Huu-Giao Nguyen1, Raphael Sznitman2, Philippe Maeder3, Ann Schalenbourg4, Marta Peroni5, Jan Hrbacek5, Damien C Weber5, Alessia Pica5, Meritxell Bach Cuadra6. 1. Proton Therapy Center, Paul Scherrer Institut, ETH Domain, Villigen, Switzerland; Ophthalmic Technology Laboratory, ARTORG Center of the University of Bern, Bern, Switzerland; Radiology Department, Lausanne University Hospital, Lausanne, Switzerland; Medica Image Analysis Laboratory, Centre d'Imagerie BioMédicale, University of Lausanne, Lausanne, Switzerland. Electronic address: huu.nguyen@artorg.unibe.ch. 2. Ophthalmic Technology Laboratory, ARTORG Center of the University of Bern, Bern, Switzerland. 3. Radiology Department, Lausanne University Hospital, Lausanne, Switzerland. 4. Adult Ocular Oncology Unit, Jules-Gonin Eye Hospital, FAA, Department of Ophthalmology, University of Lausanne, Switzerland. 5. Proton Therapy Center, Paul Scherrer Institut, ETH Domain, Villigen, Switzerland. 6. Radiology Department, Lausanne University Hospital, Lausanne, Switzerland; Medica Image Analysis Laboratory, Centre d'Imagerie BioMédicale, University of Lausanne, Lausanne, Switzerland; Signal Processing Laboratory, Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland.
Abstract
PURPOSE: We present a 3-dimensional patient-specific eye model from magnetic resonance imaging (MRI) for proton therapy treatment planning of uveal melanoma (UM). During MRI acquisition of UM patients, the point fixation can be difficult and, together with physiological blinking, can introduce motion artifacts in the images, thus challenging the model creation. Furthermore, the unclear boundary of the small objects (eg, lens, optic nerve) near the muscle or of the tumors with hemorrhage and tantalum clips can limit model accuracy. METHODS AND MATERIALS: A dataset of 37 subjects, including 30 healthy eyes of volunteers and 7 eyes of UM patients, was investigated. In our previous work, active shape model was successfully applied to retinoblastoma eye segmentation in T1-weighted 3T MRI. Here, we evaluate this method in a more challenging setting, based on 1.5T MRI acquisition and different datasets of awake adult eyes with UM. The lens and cornea together with the sclera, vitreous humor, and optic nerve were automatically segmented and validated against manual delineations of a senior ocular radiation oncologist, in terms of the Dice similarity coefficient and Hausdorff distance. RESULTS: Leave-one-out cross validation (mixing both volunteers and UM patients) yielded median Dice similarity coefficient values (respective of Hausdorff distance) of 94.5% (1.64 mm) for the sclera, 92.2% (1.73 mm) for the vitreous humor, 88.3% (1.09 mm) for the lens, and 81.9% (1.86 mm) for the optic nerve. The average computation time for an eye was 10 seconds. CONCLUSIONS: To our knowledge, our work is the first attempt to automatically segment adult eyes, including patients with UM. Our results show that automated active shape model segmentation can succeed in the presence of motion, tumors, and tantalum clips. These results are promising for inclusion in clinical practice.
PURPOSE: We present a 3-dimensional patient-specific eye model from magnetic resonance imaging (MRI) for proton therapy treatment planning of uveal melanoma (UM). During MRI acquisition of UM patients, the point fixation can be difficult and, together with physiological blinking, can introduce motion artifacts in the images, thus challenging the model creation. Furthermore, the unclear boundary of the small objects (eg, lens, optic nerve) near the muscle or of the tumors with hemorrhage and tantalum clips can limit model accuracy. METHODS AND MATERIALS: A dataset of 37 subjects, including 30 healthy eyes of volunteers and 7 eyes of UM patients, was investigated. In our previous work, active shape model was successfully applied to retinoblastoma eye segmentation in T1-weighted 3T MRI. Here, we evaluate this method in a more challenging setting, based on 1.5T MRI acquisition and different datasets of awake adult eyes with UM. The lens and cornea together with the sclera, vitreous humor, and optic nerve were automatically segmented and validated against manual delineations of a senior ocular radiation oncologist, in terms of the Dice similarity coefficient and Hausdorff distance. RESULTS: Leave-one-out cross validation (mixing both volunteers and UM patients) yielded median Dice similarity coefficient values (respective of Hausdorff distance) of 94.5% (1.64 mm) for the sclera, 92.2% (1.73 mm) for the vitreous humor, 88.3% (1.09 mm) for the lens, and 81.9% (1.86 mm) for the optic nerve. The average computation time for an eye was 10 seconds. CONCLUSIONS: To our knowledge, our work is the first attempt to automatically segment adult eyes, including patients with UM. Our results show that automated active shape model segmentation can succeed in the presence of motion, tumors, and tantalum clips. These results are promising for inclusion in clinical practice.
Authors: Myriam G Jaarsma-Coes; Marina Marinkovic; Eleftheria Astreinidou; Megan S Schuurmans; Femke P Peters; Gregorius P M Luyten; Coen R N Rasch; Jan-Willem M Beenakker Journal: Phys Imaging Radiat Oncol Date: 2020-10-06
Authors: E Fleury; P Trnková; E Erdal; M Hassan; B Stoel; M Jaarma-Coes; G Luyten; J Herault; A Webb; J-W Beenakker; J-P Pignol; M Hoogeman Journal: Med Phys Date: 2021-01-17 Impact factor: 4.071