Automatic detection of small areas of Gleason grade 5 in prostate tissue using CNN

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceedingForskningPeer review

Sammanfattning

There are several different approaches used to treat prostate cancer, depending on age and general health conditions of the patient but also how severe the cancer is. To determine the latter, Gleason grading is used. The grade is determined by a pathologist, based on structures in histology samples from prostate biopsies. To determine the diagnosis, both the most common Gleason grade but also the highest Gleason grade occurring is used. Since the tumours typically split up the more malignant they are, single cells of Gleason grade 5, the highest and most malignant Gleason grade, can occur intermingled with benign tissue. Therefore, it is of great importance to fid even very small areas of the highest grade. This is what we aim to automatically do in this work. We have trained a convolutional neural network, with a ResNet design, to classify small areas of tissue in high magnification as either Gleason 5 or non-Gleason 5. The dataset used is generated from whole slide images from Skåne University Hospital, and consists in total of 19680 small images with the size 128×128 pixels in 40X. We try to make the algorithm more robust to stain variations, which is a common issue for this type of data, by using colour augmentation. The best accuracy we achieve for classification of Gleason 5 versus non-Gleason 5 images is 92%.
Originalspråkengelska
Titel på gästpublikationMedical Imaging 2019: Digital Pathology
FörlagSPIE
Volym10956
ISBN (elektroniskt)978-151062559-4
DOI
StatusPublished - 2019
EvenemangMedical Imaging 2019: Physics of Medical Imaging - San Diego, USA
Varaktighet: 2019 feb 172019 feb 20

Konferens

KonferensMedical Imaging 2019: Physics of Medical Imaging
Land/TerritoriumUSA
OrtSan Diego
Period2019/02/172019/02/20

Ämnesklassifikation (UKÄ)

  • Medicinsk bildbehandling

Fingeravtryck

Utforska forskningsämnen för ”Automatic detection of small areas of Gleason grade 5 in prostate tissue using CNN”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här