Visual Research Articles

Research on Key Technologies of Image Steganography Based on Simultaneous Deception of Vision and Deep Learning Models

As machine learning continues to evolve, traditional image steganography techniques find themselves increasingly unable to meet the dual challenge of deceiving both the human visual system and machine learning models. In response, this paper introduces the Visually Robust Image Steganography (VRIS) model, specifically tailored for this dual deception task. The VRIS model elevates visual security through the use of specialized feature extraction and processing methodologies. It meticulously conducts feature-level fusion between secret images and cover images, ensuring a high level of visual similarity between them. To effectively mislead machine learning models, the VRIS model incorporates a sophisticated strategy utilizing random noise factors and discriminators. This involves adding controlled amounts of random Gaussian noise to the encrypted image, thereby enhancing the difficulty for machine learning frameworks to recognize it. Furthermore, the discriminator is trained to discern between the noise-infused encrypted image and the original cover image. Through adversarial training, the discriminator and VRIS model refine each other, successfully deceiving the machine learning systems. Additionally, the VRIS model presents an innovative method for extracting and reconstructing secret images. This approach safeguards secret information from unauthorized access while enabling legitimate users to non-destructively extract and reconstruct images by leveraging multi-scale features from the encrypted image, combined with advanced feature fusion and reconstruction techniques. Experimental results validate the effectiveness of the VRIS model, achieving high PSNR and SSIM scores on the LFW dataset and demonstrating significant deception capabilities against the ResNet50 model on the Mini-ImageNet dataset, with an impressive misclassification rate of 99.24%.

Synapses and dendritic spines are eliminated in the primary visual cortex of mice subjected to chronic intraocular pressure elevation

Synaptic plasticity is essential for maintaining neuronal function in the central nervous system and serves as a critical indicator of the effects of neurodegenerative disease. Glaucoma directly impairs retinal ganglion cells and their axons, leading to axonal transport dysfuntion, subsequently causing secondary damage to anterior or posterior ends of the visual system. Accordingly, recent evidence indicates that glaucoma is a degenerative disease of the central nervous system that causes damage throughout the visual pathway. However, the effects of glaucoma on synaptic plasticity in the primary visual cortex remain unclear. In this study, we established a mouse model of unilateral chronic ocular hypertension by injecting magnetic microbeads into the anterior chamber of one eye. We found that, after 4 weeks of chronic ocular hypertension, the neuronal somas were smaller in the superior colliculus and lateral geniculate body regions of the brain contralateral to the affected eye. This was accompanied by glial cell activation and increased expression of inflammatory factors. After 8 weeks of ocular hypertension, we observed a reduction in the number of excitatory and inhibitory synapses, dendritic spines, and activation of glial cells in the primary visual cortex contralateral to the affected eye. These findings suggest that glaucoma not only directly damages the retina but also induces alterations in synapses and dendritic spines in the primary visual cortex, providing new insights into the pathogenesis of glaucoma.

Anesthetic effects on electrophysiological responses across the visual pathway

Anesthetic effects on electrophysiological responses across the visual pathway

A subjective and objective fusion visual fatigue assessment system for different hardware and software parameters in SSVEP-based BCI applications

A subjective and objective fusion visual fatigue assessment system for different hardware and software parameters in SSVEP-based BCI applications

Less gets more attention: A novel human-centered MR remote collaboration assembly method with information recommendation and visual enhancement

Mixed reality remote collaboration assembly is a type of computer-supported collaborative assembly work that uses mixed reality technology to enable spatial information and collaboration status sharing among geographically distributed collaborators, including remote experts and local users. However, due to the abundance of mixed virtual and real-world information in the MR space and the limitations imposed by narrow field-of-view augmented reality (AR) glasses, users face challenges in effectively focusing on relevant and valuable visual information. Our research aims to enhance users' visual attention to critical guidance information in MR collaborative assembly tasks, thereby improving the clear expression of instructions and facilitating the transmission of collaborative intention. We developed the Information Recommendation and Visual Enhancement System (IRVES) through an assembly process information hierarchy division mechanism, a content-based information recommendation system, and a gesture interaction-based information visual enhancement method. IRVES can leverage the guidance expertise and preferences of remote experts to recommend information to filter out irrelevant information and present the key information that the remote expert conveys to the local user in an intuitive way through visual enhancement. We conducted a user study experiment of a collaborative assembly task of a small engine in a laboratory environment. The experimental results indicate that IRVES outperforms traditional MR remote collaborative assembly methods (VG3DV) in terms of time performance, operational errors, cognitive performance and user experience. Our research contributes a human-centered information visualization approach for remote experts and local users, providing a novel method and idea for designing visual information interfaces in MR remote collaboration assembly tasks.

Functional localization of the human auditory and visual thalamus using a thalamic localizer functional magnetic resonance imaging task

Abstract Functional magnetic resonance imaging (fMRI) of the auditory and visual sensory systems of the human brain is an active area of investigation in the study of human health and disease. The medial geniculate nucleus (MGN) and lateral geniculate nucleus (LGN) are key thalamic nuclei involved in the processing and relay of auditory and visual information, respectively, and are the subject of blood-oxygen-level-dependent (BOLD) fMRI studies of neural activation and functional connectivity in human participants. However, localization of BOLD fMRI signal originating from neural activity in MGN and LGN remains a technical challenge, due, in part, to the poor definition of boundaries of these thalamic nuclei in standard T1-weighted and T2-weighted magnetic resonance imaging sequences. Here, we report the development and evaluation of an auditory and visual sensory thalamic localizer (TL) fMRI task that produces participant-specific functionally-defined regions of interest (fROIs) of both MGN and LGN, using 3 Tesla multiband fMRI and a clustered-sparse temporal acquisition sequence, in less than 16 minutes of scan time. We demonstrate the use of MGN and LGN fROIs obtained from the TL fMRI task in standard resting-state functional connectivity (RSFC) fMRI analyses in the same participants. In RSFC analyses, we validated the specificity of MGN and LGN fROIs for signals obtained from primary auditory and visual cortex, respectively, and benchmarked their performance against alternative atlas- and segmentation-based localization methods. The TL fMRI task and analysis code (written in Presentation and MATLAB, respectively) have been made freely available to the wider research community.

Visible light visual indoor positioning system for based on residual convolutional networks and image restoration

Abstract Visible light positioning technology, with its advantages of low cost, strong anti-interference, and high precision, is widely researched and applied in various different scenarios. In this paper, for the complexity of indoor environments, considering the problem of occlusion by various obstacles that may exist in indoor spaces, which may lead to incomplete imaging of CMOS image sensors, a maximum gray value-based occlusion recovery and decoding scheme is proposed. This scheme effectively solves the problem of visible light transmission channel being blocked and accomplishes LED-ID decoding. In addition, the overflow effect due to uneven light irradiation gathered in each pixel row affects the accuracy of decoding LED-ID, which in turn leads to poor positioning accuracy. In this paper, we propose to use an adaptive gamma correction method to eliminate the influence of the overflow effect and to improve the accuracy of decoding. In order to improve the positioning accuracy, a visible light positioning algorithm based on residual convolutional network (VisiResNet) is proposed to achieve high accuracy positioning. The experimental results show that the average positioning error is 9.7 cm in a space of 9m× 3m× 3m, and a decoding accuracy of 90% within 1.4m is achieved in the face of different occlusion situations. The system can achieve centimeter-level positioning accuracy and meet the indoor positioning requirements.

STUDENTS’ AND TEACHERS’ PERCEPTION ON USING VIDEO STREAMING PLATFORM TO ENHANCE LISTENING SKILLS

This study investigates the influence of video streaming platforms on effective listening proficiency among English teachers and secondary school students in SMKA Tun Ahmadshah, Kota Kinabalu, Sabah. The research utilized a qualitative approach, interviewing 5 experienced English teachers and five students from Form 3 to Form 5. Among the reasons, the integration of modern technological tools was provided in the school. The theories of cognitivism and content-based learning (CBL) within the book are employed. The research focuses on these theories to explore cognitive and instructional merits of using video streaming platforms. Based on the findings, the content of video streaming platforms significantly sustains students’ engagement and motivation. At the same time, teachers comment on the content being interesting, relevant, and in multimedia format. It combines visual and auditory sense for their engagement. Among the challenges for the students was that they rely on subtitles on the video. The issue of buffering was not mentioned by the students, but it is likely to reduce their engagement. Teachers suggested that the platform content is authentic similar to that on social media, and students can receive other messages beside the expected ones. For effective teaching, the use of some features could be of help considering that buffering poses a major challenge, and some students rely on subtitles. Nevertheless, they could make the process simpler and with motivation by their utilization on the students’ part. The medium is significantly used in distance learning where it is effective since students rely on the authentic content and are engaged. Thus, the platform should be used for effective proficiency in listening with assistance from its video features. They require the employing of the platform features and adequate motivation from the participants. Keyword(s): Listening Skills, Content Based Learning (CBL), Video Streaming Platform, Cognitivism.

Functional characterization of optic photoreception in Lymnaea stagnalis

Optic photoreception is a critical function for animal survival. Across the evolutionary spectrum, diverse animal models have been used to investigate visual system function and potential mechanisms under physiological or pathophysiological states. However less is known on photoreceptive behaviors and retinal processing in invertebrates, especially molluscs. This study focuses on the freshwater pond snail, Lymnaea stagnalis (L. stagnalis), to explore its visual function and underlying mechanisms. Using anatomical and histological approaches we characterized the L. stagnalis eye structure and demonstrated structural connections and retinal rhodopsin-positive sensory cells potentially critical for phototransduction. To assess the snail phototactic responses, we developed a new neurobehavioral protocol and employed DeepLabCut to track and quantify animal locomotion. We demonstrated that L. stagnalis exhibits a positive locomotory response to intense focal light and has diverse photo-locomotory responses. Further, we conducted phylogenetic and protein structure analyses and demonstrated that L. stagnalis has a unique repertoire of both vertebrate and invertebrate phototransduction genes. Further characterization of a rhodopsin-like gene identified unique characteristics compared to other mollusks and vertebrates, suggesting different mechanisms of phototransduction. Taken together, our work establishes L. stagnalis as a model organism for studying optic photoreception, offering new insights into the evolution and diversity of visual function across animal species.

RTID-05. STUDY PROTOCOL: A MULTICENTER, INTERNATIONAL RANDOMIZED CONFIRMATORY TRIAL: LOW-ENERGY X-RAY INTRAOPERATIVE RADIATION THERAPY (LEX-IORT) VS. ADJUVANT FRACTIONATED STEREOTACTIC RADIOTHERAPY (FSRT) IN THE MANAGEMENT OF BRAIN METASTASES (LEXIMATE)

Abstract BACKGROUND Fractionated stereotactic radiotherapy to the resection cavity boosts local control of resected brain metastases significantly. However, start of systemic tumor-directed treatment may be protracted and in-hospital times prolonged. Lately, lex-ioRT of BM has been described as a safe and effective one stop-shop treatment modality with a 1-year local control rate of up to 98% while potentially improving patient convenience. Study Design: The LEXIMATE-trial is a multicenter, international, randomized open-label confirmatory trial comparing lex-IORT with FSRT of resected BM. In the experimental arm, INTRABEAM (Carl Zeiss Meditec AG) is used to deliver IORT by application of 50-kV photons at a standard dose of 30 Gy prescribed to the applicator surface. Standard linear accelerator or Gamma Knife based FSRT (3-7 fractions) to the surgical bed is used in the control arm. The primary endpoint is the cumulative incidence of local recurrences (as per RANO-BM) considering death without prior local recurrence as competing event. Inclusion criteria include histologically confirmed BM with indication for resection according to EANO-ESMO/ASCO-SNO-ASTRO guidelines, ≤5 other brain lesions compatible with BM and amenable to radiosurgery and history of solid cancer or CT scan suggestive for localized or metastasized solid cancer (except germ cell tumors, lymphoma, small-cell lung cancer). The resection cavity must be <5cm in size, IORT doses to brainstem or optical tract may not exceed 8 Gy. Study design: Randomized, open-label, non-inferiority. Sample size: 70 patients per group to show a non-inferiority of the experimental therapy compared to the control therapy with a power of approximately 80%. DISCUSSION The best radio-oncologic procedure for resected BM remains under debate. The LEXIMATE-trial offers an opportunity to provide more solid prospective data on effectiveness, safety and patient comfort both for established and new RT techniques.

Visualization of anatomical structures in the carpal region of the horse using cone beam computed tomography in comparison with conventional multidetector computed tomography

IntroductionIn the diagnostics of orthopedic diseases in the horse, diagnostic imaging often plays a decisive role. Cone beam computed tomography (CBCT) imaging is used in both human and small animal medicine and becoming increasingly popular. To see whether CBCT imaging can be useful in the diagnosis of orthopedic diseases of the carpal region of the horse and to explore possible limitations we compared CBCT images with multidetector computed tomography (MDCT) images of the carpal region of equine cadaveric specimens.Materials and methodsTwenty-eight forelimbs from fifteen horses, slaughtered for reasons unrelated to this study, were examined. Native and contrast enhanced CBCT and MDCT scans were performed. Anatomical structures were blindly evaluated by three independent experienced observers using a visual scoring system previously reported and adapted to the equine carpal region. A descriptive evaluation was carried out as well as Spearman’s rank correlation and interobserver agreement was shown by percent agreement (PA).ResultsVisualization of osseous structures was excellent in both MDCT and CBCT. Articular cartilage could only be assessed in contrast enhanced scans whereby MDCT showed a slightly better visualization than CBCT. Soft tissue structures were generally difficult to assess. An exception were the medial and lateral palmar intercarpal ligament, which could not be visualized in native but were well visualized in contrast enhanced scans in both MDCT and CBCT images.Discussion/conclusionFor the evaluation of osseous structures and some intraarticular ligaments after contrast enhancement, CBCT serves as a reliable diagnostic imaging modality for the equine carpal region. However, soft tissue structures and cartilage are imaged more reliably using MDCT.

Esports Training, Periodization, and Software—A Scoping Review

Electronic sports (esports) and research on this emerging field are interdisciplinary in nature. By extension, it is essential to understand how to standardize and structure training with the help of existing tools, developed over years of research in sports sciences and informatics. Our goal for this work is to review the available literature in esports research, focusing on sports sciences (training, periodization, planning, and career stages) and software (training tools, visualization, analytics, and feedback systems). To verify the existing sources, we applied the framework of a scoping review to address the search from multiple scientific databases with further local processing. We conclude that the current research on esports has mainly focused on describing and modeling performance metrics that span over multiple fragmented research areas (psychology, nutrition, informatics). However, these building blocks have not been assembled into a well-functioning theory of performance in esports by, e.g., providing exercise regimes or methods of periodization for esports.

Intelligent multi-robot collaborative transport system

The research on multi-robot systems has been divided into various fields, such as communication, navigation, task allocation, and collaborative transport. While significant progress has been made in each area, there has been limited research integrating these fields to build a fully autonomous multi-robot collaborative transport system. Therefore, we identify the key issues and propose a multi-robot collaborative transport system founded on ROS1 and conduct validation in a simulated environment, laying a solid foundation for the system to run on real robots. The primary contributions of this study include three key areas: (1) modeling and validating robot collaborative transport, (2) developing a visual task allocation system leveraging FastDDS service, and (3) resolving path collision issues in multi-robot navigation through both traditional methods and reinforcement learning techniques. Extensive experimental evaluations demonstrate that the proposed intelligent multi-robot collaborative transport system can autonomously navigate to target points for collaborative transport task. Performance assessments, based on the error between the target point and the object’s arrival point as well as the transport trajectory error, reveal that the system effectively completes the assigned tasks.

A VOx-based optoelectronic memristor for application in visual perception

Abstract While biological vision systems excel at in-memory processing with low power consumption, traditional silicon-based vision chips struggle with high energy demands. This gap motivates the exploration of alternative materials for artificial intelligence applications. This paper presents a VOx-based optoelectronic synaptic memristive device. The proposed artificial synaptic device ITO/VO x /Pt mimics biological functions such as potentiation (P), depression (D), long-term memory, short-term memory (STM), and paired-pulse facilitation (PPF). The PPF index, standing at 105%, suggests a favorable pattern in STM function. The device served as synapses within a spiking neural network showing an achievable pattern classification accuracy of 88.68%, highlighting the potential of the VO x synaptic device for pattern classification tasks. The suggested VO x -based synaptic devices could represent an efficient pattern recognition and visual perception application.

Research on a Method for Measuring the Pile Height of Materials in Agricultural Product Transport Vehicles Based on Binocular Vision

The advancement of unloading technology in combine harvesting is crucial for the intelligent development of agricultural machinery. Accurately measuring material pile height in transport vehicles is essential, as uneven accumulation can lead to spillage and voids, reducing loading efficiency. Relying solely on manual observation for measuring stack height can decrease harvesting efficiency and pose safety risks due to driver distraction. This research applies binocular vision to agricultural harvesting, proposing a novel method that uses a stereo matching algorithm to measure material pile height during harvesting. By comparing distance measurements taken in both empty and loaded states, the method determines stack height. A linear regression model processes the stack height data, enhancing measurement accuracy. A binocular vision system was established, applying Zhang’s calibration method on the MATLAB (R2019a) platform to correct camera parameters, achieving a calibration error of 0.15 pixels. The study implemented block matching (BM) and semi-global block matching (SGBM) algorithms using the OpenCV (4.8.1) library on the PyCharm (2020.3.5) platform for stereo matching, generating disparity, and pseudo-color maps. Three-dimensional coordinates of key points on the piled material were calculated to measure distances from the vehicle container bottom and material surface to the binocular camera, allowing for the calculation of material pile height. Furthermore, a linear regression model was applied to correct the data, enhancing the accuracy of the measured pile height. The results indicate that by employing binocular stereo vision and stereo matching algorithms, followed by linear regression, this method can accurately calculate material pile height. The average relative error for the BM algorithm was 3.70%, and for the SGBM algorithm, it was 3.35%, both within the acceptable precision range. While the SGBM algorithm was, on average, 46 ms slower than the BM algorithm, both maintained errors under 7% and computation times under 100 ms, meeting the real-time measurement requirements for combine harvesting. In practical operations, this method can effectively measure material pile height in transport vehicles. The choice of matching algorithm should consider container size, material properties, and the balance between measurement time, accuracy, and disparity map completeness. This approach aids in manual adjustment of machinery posture and provides data support for future autonomous master-slave collaborative operations in combine harvesting.

Teaching deep networks to see shape: Lessons from a simplified visual world

Deep neural networks have been remarkably successful as models of the primate visual system. One crucial problem is that they fail to account for the strong shape-dependence of primate vision. Whereas humans base their judgements of category membership to a large extent on shape, deep networks rely much more strongly on other features such as color and texture. While this problem has been widely documented, the underlying reasons remain unclear. We design simple, artificial image datasets in which shape, color, and texture features can be used to predict the image class. By training networks from scratch to classify images with single features and feature combinations, we show that some network architectures are unable to learn to use shape features, whereas others are able to use shape in principle but are biased towards the other features. We show that the bias can be explained by the interactions between the weight updates for many images in mini-batch gradient descent. This suggests that different learning algorithms with sparser, more local weight changes are required to make networks more sensitive to shape and improve their capability to describe human vision.

Visualizing the Philippines’ SDG 11.3.1 Status and Progress Using Open-Source Geospatial Software and Earth Observation Datasets

Abstract. This paper presents the development and implementation of a web GIS-based application designed to visualize the status and progress of Sustainable Development Goals (SDGs). Focusing specifically on SDG 11.3.1, which pertains to sustainable urbanization, we propose a prototype (accessible at https://ccgeoinformatics.github.io/sdg1131ph/) that leverages open-source geospatial software and earth observation (EO) datasets. By following the "where-when-what-how" framework of SDG visualization system development, we address the need for effective visualization methods while showcasing the potential of accessible datasets and technology in supporting sustainable development monitoring efforts across different administrative levels. We demonstrate the feasibility of the system in aiding policymakers and stakeholders in their decision-making processes toward achieving the SDGs by 2030. Additionally, our work exemplified how open-source software and EO datasets can address the challenges associated with SDG reporting, particularly in areas where both data and visualization tools are scarce or inaccessible. This paper also contributes to the ongoing discourse on SDG visualization and underscores the importance of localized analysis and visualization in understanding and addressing the challenges of sustainable urbanization using the example of the Philippines.

NCOG-05. HEALTH-RELATED QUALITY OF LIFE (HRQOL) IN THE PHASE 2 FIREFLY-1 (PNOC026) TRIAL OF THE TYPE II RAF INHIBITOR TOVORAFENIB IN RELAPSED/REFRACTORY (R/R) PEDIATRIC LOW-GRADE GLIOMA (PLGG)

Abstract BACKGROUND Despite favorable long-term survival, ongoing disease and treatment-related morbidity substantially impact the HRQOL of patients with pLGG. Tovorafenib is a selective, CNS-penetrant, type II RAF inhibitor. Results from the ongoing FIREFLY-1 (NCT04775485) phase 2 study (Kilburn LK, et al. Nat Med. 2023) showed clinically meaningful responses and a manageable safety profile in pLGG. Vision remained stable or improved in 89% of evaluable patients with optic pathway gliomas (Nysom K, et al. Neuro-Oncol. 2023). METHODS FIREFLY-1 arm 1 patients 6 months–25 years of age with RAF-altered r/r pLGG received tovorafenib 420 mg/m2 weekly (600 mg max) in 28-day cycles. Exploratory measures included longitudinal assessment of PedsQL in patients ≥2 years of age. PedsQL 3.0 Cancer Module child self-reports Total Score and 8 subscales were used to assess HRQOL from 0 (worst)–100 (fewer problems/symptoms) (as of December 22, 2022) baseline (BL) to cycle 13 (C13) in patients ≥5 years of age. RESULTS For the PedsQL 3.0 Cancer Module, 51 completed self-reports at BL, and 32 at C13 due to continued attrition over time. Median Total Score was 81.5 (range: 46.3-100) at BL and 85.2 (range: 50-100) at C13. At C4, 16% worsened (decrease >10 points) and 11% improved (increase >10 points); by C13, 11% worsened and 33% improved. For Cognitive Problems, patients scored a median of 75 (range: 5-100) at BL and 85 (range: 20-100) at C13, with 11% and 26% improved at C4 and C13, respectively. A similar trend was seen with Nausea. Pain and Hurt remained even throughout (median: 87.5). Treatment Anxiety was not a major concern (median: 100, C1-C13); Procedural Anxiety improved over time (median: 58.3 BL; 79.2 at C13). CONCLUSIONS HRQOL generally remained stable, or improved, in the majority of patients with r/r pLGG during the first year of treatment with tovorafenib.

CNSC-07. OLIGODENDROGLIAL IMPAIRMENT IN WHITE MATTER TRACTS FOLLOWING NEUROFIBROMATOSIS TYPE 1 (NF1) GERMLINE MUTATION OR CARBOPLATIN TREATMENT

Abstract Neurofibromatosis type 1 (NF1) is a cancer predisposition syndrome due to mutations in the NF1 gene. The disease affects 1 in 2500-3000 people worldwide and patients are predisposed to neoplasms such as optic pathway glioma, plexiform neurofibroma. In addition, NF1 patients often experience neurological issues such as learning difficulties. Unfortunately, there is no cure for NF1 yet. Chemotherapy (e.g., carboplatin) remains the first-line treatment for NF1-associated low-grade glioma; while effective in reducing tumor burden, it does not reliably restore neuronal function. In this study, we sought to determine how chemotherapy and Nf1 germline mutations influence neurological function, using genetically engineered mice of NF1. Nf1-heterozygous mice received carboplatin (60 mg/kg/day) or vehicle every other day for one week. Their optic nerves were collected and processed for immunofluorescence and transmission electron microscopy (EM). We found that carboplatin treatment reduces the density of oligodendrocytes in Nf1-heterozygous mice and impairs myelination. Moreover, a similar effect of carboplatin was observed in wild-type mice, suggesting that carboplatin impairs oligodendroglia independent of the NF1 status and the effect of carboplatin should also be evaluated in the non-NF1 context. In another set of experiments, we sought to understand how germline Nf1 mutations influences oligodendroglia. Whereas we did not observe a difference in optic nerve oligodendrocyte density in mice with an engineered mutation targeting the GTPase-activating protein-related domain (GRD) domain of the Nf1 gene, a reduction of oligodendrocyte density was observed in mice harboring a patient-derived mutation (R1809C), which localizes outside of the GRD. A similar effect was observed in the corpus callosum of Nf1+/R1809C mice together with myelin impairment, suggesting a RAS-independent mechanism of Nf1 regulation of oligodendrocytes. Together, these findings indicate that both Nf1 germline mutations and chemotherapy could contribute to oligodendrocyte and myelin deficits in white matter tracts.

A Rare Neck Lesion in Children: Bilateral Chondrocutaneous Branchial Remnant

Cervical chondrocutaneous branchial remnant is a rare congenital developmental anomaly typically located on the lateral neck. Histologically, it has the appearance of an accessory tragus demonstrating a central cartilaginous core with surrounding fibrosis located in the subcutaneous tissue. In order to address the clinical and therapeutic aspects of cervical chondrocutaneous branchial remnants in children, a 6-year-old boy who presents with bilateral hard cervical masses at the lower region of the neck is presented. Chondrocutaneous branchial remnant is a very rare cervical lesion in children, and surgical excision is the only choice of treatment. Cervical chondrocutaneous branchial remnant has been associated with a variety of congenital anomalies, particularly involving the auditory, cardiovascular, and visual systems. Despite bilateral occurrence of cervical chondrocutaneous branchial remnant, our patient had no cardiac or genitourinary anomalies.