa0749a7bc3e49e |
| institution | Kabale University |
| issn | 1471-230X |
| language | English |
| publishDate | 2025-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Gastroenterology |
| spelling | doaj-art-eacffb53d6ff400d9aa0749a7bc3e49e2025-08-20T03:53:12ZengBMCBMC Gastroenterology1471-230X2025-05-0125112010.1186/s12876-025-03952-6A novel framework for esophageal cancer grading: combining CT imaging, radiomics, reproducibility, and deep learning insightsMuna Alsallal0Hanan Hassan Ahmed1Radhwan Abdul Kareem2Anupam Yadav3Subbulakshmi Ganesan4Aman Shankhyan5Sofia Gupta6Kamal Kant Joshi7Hayder Naji Sameer8Ahmed Yaseen9Zainab H. Athab10Mohaned Adil11Bagher Farhood12Electronics and Communication Department, College of Engineering, Al- Muthanna UniversityCollege of Pharmacy, Alnoor UniversityAhl al Bayt UniversityDepartment of Computer Engineering and Application, GLA UniversityDepartment of Chemistry and Biochemistry, School of Sciences, JAIN (Deemed to be University)Centre for Research Impact & Outcome, Chitkara University Institute of Engineering and Technology, Chitkara UniversityDepartment of Chemistry, Chandigarh Engineering College, Chandigarh Group of Colleges-JhanjeriDepartment of Allied Science, Graphic Era Hill UniversityCollage of Pharmacy, National University of Science and TechnologyGilgamesh Ahliya UniversityDepartment of Pharmacy, Al-Zahrawi University CollegePharmacy College, Al-Farahidi UniversityDepartment of Medical Physics and Radiology, Faculty of Paramedical Sciences, Kashan University of Medical SciencesAbstract Objective This study aims to create a reliable framework for grading esophageal cancer. The framework combines feature extraction, deep learning with attention mechanisms, and radiomics to ensure accuracy, interpretability, and practical use in tumor analysis. Materials and methods This retrospective study used data from 2,560 esophageal cancer patients across multiple clinical centers, collected from 2018 to 2023. The dataset included CT scan images and clinical information, representing a variety of cancer grades and types. Standardized CT imaging protocols were followed, and experienced radiologists manually segmented the tumor regions. Only high-quality data were used in the study. A total of 215 radiomic features were extracted using the SERA platform. The study used two deep learning models—DenseNet121 and EfficientNet-B0—enhanced with attention mechanisms to improve accuracy. A combined classification approach used both radiomic and deep learning features, and machine learning models like Random Forest, XGBoost, and CatBoost were applied. These models were validated with strict training and testing procedures to ensure effective cancer grading. Results This study analyzed the reliability and performance of radiomic and deep learning features for grading esophageal cancer. Radiomic features were classified into four reliability levels based on their ICC (Intraclass Correlation) values. Most of the features had excellent (ICC > 0.90) or good (0.75 < ICC ≤ 0.90) reliability. Deep learning features extracted from DenseNet121 and EfficientNet-B0 were also categorized, and some of them showed poor reliability. The machine learning models, including XGBoost and CatBoost, were tested for their ability to grade cancer. XGBoost with Recursive Feature Elimination (RFE) gave the best results for radiomic features, with an AUC (Area Under the Curve) of 91.36%. For deep learning features, XGBoost with Principal Component Analysis (PCA) gave the best results using DenseNet121, while CatBoost with RFE performed best with EfficientNet-B0, achieving an AUC of 94.20%. Combining radiomic and deep features led to significant improvements, with XGBoost achieving the highest AUC of 96.70%, accuracy of 96.71%, and sensitivity of 95.44%. The combination of both DenseNet121 and EfficientNet-B0 models in ensemble models achieved the best overall performance, with an AUC of 95.14% and accuracy of 94.88%. Conclusions This study improves esophageal cancer grading by combining radiomics and deep learning. It enhances diagnostic accuracy, reproducibility, and interpretability, while also helping in personalized treatment planning through better tumor characterization. Clinical trial number Not applicable.https://doi.org/10.1186/s12876-025-03952-6Esophageal cancer gradingCT imagingRadiomicsDeep learningReproducibility |
| spellingShingle | Muna Alsallal Hanan Hassan Ahmed Radhwan Abdul Kareem Anupam Yadav Subbulakshmi Ganesan Aman Shankhyan Sofia Gupta Kamal Kant Joshi Hayder Naji Sameer Ahmed Yaseen Zainab H. Athab Mohaned Adil Bagher Farhood A novel framework for esophageal cancer grading: combining CT imaging, radiomics, reproducibility, and deep learning insights BMC Gastroenterology Esophageal cancer grading CT imaging Radiomics Deep learning Reproducibility |
| title | A novel framework for esophageal cancer grading: combining CT imaging, radiomics, reproducibility, and deep learning insights |
| title_full | A novel framework for esophageal cancer grading: combining CT imaging, radiomics, reproducibility, and deep learning insights |
| title_fullStr | A novel framework for esophageal cancer grading: combining CT imaging, radiomics, reproducibility, and deep learning insights |
| title_full_unstemmed | A novel framework for esophageal cancer grading: combining CT imaging, radiomics, reproducibility, and deep learning insights |
| title_short | A novel framework for esophageal cancer grading: combining CT imaging, radiomics, reproducibility, and deep learning insights |
| title_sort | novel framework for esophageal cancer grading combining ct imaging radiomics reproducibility and deep learning insights |
| topic | Esophageal cancer grading CT imaging Radiomics Deep learning Reproducibility |
| url | https://doi.org/10.1186/s12876-025-03952-6 |
| work_keys_str_mv | AT munaalsallal anovelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT hananhassanahmed anovelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT radhwanabdulkareem anovelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT anupamyadav anovelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT subbulakshmiganesan anovelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT amanshankhyan anovelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT sofiagupta anovelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT kamalkantjoshi anovelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT haydernajisameer anovelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT ahmedyaseen anovelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT zainabhathab anovelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT mohanedadil anovelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT bagherfarhood anovelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT munaalsallal novelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT hananhassanahmed novelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT radhwanabdulkareem novelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT anupamyadav novelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT subbulakshmiganesan novelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT amanshankhyan novelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT sofiagupta novelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT kamalkantjoshi novelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT haydernajisameer novelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT ahmedyaseen novelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT zainabhathab novelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT mohanedadil novelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights AT bagherfarhood novelframeworkforesophagealcancergradingcombiningctimagingradiomicsreproducibilityanddeeplearninginsights |