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

Eye Size and Shape in Relation to Refractive Error in Children: A Magnetic Resonance Imaging Study

Purpose

The purpose of this study was to determine the association between eye shape and volume measured with magnetic resonance imaging (MRI) and optical biometry and with spherical equivalent (SE) in children.

Methods

For this study, there were 3637 10-year-old children from a population-based birth-cohort study that underwent optical biometry (IOL-master 500) and T2-weighted MRI scanning (height, width, and volume). Cycloplegic refractive error was determined by automated refraction. The MRI images of the eyes were segmented using an automated algorithm combining atlas registration with voxel classification. Associations among optical biometry, anthropometry, MRI measurements, and RE were tested using Pearson correlation. Differences between refractive error groups were tested using ANOVA.

Results

The mean volume of the posterior segment was 6350 (±680) mm3. Myopic eyes (SE ≤ -0.5 diopters [D]) had 470 mm3 (P < 0.001) and 970 mm3 (P < 0.001) larger posterior segment volume than emmetropic and hyperopic eyes (SE ≥ +2.0D), respectively. The majority of eyes (77.1%) had an oblate shape, but 47.4% of myopic eyes had a prolate shape versus 3.9% of hyperopic eyes. The correlation between SE and MRI-derived posterior segment length (r -0.51, P < 0.001) was stronger than the correlation with height (r -0.30, P < 0.001) or width of the eye (r -0.10, P < 0.001).

Conclusions

In this study, eye shape at 10 years of age was predominantly oblate, even in eyes with myopia. Of all MRI measurements, posterior segment length was most prominently associated with SE. Whether eye shape predicts future myopia development or progression should be investigated in longitudinal studies.

The Segment, Slice, and 3D Print (SS3DP) Workflow of 3D Printing Eye Anatomy for Clinicians: A Proof-of-Concept Study

3D printing is becoming increasingly important as time passes, with the latest technologies driving innovation in many fields, including ophthalmology. However, more is needed to know how clinicians can become innovators in their daily practice without needing expert engineering knowledge of the underlying technologies. We aimed to address that shortcoming by developing a pipeline clinicians can use to 3D print. This workflow was named SS3DP: Segment, Slice, and 3D Print. It was tested by fabricating a 3D-printed eyeball. In terms of the results of this work, we observed that the segmentation process was imperfect due to the difficulty of segmenting small structures. The learning curve was steep initially, but the technique improved the more time spent on the segmentation platform. No quantitative analysis was carried out. Innovation in medicine is stifled if its leading participants, clinicians, cannot engage with it due to a lack of knowledge.

Imaging of Uveal Melanoma—Current Standard and Methods in Development

Simple Summary

Uveal melanoma is the most prevalent intraocular tumor in adults, derived from melanocytes; the liver is the most common site of its metastases. Due to troublesome tumor localization, different imaging techniques are utilized in diagnostics, i.e., fundus imaging (FI), ultrasonography (US), optical coherence tomography (OCT), single-photon emission computed tomography (SPECT), positron emission tomography/computed tomography (PET/CT), magnetic resonance imaging (MRI), fundus fluorescein angiography (FFA), indocyanine green angiography (ICGA), or fundus autofluorescence (FAF). Specialists eagerly use these techniques, but sometimes the precision and quality of the obtained images are imperfect, raising diagnostic doubts and prompting the search for new ones. In addition to analyzing the currently utilized methods, this review also introduces experimental techniques that may be adapted to clinical practice in the future. Moreover, we raise the topic and present a perspective for personalized medicine in uveal melanoma treatment.

Abstract

Uveal melanoma is the most common primary intraocular malignancy in adults, characterized by an insidious onset and poor prognosis strongly associated with tumor size and the presence of distant metastases, most commonly in the liver. Contrary to most tumor identification, a biopsy followed by a pathological exam is used only in certain cases. Therefore, an early and noninvasive diagnosis is essential to enhance patients’ chances for early treatment. We reviewed imaging modalities currently used in the diagnostics of uveal melanoma, including fundus imaging, ultrasonography (US), optical coherence tomography (OCT), single-photon emission computed tomography (SPECT), fundus fluorescein angiography (FFA), indocyanine green angiography (ICGA), fundus autofluorescence (FAF), as well as positron emission tomography/computed tomography (PET/CT) or magnetic resonance imaging (MRI). The principle of imaging techniques is briefly explained, along with their role in the diagnostic process and a summary of their advantages and limitations. Further, the experimental data and the advancements in imaging modalities are explained. We describe UM imaging innovations, show their current usage and development, and explain the possibilities of utilizing such modalities to diagnose uveal melanoma in the future.

An Automatic Framework to Create Patient-specific Eye Models From 3D Magnetic Resonance Images for Treatment Selection in Patients With Uveal Melanoma

PURPOSE

The optimal treatment strategy for uveal melanoma (UM) relies on many factors, the most important being tumor size and location. Building on recent developments in high-resolution 3D ocular magnetic resonance imaging (MRI), we developed an automatic image-processing framework to create patient-specific eye models and to subsequently determine the full 3D tumor shape and size automatically.

METHODS AND MATERIALS

From 15 patients with UM, 3D inversion-recovery gradient-echo (T1-weighted) and 3D fat-suppressed spin-echo (T2-weighted) images were acquired with a 7T MRI scanner. First, the sclera and cornea were segmented from the T2-weighted image by mesh-fitting. The T1- and T2-weighted images were then coregistered. From the registered T1-weighted image, the lens, vitreous body, retinal detachment, and tumor were segmented. Fuzzy C-means clustering was used to differentiate the tumor from retinal detachments. The tumor model was verified and (if needed) edited by an ophthalmic MRI specialist. Subsequently, the prominence and largest basal diameter of the tumor were measured automatically based on the verified contours. These results were compared with manual assessments on the original images and with ultrasound measurements to show the errors in manual analysis.

RESULTS

The framework successfully created an eye model fully automatically in 12 cases. In these cases, a Dice similarity coefficient (mean surface distance) of 97.7%±0.84% (0.17±0.11 mm) was achieved for the sclera, 96.8%±1.05% (0.20±0.06 mm) for the vitreous body, 91.6%±4.83% (0.15±0.06 mm) for the lens, and 86.0%±7.4% (0.35±0.27 mm) for the tumor. The manual assessments deviated, on average, 0.39±0.31 mm in prominence and 1.7±1.22 mm in basal diameter from the automatic measurements.

CONCLUSIONS

The described framework combined information from T1- and T2-weighted images to accurately determine tumor boundaries in 3D. The proposed process may have a direct effect on clinical workflow, as it enables an accurate 3D assessment of tumor dimensions, which directly influences therapy selection.

Characterization of the HollandPTC proton therapy beamline dedicated to uveal melanoma treatment and an interinstitutional comparison

PURPOSE

Eye-dedicated proton therapy (PT) facilities are used to treat malignant intraocular lesions, especially uveal melanoma (UM). The first commercial ocular PT beamline from Varian was installed in the Netherlands. In this work, the conceptual design of the new eyeline is presented. In addition, a comprehensive comparison against five PT centers with dedicated ocular beamlines is performed, and the clinical impact of the identified differences is analyzed.

MATERIAL/METHODS

The HollandPTC eyeline was characterized. Four centers in Europe and one in the United States joined the study. All centers use a cyclotron for proton beam generation and an eye-dedicated nozzle. Differences among the chosen ocular beamlines were in the design of the nozzle, nominal energy, and energy spectrum. The following parameters were collected for all centers: technical characteristics and a set of distal, proximal, and lateral region measurements. The measurements were performed with detectors available in-house at each institution. The institutions followed the International Atomic Energy Agency (IAEA) Technical Report Series (TRS)-398 Code of Practice for absolute dose measurement, and the IAEA TRS-398 Code of Practice, its modified version or International Commission on Radiation Units and Measurements Report No. 78 for spread-out Bragg peak normalization. Energy spreads of the pristine Bragg peaks were obtained with Monte Carlo simulations using Geant4. Seven tumor-specific case scenarios were simulated to evaluate the clinical impact among centers: small, medium, and large UM, located either anteriorly, at the equator, or posteriorly within the eye. Differences in the depth dose distributions were calculated.

RESULTS

A pristine Bragg peak of HollandPTC eyeline corresponded to the constant energy of 75 MeV (maximal range 3.97 g/cm2 in water) with an energy spread of 1.10 MeV. The pristine Bragg peaks for the five participating centers varied from 62.50 to 104.50 MeV with an energy spread variation between 0.10 and 0.70 MeV. Differences in the average distal fall-offs and lateral penumbrae (LPs) (over the complete set of clinically available beam modulations) among all centers were up to 0.25 g/cm2 , and 0.80 mm, respectively. Average distal fall-offs of the HollandPTC eyeline were 0.20 g/cm2 , and LPs were between 1.50 and 2.15 mm from proximal to distal regions, respectively. Treatment time, around 60 s, was comparable among all centers. The virtual source-to-axis distance of 120 cm at HollandPTC was shorter than for the five participating centers (range: 165-350 cm). Simulated depth dose distributions demonstrated the impact of the different beamline characteristics among institutions. The largest difference was observed for a small UM located at the posterior pole, where a proximal dose between two extreme centers was up to 20%.

CONCLUSIONS

HollandPTC eyeline specifications are in accordance with five other ocular PT beamlines. Similar clinical concepts can be applied to expect the same high local tumor control. Dosimetrical properties among the six institutions induce most likely differences in ocular radiation-related toxicities. This interinstitutional comparison could support further research on ocular post-PT complications. Finally, the findings reported in this study could be used to define dosimetrical guidelines for ocular PT to unify the concepts among institutions.

Multi-view convolutional neural networks for automated ocular structure and tumor segmentation in retinoblastoma

In retinoblastoma, accurate segmentation of ocular structure and tumor tissue is important when working towards personalized treatment. This retrospective study serves to evaluate the performance of multi-view convolutional neural networks (MV-CNNs) for automated eye and tumor segmentation on MRI in retinoblastoma patients. Forty retinoblastoma and 20 healthy-eyes from 30 patients were included in a train/test (N = 29 retinoblastoma-, 17 healthy-eyes) and independent validation (N = 11 retinoblastoma-, 3 healthy-eyes) set. Imaging was done using 3.0 T Fast Imaging Employing Steady-state Acquisition (FIESTA), T2-weighted and contrast-enhanced T1-weighted sequences. Sclera, vitreous humour, lens, retinal detachment and tumor were manually delineated on FIESTA images to serve as a reference standard. Volumetric and spatial performance were assessed by calculating intra-class correlation (ICC) and dice similarity coefficient (DSC). Additionally, the effects of multi-scale, sequences and data augmentation were explored. Optimal performance was obtained by using a three-level pyramid MV-CNN with FIESTA, T2 and T1c sequences and data augmentation. Eye and tumor volumetric ICC were 0.997 and 0.996, respectively. Median [Interquartile range] DSC for eye, sclera, vitreous, lens, retinal detachment and tumor were 0.965 [0.950-0.975], 0.847 [0.782-0.893], 0.975 [0.930-0.986], 0.909 [0.847-0.951], 0.828 [0.458-0.962] and 0.914 [0.852-0.958], respectively. MV-CNN can be used to obtain accurate ocular structure and tumor segmentations in retinoblastoma.

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

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.

Ophthalmic Magnetic Resonance Imaging: Where Are We (Heading To)?

Magnetic resonance imaging of the eye and orbit (MReye) is a cross-domain research field, combining (bio)physics, (bio)engineering, physiology, data sciences and ophthalmology. A growing number of reports document technical innovations of MReye and promote their application in preclinical research and clinical science. Realizing the progress and promises, this review outlines current trends in MReye. Examples of MReye strategies and their clinical relevance are demonstrated. Frontier applications in ocular oncology, refractive surgery, ocular muscle disorders and orbital inflammation are presented and their implications for explorations into ophthalmic diseases are provided. Substantial progress in anatomically detailed, high-spatial resolution MReye of the eye, orbit and optic nerve is demonstrated. Recent developments in MReye of ocular tumors are explored, and its value for personalized eye models derived from machine learning in the treatment planning of uveal melanoma and evaluation of retinoblastoma is highlighted. The potential of MReye for monitoring drug distribution and for improving treatment management and the assessment of individual responses is discussed. To open a window into the eye and into (patho)physiological processes that in the past have been largely inaccessible, advances in MReye at ultrahigh magnetic field strengths are discussed. A concluding section ventures a glance beyond the horizon and explores future directions of MReye across multiple scales, including in vivo electrolyte mapping of sodium and other nuclei. This review underscores the need for the (bio)medical imaging and ophthalmic communities to expand efforts to find solutions to the remaining unsolved problems and technical obstacles of MReye, with the objective to transfer methodological advancements driven by MR physics into genuine clinical value.

Automation in intensity modulated radiotherapy treatment planning-a review of recent innovations

Radiotherapy treatment planning of complex radiotherapy techniques, such as intensity modulated radiotherapy and volumetric modulated arc therapy, is a resource-intensive process requiring a high level of treatment planner intervention to ensure high plan quality. This can lead to variability in the quality of treatment plans and the efficiency in which plans are produced, depending on the skills and experience of the operator and available planning time. Within the last few years, there has been significant progress in the research and development of intensity modulated radiotherapy treatment planning approaches with automation support, with most commercial manufacturers now offering some form of solution. There is a rapidly growing number of research articles published in the scientific literature on the topic. This paper critically reviews the body of publications up to April 2018. The review describes the different types of automation algorithms, including the advantages and current limitations. Also included is a discussion on the potential issues with routine clinical implementation of such software, and highlights areas for future research.

Personalized Anatomic Eye Model From T1-Weighted Volume Interpolated Gradient Echo Magnetic Resonance Imaging of Patients With Uveal Melanoma

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.

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

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, 2017. © 2016 Wiley Periodicals, Inc.

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

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.