Convolutional Neural Networks Cascade for Automatic Pupil and Iris Detection in Ocular Proton Therapy

Abstract

Eye tracking techniques based on deep learning are rapidly spreading in a wide variety of application fields. With this study, we want to exploit the potentiality of eye tracking techniques in ocular proton therapy (OPT) applications. We implemented a fully automatic approach based on two-stage convolutional neural networks (CNNs): the first stage roughly identifies the eye position and the second one performs a fine iris and pupil detection. We selected 707 video frames recorded during clinical operations during OPT treatments performed at our institute. 650 frames were used for training and 57 for a blind test. The estimations of iris and pupil were evaluated against the manual labelled contours delineated by a clinical operator. For iris and pupil predictions, Dice coefficient (median = 0.94 and 0.97), Szymkiewicz–Simpson coefficient (median = 0.97 and 0.98), Intersection over Union coefficient (median = 0.88 and 0.94) and Hausdorff distance (median = 11.6 and 5.0 (pixels)) were quantified. Iris and pupil regions were found to be comparable to the manually labelled ground truths. Our proposed framework could provide an automatic approach to quantitatively evaluating pupil and iris misalignments, and it could be used as an additional support tool for clinical activity, without impacting in any way with the consolidated routine.

Assessment of the Effect of Cleanliness on the Visual Inspection of Aircraft Engine Blades: An Eye Tracking Study

“…The technology has improved in accuracy and usefulness [ 39 , 40 , 41 ], enabling widespread application. Examples of areas of application are health and safety [ 36 ], retail [ 42 , 43 ], medical [ 44 , 45 , 46 ], education [ 47 , 48 , 49 ], neuroscience and psychology [ 50 , 51 ], marketing and advertisement [ 52 ], conservation and animal welfare [ 53 ], construction [ 54 ], automotive [ 55 ], aerospace [ 54 , 56 ], maritime [ 54 ], consumer electronics [ 57 , 58 ], tourism [ 59 ] and security [ 60 ]. Eye tracking helps illuminate the visual processes of perception [ 36 , 61 ], task-specific human behaviour [ 62 ] and cognitive processing during complex tasks [ 62 , 63 ].…”

Non-Cancer Effects following Ionizing Irradiation Involving the Eye and Orbit

“…Once a fraction is initiated, the gaze angle should be maintained identical (and eyelids remain in the same position using retractors from one fraction to another) during the whole duration of irradiation in a given session. This requires additional in-room devices, not interfering with the beams, that could image the pupil or limbus with a video camera and that instantaneous beam interruption be feasible [ 16 ]. Without gating or tracking techniques, larger margins are added around the tumor.…”

Ultrasonic tomography imaging enhancement approach based on deep convolutional neural networks

“…The increasing use of deep learning in computer vision applications is due to the advancements in deep learning architecture, including the popularly used U-Net (Siddique et al 2021 ; Malikov et al 2022 ). U-Net is mainly adopted within medical imaging and specifically created for image segmentation (Antonioli et al 2021 ). The encoder and decoder architecture are used in the U-Net model and image segmentation allows automatically detecting the particular objects in the image (Wu et al 2021 ).…”