Dilated Volumetric Network: an Enhanced Fully Convolutional Network for Volumetric Prostate Segmentation from Magnetic Resonance Imaging

Magnetic Resonance Imaging-based prostate segmentation is an essential task for adaptive radiotherapy and for radiomics studies whose purpose is to identify associations between imaging features and patient outcomes. Because manual delineation is a time-consuming task, we present three deep-learning (DL) approaches, namely UNet, efficient neural network (ENet), and efficient residual factorized convNet (ERFNet), whose aim is to tackle the fully-automated, real-time, and 3D delineation process of the prostate gland on T2-weighted MRI. While UNet is used in many biomedical image delineation applications, ENet and ERFNet are mainly applied in self-driving cars to compensate for limited hardware availability while still achieving accurate segmentation. We apply these models to a limited set of 85 manual prostate segmentations using the k-fold validation strategy and the Tversky loss function and we compare their results. We find that ENet and UNet are more accurate than ERFNet, with ENet much faster than UNet. Specifically, ENet obtains a dice similarity coefficient of 90.89% and a segmentation time of about 6 s using central processing unit (CPU) hardware to simulate real clinical conditions where graphics processing unit (GPU) is not always available. In conclusion, ENet could be efficiently applied for prostate delineation even in small image training datasets with potential benefit for patient management personalization.

Download Full-text

Atlas registration and ensemble deep convolutional neural network-based prostate segmentation using magnetic resonance imaging

Neurocomputing ◽

10.1016/j.neucom.2017.09.084 ◽

2018 ◽

Vol 275 ◽

pp. 1358-1369 ◽

Cited By ~ 35

Author(s):

Haozhe Jia ◽

Yong Xia ◽

Yang Song ◽

Weidong Cai ◽

Michael Fulham ◽

...

Keyword(s):

Neural Network ◽

Magnetic Resonance Imaging ◽

Magnetic Resonance ◽

Convolutional Neural Network ◽

Deep Convolutional Neural Network ◽

Resonance Imaging ◽

Prostate Segmentation ◽

Atlas Registration

Download Full-text

Automatic prostate segmentation of magnetic resonance imaging using Res-Net

Magnetic Resonance Materials in Physics Biology and Medicine ◽

10.1007/s10334-021-00979-0 ◽

2021 ◽

Author(s):

Asha Kuppe Kumaraswamy ◽

Chandrashekar M. Patil

Keyword(s):

Magnetic Resonance Imaging ◽

Magnetic Resonance ◽

Resonance Imaging ◽

Prostate Segmentation

Download Full-text

Deep dense multi-path neural network for prostate segmentation in magnetic resonance imaging

International Journal of Computer Assisted Radiology and Surgery ◽

10.1007/s11548-018-1841-4 ◽

2018 ◽

Vol 13 (11) ◽

pp. 1687-1696 ◽

Cited By ~ 21

Author(s):

Minh Nguyen Nhat To ◽

Dang Quoc Vu ◽

Baris Turkbey ◽

Peter L. Choyke ◽

Jin Tae Kwak

Keyword(s):

Neural Network ◽

Magnetic Resonance Imaging ◽

Magnetic Resonance ◽

Resonance Imaging ◽

Prostate Segmentation

Download Full-text

Prostate segmentation in transrectal ultrasound using magnetic resonance imaging priors

International Journal of Computer Assisted Radiology and Surgery ◽

10.1007/s11548-018-1742-6 ◽

2018 ◽

Vol 13 (6) ◽

pp. 749-757 ◽

Cited By ~ 6

Author(s):

Qi Zeng ◽

Golnoosh Samei ◽

Davood Karimi ◽

Claudia Kesch ◽

Sara S. Mahdavi ◽

...

Keyword(s):

Magnetic Resonance Imaging ◽

Magnetic Resonance ◽

Transrectal Ultrasound ◽

Resonance Imaging ◽

Prostate Segmentation

Download Full-text

Convolutional Neural Network Intelligent Segmentation Algorithm-Based Magnetic Resonance Imaging in Diagnosis of Nasopharyngeal Carcinoma Foci

Contrast Media & Molecular Imaging ◽

10.1155/2021/2033806 ◽

2021 ◽

Vol 2021 ◽

pp. 1-9

Author(s):

Deli Wang ◽

Zheng Gong ◽

Yanfen Zhang ◽

Shouxi Wang

Keyword(s):

Neural Network ◽

Magnetic Resonance Imaging ◽

Magnetic Resonance ◽

Nasopharyngeal Carcinoma ◽

Convolutional Neural Network ◽

Batch Size ◽

Resonance Imaging ◽

Dice Coefficient ◽

Convolutional Network ◽

Mri Image

The aim of this study was to explore the adoption value of convolutional neural network- (CNN-) based magnetic resonance imaging (MRI) image intelligent segmentation model in the identification of nasopharyngeal carcinoma (NPC) lesions. The multisequence cross convolutional (MSCC) method was used in the complex convolutional network algorithm to establish the intelligent segmentation model two-dimensional (2D) ResUNet for the MRI image of the NPC lesion. Moreover, a multisequence multidimensional fusion segmentation model (MSCC-MDF) was further established. With 45 patients with NPC as the research objects, the Dice coefficient, Hausdorff distance (HD), and percentage of area difference (PAD) were calculated to evaluate the segmentation effect of MRI lesions. The results showed that the 2D-ResUNet model processed by MSCC had the largest Dice coefficient of 0.792 ± 0.045 for segmenting the tumor lesions of NPC, and it also had the smallest HD and PAD, which were 5.94 ± 0.41 mm and 15.96 ± 1.232%, respectively. When batch size = 5, the convergence curve was relatively gentle, and the convergence speed was the best. The largest Dice coefficient of MSCC-MDF model segmenting NPC tumor lesions was 0.896 ± 0.09, and its HD and PAD were the smallest, which were 5.07 ± 0.54 mm and 14.41 ± 1.33%, respectively. Its Dice coefficient was lower than other algorithms ( P < 0.05 ), but HD and PAD were significantly higher than other algorithms ( P < 0.05 ). To sum up, the MSCC-MDF model significantly improved the segmentation performance of MRI lesions in NPC patients, which provided a reference for the diagnosis of NPC.

Download Full-text

Lesion Detection of Computed Tomography and Magnetic Resonance Imaging Image Based on Fully Convolutional Networks

Journal of Medical Imaging and Health Informatics ◽

10.1166/jmihi.2018.2565 ◽

2018 ◽

Vol 8 (9) ◽

pp. 1819-1825 ◽

Cited By ~ 9

Author(s):

Shanwen Zhang ◽

Wenzhun Huang ◽

Harry Wang

Keyword(s):

Magnetic Resonance Imaging ◽

Computed Tomography ◽

Magnetic Resonance ◽

Lesion Detection ◽

Resonance Imaging ◽

Convolutional Network ◽

Final Model ◽

Fully Convolutional Networks ◽

Mri Image ◽

Ct And Mri

Computed tomography (CT) and Magnetic resonance imaging (MRI) are two kinds of important medical images, simply namely CT and MRI. Automatic lesion detection of CT and MRI is an important step for accurate clinical diagnosis. The classical CT and MRI lesion segmentation methods have bad performance due to the complex background noise, various illumination, and uneven color on CT image. In this paper, an improved fully convolutional network (FCN) model is proposed for lesion detection of CT and MRI image. The structure is same as FCN, and the lesion information from a deep layer is combined with appearance information from a shallow layer. First, we labeled all of the images from training set manually, the lesion and background labeled as 1 and 0, respectively. Then, the whole CT and MRI image dataset is fed to FCN. After 100 epochs training iterations, the model after the last iteration is selected as the final model, and then test dataset is put into the final model to obtain the detection results. The experimental results show that the proposed method can effectively detect and segment the lesion of CT and MRI images and greatly improve the segmentation accuracy, and can be used for the automatic lesion detection of CT and MRI images.

Download Full-text