Xinyi Wang1, Da He1, Fei Feng1, James A Ashton-Miller2, John O L DeLancey3, Jiajia Luo4. 1. University of Michigan-Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University, Shanghai, 200240, China. 2. Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI, 48109, USA. 3. Department of Obstetrics and Gynecology, University of Michigan, Ann Arbor, MI, 48109, USA. 4. Biomedical Engineering Department, Peking University, Beijing, 100191, China. jiajia.luo@pku.edu.cn.
Abstract
INTRODUCTION AND HYPOTHESIS: We aimed to develop a deep learning-based multi-label classification model to simultaneously diagnose three types of pelvic organ prolapse using stress magnetic resonance imaging (MRI). METHODS: Our dataset consisted of 213 midsagittal labeled MR images at maximum Valsalva. For each MR image, the two endpoints of the sacrococcygeal inferior-pubic point line were auto-localized. Based on this line, a region of interest was automatically selected as input to a modified deep learning model, ResNet-50, for diagnosis. An unlabeled MRI dataset, a public dataset, and a synthetic dataset were used along with the labeled image dataset to train the model through a novel training strategy. We conducted a fivefold cross-validation and evaluated the classification results using precision, recall, F1 score, and area under the curve (AUC). RESULTS: The average precision, recall, F1 score, and AUC of our proposed multi-label classification model for the three types of prolapse were 0.84, 0.72, 0.77, and 0.91 respectively, which were improved from 0.64, 0.53, 0.57, and 0.83 from the original ResNet-50. Classification took 0.18 s to diagnose one patient. CONCLUSIONS: The proposed deep learning-based model were demonstrated feasible and fast in simultaneously diagnosing three types of prolapse based on pelvic floor stress MRI, which could facilitate computer-aided prolapse diagnosis and treatment planning.
INTRODUCTION AND HYPOTHESIS: We aimed to develop a deep learning-based multi-label classification model to simultaneously diagnose three types of pelvic organ prolapse using stress magnetic resonance imaging (MRI). METHODS: Our dataset consisted of 213 midsagittal labeled MR images at maximum Valsalva. For each MR image, the two endpoints of the sacrococcygeal inferior-pubic point line were auto-localized. Based on this line, a region of interest was automatically selected as input to a modified deep learning model, ResNet-50, for diagnosis. An unlabeled MRI dataset, a public dataset, and a synthetic dataset were used along with the labeled image dataset to train the model through a novel training strategy. We conducted a fivefold cross-validation and evaluated the classification results using precision, recall, F1 score, and area under the curve (AUC). RESULTS: The average precision, recall, F1 score, and AUC of our proposed multi-label classification model for the three types of prolapse were 0.84, 0.72, 0.77, and 0.91 respectively, which were improved from 0.64, 0.53, 0.57, and 0.83 from the original ResNet-50. Classification took 0.18 s to diagnose one patient. CONCLUSIONS: The proposed deep learning-based model were demonstrated feasible and fast in simultaneously diagnosing three types of prolapse based on pelvic floor stress MRI, which could facilitate computer-aided prolapse diagnosis and treatment planning.
Authors: Kindra A Larson; Jiajia Luo; Kenneth E Guire; Luyun Chen; James A Ashton-Miller; John O L DeLancey Journal: Int Urogynecol J Date: 2011-11-09 Impact factor: 2.894
Authors: Bernard T Haylen; Christopher F Maher; Matthew D Barber; Sérgio Camargo; Vani Dandolu; Alex Digesu; Howard B Goldman; Martin Huser; Alfredo L Milani; Paul A Moran; Gabriel N Schaer; Mariëlla I J Withagen Journal: Int Urogynecol J Date: 2016-04 Impact factor: 2.894
Authors: Luyun Chen; Sean Lisse; Kindra Larson; Mitchell B Berger; James A Ashton-Miller; John O L DeLancey Journal: Obstet Gynecol Date: 2016-10 Impact factor: 7.661
Authors: Yvonne Hsu; Luyun Chen; Aimee Summers; James A Ashton-Miller; John O L DeLancey; James O L DeLancey Journal: Int Urogynecol J Pelvic Floor Dysfunct Date: 2007-06-20
Authors: Carolyn W Swenson; Tovia M Smith; Jiajia Luo; Giselle E Kolenic; James A Ashton-Miller; John O DeLancey Journal: Am J Obstet Gynecol Date: 2016-09-08 Impact factor: 8.661