Improving CNN Training using Disentanglement for Liver Lesion Classification in CT

Avi Ben-Cohen, Roey Mechrez, Noa Yedidia, Hayit Greenspan

פרסום מחקרי: פרק בספר / בדוח / בכנספרסום בספר כנסביקורת עמיתים

תקציר

Training data is the key component in designing algorithms for medical image analysis and in many cases it is the main bottleneck in achieving good results. Recent progress in image generation has enabled the training of neural network based solutions using synthetic data. A key factor in the generation of new samples is controlling the important appearance features and potentially being able to generate a new sample of a specific class with different variants. In this work we suggest the synthesis of new data by mixing the class specified and unspecified representation of different factors in the training data which are separated using a disentanglement based scheme. Our experiments on liver lesion classification in CT show an average improvement of 7.4% in accuracy over the baseline training scheme.

שפה מקוריתאנגלית
כותר פרסום המארח2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019
מוציא לאורInstitute of Electrical and Electronics Engineers Inc.
עמודים886-889
מספר עמודים4
מסת"ב (אלקטרוני)9781538613115
מזהי עצם דיגיטלי (DOIs)
סטטוס פרסוםפורסם - יולי 2019
אירוע41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019 - Berlin, גרמניה
משך הזמן: 23 יולי 201927 יולי 2019

סדרות פרסומים

שםProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

כנס

כנס41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019
מדינה/אזורגרמניה
עירBerlin
תקופה23/07/1927/07/19

ASJC Scopus subject areas

  • ???subjectarea.asjc.1700.1711???
  • ???subjectarea.asjc.2200.2204???
  • ???subjectarea.asjc.1700.1707???
  • ???subjectarea.asjc.2700.2718???

טביעת אצבע

להלן מוצגים תחומי המחקר של הפרסום 'Improving CNN Training using Disentanglement for Liver Lesion Classification in CT'. יחד הם יוצרים טביעת אצבע ייחודית.

פורמט ציטוט ביבליוגרפי