Segmentation of prostate and prostate zones using deep learning

Zavala-Romero, Olmo; Breto, Adrian L.; Xu, Isaac; Chang, Yeon S.; Gautney, Nicole; Pra, Alan Dal; Abramowitz, Matthew C.; Pollack, Alan; Stoyanova, Radka

doi:10.1007/s00066-020-01607-x

Cited by 42 publications

(44 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Advanced software providing the registration with minimal deformation of image scans and landmarks should be analysed in further studies. Despite some diagnostic limitations, the mpMRI was recommended in several guidelines as staging method as well as method for targeted biopsy in the diagnostic of primary PCa [26][27][28][39][40][41][42][43][44]. In agreement with other studies, both manual and automatic contouring using PSMA-PET techniques showed more accuracy compared to mpMRI for localizing IPLs when correlated with reference biopsy results [4][5][6][7][8].…”

Section: Discussionsupporting

confidence: 60%

Diagnostic efficiency of hybrid imaging using PSMA ligands, PET/CT, PET/MRI and MRI in identifying malignant prostate lesions

et al. 2021

View full text Add to dashboard Cite

Objective The objective of this study was to assess the accuracy of 68Ga-PSMA-11 PET/MRI, 18F-PSMA-1007 PET/CT, 68Ga-PSMA-11 PET/CT, and multiparametric (mp)MRI for the delineating of dominant intraprostatic lesions (IPL). Materials and methods 35 patients with organ-confined prostate cancer who were assigned to definitive radiotherapy (RT) were divided into three groups based on imaging techniques: 68Ga-PSMA-PET/MRI (n = 9), 18F-PSMA-PET/CT (n = 16) and 68Ga-PSMA-PET/CT (n = 10). All patients without PSMA-PET/MRI received an additional mpMRI. PSMA-PET-based automatic isocontours and manual contours of the dominant IPLs were generated for each modality. The biopsy results were then used to validate whether any of the prostate biopsies were positive in the marked lesion using Dice similarity coefficient (DSC), Youden index (YI), sensitivity and specificity. Factors that can predict the accuracy of IPLs contouring were analysed. Results Diagnostic performance was significantly superior both for manual and automatic IPLs contouring using 68Ga-PSMA-PET/MRI (DSC/YI SUV70%—0.62/0.51), 18F-PSMA-PET/CT (DSC/YI SUV70%—0.67/0.53) or 68Ga-PSMA-PET/CT (DSC/YI SUV70%—0.63/0.51) compared to mpMRI (DSC/YI—0.47/0.41; p < 0.001). The accuracy for delineating IPLs was not improved by combination of PET/CT and mpMRI images compared to PET/CT alone. Significantly superior diagnostic accuracy was found for large prostate lesions (at least 15% from the prostate volume) and higher Gleason score (at least 7b) comparing to smaller lesions with lower GS. Conclusion IPL localization was significantly improved when using PSMA-imaging procedures compared to mpMRI. No significant difference for delineating IPLs was found between hybrid method PSMA-PET/MRI and PSMA-PET/CT. PSMA-based imaging technique should be considered for the diagnostics of IPLs and focal treatment modality.

show abstract

Section: Discussionsupporting

confidence: 60%

Diagnostic efficiency of hybrid imaging using PSMA ligands, PET/CT, PET/MRI and MRI in identifying malignant prostate lesions

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Future studies should also address the implementation of RF-based detection of PCa lesions in clinical routine workflows. First, an accurate segmentation of the visible tumor mass in PSMA-PET and mpMRI and the prostatic gland in CT or mpMRI should be performed manually or by using automatic tools (for example deep learning approaches [ 40 , 41 ]). Second, RF should be extracted by implementing already developed software tools for RF calculation [ 42 ].…”

Section: Discussionmentioning

confidence: 99%

Uncovering the invisible—prevalence, characteristics, and radiomics feature–based detection of visually undetectable intraprostatic tumor lesions in 68GaPSMA-11 PET images of patients with primary prostate cancer

Zamboglou

Bettermann

Gratzke

et al. 2020

Eur J Nucl Med Mol Imaging

View full text Add to dashboard Cite

Introduction Primary prostate cancer (PCa) can be visualized on prostate-specific membrane antigen positron emission tomography (PSMA-PET) with high accuracy. However, intraprostatic lesions may be missed by visual PSMA-PET interpretation. In this work, we quantified and characterized the intraprostatic lesions which have been missed by visual PSMA-PET image interpretation. In addition, we investigated whether PSMA-PET-derived radiomics features (RFs) could detect these lesions. Methodology This study consists of two cohorts of primary PCa patients: a prospective training cohort (n = 20) and an external validation cohort (n = 52). All patients underwent 68Ga-PSMA-11 PET/CT and histology sections were obtained after surgery. PCa lesions missed by visual PET image interpretation were counted and their International Society of Urological Pathology score (ISUP) was obtained. Finally, 154 RFs were derived from the PET images and the discriminative power to differentiate between prostates with or without visually undetectable lesions was assessed and areas under the receiver-operating curve (ROC-AUC) as well as sensitivities/specificities were calculated. Results In the training cohort, visual PET image interpretation missed 134 tumor lesions in 60% (12/20) of the patients, and of these patients, 75% had clinically significant (ISUP > 1) PCa. The median diameter of the missed lesions was 2.2 mm (range: 1–6). Standard clinical parameters like the NCCN risk group were equally distributed between patients with and without visually missed lesions (p < 0.05). Two RFs (local binary pattern (LBP) size-zone non-uniformality normalized and LBP small-area emphasis) were found to perform excellently in visually unknown PCa detection (Mann-Whitney U: p < 0.01, ROC-AUC: ≥ 0.93). In the validation cohort, PCa was missed in 50% (26/52) of the patients and 77% of these patients possessed clinically significant PCa. The sensitivities of both RFs in the validation cohort were ≥ 0.8. Conclusion Visual PSMA-PET image interpretation may miss small but clinically significant PCa in a relevant number of patients and RFs can be implemented to uncover them. This could be used for guiding personalized treatments.

show abstract

“…Most reported DL networks were monomodal, with T2w images as input and yielded DSC ranging from 0.73 to 0.93 ( Table 5 ). 3D Multistream UNet uses three T2w images acquired in the axial, coronal, and sagittal planes to segment the PZ and CG [ 24 ]. The network is relatively similar to our multimodal network.…”

Section: Discussionmentioning

confidence: 99%

Evaluation of Multimodal Algorithms for the Segmentation of Multiparametric MRI Prostate Images

Nai

Teo

Tan³

et al. 2020

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Prostate segmentation in multiparametric magnetic resonance imaging (mpMRI) can help to support prostate cancer diagnosis and therapy treatment. However, manual segmentation of the prostate is subjective and time-consuming. Many deep learning monomodal networks have been developed for automatic whole prostate segmentation from T2-weighted MR images. We aimed to investigate the added value of multimodal networks in segmenting the prostate into the peripheral zone (PZ) and central gland (CG). We optimized and evaluated monomodal DenseVNet, multimodal ScaleNet, and monomodal and multimodal HighRes3DNet, which yielded dice score coefficients (DSC) of 0.875, 0.848, 0.858, and 0.890 in WG, respectively. Multimodal HighRes3DNet and ScaleNet yielded higher DSC with statistical differences in PZ and CG only compared to monomodal DenseVNet, indicating that multimodal networks added value by generating better segmentation between PZ and CG regions but did not improve the WG segmentation. No significant difference was observed in the apex and base of WG segmentation between monomodal and multimodal networks, indicating that the segmentations at the apex and base were more affected by the general network architecture. The number of training data was also varied for DenseVNet and HighRes3DNet, from 20 to 120 in steps of 20. DenseVNet was able to yield DSC of higher than 0.65 even for special cases, such as TURP or abnormal prostate, whereas HighRes3DNet’s performance fluctuated with no trend despite being the best network overall. Multimodal networks did not add value in segmenting special cases but generally reduced variations in segmentation compared to the same matched monomodal network.

show abstract

Segmentation of prostate and prostate zones using deep learning

Cited by 42 publications

References 20 publications

Diagnostic efficiency of hybrid imaging using PSMA ligands, PET/CT, PET/MRI and MRI in identifying malignant prostate lesions

Diagnostic efficiency of hybrid imaging using PSMA ligands, PET/CT, PET/MRI and MRI in identifying malignant prostate lesions

Uncovering the invisible—prevalence, characteristics, and radiomics feature–based detection of visually undetectable intraprostatic tumor lesions in 68GaPSMA-11 PET images of patients with primary prostate cancer

Evaluation of Multimodal Algorithms for the Segmentation of Multiparametric MRI Prostate Images

Contact Info

Product

Resources

About