Artificial intelligence can help individualize Wilms tumor treatment by predicting tumor response to preoperative chemotherapy
"Purpose: To create a computer-aided prediction (CAP) system to predict Wilms tumor (WT) responsiveness to preoperative chemotherapy (PC) using pre-therapy contrast-enhanced computed tomography (CECT). Materials and Methods: A single-center database was reviewed for children <18 years diagn...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Korean Urological Association
2025-01-01
|
| Series: | Investigative and Clinical Urology |
| Subjects: | |
| Online Access: | https://www.icurology.org/pdf/10.4111/icu.20240135 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841553417275703296 |
|---|---|
| author | Ahmed Nashat Ahmed Alksas Rasha T. Aboulelkheir Ahmed Elmahdy Sherry M. Khater Hossam M. Balaha Israa Sharaby Mohamed Shehata Mohammed Ghazal Salama Abd El-Wadoud Ayman El-Baz Ahmed Mosbah Ahmed Abdelhalim |
| author_facet | Ahmed Nashat Ahmed Alksas Rasha T. Aboulelkheir Ahmed Elmahdy Sherry M. Khater Hossam M. Balaha Israa Sharaby Mohamed Shehata Mohammed Ghazal Salama Abd El-Wadoud Ayman El-Baz Ahmed Mosbah Ahmed Abdelhalim |
| author_sort | Ahmed Nashat |
| collection | DOAJ |
| description | "Purpose: To create a computer-aided prediction (CAP) system to predict Wilms tumor (WT) responsiveness to preoperative chemotherapy (PC) using pre-therapy contrast-enhanced computed tomography (CECT).
Materials and Methods: A single-center database was reviewed for children <18 years diagnosed with WT and received PC between 2001 and 2021. Patients were excluded if pre- and post-PC CECT were not retrievable. According to the Response Evaluation Criteria in Solid Tumors criteria, volumetric response was considered favorable if PC resulted in ≥30% tumor volume reduction. Histological response was considered favorable if post-nephrectomy specimens had ≥66% necrosis. Four steps were used to create the prediction model: tumor delineation; extraction of shape, texture and functionality-based features; integration of the extracted features and selection of the prediction model with the highest diagnostic performance. K-fold cross-validation allowed the presentation of all data in the training and testing phases.
Results: A total of 63 tumors in 54 patients were used to train and test the prediction model. Patients were treated with 4–8 weeks of vincristine/actinomycin-D combination. Favorable volumetric and histologic responses were achieved in 46 tumors (73.0%) and 38 tumors (60.3%), respectively. Among machine learning classifiers, support vector machine had the best diagnostic performance with an accuracy, sensitivity, and specificity of 95.24%, 95.65%, and 94.12% for volumetric and 84.13%, 89.47%, 88% for histologic response prediction.
Conclusions: Based on pre-therapy CECT, CAP systems can help identify WT that are less likely to respond to PC with excellent accuracy. These tumors can be offered upfront surgery, avoiding the cons of PC."
|
| format | Article |
| id | doaj-art-e44442a37f7e4ab891a0d5b5ce16dc3b |
| institution | Kabale University |
| issn | 2466-0493 2466-054X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Korean Urological Association |
| record_format | Article |
| series | Investigative and Clinical Urology |
| spelling | doaj-art-e44442a37f7e4ab891a0d5b5ce16dc3b2025-01-09T09:16:09ZengKorean Urological AssociationInvestigative and Clinical Urology2466-04932466-054X2025-01-01661475510.4111/icu.20240135Artificial intelligence can help individualize Wilms tumor treatment by predicting tumor response to preoperative chemotherapyAhmed Nashat0https://orcid.org/0000-0002-7371-6144Ahmed Alksas1https://orcid.org/0000-0001-9409-931XRasha T. Aboulelkheir2https://orcid.org/0000-0002-4250-8772Ahmed Elmahdy3Sherry M. Khater4https://orcid.org/0000-0001-5988-9711Hossam M. Balaha5https://orcid.org/0000-0002-0686-4411 Israa Sharaby6https://orcid.org/0000-0003-2287-3315Mohamed Shehata7https://orcid.org/0000-0001-6640-6183Mohammed Ghazal8https://orcid.org/0000-0002-9045-6698 Salama Abd El-Wadoud9https://orcid.org/0009-0000-6893-0018 Ayman El-Baz10https://orcid.org/0000-0001-7264-1323Ahmed Mosbah11 Ahmed Abdelhalim12https://orcid.org/0000-0002-4451-0032Department of Urology, Mansoura Urology and Nephrology Center, Mansoura University, Mansoura, Egypt.Bioengineering Department, University of Louisville, Louisville, KY, USA.Department of Radiology, Mansoura Urology and Nephrology Center, Mansoura University, Mansoura, Egypt.Department of Radiology, Mansoura Urology and Nephrology Center, Mansoura University, Mansoura, Egypt.Department of Pathology, Mansoura Urology and Nephrology Center, Mansoura University, Mansoura, Egypt.Bioengineering Department, University of Louisville, Louisville, KY, USA.Bioengineering Department, University of Louisville, Louisville, KY, USA.Bioengineering Department, University of Louisville, Louisville, KY, USA.Electrical, Computer and Biomedical Engineering Department, Abu Dhabi University, Abu Dhabi, United Arab Emirates.Department of Emergency Medicine, Royal Berkshire Hospital, Reading, UK.Bioengineering Department, University of Louisville, Louisville, KY, USA.Department of Urology, Mansoura Urology and Nephrology Center, Mansoura University, Mansoura, Egypt.Department of Urology, Mansoura Urology and Nephrology Center, Mansoura University, Mansoura, Egypt."Purpose: To create a computer-aided prediction (CAP) system to predict Wilms tumor (WT) responsiveness to preoperative chemotherapy (PC) using pre-therapy contrast-enhanced computed tomography (CECT). Materials and Methods: A single-center database was reviewed for children <18 years diagnosed with WT and received PC between 2001 and 2021. Patients were excluded if pre- and post-PC CECT were not retrievable. According to the Response Evaluation Criteria in Solid Tumors criteria, volumetric response was considered favorable if PC resulted in ≥30% tumor volume reduction. Histological response was considered favorable if post-nephrectomy specimens had ≥66% necrosis. Four steps were used to create the prediction model: tumor delineation; extraction of shape, texture and functionality-based features; integration of the extracted features and selection of the prediction model with the highest diagnostic performance. K-fold cross-validation allowed the presentation of all data in the training and testing phases. Results: A total of 63 tumors in 54 patients were used to train and test the prediction model. Patients were treated with 4–8 weeks of vincristine/actinomycin-D combination. Favorable volumetric and histologic responses were achieved in 46 tumors (73.0%) and 38 tumors (60.3%), respectively. Among machine learning classifiers, support vector machine had the best diagnostic performance with an accuracy, sensitivity, and specificity of 95.24%, 95.65%, and 94.12% for volumetric and 84.13%, 89.47%, 88% for histologic response prediction. Conclusions: Based on pre-therapy CECT, CAP systems can help identify WT that are less likely to respond to PC with excellent accuracy. These tumors can be offered upfront surgery, avoiding the cons of PC." https://www.icurology.org/pdf/10.4111/icu.20240135artificial intelligenceneoadjuvant therapysensitivity and specificitytomographyspiral computedwilms tumor |
| spellingShingle | Ahmed Nashat Ahmed Alksas Rasha T. Aboulelkheir Ahmed Elmahdy Sherry M. Khater Hossam M. Balaha Israa Sharaby Mohamed Shehata Mohammed Ghazal Salama Abd El-Wadoud Ayman El-Baz Ahmed Mosbah Ahmed Abdelhalim Artificial intelligence can help individualize Wilms tumor treatment by predicting tumor response to preoperative chemotherapy Investigative and Clinical Urology artificial intelligence neoadjuvant therapy sensitivity and specificity tomography spiral computed wilms tumor |
| title | Artificial intelligence can help individualize Wilms tumor treatment by predicting tumor response to preoperative chemotherapy |
| title_full | Artificial intelligence can help individualize Wilms tumor treatment by predicting tumor response to preoperative chemotherapy |
| title_fullStr | Artificial intelligence can help individualize Wilms tumor treatment by predicting tumor response to preoperative chemotherapy |
| title_full_unstemmed | Artificial intelligence can help individualize Wilms tumor treatment by predicting tumor response to preoperative chemotherapy |
| title_short | Artificial intelligence can help individualize Wilms tumor treatment by predicting tumor response to preoperative chemotherapy |
| title_sort | artificial intelligence can help individualize wilms tumor treatment by predicting tumor response to preoperative chemotherapy |
| topic | artificial intelligence neoadjuvant therapy sensitivity and specificity tomography spiral computed wilms tumor |
| url | https://www.icurology.org/pdf/10.4111/icu.20240135 |
| work_keys_str_mv | AT ahmednashat artificialintelligencecanhelpindividualizewilmstumortreatmentbypredictingtumorresponsetopreoperativechemotherapy AT ahmedalksas artificialintelligencecanhelpindividualizewilmstumortreatmentbypredictingtumorresponsetopreoperativechemotherapy AT rashataboulelkheir artificialintelligencecanhelpindividualizewilmstumortreatmentbypredictingtumorresponsetopreoperativechemotherapy AT ahmedelmahdy artificialintelligencecanhelpindividualizewilmstumortreatmentbypredictingtumorresponsetopreoperativechemotherapy AT sherrymkhater artificialintelligencecanhelpindividualizewilmstumortreatmentbypredictingtumorresponsetopreoperativechemotherapy AT hossammbalaha artificialintelligencecanhelpindividualizewilmstumortreatmentbypredictingtumorresponsetopreoperativechemotherapy AT israasharaby artificialintelligencecanhelpindividualizewilmstumortreatmentbypredictingtumorresponsetopreoperativechemotherapy AT mohamedshehata artificialintelligencecanhelpindividualizewilmstumortreatmentbypredictingtumorresponsetopreoperativechemotherapy AT mohammedghazal artificialintelligencecanhelpindividualizewilmstumortreatmentbypredictingtumorresponsetopreoperativechemotherapy AT salamaabdelwadoud artificialintelligencecanhelpindividualizewilmstumortreatmentbypredictingtumorresponsetopreoperativechemotherapy AT aymanelbaz artificialintelligencecanhelpindividualizewilmstumortreatmentbypredictingtumorresponsetopreoperativechemotherapy AT ahmedmosbah artificialintelligencecanhelpindividualizewilmstumortreatmentbypredictingtumorresponsetopreoperativechemotherapy AT ahmedabdelhalim artificialintelligencecanhelpindividualizewilmstumortreatmentbypredictingtumorresponsetopreoperativechemotherapy |