Binocular vision supports the development of scene segmentation capabilities: Evidence from a deep learning model.
Ontology highlight
ABSTRACT:
SUBMITTER: Goutcher R
PROVIDER: S-EPMC8300045 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Polyps are well-known cancer precursors identified by colonoscopy. However, variability in their size, appearance, and location makes the detection of polyps challenging. Moreover, colonoscopy surveillance and removal of polyps are highly operator-dependent procedures and occur in a highly complex organ topology. There exists a high missed detection rate and incomplete removal of colonic polyps. To assist in clinical procedures and reduce missed rates, automated methods for detecting and segmenting polyps using machine learning have been achieved in past years. However, the major drawback in most of these methods is their ability to generalise to out-of-sample unseen datasets from different centres, populations, modalities, and acquisition systems. To test this hypothesis rigorously, we, together with expert gastroenterologists, curated a multi-centre and multi-population dataset acquired from six different colonoscopy systems and challenged the computational expert teams to develop robust automated detection and segmentation methods in a crowd-sourcing Endoscopic computer vision challenge. This work put forward rigorous generalisability tests and assesses the usability of devised deep learning methods in dynamic and actual clinical colonoscopy procedures. We analyse the results of four top performing teams for the detection task and five top performing teams for the segmentation task. Our analyses demonstrate that the top-ranking teams concentrated mainly on accuracy over the real-time performance required for clinical applicability. We further dissect the devised methods and provide an experiment-based hypothesis that reveals the need for improved generalisability to tackle diversity present in multi-centre datasets and routine clinical procedures.
| S-EPMC10805888 | biostudies-literature
Project description:Amblyopia is the most common cause of monocular visual loss in children, affecting 1.3%-3.6% of children. Current treatments are effective in reducing the visual acuity deficit but many amblyopic individuals are left with residual visual acuity deficits, ocular motor abnormalities, deficient fine motor skills, and risk for recurrent amblyopia. Using a combination of psychophysical, electrophysiological, imaging, risk factor analysis, and fine motor skill assessment, the primary role of binocular dysfunction in the genesis of amblyopia and the constellation of visual and motor deficits that accompany the visual acuity deficit has been identified. These findings motivated us to evaluate a new, binocular approach to amblyopia treatment with the goals of reducing or eliminating residual and recurrent amblyopia and of improving the deficient ocular motor function and fine motor skills that accompany amblyopia.
| S-EPMC3577063 | biostudies-literature
Project description:There have been few anatomical structure segmentation studies using deep learning. Numbers of training and ground truth images applied were small and the accuracies of which were low or inconsistent. For a surgical video anatomy analysis, various obstacles, including a variable fast-changing view, large deformations, occlusions, low illumination, and inadequate focus occur. In addition, it is difficult and costly to obtain a large and accurate dataset on operational video anatomical structures, including arteries. In this study, we investigated cerebral artery segmentation using an automatic ground-truth generation method. Indocyanine green (ICG) fluorescence intraoperative cerebral videoangiography was used to create a ground-truth dataset mainly for cerebral arteries and partly for cerebral blood vessels, including veins. Four different neural network models were trained using the dataset and compared. Before augmentation, 35,975 training images and 11,266 validation images were used. After augmentation, 260,499 training and 90,129 validation images were used. A Dice score of 79% for cerebral artery segmentation was achieved using the DeepLabv3+ model trained using an automatically generated dataset. Strict validation in different patient groups was conducted. Arteries were also discerned from the veins using the ICG videoangiography phase. We achieved fair accuracy, which demonstrated the appropriateness of the methodology. This study proved the feasibility of operating field view of the cerebral artery segmentation using deep learning, and the effectiveness of the automatic blood vessel ground truth generation method using ICG fluorescence videoangiography. Using this method, computer vision can discern blood vessels and arteries from veins in a neurosurgical microscope field of view. Thus, this technique is essential for neurosurgical field vessel anatomy-based navigation. In addition, surgical assistance, safety, and autonomous surgery neurorobotics that can detect or manipulate cerebral vessels would require computer vision to identify blood vessels and arteries.
| S-EPMC8790180 | biostudies-literature
Project description:The endogenous neurotransmitter acetylcholine (ACh) is known to affect the excitatory/inhibitory (E/I) balance of primate visual cortex, enhancing feedforward thalamocortical gain while suppressing corticocortical synapses. Recent advances in the study of the human visual system suggest that ACh is a likely component underlying interocular interactions. However, our understanding of its precise role in binocular processes is currently lacking. Here we use binocular rivalry as a probe of interocular dynamics to determine ACh's effects, via the acetylcholinesterase inhibitor (AChEI) donepezil, on the binocular visual system. A total of 23 subjects (13 male) completed two crossover experimental sessions where binocular rivalry measurements were obtained before and after taking either donepezil (5 mg) or a placebo (lactose) pill. We report that enhanced cholinergic potentiation attenuates perceptual suppression during binocular rivalry, reducing the overall rate of interocular competition while enhancing the visibility of superimposition mixed percepts. Considering recent evidence that perceptual suppression during binocular rivalry is causally modulated by the inhibitory neurotransmitter GABA, our results suggest that cholinergic activity counteracts the effect of GABA with regards to interocular dynamics and may modulate the inhibitory drive within the visual cortex.SIGNIFICANCE STATEMENT Our research demonstrates that the cholinergic system is implicated in modulating binocular interactions in the human visual cortex. Potentiating the transmission of acetylcholine (ACh) via the cholinergic drug donepezil reduces the extent to which the eyes compete for perceptual dominance when presented two separate, incongruent images.
| S-EPMC7329301 | biostudies-literature
Project description:Stereopsis, the perception of depth based on the disparity of the images projected to the retinas of the two eyes, is an important process in our three-dimensional world; however, 3-5% of the population is stereoblind or has seriously impaired stereovision. Here we provide evidence for the recovery of stereopsis through perceptual learning, the repetitive practice of a demanding visual task, in human adults long deprived of normal binocular vision. We used a training paradigm that combines monocular cues that were correlated perfectly with the disparity cues. Following perceptual learning (thousands of trials) with stereoscopic gratings, five adults who initially were stereoblind or stereoanomalous showed substantial recovery of stereopsis, both on psychophysical tests with stimuli that contained no monocular cues and on clinical testing. They reported that depth "popped out" in daily life, and enjoyed 3D movies for the first time. After training, stereo tests with dynamic random-dot stereograms and band-pass noise revealed the properties of the recovered stereopsis: It has reduced resolution and precision, although it is based on perceiving depth by detecting binocular disparity. We conclude that some human adults deprived of normal binocular vision can recover stereopsis at least partially.
| S-EPMC3174650 | biostudies-literature
Project description:We present a model for the autonomous and simultaneous learning of active binocular and motion vision. The model is based on the Active Efficient Coding (AEC) framework, a recent generalization of classic efficient coding theories to active perception. The model learns how to efficiently encode the incoming visual signals generated by an object moving in 3-D through sparse coding. Simultaneously, it learns how to produce eye movements that further improve the efficiency of the sensory coding. This learning is driven by an intrinsic motivation to maximize the system's coding efficiency. We test our approach on the humanoid robot iCub using simulations. The model demonstrates self-calibration of accurate object fixation and tracking of moving objects. Our results show that the model keeps improving until it hits physical constraints such as camera or motor resolution, or limits on its internal coding capacity. Furthermore, we show that the emerging sensory tuning properties are in line with results on disparity, motion, and motion-in-depth tuning in the visual cortex of mammals. The model suggests that vergence and tracking eye movements can be viewed as fundamentally having the same objective of maximizing the coding efficiency of the visual system and that they can be learned and calibrated jointly through AEC.
| S-EPMC6646586 | biostudies-literature
Project description:The development of binocular vision is an active learning process comprising the development of disparity tuned neurons in visual cortex and the establishment of precise vergence control of the eyes. We present a computational model for the learning and self-calibration of active binocular vision based on the Active Efficient Coding framework, an extension of classic efficient coding ideas to active perception. Under normal rearing conditions with naturalistic input, the model develops disparity tuned neurons and precise vergence control, allowing it to correctly interpret random dot stereograms. Under altered rearing conditions modeled after neurophysiological experiments, the model qualitatively reproduces key experimental findings on changes in binocularity and disparity tuning. Furthermore, the model makes testable predictions regarding how altered rearing conditions impede the learning of precise vergence control. Finally, the model predicts a surprising new effect that impaired vergence control affects the statistics of orientation tuning in visual cortical neurons.
| S-EPMC8445622 | biostudies-literature
Project description:Experience-driven neuronal plasticity allows the brain to adapt its functional connectivity to recent sensory input. Here we use binocular rivalry, an experimental paradigm in which conflicting images are presented to the individual eyes, to demonstrate plasticity in the neuronal mechanisms that convert visual information from two separated retinas into single perceptual experiences. Perception during binocular rivalry tended to initially consist of alternations between exclusive representations of monocularly defined images, but upon prolonged exposure, mixture percepts became more prevalent. The completeness of suppression, reflected in the incidence of mixture percepts, plausibly reflects the strength of inhibition that likely plays a role in binocular rivalry. Recovery of exclusivity was possible but required highly specific binocular stimulation. Documenting the prerequisites for these observed changes in perceptual exclusivity, our experiments suggest experience-driven plasticity at interocular inhibitory synapses, driven by the correlated activity (and also the lack thereof) of neurons representing the conflicting stimuli. This form of plasticity is consistent with a previously proposed but largely untested anti-Hebbian learning mechanism for inhibitory synapses in vision. Our results implicate experience-driven plasticity as one governing principle in the neuronal organization of binocular vision.
| S-EPMC2926173 | biostudies-literature
Project description:Deep learning is rapidly becoming the technique of choice for automated segmentation of nuclei in biological image analysis workflows. In order to evaluate the feasibility of training nuclear segmentation models on small, custom annotated image datasets that have been augmented, we have designed a computational pipeline to systematically compare different nuclear segmentation model architectures and model training strategies. Using this approach, we demonstrate that transfer learning and tuning of training parameters, such as the composition, size, and preprocessing of the training image dataset, can lead to robust nuclear segmentation models, which match, and often exceed, the performance of existing, off-the-shelf deep learning models pretrained on large image datasets. We envision a practical scenario where deep learning nuclear segmentation models trained in this way can be shared across a laboratory, facility, or institution, and continuously improved by training them on progressively larger and varied image datasets. Our work provides computational tools and a practical framework for deep learning-based biological image segmentation using small annotated image datasets. Published [2020]. This article is a U.S. Government work and is in the public domain in the USA.
| S-EPMC8914348 | biostudies-literature
Project description:PurposeThe current understanding of binocular processing is primarily derived from static spatial visual perception: this leaves the role of temporal information unclear. In this study, we addressed this gap by testing the effect of alternating flicker on binocular information processing in adults with abnormal binocular vision. Our goal was to determine which temporal frequency optimally balanced input from both eyes.MethodsWe took measurements in four groups of human adults: 10 normal adults with the individual's nondominant eye covered by a 2% neutral density filter (aged 25.60 ± 1.43 years, experiment 1), 9 nonamblyopic anisometropes (aged 24.33 ± 1.66 years, experiment 2), 7 amblyopes (aged 26.5 ± 1.64 years, experiment 3), and 7 treated amblyopes (aged 24 ± 3.21 years, experiment 4). The balance point (BP), where participants' two eyes are equally effective, was measured using a binocular orientation combination task at four spatial frequencies (SFs; 0.5-4 c/d) and five temporal frequencies (TFs; baseline and 4, 7, 10, and 15 Hz). Its log transformation |logBP| was taken into further analysis.ResultsWe observed clear U-shaped temporal tuning of the |logBP| for the entire range of TFs (that we measured: trough occurred at 7 Hz). This pattern occurred and was significant in all four groups (P < 0.001). In addition, the effect of SFs on |logBP| was significant in normal, amblyopic, and treated amblyopic groups (all P < 0.001) and was marginally significant in the nonamblyopic anisometropic group (P = 0.086).ConclusionsAlternating flicker around 7 Hz may be the optimal temporal frequency for balancing eyes in human adults with binocular imbalance.
| S-EPMC9932553 | biostudies-literature