Selected article for: "classification segmentation reconstruction and ROC curve area"
Author: Amyar, Amine; Modzelewski, Romain; Li, Hua; Ruan, Su
Title: Multi-task Deep Learning Based CT Imaging Analysis For COVID-19 Pneumonia: Classification and Segmentation
  • Cord-id: 9a7fi46y
  • Document date: 2020_10_8
    • ID: 9a7fi46y
    Snippet: This paper presents an automatic classification segmentation tool for helping screening COVID-19 pneumonia using chest CT imaging. The segmented lesions can help to assess the severity of pneumonia and follow-up the patients. In this work, we propose a new multitask deep learning model to jointly identify COVID-19 patient and segment COVID-19 lesion from chest CT images. Three learning tasks: segmentation, classification and reconstruction are jointly performed with different datasets. Our motiv
    Document: This paper presents an automatic classification segmentation tool for helping screening COVID-19 pneumonia using chest CT imaging. The segmented lesions can help to assess the severity of pneumonia and follow-up the patients. In this work, we propose a new multitask deep learning model to jointly identify COVID-19 patient and segment COVID-19 lesion from chest CT images. Three learning tasks: segmentation, classification and reconstruction are jointly performed with different datasets. Our motivation is on the one hand to leverage useful information contained in multiple related tasks to improve both segmentation and classification performances, and on the other hand to deal with the problems of small data because each task can have a relatively small dataset. Our architecture is composed of a common encoder for disentangled feature representation with three tasks, and two decoders and a multi-layer perceptron for reconstruction, segmentation and classification respectively. The proposed model is evaluated and compared with other image segmentation techniques using a dataset of 1369 patients including 449 patients with COVID-19, 425 normal ones, 98 with lung cancer and 397 of different kinds of pathology. The obtained results show very encouraging performance of our method with a dice coefficient higher than 0.88 for the segmentation and an area under the ROC curve higher than 97% for the classification.

    Search related documents:
    Co phrase search for related documents
    • acc accuracy and lung cancer: 1, 2
    • activation function and adam optimizer: 1, 2, 3
    • activation function and adam optimizer metric accuracy: 1
    • activation function and local information: 1
    • activation function and loss function: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12
    • activation function and loss function binary cross: 1, 2
    • activation function elu and adam optimizer: 1
    • activation function elu and adam optimizer metric accuracy: 1
    • activation function elu and loss function: 1, 2
    • activation function elu and loss function binary cross: 1, 2
    • activation function elu dropout and loss function: 1
    • activation function elu dropout and loss function binary cross: 1
    • adam optimizer and loss function: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10
    • adam optimizer and loss function binary cross: 1, 2, 3, 4
    • adam optimizer and loss glob global loss function: 1
    • adam optimizer and lung cancer: 1
    • adam optimizer metric accuracy and loss function: 1
    • adam optimizer metric accuracy and loss function binary cross: 1
    • local information and lung cancer: 1