Deep Learning with Quantitative Features of Magnetic Resonance Images to Predict Biochemical Recurrence of Radical Prostatectomy: A Multi-Center Study
Biochemical recurrence (BCR) occurs in up to 27% of patients after radical prostatectomy (RP) and often compromises oncologic survival. To determine whether imaging signatures on clinical prostate magnetic resonance imaging (MRI) could noninvasively characterize biochemical recurrence and optimize t...
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Cancers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-6694/13/12/3098 |
| _version_ | 1797529363787284480 |
|---|---|
| author | Ye Yan Lizhi Shao Zhenyu Liu Wei He Guanyu Yang Jiangang Liu Haizhui Xia Yuting Zhang Huiying Chen Cheng Liu Min Lu Lulin Ma Kai Sun Xuezhi Zhou Xiongjun Ye Lei Wang Jie Tian Jian Lu |
| author_facet | Ye Yan Lizhi Shao Zhenyu Liu Wei He Guanyu Yang Jiangang Liu Haizhui Xia Yuting Zhang Huiying Chen Cheng Liu Min Lu Lulin Ma Kai Sun Xuezhi Zhou Xiongjun Ye Lei Wang Jie Tian Jian Lu |
| author_sort | Ye Yan |
| collection | DOAJ |
| description | Biochemical recurrence (BCR) occurs in up to 27% of patients after radical prostatectomy (RP) and often compromises oncologic survival. To determine whether imaging signatures on clinical prostate magnetic resonance imaging (MRI) could noninvasively characterize biochemical recurrence and optimize treatment. We retrospectively enrolled 485 patients underwent RP from 2010 to 2017 in three institutions. Quantitative and interpretable features were extracted from T2 delineated tumors. Deep learning-based survival analysis was then applied to develop the deep-radiomic signature (DRS-BCR). The model’s performance was further evaluated, in comparison with conventional clinical models. The model achieved C-index of 0.802 in both primary and validating cohorts, outweighed the CAPRA-S score (0.677), NCCN model (0.586) and Gleason grade group systems (0.583). With application analysis, DRS-BCR model can significantly reduce false-positive predictions, so that nearly one-third of patients could benefit from the model by avoiding overtreatments. The deep learning-based survival analysis assisted quantitative image features from MRI performed well in prediction for BCR and has significant potential in optimizing systemic neoadjuvant or adjuvant therapies for prostate cancer patients. |
| first_indexed | 2024-03-10T10:12:46Z |
| format | Article |
| id | doaj.art-8c9e218a8437451faa43e21032de2383 |
| institution | Directory Open Access Journal |
| issn | 2072-6694 |
| language | English |
| last_indexed | 2024-03-10T10:12:46Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cancers |
| spelling | doaj.art-8c9e218a8437451faa43e21032de23832023-11-22T01:04:59ZengMDPI AGCancers2072-66942021-06-011312309810.3390/cancers13123098Deep Learning with Quantitative Features of Magnetic Resonance Images to Predict Biochemical Recurrence of Radical Prostatectomy: A Multi-Center StudyYe Yan0Lizhi Shao1Zhenyu Liu2Wei He3Guanyu Yang4Jiangang Liu5Haizhui Xia6Yuting Zhang7Huiying Chen8Cheng Liu9Min Lu10Lulin Ma11Kai Sun12Xuezhi Zhou13Xiongjun Ye14Lei Wang15Jie Tian16Jian Lu17Department of Urology, Peking University Third Hospital, Peking University, Beijing 100191, ChinaCAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, the State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaCAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, the State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaDepartment of Radiology, Peking University Third Hospital, Peking University, Beijing 100191, ChinaSchool of Computer Science and Engineering, Southeast University, Nanjing 210096, ChinaBeijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Engineering Medicine, Beihang University, Beijing 100191, ChinaDepartment of Urology, Peking University Third Hospital, Peking University, Beijing 100191, ChinaDepartment of Urology, Peking University Third Hospital, Peking University, Beijing 100191, ChinaDepartment of Radiology, Peking University Third Hospital, Peking University, Beijing 100191, ChinaDepartment of Urology, Peking University Third Hospital, Peking University, Beijing 100191, ChinaDepartment of Pathology, Peking University Third Hospital, Peking University, Beijing 100191, ChinaDepartment of Urology, Peking University Third Hospital, Peking University, Beijing 100191, ChinaCAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, the State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaCAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, the State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaUrology and Lithotripsy Center, Peking University People’s Hospital, Peking University, Beijing 100044, ChinaDepartment of Urology, Beijing Friendship Hospital, Capital Medical University, Beijing 100050, ChinaCAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, the State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaDepartment of Urology, Peking University Third Hospital, Peking University, Beijing 100191, ChinaBiochemical recurrence (BCR) occurs in up to 27% of patients after radical prostatectomy (RP) and often compromises oncologic survival. To determine whether imaging signatures on clinical prostate magnetic resonance imaging (MRI) could noninvasively characterize biochemical recurrence and optimize treatment. We retrospectively enrolled 485 patients underwent RP from 2010 to 2017 in three institutions. Quantitative and interpretable features were extracted from T2 delineated tumors. Deep learning-based survival analysis was then applied to develop the deep-radiomic signature (DRS-BCR). The model’s performance was further evaluated, in comparison with conventional clinical models. The model achieved C-index of 0.802 in both primary and validating cohorts, outweighed the CAPRA-S score (0.677), NCCN model (0.586) and Gleason grade group systems (0.583). With application analysis, DRS-BCR model can significantly reduce false-positive predictions, so that nearly one-third of patients could benefit from the model by avoiding overtreatments. The deep learning-based survival analysis assisted quantitative image features from MRI performed well in prediction for BCR and has significant potential in optimizing systemic neoadjuvant or adjuvant therapies for prostate cancer patients.https://www.mdpi.com/2072-6694/13/12/3098prostate cancerbiochemical recurrencesurvival predictiondeep learningMRI |
| spellingShingle | Ye Yan Lizhi Shao Zhenyu Liu Wei He Guanyu Yang Jiangang Liu Haizhui Xia Yuting Zhang Huiying Chen Cheng Liu Min Lu Lulin Ma Kai Sun Xuezhi Zhou Xiongjun Ye Lei Wang Jie Tian Jian Lu Deep Learning with Quantitative Features of Magnetic Resonance Images to Predict Biochemical Recurrence of Radical Prostatectomy: A Multi-Center Study Cancers prostate cancer biochemical recurrence survival prediction deep learning MRI |
| title | Deep Learning with Quantitative Features of Magnetic Resonance Images to Predict Biochemical Recurrence of Radical Prostatectomy: A Multi-Center Study |
| title_full | Deep Learning with Quantitative Features of Magnetic Resonance Images to Predict Biochemical Recurrence of Radical Prostatectomy: A Multi-Center Study |
| title_fullStr | Deep Learning with Quantitative Features of Magnetic Resonance Images to Predict Biochemical Recurrence of Radical Prostatectomy: A Multi-Center Study |
| title_full_unstemmed | Deep Learning with Quantitative Features of Magnetic Resonance Images to Predict Biochemical Recurrence of Radical Prostatectomy: A Multi-Center Study |
| title_short | Deep Learning with Quantitative Features of Magnetic Resonance Images to Predict Biochemical Recurrence of Radical Prostatectomy: A Multi-Center Study |
| title_sort | deep learning with quantitative features of magnetic resonance images to predict biochemical recurrence of radical prostatectomy a multi center study |
| topic | prostate cancer biochemical recurrence survival prediction deep learning MRI |
| url | https://www.mdpi.com/2072-6694/13/12/3098 |
| work_keys_str_mv | AT yeyan deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy AT lizhishao deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy AT zhenyuliu deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy AT weihe deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy AT guanyuyang deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy AT jiangangliu deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy AT haizhuixia deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy AT yutingzhang deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy AT huiyingchen deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy AT chengliu deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy AT minlu deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy AT lulinma deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy AT kaisun deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy AT xuezhizhou deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy AT xiongjunye deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy AT leiwang deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy AT jietian deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy AT jianlu deeplearningwithquantitativefeaturesofmagneticresonanceimagestopredictbiochemicalrecurrenceofradicalprostatectomyamulticenterstudy |