A multi-object deep neural network architecture to detect prostate anatomy in T2-weighted MRI: Performance evaluation

Frontiers in Nuclear Medicine

Nuclear Medicine

Maria Baldeon-Calisto¹  Yasin Yilmaz²  Zhouping Wei³  Yoganand Balagurunathan³  Shatha Abudalou⁴  Kenneth Gage⁵  Julio Pow-Sang⁶ 

[1] Departamento de Ingeniería Industrial and Instituto de Innovación en Productividad y Logística CATENA-USFQ, Universidad San Francisco de Quito, Quito, Ecuador;Department of Electrical Engineering, University of South Florida, Tampa, FL, United States;Department of Machine Learning, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL, United States;Department of Machine Learning, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL, United States;Department of Electrical Engineering, University of South Florida, Tampa, FL, United States;Diagnostic Radiology, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL, United States;Genitourinary Oncology, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL, United States;

关键词: prostate cancer;    prostate segmentation;    machine learning;    deep learning;    neural network;    neural architecture search;    EMONAS;    AdaEn-Net;   

DOI  :  10.3389/fnume.2022.1083245

 received in 2022-10-28, accepted in 2022-12-30,  发布年份 2023

来源: Frontiers

【 摘 要 】

Prostate gland segmentation is the primary step to estimate gland volume, which aids in the prostate disease management. In this study, we present a 2D-3D convolutional neural network (CNN) ensemble that automatically segments the whole prostate gland along with the peripheral zone (PZ) (PPZ-SegNet) using a T2-weighted sequence (T2W) of Magnetic Resonance Imaging (MRI). The study used 4 different public data sets organized as Train #1 and Test #1 (independently derived from the same cohort), Test #2, Test #3 and Test #4. The prostate gland and the peripheral zone (PZ) anatomy were manually delineated with consensus read by a radiologist, except for Test #4 cohorts that had pre-marked glandular anatomy. A Bayesian hyperparameter optimization method was applied to construct the network model (PPZ-SegNet) with a training cohort (Train #1, n = 150) using a five-fold cross validation. The model evaluation was performed on an independent cohort of 283 T2W MRI prostate cases (Test #1 to #4) without any additional tuning. The data cohorts were derived from The Cancer Imaging Archives (TCIA): PROSTATEx Challenge, Prostatectomy, Repeatability studies and PROMISE12-Challenge. The segmentation performance was evaluated by computing the Dice similarity coefficient and Hausdorff distance between the estimated-deep-network identified regions and the radiologist-drawn annotations. The deep network architecture was able to segment the prostate gland anatomy with an average Dice score of 0.86 in Test #1 (n = 192), 0.79 in Test #2 (n = 26), 0.81 in Test #3 (n = 15), and 0.62 in Test #4 (n = 50). We also found the Dice coefficient improved with larger prostate volumes in 3 of the 4 test cohorts. The variation of the Dice scores from different cohorts of test images suggests the necessity of more diverse models that are inclusive of dependencies such as the gland sizes and others, which will enable us to develop a universal network for prostate and PZ segmentation. Our training and evaluation code can be accessed through the link: https://github.com/mariabaldeon/PPZ-SegNet.git.

【 授权许可】

Unknown   
© 2023 Baldeon-Calisto, Wei, Abudalou, Yilmaz, Gage, Pow-Sang and Balagurunathan.