Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  Convolutional neural network stacking for medical image segmentation in CT scans

Kloenne, M., Niehaus, S., Lampe, L., Merola, A., Reinelt, J., & Scherf, N. (2019). Convolutional neural network stacking for medical image segmentation in CT scans. In 2019 Kidney Tumor Segmentation Challenge. Minneapolis, MN: University of Minnesota Libraries Publishing. doi:10.24926/548719.090.

Item is

Basisdaten

einblenden: ausblenden:
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Kloenne, Marie 1, Autor
Niehaus, Sebastian 1, Autor
Lampe, Leonie1, Autor
Merola, Alberto1, Autor           
Reinelt, Janis1, Autor           
Scherf, Nico1, 2, Autor           
Affiliations:
1External Organizations, ou_persistent22              
2Department Neurophysics (Weiskopf), MPI for Human Cognitive and Brain Sciences, Max Planck Society, ou_2205649              

Inhalt

einblenden:
ausblenden:
Schlagwörter: Medical image segmentation ; Computed Tomography (CT)·Kidney tumor segmentation
 Zusammenfassung: Computed tomography (CT) data poses many challenges to medical image segmentation based on convolutional neural networks (CNNs). The main challenges in handling CT scans with CNN are the scale of data (large range of Hounsfield Units) and the processing of the slices. In this paper, we consider a framework, which addresses these demands regarding the data preprocessing, the data augmentation, and the CNN architecture itself. For this purpose, we present a data preprocessing and an augmentation method tailored to CT data. We evaluate and compare different input dimensionalities and two different CNN architectures. One of the architectures is a modified U-Net and the other a modified Mixed-Scale Dense Network (MS-D Net). Thus, we compare dilated convolutions for parallel multi-scale processing to the U-Net approach with traditional scaling operations based on the different input dimensionalities. Finally, we combine a set of 3D modified MS-D Nets and a set of 2D modified U-Nets as a stacked CNN-model to combine the different strengths of both model.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2019-01
 Publikationsstatus: Online veröffentlicht
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: DOI: 10.24926/548719.090
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: MICCAI 2019
Veranstaltungsort: Shenzhen, China
Start-/Enddatum: 2019-10-13 - 2019-10-19

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: 2019 Kidney Tumor Segmentation Challenge
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Minneapolis, MN : University of Minnesota Libraries Publishing
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: - Identifikator: -