6533b831fe1ef96bd1298faf
RESEARCH PRODUCT
CNN-Based Prostate Zonal Segmentation on T2-Weighted MR Images: A Cross-Dataset Study
Yudai NaganoClaudio FerrettiCarmelo MilitelloLeonardo RundoLeonardo RundoRyuichiro HatayaSalvatore VitabileGiancarlo MauriMarco S. NobileChanghee HanMaria Carla GilardiJin ZhangAndrea TangherloniHideki Nakayamasubject
Urologic DiseasesComputer scienceContext (language use)32 Biomedical and Clinical Sciences-Convolutional neural networkDeep convolutional neural networks Prostate zonal segmentation Cross-dataset generalizationProstate cancer46 Information and Computing SciencesProstateDeep convolutional neural networksmedicineAnatomical MRISegmentationProstate zonal segmentation; Prostate cancer; Anatomical MRI; Deep convolutional neural networks; Cross-dataset generalization;3202 Clinical SciencesCancerSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniProstate cancerSettore INF/01 - Informaticamedicine.diagnostic_testbusiness.industryDeep learningINF/01 - INFORMATICAMagnetic resonance imagingPattern recognitionmedicine.disease3211 Oncology and Carcinogenesismedicine.anatomical_structureCross-dataset generalizationProstate zonal segmentationBiomedical ImagingArtificial intelligenceDeep convolutional neural networkbusinessT2 weightedAnatomical MRI; Cross-dataset generalization; Deep convolutional neural networks; Prostate cancer; Prostate zonal segmentationdescription
Prostate cancer is the most common cancer among US men. However, prostate imaging is still challenging despite the advances in multi-parametric magnetic resonance imaging (MRI), which provides both morphologic and functional information pertaining to the pathological regions. Along with whole prostate gland segmentation, distinguishing between the central gland (CG) and peripheral zone (PZ) can guide toward differential diagnosis, since the frequency and severity of tumors differ in these regions; however, their boundary is often weak and fuzzy. This work presents a preliminary study on deep learning to automatically delineate the CG and PZ, aiming at evaluating the generalization ability of convolutional neural networks (CNNs) on two multi-centric MRI prostate datasets. Especially, we compared three CNN-based architectures: SegNet, U-Net, and pix2pix. In such a context, the segmentation performances achieved with/without pre-training were compared in 4-fold cross-validation. In general, U-Net outperforms the other methods, especially when training and testing are performed on multiple datasets.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2020-01-01 |