Abstract
Retinoblastoma and uveal melanoma are fast spreading eye tumors usually diagnosed by using 2D Fundus Image Photography (Fundus) and 2D Ultrasound (US). Diagnosis and treatment planning of such diseases often require additional complementary imaging to confirm the tumor extend via 3D Magnetic Resonance Imaging (MRI). In this context, having automatic segmentations to estimate the size and the distribution of the pathological tissue would be advantageous towards tumor characterization. Until now, the alternative has been the manual delineation of eye structures, a rather time consuming and error-prone task, to be conducted in multiple MRI sequences simultaneously. This situation, and the lack of tools for accurate eye MRI analysis, reduces the interest in MRI beyond the qualitative evaluation of the optic nerve invasion and the confirmation of recurrent malignancies below calcified tumors. In this manuscript, we propose a new framework for the automatic segmentation of eye structures and ocular tumors in multi-sequence MRI. Our key contribution is the introduction of a pathological eye model from which Eye Patient-Specific Features (EPSF) can be computed. These features combine intensity and shape information of pathological tissue while embedded in healthy structures of the eye. We assess our work on a dataset of pathological patient eyes by computing the Dice Similarity Coefficient (DSC) of the sclera, the cornea, the vitreous humor, the lens and the tumor. In addition, we quantitatively show the superior performance of our pathological eye model as compared to the segmentation obtained by using a healthy model (over 4% DSC) and demonstrate the relevance of our EPSF, which improve the final segmentation regardless of the classifier employed.
Highlights
Common forms of ocular cancer are related to high morbidity and mortality rates [1]
We present a set of eye delineation techniques in 3D Magnetic Resonance Imaging (MRI), both for healthy structures and for pathological tissue
From this pathologically-based Active Shape Models (ASMs), we propose the use of Eye Patient-Specific Features (EPSF) to characterize pathological tissue within healthy anatomy
Summary
Common forms of ocular cancer are related to high morbidity and mortality rates [1]. Imaging of these tumors has generally been performed using 2D Fundus imaging, 2D US or 3D Computed Tomography (CT). MRI is becoming a key modality for pre-treatment diagnostics of tumor extent, especially for retinoblastoma in children, and is gaining a great interest for treatment planning with external beam radiotherapy of uveal melanomas in adults Examples of these are the works by Beenakker et al [3] that imaged uveal melanoma at 7-Tesla high-resolution or more recently, measurement comparisons between US and MRI, for assessing tumor dimensions [4]. Treated tumors present second recurrent malignancies under the calcified area, a pathology that can more be observed via MRI [1] In this context, having accurate 3D segmentations of eyes with pathology would help better characterize and quantify intraocular tumors more effectively. This would allow for reliable large-scale longitudinal treatment-response studies but would allow for direct imaging and targeting of tumors during treatment procedures, such as the applied in brachytherapy/cryotherapy to children with retinoblastoma [5]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
