Toward Precision Diagnosis: Machine Learning in Identifying Malignant Orbital Tumors With Multiparametric 3 T MRI.

BACKGROUND: Orbital tumors present a diagnostic challenge due to their varied locations and histopathological differences. Although recent advancements in imaging have improved diagnosis, classification remains a challenge. The integration of artificial intelligence in radiology and ophthalmology has demonstrated promising outcomes. PURPOSE: This study aimed to evaluate the performance of machine learning models in accurately distinguishing malignant orbital tumors from benign ones using multiparametric 3 T magnetic resonance imaging (MRI) data. MATERIALS AND METHODS: In this single-center prospective study, patients with orbital masses underwent presurgery 3 T MRI scans between December 2015 and May 2021. The MRI protocol comprised multiparametric imaging including dynamic contrast-enhanced (DCE), diffusion-weighted imaging (DWI), intravoxel incoherent motion (IVIM), as well as morphological imaging acquisitions. A repeated nested cross-validation strategy using random forest classifiers was used for model training and evaluation, considering 8 combinations of explanatory features. Shapley additive explanations (SHAP) values were used to assess feature contributions, and the model performance was evaluated using multiple metrics. RESULTS: One hundred thirteen patients were analyzed (57/113 [50.4%] were women; average age was 51.5 ± 17.5 years, range: 19-88 years). Among the 8 combinations of explanatory features assessed, the performance on predicting malignancy when using the most comprehensive model, which is the most exhaustive one incorporating all 46 explanatory features-including morphology, DWI, DCE, and IVIM, achieved an area under the curve of 0.9 [0.73-0.99]. When using the streamlined "10-feature signature" model, performance reached an area under the curve of 0.88 [0.71-0.99]. Random forest feature importance graphs measured by the mean of SHAP values pinpointed the 10 most impactful features, which comprised 3 quantitative IVIM features, 4 quantitative DCE features, 1 quantitative DWI feature, 1 qualitative DWI feature, and age. CONCLUSIONS: Our findings demonstrate that a machine learning approach, integrating multiparametric MRI data such as DCE, DWI, IVIM, and morphological imaging, offers high-performing models for differentiating malignant from benign orbital tumors. The streamlined 10-feature signature, with a performance close to the comprehensive model, may be more suitable for clinical application.

Incidence and Outcomes of Eye Trauma Associated With Recreative Use of Nonpowder Toy Guns: A 12-Year Retrospective Study.

PURPOSE: Nonpowder toy guns (NPTGs) are responsible for many ocular traumas. This study aims to detail the outcomes of these injuries depending on the causative NPTG. DESIGN: Retrospective, observational case series. METHODS: Cases of NPTG-associated ocular trauma managed in a Parisian eye emergency department between August 1, 2010, and January 1, 2023, were reviewed. The date of trauma, causative NPTG, patient demographics, initial and follow-up eye examinations, any surgical procedure, and visual outcomes for each ocular trauma were analyzed. RESULTS: Over 12 years, NPTGs were responsible for 324 eye injuries and 980 visits. Patients were mostly male (77.5%), and mean age at trauma was 16.2 years. Foam bullets or foam dart blasters accounted for 54.9% of traumas and were mainly responsible for corneal injuries and hyphema (30.9% and 27%, respectively). BB guns and airsoft guns were frequently responsible for anterior segment lesions, as well as intravitreal hemorrhages (14.7%) and commotio retinae (21.1%). Paintball guns accounted for the largest proportion of posterior segment lesions (eg, intraretinal or subretinal hemorrhages leading to macular atrophy/contusion maculopathy), and one-third of casualties had undergone ocular surgery. Among all traumas, final visual acuity was lower than 20/200 in 6.5% of cases. Phthisis occurred in 8 cases: Two were related to foam bullets or foam dart blaster injuries (1 contusion and 1 rupture), 2 other cases followed a rupture due to BB guns/airsoft guns, 1 case occurred after a rupture related to a paintball gunshot, and 3 others were due to other types of compressed air guns (1 rupture, 1 intraocular foreign body, and 1 total retinal detachment). CONCLUSIONS: NPTG-related ocular trauma outcomes differ according to the causative toy. Paintball guns and BB guns/airsoft gun-related traumas were more likely to be associated with severe lesions, but an increasing number of ocular injuries related to the use of foam bullets or foam dart blasters are reported in younger and younger children. Public health policies should promote the use of protective eyewear.