Automatic Segmentation of the Eye in 3D Magnetic Resonance Imaging: A Novel Statistical Shape Model for Treatment Planning of Retinoblastoma

Ciller, Carlos; Zanet, Sandro I. De; Rüegsegger, Michael B.; Pica, Alessia; Sznitman, Raphael; Thiran, Jean‐Philippe; Maeder, Philippe; Munier, Francis L.; Kowal, Jens; Cuadra, Meritxell Bach

doi:10.1016/j.ijrobp.2015.02.056

Cited by 21 publications

(30 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that this model is trained exclusively on pathological eye MRI data, in contrast to our previous work [15, 16]. This model aims at delineating the regions of the sclera, the cornea, the lens and the vitreous humor in an automatic fashion.…”

Section: Methodsmentioning

confidence: 99%

“…Following the landmark-based registration described in [15, 18], we detect the center of the VH, the center of the lens and the optic disc and use this information to align the eyes to a common coordinate system. This pre-processing allows us to form a coherent dataset representing the same anatomical regions across subjects.…”

Section: Methodsmentioning

confidence: 99%

“…Also, other approaches such as the one presented by Beenakker et al [13] aimed at measuring the three-dimensional shape of the retina to study abnormal shape changes and peripheral vision. Along this lines, Active Shape Models (ASMs), originally introduced by Cootes et al [14] have recently been proposed by our group to more precisely delineate eye anatomy using T1w Volumetric Interpolated Brain Examination (VIBE) MR and CT images [15, 16]. In that work, the main goal was to delineate healthy eye structures, but the challenge of eye tumor delineation has yet to be addressed.…”

Section: Introductionmentioning

confidence: 99%

“…We present a set of eye delineation techniques in 3D MRI, both for healthy structures and for pathological tissue. In a nutshell, our contributions can be summarized as follows: We present a new Pathological Model (PM) of the eye, built out of pathological patient eyes and compare the results with the Healthy Model (HM) presented in [15], achieving better healthy tissue segmentation performance.We introduce novel EPSF, derived from our pathological Active Shape Model (ASM), which help characterize pathological tissue, even when only small amounts of training data is available.We introduce a novel automatic segmentation framework tailored to ocular tumors. Similar to top ranking algorithms for brain tumor segmentation [17], our method makes use of a Markov Random Field (MRF) to represent the presence of healthy and pathological tissue, allowing for both local and neighborhood information to be utilized in a joint manner.…”

Section: Introductionmentioning

confidence: 99%

“…We present a new Pathological Model (PM) of the eye, built out of pathological patient eyes and compare the results with the Healthy Model (HM) presented in [15], achieving better healthy tissue segmentation performance.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Multi-channel MRI segmentation of eye structures and tumors using patient-specific features

et al. 2017

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Multi-channel MRI segmentation of eye structures and tumors using patient-specific features

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

Sexual Dimorphism and Population Affinity in the Human Zygomatic Structure—Comparing Surface to Outline Data

Schlager

Rüdell

2016

The Anatomical Record

View full text Add to dashboard Cite

The human zygomatic structure, consisting of the zygomatic bone and the zygomatic process of the temporal bone, is an essential part of the masticatory apparatus and has been shown to reflect population history and sexual dimorphism to varying degrees. In this study, we analyzed the predictive value of the outlines vs. the complete surface shape of the zygomatic bone in a sample of 98 Chinese (50 $, 48 #) and 96 Germans (49 $, 47 #). We first applied a surface registration process based on statistical shape modeling. A dense set of 1,480 pseudo-landmarks was then sampled automatically from the surface of the pooled mean shape and three curves were digitized manually along the outlines of the zygomatic bone. Both sets of pseudo-landmarks were automatically transferred to all specimens. Analysis of sex and population affinity showed both factors to be independently significant, but the interaction between them was not. Population affinity could be predicted quite accurately with correct classification of 97.9% using the surface data and 93.3% with the curve data. Sexual dimorphism was less distinct with 89.2% correct sex determination when using surface information compared with 77.8% when using the curve data. Population-related shape differences were captured primarily in the outlines, while sexual dimorphism is distributed more uniformly throughout the entire surface of the zygomatic structure. Anat Rec, 300:226-237,

show abstract

Three‐dimensional MRI‐based treatment planning approach for non‐invasive ocular proton therapy

et al. 2021

View full text Add to dashboard Cite

Purpose To develop a high‐resolution three‐dimensional (3D) magnetic resonance imaging (MRI)‐based treatment planning approach for uveal melanomas (UM) in proton therapy. Materials/methods For eight patients with UM, a segmentation of the gross tumor volume (GTV) and organs‐at‐risk (OARs) was performed on T1‐ and T2‐weighted 7 Tesla MRI image data to reconstruct the patient MR‐eye. An extended contour was defined with a 2.5‐mm isotropic margin derived from the GTV. A broad beam algorithm, which we have called πDose, was implemented to calculate relative proton absorbed doses to the ipsilateral OARs. Clinically favorable gazing angles of the treated eye were assessed by calculating a global weighted‐sum objective function, which set penalties for OARs and extreme gazing angles. An optimizer, which we have named OPT’im‐Eye‐Tool, was developed to tune the parameters of the functions for sparing critical‐OARs. Results In total, 441 gazing angles were simulated for every patient. Target coverage including margins was achieved in all the cases (V95% > 95%). Over the whole gazing angles solutions space, maximum dose (Dmax) to the optic nerve and the macula, and mean doses (Dmean) to the lens, the ciliary body and the sclera were calculated. A forward optimization was applied by OPT’im‐Eye‐Tool in three different prioritizations: iso‐weighted, optic nerve prioritized, and macula prioritized. In each, the function values were depicted in a selection tool to select the optimal gazing angle(s). For example, patient 4 had a T2 equatorial tumor. The optimization applied for the straight gazing angle resulted in objective function values of 0.46 (iso‐weighted situation), 0.90 (optic nerve prioritization) and 0.08 (macula prioritization) demonstrating the impact of that angle in different clinical approaches. Conclusions The feasibility and suitability of a 3D MRI‐based treatment planning approach have been successfully tested on a cohort of eight patients diagnosed with UM. Moreover, a gaze‐angle trade‐off dose optimization with respect to OARs sparing has been developed. Further validation of the whole treatment process is the next step in the goal to achieve both a non‐invasive and a personalized proton therapy treatment.

show abstract

Automatic Segmentation of the Eye in 3D Magnetic Resonance Imaging: A Novel Statistical Shape Model for Treatment Planning of Retinoblastoma

Cited by 21 publications

References 27 publications

Multi-channel MRI segmentation of eye structures and tumors using patient-specific features

Multi-channel MRI segmentation of eye structures and tumors using patient-specific features

Sexual Dimorphism and Population Affinity in the Human Zygomatic Structure—Comparing Surface to Outline Data

Three‐dimensional MRI‐based treatment planning approach for non‐invasive ocular proton therapy

Contact Info

Product

Resources

About