Towards Detecting High-Uptake Lesions from Lung CT Scans Using Deep Learning
| Autor: | Balaji Ganeshan, Sarah J. McQuaid, Michal Kawulok, Michael P. Hayball, Jakub Nalepa, Krzysztof Pawełczyk, Vineet Prakash |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
medicine.medical_specialty
Lung medicine.diagnostic_test business.industry Deep learning Computed tomography 02 engineering and technology medicine.disease 030218 nuclear medicine & medical imaging High uptake 03 medical and health sciences Tumour tissue 0302 clinical medicine medicine.anatomical_structure Positron emission tomography High glucose 0202 electrical engineering electronic engineering information engineering medicine 020201 artificial intelligence & image processing Artificial intelligence Radiology business Lung cancer |
| Zdroj: | Image Analysis and Processing-ICIAP 2017 ISBN: 9783319685472 ICIAP (2) |
| DOI: | 10.1007/978-3-319-68548-9_29 |
| Popis: | Automatic detection of lung lesions from computed tomography (CT) and positron emission tomography (PET) is an important task in lung cancer diagnosis. While CT scans make it possible to retrieve structural information, PET images reveal the functional aspects of the tissue, hence combined PET/CT imagery allows for detecting metabolically active lesions. In this paper, we explore how to exploit deep convolutional neural networks to identify the active tumour tissue exclusively from CT scans, which, to the best of our knowledge, has not been attempted yet. Our experimental results are very encouraging and they clearly indicate the possibility of detecting lesions with high glucose uptake, which could increase the utility of CT in lung cancer diagnosis. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|