Published April 27, 2022 | Version v1
Miscellaneous Metadata-only

Radiotracer uptake classification using deep learning for evaluation of image-derived cancer biomarkers in PET/CT

Creators

Description

Accurate assessment of disease spread is crucial in the care of cancer patients, and medical imaging is frequently used as noninvasive diagnostic tool. This dissertation presents methods for the analysis of positron emission tomography (PET) / computed tomography (CT) images in oncology. A deep learning method for classification of image regions with elevated radiotracer uptake is described and shown to support the evaluation of image-derived biomarkers such as cancer stage and tumor burden.

Availability note (English)

Available from: https://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:91-diss-20220622-1624506-1-9

Additional details

Identifiers

URL
https://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:91-diss-20220622-1624506-1-9;

Publishing Information

Imprint Pagination
101 p.

INIS

Country of Publication
Germany
Country of Input or Organization
Germany
INIS RN
55002810
Subject category
S62: RADIOLOGY AND NUCLEAR MEDICINE;
Resource subtype / Literary indicator
Thesis, Non-conventional Literature
Descriptors DEI
BIOLOGICAL MARKERS; CARCINOMAS; CLASSIFICATION; IMAGE PROCESSING; MACHINE LEARNING; POSITRON COMPUTED TOMOGRAPHY; RADIOPHARMACEUTICALS; TRACER TECHNIQUES; UPTAKE
Descriptors DEC
ALGORITHMS; ARTIFICIAL INTELLIGENCE; COMPUTERIZED TOMOGRAPHY; DIAGNOSTIC TECHNIQUES; DISEASES; DRUGS; EMISSION COMPUTED TOMOGRAPHY; ISOTOPE APPLICATIONS; LABELLED COMPOUNDS; LEARNING; MATERIALS; MATHEMATICAL LOGIC; NEOPLASMS; PROCESSING; RADIOACTIVE MATERIALS; TOMOGRAPHY