Author/Authors :
Nai, Ying-Hwey Yong Loo Lin School of Medicine - National University of Singapore, Singapore , Teo, Bernice W Nanyang Junior College, Singapore , Tan, Nadya L St. Joseph’s Institution International, Singapore , Chua, Koby Yi Wei Anglo-Chinese Independent, Singapore , Wong, Chun Kit Yong Loo Lin School of Medicine - National University of Singapore, Singapore , O’Doherty, Sophie Yong Loo Lin School of Medicine - National University of Singapore, Singapore , Stephenson, Mary C Yong Loo Lin School of Medicine - National University of Singapore, Singapore , Schaefferkoetter, Josh Yong Loo Lin School of Medicine - National University of Singapore, Singapore , Thian, Yee Liang Department of Diagnostic Imaging - National University Hospital, Singapore , Chiong, Edmund Department of Urology - National University Hospital, Singapore , Reilhac, Anthonin Yong Loo Lin School of Medicine - National University of Singapore, Singapore
Abstract :
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.
