Literature DB >> 32653985

Fast interactive medical image segmentation with weakly supervised deep learning method.

Kibrom Berihu Girum1,2, Gilles Créhange3,4, Raabid Hussain3, Alain Lalande3,5.   

Abstract

PURPOSE: To achieve accurate image segmentation, which is the first critical step in medical image analysis and interventions, using deep neural networks seems a promising approach provided sufficiently large and diverse annotated data from experts. However, annotated datasets are often limited because it is prone to variations in acquisition parameters and require high-level expert's knowledge, and manually labeling targets by tracing their contour is often laborious. Developing fast, interactive, and weakly supervised deep learning methods is thus highly desirable.
METHODS: We propose a new efficient deep learning method to accurately segment targets from images while generating an annotated dataset for deep learning methods. It involves a generative neural network-based prior-knowledge prediction from pseudo-contour landmarks. The predicted prior knowledge (i.e., contour proposal) is then refined using a convolutional neural network that leverages the information from the predicted prior knowledge and the raw input image. Our method was evaluated on a clinical database of 145 intraoperative ultrasound and 78 postoperative CT images of image-guided prostate brachytherapy. It was also evaluated on a cardiac multi-structure segmentation from 450 2D echocardiographic images.
RESULTS: Experimental results show that our model can segment the prostate clinical target volume in 0.499 s (i.e., 7.79 milliseconds per image) with an average Dice coefficient of 96.9 ± 0.9% and 95.4 ± 0.9%, 3D Hausdorff distance of 4.25 ± 4.58 and 5.17 ± 1.41 mm, and volumetric overlap ratio of 93.9 ± 1.80% and 91.3 ± 1.70 from TRUS and CT images, respectively. It also yielded an average Dice coefficient of 96.3 ± 1.3% on echocardiographic images.
CONCLUSIONS: We proposed and evaluated a fast, interactive deep learning method for accurate medical image segmentation. Moreover, our approach has the potential to solve the bottleneck of deep learning methods in adapting to inter-clinical variations and speed up the annotation processes.

Keywords:  Brachytherapy; CNN; Domain adaptation; Echocardiography; Generative model; Weakly supervised segmentation

Mesh:

Year:  2020        PMID: 32653985     DOI: 10.1007/s11548-020-02223-x

Source DB:  PubMed          Journal:  Int J Comput Assist Radiol Surg        ISSN: 1861-6410            Impact factor:   2.924


  5 in total

1.  Effect Evaluation of Perioperative Fast-Track Surgery Nursing for Tibial Fracture Patients with Computerized Tomography Images under Intelligent Algorithm.

Authors:  Mengmeng Zhang; Chuanbo Li; Fulan Rao
Journal:  Contrast Media Mol Imaging       Date:  2022-06-24       Impact factor: 3.009

2.  New Methods for the Acoustic-Signal Segmentation of the Temporomandibular Joint.

Authors:  Marcin Kajor; Dariusz Kucharski; Justyna Grochala; Jolanta E Loster
Journal:  J Clin Med       Date:  2022-05-11       Impact factor: 4.964

3.  Intelligent Algorithm-Based Magnetic Resonance Imaging in Radical Gastrectomy under Laparoscope.

Authors:  Wenkui Mo; Cansong Zhao
Journal:  Contrast Media Mol Imaging       Date:  2021-09-14       Impact factor: 3.161

4.  AAWS-Net: Anatomy-aware weakly-supervised learning network for breast mass segmentation.

Authors:  Yeheng Sun; Yule Ji
Journal:  PLoS One       Date:  2021-08-30       Impact factor: 3.240

5.  Deep convolutional neural network-based classification of cancer cells on cytological pleural effusion images.

Authors:  Xiaofeng Xie; Chi-Cheng Fu; Lei Lv; Qiuyi Ye; Yue Yu; Qu Fang; Liping Zhang; Likun Hou; Chunyan Wu
Journal:  Mod Pathol       Date:  2022-01-10       Impact factor: 8.209

  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.