Evaluating the feasibility of AI-predicted bpMRI image features for predicting prostate cancer aggressiveness: a multi-center study
Abstract Objective To evaluate the feasibility of utilizing artificial intelligence (AI)-predicted biparametric MRI (bpMRI) image features for predicting the aggressiveness of prostate cancer (PCa). Materials and methods A total of 878 PCa patients from 4 hospitals were retrospectively collected, al...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | Insights into Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13244-024-01865-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594703990652928 |
|---|---|
| author | Kexin Wang Ning Luo Zhaonan Sun Xiangpeng Zhao Lilan She Zhangli Xing Yuntian Chen Chunlei He Pengsheng Wu Xiangpeng Wang ZiXuan Kong |
| author_facet | Kexin Wang Ning Luo Zhaonan Sun Xiangpeng Zhao Lilan She Zhangli Xing Yuntian Chen Chunlei He Pengsheng Wu Xiangpeng Wang ZiXuan Kong |
| author_sort | Kexin Wang |
| collection | DOAJ |
| description | Abstract Objective To evaluate the feasibility of utilizing artificial intelligence (AI)-predicted biparametric MRI (bpMRI) image features for predicting the aggressiveness of prostate cancer (PCa). Materials and methods A total of 878 PCa patients from 4 hospitals were retrospectively collected, all of whom had pathological results after radical prostatectomy (RP). A pre-trained AI algorithm was used to select suspected PCa lesions and extract lesion features for model development. The study evaluated five prediction methods, including (1) A clinical-imaging model of clinical features and image features of suspected PCa lesions selected by AI algorithm, (2) the PIRADS category, (3) a conventional radiomics model, (4) a deep-learning bases radiomics model, and (5) biopsy pathology. Results In the externally validated dataset, the deep learning-based radiomics model showed the highest area under the curve (AUC 0.700 to 0.791). It exceeded the clinical-imaging model (AUC 0.597 to 0.718), conventional radiomic model (AUC 0.566 to 0.632), PIRADS score (AUC 0.554 to 0.613), and biopsy pathology (AUC 0.537 to 0.578). The AUC predicted by the model did not show a statistically significant difference among the three externally verified hospitals (p > 0.05). Conclusion Deep-learning radiomics models utilizing AI-extracted image features from bpMRI images can potentially be used to predict PCa aggressiveness, demonstrating a generalized ability for external validation. Critical relevance statement Predicting the aggressiveness of prostate cancer (PCa) is important for formulating the best treatment plan for patients. The radiomic model based on deep learning is expected to provide an objective and non-invasive method for evaluating the aggressiveness of PCa. Key Points Predicting the aggressiveness of PCa is important for patients to obtain the best treatment options. The deep learning-based radiomics model can predict the aggressiveness of PCa with high accuracy. The model has good universality when tested on multiple external datasets. Graphical Abstract |
| format | Article |
| id | doaj-art-88511c844acf486899623a5e596bcfb0 |
| institution | Kabale University |
| issn | 1869-4101 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Insights into Imaging |
| spelling | doaj-art-88511c844acf486899623a5e596bcfb02025-01-19T12:26:12ZengSpringerOpenInsights into Imaging1869-41012025-01-0116111810.1186/s13244-024-01865-8Evaluating the feasibility of AI-predicted bpMRI image features for predicting prostate cancer aggressiveness: a multi-center studyKexin Wang0Ning Luo1Zhaonan Sun2Xiangpeng Zhao3Lilan She4Zhangli Xing5Yuntian Chen6Chunlei He7Pengsheng Wu8Xiangpeng Wang9ZiXuan Kong10School of Basic Medical Sciences, Capital Medical UniversityDepartment of Radiology, the Second Affiliated Hospital of Dalian Medical UniversityDepartment of Radiology, Peking University First HospitalDepartment of Radiology, the Second Affiliated Hospital of Dalian Medical UniversityDepartment of Radiology, Fujian Medical University Union HospitalDepartment of Radiology, Fujian Medical University Union HospitalDepartment of Radiology, West China Hospital, Sichuan UniversityDepartment of Radiology, West China Hospital, Sichuan UniversityBeijing Smart Tree Medical Technology Co. Ltd.Beijing Smart Tree Medical Technology Co. Ltd.Department of Radiology, the Second Affiliated Hospital of Dalian Medical UniversityAbstract Objective To evaluate the feasibility of utilizing artificial intelligence (AI)-predicted biparametric MRI (bpMRI) image features for predicting the aggressiveness of prostate cancer (PCa). Materials and methods A total of 878 PCa patients from 4 hospitals were retrospectively collected, all of whom had pathological results after radical prostatectomy (RP). A pre-trained AI algorithm was used to select suspected PCa lesions and extract lesion features for model development. The study evaluated five prediction methods, including (1) A clinical-imaging model of clinical features and image features of suspected PCa lesions selected by AI algorithm, (2) the PIRADS category, (3) a conventional radiomics model, (4) a deep-learning bases radiomics model, and (5) biopsy pathology. Results In the externally validated dataset, the deep learning-based radiomics model showed the highest area under the curve (AUC 0.700 to 0.791). It exceeded the clinical-imaging model (AUC 0.597 to 0.718), conventional radiomic model (AUC 0.566 to 0.632), PIRADS score (AUC 0.554 to 0.613), and biopsy pathology (AUC 0.537 to 0.578). The AUC predicted by the model did not show a statistically significant difference among the three externally verified hospitals (p > 0.05). Conclusion Deep-learning radiomics models utilizing AI-extracted image features from bpMRI images can potentially be used to predict PCa aggressiveness, demonstrating a generalized ability for external validation. Critical relevance statement Predicting the aggressiveness of prostate cancer (PCa) is important for formulating the best treatment plan for patients. The radiomic model based on deep learning is expected to provide an objective and non-invasive method for evaluating the aggressiveness of PCa. Key Points Predicting the aggressiveness of PCa is important for patients to obtain the best treatment options. The deep learning-based radiomics model can predict the aggressiveness of PCa with high accuracy. The model has good universality when tested on multiple external datasets. Graphical Abstracthttps://doi.org/10.1186/s13244-024-01865-8Gleason scoreProstate cancerMultiparametric magnetic resonance imagingDeep learningRadiomics |
| spellingShingle | Kexin Wang Ning Luo Zhaonan Sun Xiangpeng Zhao Lilan She Zhangli Xing Yuntian Chen Chunlei He Pengsheng Wu Xiangpeng Wang ZiXuan Kong Evaluating the feasibility of AI-predicted bpMRI image features for predicting prostate cancer aggressiveness: a multi-center study Insights into Imaging Gleason score Prostate cancer Multiparametric magnetic resonance imaging Deep learning Radiomics |
| title | Evaluating the feasibility of AI-predicted bpMRI image features for predicting prostate cancer aggressiveness: a multi-center study |
| title_full | Evaluating the feasibility of AI-predicted bpMRI image features for predicting prostate cancer aggressiveness: a multi-center study |
| title_fullStr | Evaluating the feasibility of AI-predicted bpMRI image features for predicting prostate cancer aggressiveness: a multi-center study |
| title_full_unstemmed | Evaluating the feasibility of AI-predicted bpMRI image features for predicting prostate cancer aggressiveness: a multi-center study |
| title_short | Evaluating the feasibility of AI-predicted bpMRI image features for predicting prostate cancer aggressiveness: a multi-center study |
| title_sort | evaluating the feasibility of ai predicted bpmri image features for predicting prostate cancer aggressiveness a multi center study |
| topic | Gleason score Prostate cancer Multiparametric magnetic resonance imaging Deep learning Radiomics |
| url | https://doi.org/10.1186/s13244-024-01865-8 |
| work_keys_str_mv | AT kexinwang evaluatingthefeasibilityofaipredictedbpmriimagefeaturesforpredictingprostatecanceraggressivenessamulticenterstudy AT ningluo evaluatingthefeasibilityofaipredictedbpmriimagefeaturesforpredictingprostatecanceraggressivenessamulticenterstudy AT zhaonansun evaluatingthefeasibilityofaipredictedbpmriimagefeaturesforpredictingprostatecanceraggressivenessamulticenterstudy AT xiangpengzhao evaluatingthefeasibilityofaipredictedbpmriimagefeaturesforpredictingprostatecanceraggressivenessamulticenterstudy AT lilanshe evaluatingthefeasibilityofaipredictedbpmriimagefeaturesforpredictingprostatecanceraggressivenessamulticenterstudy AT zhanglixing evaluatingthefeasibilityofaipredictedbpmriimagefeaturesforpredictingprostatecanceraggressivenessamulticenterstudy AT yuntianchen evaluatingthefeasibilityofaipredictedbpmriimagefeaturesforpredictingprostatecanceraggressivenessamulticenterstudy AT chunleihe evaluatingthefeasibilityofaipredictedbpmriimagefeaturesforpredictingprostatecanceraggressivenessamulticenterstudy AT pengshengwu evaluatingthefeasibilityofaipredictedbpmriimagefeaturesforpredictingprostatecanceraggressivenessamulticenterstudy AT xiangpengwang evaluatingthefeasibilityofaipredictedbpmriimagefeaturesforpredictingprostatecanceraggressivenessamulticenterstudy AT zixuankong evaluatingthefeasibilityofaipredictedbpmriimagefeaturesforpredictingprostatecanceraggressivenessamulticenterstudy |