Automatic detection of small areas of Gleason grade 5 in prostate tissue using CNN
(2019) Medical Imaging 2019: Physics of Medical Imaging 10956.- Abstract
- 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... (More)
- 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%. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/38d31ad6-e2af-47f3-b77c-405072449e8c
- author
- Tall, Kasper
; Arvidsson, Ida
LU
; Overgaard, Niels Christian
LU
; Åström, Karl
LU
and Heyden, Anders LU
- organization
- publishing date
- 2019
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- prostate cancer, Gleason grade, Deep Learning, Convolutional Neural Networks
- host publication
- Medical Imaging 2019: Digital Pathology
- volume
- 10956
- article number
- 109560E
- publisher
- SPIE
- conference name
- Medical Imaging 2019: Physics of Medical Imaging
- conference location
- San Diego, United States
- conference dates
- 2019-02-17 - 2019-02-20
- external identifiers
-
- scopus:85068696588
- ISBN
- 978-151062559-4
- DOI
- 10.1117/12.2512924
- language
- English
- LU publication?
- yes
- id
- 38d31ad6-e2af-47f3-b77c-405072449e8c
- date added to LUP
- 2019-05-29 16:15:41
- date last changed
- 2023-10-21 09:41:57
@inproceedings{38d31ad6-e2af-47f3-b77c-405072449e8c, abstract = {{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%.}}, author = {{Tall, Kasper and Arvidsson, Ida and Overgaard, Niels Christian and Åström, Karl and Heyden, Anders}}, booktitle = {{Medical Imaging 2019: Digital Pathology}}, isbn = {{978-151062559-4}}, keywords = {{prostate cancer; Gleason grade; Deep Learning; Convolutional Neural Networks}}, language = {{eng}}, publisher = {{SPIE}}, title = {{Automatic detection of small areas of Gleason grade 5 in prostate tissue using CNN}}, url = {{http://dx.doi.org/10.1117/12.2512924}}, doi = {{10.1117/12.2512924}}, volume = {{10956}}, year = {{2019}}, }