Joint Cancer Segmentation and PI-RADS Classification on Multiparametric MRI Using MiniSegCaps Network
MRI is the primary imaging approach for diagnosing prostate cancer. Prostate Imaging Reporting and Data System (PI-RADS) on multiparametric MRI (mpMRI) provides fundamental MRI interpretation guidelines but suffers from inter-reader variability. Deep learning networks show great promise in automatic...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/4/615 |
| _version_ | 1827757888673677312 |
|---|---|
| author | Wenting Jiang Yingying Lin Varut Vardhanabhuti Yanzhen Ming Peng Cao |
| author_facet | Wenting Jiang Yingying Lin Varut Vardhanabhuti Yanzhen Ming Peng Cao |
| author_sort | Wenting Jiang |
| collection | DOAJ |
| description | MRI is the primary imaging approach for diagnosing prostate cancer. Prostate Imaging Reporting and Data System (PI-RADS) on multiparametric MRI (mpMRI) provides fundamental MRI interpretation guidelines but suffers from inter-reader variability. Deep learning networks show great promise in automatic lesion segmentation and classification, which help to ease the burden on radiologists and reduce inter-reader variability. In this study, we proposed a novel multi-branch network, MiniSegCaps, for prostate cancer segmentation and PI-RADS classification on mpMRI. MiniSeg branch outputted the segmentation in conjunction with PI-RADS prediction, guided by the attention map from the CapsuleNet. CapsuleNet branch exploited the relative spatial information of prostate cancer to anatomical structures, such as the zonal location of the lesion, which also reduced the sample size requirement in training due to its equivariance properties. In addition, a gated recurrent unit (GRU) is adopted to exploit spatial knowledge across slices, improving through-plane consistency. Based on the clinical reports, we established a prostate mpMRI database from 462 patients paired with radiologically estimated annotations. MiniSegCaps was trained and evaluated with fivefold cross-validation. On 93 testing cases, our model achieved a 0.712 dice coefficient on lesion segmentation, 89.18% accuracy, and 92.52% sensitivity on PI-RADS classification (PI-RADS ≥ 4) in patient-level evaluation, significantly outperforming existing methods. In addition, a graphical user interface (GUI) integrated into the clinical workflow can automatically produce diagnosis reports based on the results from MiniSegCaps. |
| first_indexed | 2024-03-11T08:56:49Z |
| format | Article |
| id | doaj.art-41fdd118c60d400189b81d3a245a9eb0 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-11T08:56:49Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-41fdd118c60d400189b81d3a245a9eb02023-11-16T20:00:27ZengMDPI AGDiagnostics2075-44182023-02-0113461510.3390/diagnostics13040615Joint Cancer Segmentation and PI-RADS Classification on Multiparametric MRI Using MiniSegCaps NetworkWenting Jiang0Yingying Lin1Varut Vardhanabhuti2Yanzhen Ming3Peng Cao4Department of Diagnostic Radiology, University of Hong Kong, Hong Kong SAR, ChinaDepartment of Diagnostic Radiology, University of Hong Kong, Hong Kong SAR, ChinaDepartment of Diagnostic Radiology, University of Hong Kong, Hong Kong SAR, ChinaDepartment of Diagnostic Radiology, University of Hong Kong, Hong Kong SAR, ChinaDepartment of Diagnostic Radiology, University of Hong Kong, Hong Kong SAR, ChinaMRI is the primary imaging approach for diagnosing prostate cancer. Prostate Imaging Reporting and Data System (PI-RADS) on multiparametric MRI (mpMRI) provides fundamental MRI interpretation guidelines but suffers from inter-reader variability. Deep learning networks show great promise in automatic lesion segmentation and classification, which help to ease the burden on radiologists and reduce inter-reader variability. In this study, we proposed a novel multi-branch network, MiniSegCaps, for prostate cancer segmentation and PI-RADS classification on mpMRI. MiniSeg branch outputted the segmentation in conjunction with PI-RADS prediction, guided by the attention map from the CapsuleNet. CapsuleNet branch exploited the relative spatial information of prostate cancer to anatomical structures, such as the zonal location of the lesion, which also reduced the sample size requirement in training due to its equivariance properties. In addition, a gated recurrent unit (GRU) is adopted to exploit spatial knowledge across slices, improving through-plane consistency. Based on the clinical reports, we established a prostate mpMRI database from 462 patients paired with radiologically estimated annotations. MiniSegCaps was trained and evaluated with fivefold cross-validation. On 93 testing cases, our model achieved a 0.712 dice coefficient on lesion segmentation, 89.18% accuracy, and 92.52% sensitivity on PI-RADS classification (PI-RADS ≥ 4) in patient-level evaluation, significantly outperforming existing methods. In addition, a graphical user interface (GUI) integrated into the clinical workflow can automatically produce diagnosis reports based on the results from MiniSegCaps.https://www.mdpi.com/2075-4418/13/4/615prostate cancerPI-RADS classificationmulti-parametric MRICapsuleNetconvolutional neural network |
| spellingShingle | Wenting Jiang Yingying Lin Varut Vardhanabhuti Yanzhen Ming Peng Cao Joint Cancer Segmentation and PI-RADS Classification on Multiparametric MRI Using MiniSegCaps Network Diagnostics prostate cancer PI-RADS classification multi-parametric MRI CapsuleNet convolutional neural network |
| title | Joint Cancer Segmentation and PI-RADS Classification on Multiparametric MRI Using MiniSegCaps Network |
| title_full | Joint Cancer Segmentation and PI-RADS Classification on Multiparametric MRI Using MiniSegCaps Network |
| title_fullStr | Joint Cancer Segmentation and PI-RADS Classification on Multiparametric MRI Using MiniSegCaps Network |
| title_full_unstemmed | Joint Cancer Segmentation and PI-RADS Classification on Multiparametric MRI Using MiniSegCaps Network |
| title_short | Joint Cancer Segmentation and PI-RADS Classification on Multiparametric MRI Using MiniSegCaps Network |
| title_sort | joint cancer segmentation and pi rads classification on multiparametric mri using minisegcaps network |
| topic | prostate cancer PI-RADS classification multi-parametric MRI CapsuleNet convolutional neural network |
| url | https://www.mdpi.com/2075-4418/13/4/615 |
| work_keys_str_mv | AT wentingjiang jointcancersegmentationandpiradsclassificationonmultiparametricmriusingminisegcapsnetwork AT yingyinglin jointcancersegmentationandpiradsclassificationonmultiparametricmriusingminisegcapsnetwork AT varutvardhanabhuti jointcancersegmentationandpiradsclassificationonmultiparametricmriusingminisegcapsnetwork AT yanzhenming jointcancersegmentationandpiradsclassificationonmultiparametricmriusingminisegcapsnetwork AT pengcao jointcancersegmentationandpiradsclassificationonmultiparametricmriusingminisegcapsnetwork |