Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Apr 19:13:1095353.
doi: 10.3389/fonc.2023.1095353. eCollection 2023.

A novel approach for automatic segmentation of prostate and its lesion regions on magnetic resonance imaging

Huipeng Ren  1   2 , Chengjuan Ren  3 , Ziyu Guo  4 , Guangnan Zhang  5 , Xiaohui Luo  6 , Zhuanqin Ren  2 , Hongzhe Tian  2 , Wei Li  2 , Hao Yuan  5 , Lele Hao  5 , Jiacheng Wang  5 , Ming Zhang  1
Affiliations

A novel approach for automatic segmentation of prostate and its lesion regions on magnetic resonance imaging

Huipeng Ren et al. Front Oncol. .

Abstract

Objective: To develop an accurate and automatic segmentation model based on convolution neural network to segment the prostate and its lesion regions.

Methods: Of all 180 subjects, 122 healthy individuals and 58 patients with prostate cancer were included. For each subject, all slices of the prostate were comprised in the DWIs. A novel DCNN is proposed to automatically segment the prostate and its lesion regions. This model is inspired by the U-Net model with the encoding-decoding path as the backbone, importing dense block, attention mechanism techniques, and group norm-Atrous Spatial Pyramidal Pooling. Data augmentation was used to avoid overfitting in training. In the experimental phase, the data set was randomly divided into a training (70%), testing set (30%). four-fold cross-validation methods were used to obtain results for each metric.

Results: The proposed model achieved in terms of Iou, Dice score, accuracy, sensitivity, 95% Hausdorff Distance, 86.82%,93.90%, 94.11%, 93.8%,7.84 for the prostate, 79.2%, 89.51%, 88.43%,89.31%,8.39 for lesion region in segmentation. Compared to the state-of-the-art models, FCN, U-Net, U-Net++, and ResU-Net, the segmentation model achieved more promising results.

Conclusion: The proposed model yielded excellent performance in accurate and automatic segmentation of the prostate and lesion regions, revealing that the novel deep convolutional neural network could be used in clinical disease treatment and diagnosis.

Keywords: U-Net; attention mechanism; convolution neural network; dense block; prostate cancer.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Structure of the proposed method. Yellow for CBMA module, dark blue for dense unit, with ASSP added to the end of the model.
Figure 2
Figure 2
Schematic representation of the spatial pyramid set (ASPP) for dilated convolution and group norm (GN).
Figure 3
Figure 3
Loss vs epoch of prostate area on training data.
Figure 4
Figure 4
Loss vs epoch of prostate lesion area on training data.
Figure 5
Figure 5
Iou vs epoch of the prostate area on testing data.
Figure 6
Figure 6
Iou vs epoch of prostate lesion area on testing data.
Figure 7
Figure 7
Segmentation performance of the proposed method in 4 different patients (row), and columns from left to right show input image, ground truth, and segmentation results of the proposed model. In the experiments, non-target regions were masked black to provide greater clarity. The lesion region is marked in yellow, while the prostate region in rose.
Figure 8
Figure 8
Visualization of the final layer of our model for prostate lesion region.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Aldoj N, Lukas S, Dewey M, Penzkofer T. Semi-automatic classification of prostate cancer on multi-parametric MR imaging using a multi-channel 3D convolutional neural network. Eur Radiol (2020) 30(2):1243–53. doi: 10.1007/s00330-019-06417-z - DOI - PubMed
    1. Ferlay J, Colombet M, Soerjomataram I, Parkin DM, Piñeros M, Znaor A, et al. . Cancer statistics for the year 2020: An overview. Int J Cancer (2021) 149(4):778–89. doi: 10.1002/ijc.33588 - DOI - PubMed
    1. Zettinig O, Shah A, Hennersperger C, Eiber M, Kroll C, Kübler H, et al. . Multimodal image-guided prostate fusion biopsy based on automatic deformable registration. Int J Comput Assisted Radiol Surg (2015) 10(12):1997–2007. doi: 10.1007/s11548-015-1233-y - DOI - PubMed
    1. Ozer S, Langer DL, Liu X, Haider MA, van der Kwast TH, Evans AJ, et al. . Supervised and unsupervised methods for prostate cancer segmentation with multispectral MRI. Med Phys (2010) 37(4):1873–83. doi: 10.1118/1.3359459 - DOI - PubMed
    1. Puech P, Betrouni N, Makni N, Dewalle AS, Villers A, Lemaitre L. Computer-assisted diagnosis of prostate cancer using DCE-MRI data: design, implementation and preliminary results. Int J Comput Assisted Radiol Surg (2009) 4(1):1–10. doi: 10.1007/s11548-008-0261-2 - DOI - PubMed

LinkOut - more resources