Selected article for: "different dataset and significant difference"
Author: Guillaume Chassagnon; Maria Vakalopoulou; Enzo Battistella; Stergios Christodoulidis; Trieu-Nghi Hoang-Thi; Severine Dangeard; Eric Deutsch; Fabrice Andre; Enora Guillo; Nara Halm; Stefany El Hajj; Florian Bompard; Sophie Neveu; Chahinez Hani; Ines Saab; Alienor Campredon; Hasmik Koulakian; Souhail Bennani; Gael Freche; Aurelien Lombard; Laure Fournier; Hippolyte Monnier; Teodor Grand; Jules Gregory; Antoine Khalil; Elyas Mahdjoub; Pierre-Yves Brillet; Stephane Tran Ba; Valerie Bousson; Marie-Pierre Revel; Nikos Paragios
Title: AI-Driven CT-based quantification, staging and short-term outcome prediction of COVID-19 pneumonia
  • Document date: 2020_4_22
    • ID: nxm1jr0x_5
    Snippet: patients with positive RT-PCR. The multicentric dataset was acquired at 6 Hospitals, equipped with 4 different CT models from 3 different 91 manufacturers, with different acquisition protocols and radiation dose (Table 1) . Fifty CT exams from 3 centers were used for training and 130 CT exams from 3 other centers were used for test (Table 2 ). Disease and lung were delineated on all 23, 423 images used as training dataset, and on only 20 images p.....
    Document: patients with positive RT-PCR. The multicentric dataset was acquired at 6 Hospitals, equipped with 4 different CT models from 3 different 91 manufacturers, with different acquisition protocols and radiation dose (Table 1) . Fifty CT exams from 3 centers were used for training and 130 CT exams from 3 other centers were used for test (Table 2 ). Disease and lung were delineated on all 23, 423 images used as training dataset, and on only 20 images per exam but by 2 independent annotators in the test dataset (2, 600 images). The overall annotation effort took approximately 800 hours and involved 15 radiologists with 1 to 7 years of experience in chest imaging. The consensus between manual (2 annotators) and automated segmentation was measured using the Dice similarity score (DSC) 26 and the Haussdorf distance (HD). The CovidENet performed equally well to trained radiologists in terms of DSCs and better in terms HD ( Figure 2 ). The mean/median DSCs between the two expert's annotations on the test dataset were 0.70/0.72 for disease segmentation. For the same task, DSCs between CovidENet and the manual segmentations were 0.69/0.71 and 0.70/0.73. In terms of HDs, the observed average value between the two experts was 9.16mm while it was 8.96mm between CovidENet and the two experts. When looking at disease extent, defined as the percentage of lung affected by the disease, we found no significant difference between automated segmentation and the average of the two manual segmentations (

    Search related documents:
    Co phrase search for related documents
    • average value and CT model: 1, 2
    • chest imaging and CT exam: 1, 2, 3, 4, 5
    • chest imaging and CT model: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12
    • chest imaging and disease affect: 1, 2
    • chest imaging and disease extent: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11
    • chest imaging and disease segmentation: 1
    • CT exam and CT model: 1
    • CT exam and Dice similarity score: 1
    • CT exam and disease extent: 1
    • CT exam and DSC Dice similarity score: 1
    • CT model and different CT model: 1, 2
    • CT model and disease extent: 1
    • CT model and disease segmentation: 1, 2, 3, 4
    • Dice similarity score and disease extent: 1
    • Dice similarity score and DSC Dice similarity score: 1
    • disease extent and DSC Dice similarity score: 1