Computer vision for tissue characterization and outcome prediction in cancer

Research output: ThesisDoctoral ThesisCollection of Articles

Abstract

The aim of this dissertation was to investigate the use of computer vision for tissue characterization and patient outcome prediction in cancer. This work focused on analysis of digitized tissue specimens, which were stained only for basic morphology (i.e. hematoxylin and eosin). The applicability of texture analysis and convolutional neural networks was evaluated for detection of biologically and clinically relevant features. Moreover, novel approaches to guide ground-truth annotation and outcome-supervised learning for prediction of patient survival directly from the tumor tissue images without expert guidance was investigated. We first studied quantification of tumor viability through segmentation of necrotic and viable tissue compartments. We developed a regional texture analysis method, which was trained and tested on whole sections of mouse xenograft models of human lung cancer. Our experiments showed that the proposed segmentation was able to discriminate between viable and non-viable tissue regions with high accuracy when compared to human expert assessment. We next investigated the feasibility of pre-trained convolutional neural networks in analysis of breast cancer tissue, aiming to quantify tumor-infiltrating lymphocytes in the specimens. Interestingly, our results showed that pre-trained convolutional neural networks can be adapted for analysis of histological image data, outperforming texture analysis. The results also indicated that the computerized assessment was on par with pathologist assessments. Moreover, the study presented an image annotation technique guided by specific antibody staining for improved ground-truth labeling. Direct outcome prediction in breast cancer was then studied using a nationwide patient cohort. A computerized pipeline, which incorporated orderless feature aggregation and convolutional image descriptors for outcome-supervised classification, resulted in a risk grouping that was predictive of both disease-specific and overall survival. Surprisingly, further analysis suggested that the computerized risk prediction was also an independent prognostic factor that provided information complementary to the standard clinicopathological factors. This doctoral thesis demonstrated how computer-vision methods can be powerful tools in analysis of cancer tissue samples, highlighting strategies for supervised characterization of tissue entities and an approach for identification of novel prognostic morphological features.
Original languageEnglish
Place of PublicationHelsinki
Publisher
Print ISBNs978-951-51-4397-6
Electronic ISBNs978-951-51-4398-3
Publication statusPublished - 2018
MoE publication typeG5 Doctoral dissertation (article)

Fields of Science

  • Neoplasms
  • +diagnosis
  • Breast Neoplasms
  • Lung Neoplasms
  • Artificial Intelligence
  • Supervised Machine Learning
  • Deep Learning
  • Heterografts
  • Lymphocytes, Tumor-Infiltrating
  • Neural Networks (Computer)
  • Survival Analysis
  • 3122 Cancers

Cite this

@phdthesis{02f12deef3e04f1aad22badf198927e6,
title = "Computer vision for tissue characterization and outcome prediction in cancer",
abstract = "The aim of this dissertation was to investigate the use of computer vision for tissue characterization and patient outcome prediction in cancer. This work focused on analysis of digitized tissue specimens, which were stained only for basic morphology (i.e. hematoxylin and eosin). The applicability of texture analysis and convolutional neural networks was evaluated for detection of biologically and clinically relevant features. Moreover, novel approaches to guide ground-truth annotation and outcome-supervised learning for prediction of patient survival directly from the tumor tissue images without expert guidance was investigated. We first studied quantification of tumor viability through segmentation of necrotic and viable tissue compartments. We developed a regional texture analysis method, which was trained and tested on whole sections of mouse xenograft models of human lung cancer. Our experiments showed that the proposed segmentation was able to discriminate between viable and non-viable tissue regions with high accuracy when compared to human expert assessment. We next investigated the feasibility of pre-trained convolutional neural networks in analysis of breast cancer tissue, aiming to quantify tumor-infiltrating lymphocytes in the specimens. Interestingly, our results showed that pre-trained convolutional neural networks can be adapted for analysis of histological image data, outperforming texture analysis. The results also indicated that the computerized assessment was on par with pathologist assessments. Moreover, the study presented an image annotation technique guided by specific antibody staining for improved ground-truth labeling. Direct outcome prediction in breast cancer was then studied using a nationwide patient cohort. A computerized pipeline, which incorporated orderless feature aggregation and convolutional image descriptors for outcome-supervised classification, resulted in a risk grouping that was predictive of both disease-specific and overall survival. Surprisingly, further analysis suggested that the computerized risk prediction was also an independent prognostic factor that provided information complementary to the standard clinicopathological factors. This doctoral thesis demonstrated how computer-vision methods can be powerful tools in analysis of cancer tissue samples, highlighting strategies for supervised characterization of tissue entities and an approach for identification of novel prognostic morphological features.",
keywords = "Neoplasms, +diagnosis, Breast Neoplasms, Lung Neoplasms, Artificial Intelligence, Supervised Machine Learning, Deep Learning, Heterografts, Lymphocytes, Tumor-Infiltrating, Neural Networks (Computer), Survival Analysis, 3122 Cancers",
author = "Riku Turkki",
note = "M1 - 66 s. + liitteet",
year = "2018",
language = "English",
isbn = "978-951-51-4397-6",
series = "Dissertationes Scholae Doctoralis Ad Sanitatem Investigandam Universitatis Helsinkiensis",
publisher = "Helsingin yliopisto",
number = "50/2018",
address = "Finland",

}

Computer vision for tissue characterization and outcome prediction in cancer. / Turkki, Riku.

Helsinki : Helsingin yliopisto, 2018. 66 p.

Research output: ThesisDoctoral ThesisCollection of Articles

TY - THES

T1 - Computer vision for tissue characterization and outcome prediction in cancer

AU - Turkki, Riku

N1 - M1 - 66 s. + liitteet

PY - 2018

Y1 - 2018

N2 - The aim of this dissertation was to investigate the use of computer vision for tissue characterization and patient outcome prediction in cancer. This work focused on analysis of digitized tissue specimens, which were stained only for basic morphology (i.e. hematoxylin and eosin). The applicability of texture analysis and convolutional neural networks was evaluated for detection of biologically and clinically relevant features. Moreover, novel approaches to guide ground-truth annotation and outcome-supervised learning for prediction of patient survival directly from the tumor tissue images without expert guidance was investigated. We first studied quantification of tumor viability through segmentation of necrotic and viable tissue compartments. We developed a regional texture analysis method, which was trained and tested on whole sections of mouse xenograft models of human lung cancer. Our experiments showed that the proposed segmentation was able to discriminate between viable and non-viable tissue regions with high accuracy when compared to human expert assessment. We next investigated the feasibility of pre-trained convolutional neural networks in analysis of breast cancer tissue, aiming to quantify tumor-infiltrating lymphocytes in the specimens. Interestingly, our results showed that pre-trained convolutional neural networks can be adapted for analysis of histological image data, outperforming texture analysis. The results also indicated that the computerized assessment was on par with pathologist assessments. Moreover, the study presented an image annotation technique guided by specific antibody staining for improved ground-truth labeling. Direct outcome prediction in breast cancer was then studied using a nationwide patient cohort. A computerized pipeline, which incorporated orderless feature aggregation and convolutional image descriptors for outcome-supervised classification, resulted in a risk grouping that was predictive of both disease-specific and overall survival. Surprisingly, further analysis suggested that the computerized risk prediction was also an independent prognostic factor that provided information complementary to the standard clinicopathological factors. This doctoral thesis demonstrated how computer-vision methods can be powerful tools in analysis of cancer tissue samples, highlighting strategies for supervised characterization of tissue entities and an approach for identification of novel prognostic morphological features.

AB - The aim of this dissertation was to investigate the use of computer vision for tissue characterization and patient outcome prediction in cancer. This work focused on analysis of digitized tissue specimens, which were stained only for basic morphology (i.e. hematoxylin and eosin). The applicability of texture analysis and convolutional neural networks was evaluated for detection of biologically and clinically relevant features. Moreover, novel approaches to guide ground-truth annotation and outcome-supervised learning for prediction of patient survival directly from the tumor tissue images without expert guidance was investigated. We first studied quantification of tumor viability through segmentation of necrotic and viable tissue compartments. We developed a regional texture analysis method, which was trained and tested on whole sections of mouse xenograft models of human lung cancer. Our experiments showed that the proposed segmentation was able to discriminate between viable and non-viable tissue regions with high accuracy when compared to human expert assessment. We next investigated the feasibility of pre-trained convolutional neural networks in analysis of breast cancer tissue, aiming to quantify tumor-infiltrating lymphocytes in the specimens. Interestingly, our results showed that pre-trained convolutional neural networks can be adapted for analysis of histological image data, outperforming texture analysis. The results also indicated that the computerized assessment was on par with pathologist assessments. Moreover, the study presented an image annotation technique guided by specific antibody staining for improved ground-truth labeling. Direct outcome prediction in breast cancer was then studied using a nationwide patient cohort. A computerized pipeline, which incorporated orderless feature aggregation and convolutional image descriptors for outcome-supervised classification, resulted in a risk grouping that was predictive of both disease-specific and overall survival. Surprisingly, further analysis suggested that the computerized risk prediction was also an independent prognostic factor that provided information complementary to the standard clinicopathological factors. This doctoral thesis demonstrated how computer-vision methods can be powerful tools in analysis of cancer tissue samples, highlighting strategies for supervised characterization of tissue entities and an approach for identification of novel prognostic morphological features.

KW - Neoplasms

KW - +diagnosis

KW - Breast Neoplasms

KW - Lung Neoplasms

KW - Artificial Intelligence

KW - Supervised Machine Learning

KW - Deep Learning

KW - Heterografts

KW - Lymphocytes, Tumor-Infiltrating

KW - Neural Networks (Computer)

KW - Survival Analysis

KW - 3122 Cancers

M3 - Doctoral Thesis

SN - 978-951-51-4397-6

T3 - Dissertationes Scholae Doctoralis Ad Sanitatem Investigandam Universitatis Helsinkiensis

PB - Helsingin yliopisto

CY - Helsinki

ER -

Turkki R. Computer vision for tissue characterization and outcome prediction in cancer. Helsinki: Helsingin yliopisto, 2018. 66 p. (Dissertationes Scholae Doctoralis Ad Sanitatem Investigandam Universitatis Helsinkiensis; 50/2018 ).