University of Patras
Μελέτη με MRI μετακτινικών αλλοιώσεων στα οστά ασθενών με μεταστατικούς ή πρωτοπαθείς όγκους που υποβάλλονται σε ακτινοθεραπεία
Abstract
dc:descriptionINTRODUCTION - OBJECTIVES:Bone marrow can be affected by lymphoproliferative disorders and metastatic disease but also byseveral therapeutic approaches. MRI is the most suitable method for the detection of metastases andpost-treatment follow-up. Image analysis techniques are now used to extract additional diagnosticinformation. This study focuses on the early radiation-induced changes that can be detected by MRIand compares the established methods for the identification and characterization of these lesions withan automated classification system.METHODS: 36 patients with histologically confirmed primary malignancy and associated bonemetastases were included in the study. All patients underwent radiation therapy (RT) to treat bonemetastases to the spinal column or the pelvis. Magnetic resonance imaging (MRI) was performed justbefore the start of RT, 12 to 18 days and up to 3 months after the start of RT. Images were obtained within, adjacent and outside the radiation field. Qualitative assessment was performed independentlyby two experienced radiologists. For quantitative assessment, specific measurements were selectedand evaluated by the method of the region of interest (ROI). In addition, textural features of 1st and 2ndclass were exported and inserted into a probabilistic neural network classifier, in order to create anautomatic classification system for these lesions.RESULTS: Following qualitative and quantitative assessment, within the radiation field, 22.22% and33.33% of patients respectively showed fatty conversion of the bone marrow, 19.44% and 16.67% ofpatients showed haemorrhage, while 11.11% and 16.67% of the patients demonstrated bone marrowoedema. Adjacent to the radiation field, 11.11% and 19.44% of patients showed fatty conversion,8.33% showed haemorrhage, while 2.78% and 8.33% demonstrated bone marrow oedema. Outside ofthe radiation field, 5.56% of patients showed changes compatible with fatty conversion, while theremaining 94.44% showed no significant change.There was no statistically significant change of the enhancement index after gadolinium administration.In multivariate analysis, none of the studied parameters did not appear to affect significantly theappearance of any of the radiation-induced lesions.The largest overall classification accuracy of the system designed to distinguish between the preradiationand radiation-induced images was 93.02% using the LSFT-PNN classification system ofmultiple sequences and the ECV method. Discrimination accuracy of the classification systemdesigned to distinguish between the three main types of post-radiation lesions was 86.67%.CONCLUSIONS: This study shows that a significant proportion of patients undergoing RT willexperience at least one of the common radiation-induced bone marrow changes. Fatty marrowconversion is the most often featured change in the examined period. Qualitative analysis of the MRIimages lacks sensitivity comparing to quantitative measurements. The proposed classification system,based on the neural network, can be used as a very helpful tool for the characterization of theselesions.
Degree
thesis:*- Grantor dc:publisher
- University of Patras
- Year dc:date
- 2013
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Romanos, Odyssefs
- Ρωμανός, Οδυσσεύς
Subjects
dc:subject × 16- Οστικές μεταστάσεις
- Ακτινοθεραπεία
- Μαγνητική τομογραφία
- Συστήματα αναγνώρισης προτύπων
- Πιθανοκρατικά νευρωνικά δίκτυα
- Bone metastases
- Radiation therapy
- Magnetic resonance imaging
- Pattern recognition
- Probabilistic neural networks
- Ιατρική και Επιστήμες Υγείας
- Κλινική Ιατρική
- Άλλες Ιατρικές Επιστήμες
- Medical and Health Sciences
- Clinical Medicine
- Other Medical Sciences
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/36310