Detecting MRI-Invisible Prostate Cancers Using a Weakly Supervised Deep Learning Model
Background. MRI is an important tool for accurate detection and targeted biopsy of prostate lesions. However, the imaging appearances of some prostate cancers are similar to those of the surrounding normal tissue on MRI, which are referred to as MRI-invisible prostate cancers (MIPCas). The detection...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | International Journal of Biomedical Imaging |
| Online Access: | http://dx.doi.org/10.1155/2024/2741986 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841524318078500864 |
|---|---|
| author | Yao Zheng Jingliang Zhang Dong Huang Xiaoshuo Hao Weijun Qin Yang Liu |
| author_facet | Yao Zheng Jingliang Zhang Dong Huang Xiaoshuo Hao Weijun Qin Yang Liu |
| author_sort | Yao Zheng |
| collection | DOAJ |
| description | Background. MRI is an important tool for accurate detection and targeted biopsy of prostate lesions. However, the imaging appearances of some prostate cancers are similar to those of the surrounding normal tissue on MRI, which are referred to as MRI-invisible prostate cancers (MIPCas). The detection of MIPCas remains challenging and requires extensive systematic biopsy for identification. In this study, we developed a weakly supervised UNet (WSUNet) to detect MIPCas. Methods. The study included 777 patients (training set: 600; testing set: 177), all of them underwent comprehensive prostate biopsies using an MRI-ultrasound fusion system. MIPCas were identified in MRI based on the Gleason grade (≥7) from known systematic biopsy results. Results. The WSUNet model underwent validation through systematic biopsy in the testing set with an AUC of 0.764 (95% CI: 0.728-0.798). Furthermore, WSUNet exhibited a statistically significant precision improvement of 91.3% (p<0.01) over conventional systematic biopsy methods in the testing set. This improvement resulted in a substantial 47.6% (p<0.01) decrease in unnecessary biopsy needles, while maintaining the same number of positively identified cores as in the original systematic biopsy. Conclusions. In conclusion, the proposed WSUNet could effectively detect MIPCas, thereby reducing unnecessary biopsies. |
| format | Article |
| id | doaj-art-fe62c2fb310841a98a7cae94b7c2cd98 |
| institution | Kabale University |
| issn | 1687-4196 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Biomedical Imaging |
| spelling | doaj-art-fe62c2fb310841a98a7cae94b7c2cd982025-02-03T07:23:25ZengWileyInternational Journal of Biomedical Imaging1687-41962024-01-01202410.1155/2024/2741986Detecting MRI-Invisible Prostate Cancers Using a Weakly Supervised Deep Learning ModelYao Zheng0Jingliang Zhang1Dong Huang2Xiaoshuo Hao3Weijun Qin4Yang Liu5School of Biomedical EngineeringDepartment of UrologySchool of Biomedical EngineeringSchool of Biomedical EngineeringDepartment of UrologySchool of Biomedical EngineeringBackground. MRI is an important tool for accurate detection and targeted biopsy of prostate lesions. However, the imaging appearances of some prostate cancers are similar to those of the surrounding normal tissue on MRI, which are referred to as MRI-invisible prostate cancers (MIPCas). The detection of MIPCas remains challenging and requires extensive systematic biopsy for identification. In this study, we developed a weakly supervised UNet (WSUNet) to detect MIPCas. Methods. The study included 777 patients (training set: 600; testing set: 177), all of them underwent comprehensive prostate biopsies using an MRI-ultrasound fusion system. MIPCas were identified in MRI based on the Gleason grade (≥7) from known systematic biopsy results. Results. The WSUNet model underwent validation through systematic biopsy in the testing set with an AUC of 0.764 (95% CI: 0.728-0.798). Furthermore, WSUNet exhibited a statistically significant precision improvement of 91.3% (p<0.01) over conventional systematic biopsy methods in the testing set. This improvement resulted in a substantial 47.6% (p<0.01) decrease in unnecessary biopsy needles, while maintaining the same number of positively identified cores as in the original systematic biopsy. Conclusions. In conclusion, the proposed WSUNet could effectively detect MIPCas, thereby reducing unnecessary biopsies.http://dx.doi.org/10.1155/2024/2741986 |
| spellingShingle | Yao Zheng Jingliang Zhang Dong Huang Xiaoshuo Hao Weijun Qin Yang Liu Detecting MRI-Invisible Prostate Cancers Using a Weakly Supervised Deep Learning Model International Journal of Biomedical Imaging |
| title | Detecting MRI-Invisible Prostate Cancers Using a Weakly Supervised Deep Learning Model |
| title_full | Detecting MRI-Invisible Prostate Cancers Using a Weakly Supervised Deep Learning Model |
| title_fullStr | Detecting MRI-Invisible Prostate Cancers Using a Weakly Supervised Deep Learning Model |
| title_full_unstemmed | Detecting MRI-Invisible Prostate Cancers Using a Weakly Supervised Deep Learning Model |
| title_short | Detecting MRI-Invisible Prostate Cancers Using a Weakly Supervised Deep Learning Model |
| title_sort | detecting mri invisible prostate cancers using a weakly supervised deep learning model |
| url | http://dx.doi.org/10.1155/2024/2741986 |
| work_keys_str_mv | AT yaozheng detectingmriinvisibleprostatecancersusingaweaklysuperviseddeeplearningmodel AT jingliangzhang detectingmriinvisibleprostatecancersusingaweaklysuperviseddeeplearningmodel AT donghuang detectingmriinvisibleprostatecancersusingaweaklysuperviseddeeplearningmodel AT xiaoshuohao detectingmriinvisibleprostatecancersusingaweaklysuperviseddeeplearningmodel AT weijunqin detectingmriinvisibleprostatecancersusingaweaklysuperviseddeeplearningmodel AT yangliu detectingmriinvisibleprostatecancersusingaweaklysuperviseddeeplearningmodel |