A Multi-scale U-Net for Semantic Segmentation of Histological Images from Radical Prostatectomies

Gleason grading of histological images is important in risk assessment and treatment planning for prostate cancer patients. Much research has been done in classifying small homogeneous cancer regions within histological images. However, semi-supervised methods published to date depend on pre-selecte...

Full description

Saved in:
Bibliographic Details
Published inAMIA ... Annual Symposium proceedings Vol. 2017; pp. 1140 - 1148
Main Authors Li, Jiayun, Sarma, Karthik V, Chung Ho, King, Gertych, Arkadiusz, Knudsen, Beatrice S, Arnold, Corey W
Format Journal Article
LanguageEnglish
Published United States American Medical Informatics Association 2017
Subjects
Deep Learning
Diagnosis, Computer-Assisted
Humans
Machine Learning
Male
Neoplasm Grading
Prostate - pathology
Prostatectomy
Prostatic Neoplasms - pathology
Prostatic Neoplasms - surgery
Risk Assessment
Semantics
Support Vector Machine
Online AccessGet full text

Cover

More Information
Summary:Gleason grading of histological images is important in risk assessment and treatment planning for prostate cancer patients. Much research has been done in classifying small homogeneous cancer regions within histological images. However, semi-supervised methods published to date depend on pre-selected regions and cannot be easily extended to an image of heterogeneous tissue composition. In this paper, we propose a multi-scale U-Net model to classify images at the pixel-level using 224 histological image tiles from radical prostatectomies of 20 patients. Our model was evaluated by a patient-based 10-fold cross validation, and achieved a mean Jaccard index of 65.8% across 4 classes (stroma, Gleason 3, Gleason 4 and benign glands), and 75.5% for 3 classes (stroma, benign glands, prostate cancer), outperforming other methods.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:1942-597X
1559-4076