Deep learning based multiple sclerosis lesion detection utilizing synthetic data generation and soft attention mechanism

Omer Zucker Shmueli, Chen Solomon, Noam Ben-Eliezer, Hayit Greenspan

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

תקציר

In this work we focus on identifying healthy brain slices vs brain slices with Multiple sclerosis (MS) lesions. MS is an autoimmune, demyelinating disease characterized by inflammatory lesions in the central nervous system. MRI is commonly used for diagnosis of MS, and enables accurate detection and classification of lesions for early diagnosis and treatment. Visual attention mechanisms may be beneficial for the detection of MS brain lesions, as they tend to be small. The attention mechanism prevents overfitting of the background when the amount of data is limited. In addition, enough data is necessary for training a successful machine learning algorithms for medical image analysis. Data with insufficient variability leads to poor classification performance. This is problematic in medical imaging where abnormal findings are uncommon and data labeling requires expensive expert's time. In this work, we suggest a new network architecture, based on Y-net and EfficientNet models, with attention layers to improve the network performance and reduce overfitting. Furthermore, the attention layers allow extraction of lesion locations. In addition, we show an innovative regularization scheme on the attention weight mask to make it focus on the lesions while letting it search in different areas. Finally, we explore an option to add synthetic lesions in the training process. Based on recent work, we generate artificial lesions in healthy brain MRI scans to augment our training data. Our system achieves 91% accuracy in identifying cases that contain lesions (vs. healthy cases) with more than 13% improvement over an equivalent system without the attention and the data added.

שפה מקוריתאנגלית
כותר פרסום המארחMedical Imaging 2022
כותר משנה של פרסום המארחComputer-Aided Diagnosis
עורכיםKaren Drukker, Khan M. Iftekharuddin
מוציא לאורSPIE
מסת"ב (אלקטרוני)9781510649415
מזהי עצם דיגיטלי (DOIs)
סטטוס פרסוםפורסם - 2022
אירועMedical Imaging 2022: Computer-Aided Diagnosis - Virtual, Online
משך הזמן: 21 מרץ 202227 מרץ 2022

סדרות פרסומים

שםProgress in Biomedical Optics and Imaging - Proceedings of SPIE
כרך12033

כנס

כנסMedical Imaging 2022: Computer-Aided Diagnosis
עירVirtual, Online
תקופה21/03/2227/03/22

ASJC Scopus subject areas

  • ???subjectarea.asjc.2500.2504???
  • ???subjectarea.asjc.3100.3107???
  • ???subjectarea.asjc.2500.2502???
  • ???subjectarea.asjc.2700.2741???

טביעת אצבע

להלן מוצגים תחומי המחקר של הפרסום 'Deep learning based multiple sclerosis lesion detection utilizing synthetic data generation and soft attention mechanism'. יחד הם יוצרים טביעת אצבע ייחודית.

פורמט ציטוט ביבליוגרפי