Literature DB >> 35290645

Improving segmentation and classification of renal tumors in small sample 3D CT images using transfer learning with convolutional neural networks.

Xi-Liang Zhu1,2, Hong-Bin Shen3, Haitao Sun4, Li-Xia Duan5, Ying-Ying Xu6,7.   

Abstract

PURPOSE: Computed tomography (CT) images can display internal organs of patients and are particularly suitable for preoperative surgical diagnoses. The increasing demands for computer-aided systems in recent years have facilitated the development of many automated algorithms, especially deep convolutional neural networks, to segment organs and tumors or identify diseases from CT images. However, performances of some systems are highly affected by the amount of training data, while the sizes of medical image data sets, especially three-dimensional (3D) data sets, are usually small. This condition limits the application of deep learning.
METHODS: In this study, given a practical clinical data set that has 3D CT images of 20 patients with renal carcinoma, we designed a pipeline employing transfer learning to alleviate the detrimental effect of the small sample size. A dual-channel fine segmentation network (FS-Net) was constructed to segment kidney and tumor regions, with 210 publicly available 3D images from a competition employed during the training phase. We also built discriminative classifiers to classify the benign and malignant tumors based on the segmented regions, where both handcrafted and deep features were tested.
RESULTS: Our experimental results showed that the Dice values of segmented kidney and tumor regions were 0.9662 and 0.7685, respectively, which were better than those of state-of-the-art methods. The classification model using radiomics features can classify most of the tumors correctly.
CONCLUSIONS: The designed FS-Net was demonstrated to be more effective than simply fine-tuning on the practical small size data set given that the model can borrow knowledge from large auxiliary data without diluting the signal in primary data. For the small data set, radiomics features outperformed deep features in the classification of benign and malignant tumors. This work highlights the importance of architecture design in transfer learning, and the proposed pipeline is anticipated to provide a reference and inspiration for small data analysis.
© 2022. CARS.

Entities:  

Keywords:  CT images; Deep learning; Image classification; Image segmentation; Renal carcinoma

Mesh:

Year:  2022        PMID: 35290645     DOI: 10.1007/s11548-022-02587-2

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


  9 in total

1.  Prognostic impact of the integration of volumetric quantification of the solid part of the tumor on 3DCT and FDG-PET imaging in clinical stage IA adenocarcinoma of the lung.

Authors:  Hideyuki Furumoto; Yoshihisa Shimada; Kentaro Imai; Sachio Maehara; Junichi Maeda; Masaru Hagiwara; Tetsuya Okano; Ryuhei Masuno; Masatoshi Kakihana; Naohiro Kajiwara; Tatsuo Ohira; Norihiko Ikeda
Journal:  Lung Cancer       Date:  2018-05-04       Impact factor: 5.705

2.  Differentiating kidney stones from phleboliths in unenhanced low-dose computed tomography using radiomics and machine learning.

Authors:  Thomas De Perrot; Jeremy Hofmeister; Simon Burgermeister; Steve P Martin; Gregoire Feutry; Jacques Klein; Xavier Montet
Journal:  Eur Radiol       Date:  2019-02-12       Impact factor: 5.315

3.  A CT-based radiomics nomogram for differentiation of renal angiomyolipoma without visible fat from homogeneous clear cell renal cell carcinoma.

Authors:  Pei Nie; Guangjie Yang; Zhenguang Wang; Lei Yan; Wenjie Miao; Dapeng Hao; Jie Wu; Yujun Zhao; Aidi Gong; Jingjing Cui; Yan Jia; Haitao Niu
Journal:  Eur Radiol       Date:  2019-09-10       Impact factor: 5.315

4.  Automated segmentation of kidney and renal mass and automated detection of renal mass in CT urography using 3D U-Net-based deep convolutional neural network.

Authors:  Zhiyong Lin; Yingpu Cui; Jia Liu; Zhaonan Sun; Shuai Ma; Xiaodong Zhang; Xiaoying Wang
Journal:  Eur Radiol       Date:  2021-01-13       Impact factor: 5.315

5.  Differentiation of fat-poor angiomyolipoma from clear cell renal cell carcinoma in contrast-enhanced MDCT images using quantitative feature classification.

Authors:  Han Sang Lee; Helen Hong; Dae Chul Jung; Seunghyun Park; Junmo Kim
Journal:  Med Phys       Date:  2017-06-09       Impact factor: 4.071

6.  A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data.

Authors:  Bjoern H Menze; B Michael Kelm; Ralf Masuch; Uwe Himmelreich; Peter Bachert; Wolfgang Petrich; Fred A Hamprecht
Journal:  BMC Bioinformatics       Date:  2009-07-10       Impact factor: 3.169

7.  nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation.

Authors:  Fabian Isensee; Paul F Jaeger; Simon A A Kohl; Jens Petersen; Klaus H Maier-Hein
Journal:  Nat Methods       Date:  2020-12-07       Impact factor: 28.547

8.  The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge.

Authors:  Nicholas Heller; Fabian Isensee; Klaus H Maier-Hein; Xiaoshuai Hou; Chunmei Xie; Fengyi Li; Yang Nan; Guangrui Mu; Zhiyong Lin; Miofei Han; Guang Yao; Yaozong Gao; Yao Zhang; Yixin Wang; Feng Hou; Jiawei Yang; Guangwei Xiong; Jiang Tian; Cheng Zhong; Jun Ma; Jack Rickman; Joshua Dean; Bethany Stai; Resha Tejpaul; Makinna Oestreich; Paul Blake; Heather Kaluzniak; Shaneabbas Raza; Joel Rosenberg; Keenan Moore; Edward Walczak; Zachary Rengel; Zach Edgerton; Ranveer Vasdev; Matthew Peterson; Sean McSweeney; Sarah Peterson; Arveen Kalapara; Niranjan Sathianathen; Nikolaos Papanikolopoulos; Christopher Weight
Journal:  Med Image Anal       Date:  2020-10-02       Impact factor: 8.545

9.  Towards image-based cancer cell lines authentication using deep neural networks.

Authors:  Deogratias Mzurikwao; Muhammad Usman Khan; Oluwarotimi Williams Samuel; Jindrich Cinatl; Mark Wass; Martin Michaelis; Gianluca Marcelli; Chee Siang Ang
Journal:  Sci Rep       Date:  2020-11-16       Impact factor: 4.379

  9 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.