Visual images in radiography: pareidolia as a useful tool for physicians and artificial intelligence

Cover Image


Cite item

Full Text

Abstract

This article explored the role of pareidolia in radiography and its potential in improving diagnosis and medical personnel training. Pareidolia is the phenomenon of perceiving familiar patterns in random objects, such as faces on the moon’s surface and animal figures in clouds. In radiography, pareidolia can manifest as recognizable patterns in medical images. This enables radiographers to identify abnormalities and improve their diagnostic skills.

This work aimed to evaluate pareidolia caused by the interpretation of X-ray images and determine its potential applications.

From June to December 2023, a competition was held to create a dataset of pareidolic illusions. Thirty-one individuals participated, including medical imaging specialists who had access to radiographic images. Images from nine additional participants were obtained outside the competition. Overall, 71 images were received. Participants uploaded images using a form on Yandex Forms. Data quality was ensured by clearly defined inclusion and exclusion criteria.

Data analysis revealed that people most frequently perceive human faces, animal snouts, and the heart symbol. These findings indicate the possibility of further research. This article discusses the potential applications of pareidolia in developing neural networks for automated medical image analysis and in educational activities that stimulate creative thinking and association.

Moreover, the article emphasizes the importance of ongoing research in this area to develop effective diagnostic tools and educational programs by expanding the evidence base.

Full Text

INTRODUCTION

Pareidolia is a visual perception phenomenon in which the brain interprets random stimuli (spots, shadows, patterns) as meaningful images. Common everyday examples of pareidolia include perceiving a face on the surface of the Moon or animal shapes in clouds. Notably, pareidolia does not always result in visual illusions and may also occur in other sensory domains (for example, when listening to recorded music played in reverse). Pareidolic phenomena arise from the same neural processes that extract real, rather than imagined, meaning from salient objects in the surrounding world [1].

Imaging findings that resemble objects not actually present in the image are, by analogy with everyday experience, referred to as pareidolic illusions, metaphorical signs, or visual illusions. Such signs have been widely discussed in scientific publications and are frequently used in physician training programs. The use of pareidolic signs in teaching the interpretation of radiologic images increases medical student engagement, descriptive abilities, and short-term retention of material compared with conventional anatomy-based explanations of the same content [2].

Beyond education, pareidolia may also be used to reduce the number of diagnostic errors in radiology. The frequency of such errors is estimated at 4%, corresponding to approximately 40 million errors annually, and this figure has remained remarkably stable over the past 70 years [3, 4]. Computer-based decision support methods are expected to improve diagnostic accuracy; however, at present, these same technologies place new demands on radiologists and may give rise to new sources of perceptual error [5–7].

For this reason, radiologists who are familiar with common perceptual illusions may not only be better able to avoid diagnostic errors but may also use such illusions, when present, to establish a diagnosis [8].

Although pareidolia is often perceived as an incidental finding, in diagnostic imaging it may be representative of specific conditions and therefore clinically useful for establishing a diagnosis [9]. Radiologists have described many such diagnostic signs—visual illusions that indicate the presence of a particular condition or disease [10, 11]. Table 1 [12–22] presents a selection of pareidolic signs that frequently serve as effective diagnostic heuristics [23, 24].

 

Table 1. Examples of pareidolic signs used as diagnostic heuristics in radiology

Visual illusion

Description

Reference

Snowman sign

  • Visualized in the sellar region;
  • Suggests that a pituitary macroadenoma is more likely than a meningioma.

[12]

Swallow tail sign

  • In certain cases, the absence of this pareidolic sign may indicate the presence of disease;
  • Linear or comma-shaped structures (resembling a swallow’s tail) are normally seen in images of the substantia nigra but are absent in most patients with Parkinson disease or dementia with Lewy bodies.

[13]

Wisdom tooth (molar tooth) sign

  • On axial computed tomography images, the midbrain resembles a molar or wisdom tooth;
  • The wisdom tooth sign was first described in Joubert syndrome and related ciliopathies.

[14, 15]

Hummingbird, penguin, Mickey Mouse signs

  • On mid-sagittal magnetic resonance imaging, midbrain atrophy in patients with progressive supranuclear palsy resembles a hummingbird or penguin;
  • On axial images, the atrophic midbrain forms a Mickey Mouse face with paired ears represented by the cerebral peduncles.

[16, 17]

Double panda sign

  • Associated with Wilson disease;
  • Characterized by two distinct panda faces: the giant panda face in the midbrain and the miniature panda face in the pontine tegmentum;
  • Other conditions, such as methanol intoxication and Leigh disease, may also produce the double panda sign;
  • Therefore, its presence alone is insufficient for a definitive diagnosis without additional data.

[18]

Eye of the tiger sign

  • Neurodegeneration with brain iron accumulation type 1;
  • Characteristic eye of the tiger appearance in the globus pallidus on T2-weighted magnetic resonance imaging;
  • Consists of two components: an anteromedial hyperintense focus, likely due to neuronal loss, gliosis, and increased water content, surrounded by a rim of marked hypointensity caused by pathological iron accumulation;
  • The eye of the tiger sign is considered pathognomonic (present in > 95% of cases) for pantothenate kinase–associated neurodegeneration, although it is not entirely specific;
  • It has also been reported in other brain iron accumulation syndromes and in asymptomatic healthy individuals.

[19–21]

Tadpole sign

  • A classic neuroradiological sign of adult-onset Alexander disease;
  • The late-onset form, caused by mutations in the glial fibrillary acidic protein gene, typically presents with brainstem, cerebellar, or myelopathic symptoms;
  • The tadpole appearance results from marked atrophy of the medulla oblongata and upper cervical spinal cord;
  • The spinal cord forms the thin tail, whereas preservation of pontine volume constitutes the head.

[22]

 

Until recently, these signs were largely empirical; however, artificial intelligence technologies have opened up new opportunities for their analysis. Image analysis tools, including computer vision, have become an integral part of modern life [25]. Healthcare is no exception: one of the largest initiatives in this field is the Experiment on Using Innovative Computer Vision Technologies for Medical Image Analysis and Their Subsequent Implementation in Healthcare Systems [26, 27]. The digitalization of medical data and the emergence of artificial intelligence–based software capable of its analysis may help to systematize knowledge about pareidolia, identify and substantiate new relationships, and define new ways of its application.

Medicine is not the only domain in which such knowledge is applied. For example, De la Torre [28] employed artificial intelligence technologies to search for extraterrestrial intelligence in images of cosmic objects and suggested that the results of this work may be useful not only for space research but also for understanding the nature of artificial intelligence, its functioning, and certain ethical issues. Furthermore, pareidolia is actively used in psychology and psychotherapy [29], education [30], art,1 and many other fields [31].

Interest in pareidolia has increased so markedly in recent years that specialized neural networks have been developed that not only detect pareidolic patterns but also generate such images.23

This work aimed to evaluate pareidolia arising during the interpretation of X-ray images and determine its potential applications.

DATA COLLECTION

To obtain a dataset of pareidolic illusions for subsequent analysis and application, we organized a competition—a volunteer-based project open both to specialists working with medical images and to the general public. The competition, conducted from June to December 2023, was announced through various communication channels, including the website of the Scientific and Practical Clinical Center for Diagnostics and Telemedicine Technologies, as well as the Science ID platform (a national identification and communication service platform for early-career researchers). The initiative attracted 31 participants. Subsequently, outside the competition, images were additionally received from 9 participants.

We collected anonymized radiological images obtained using various imaging modalities, including computed tomography, magnetic resonance imaging, radiography, and ultrasound. The images were provided by medical professionals (radiologists) or participants with authorized access to these data in cases where pareidolic phenomena were observed.

Data were collected using Yandex.Forms® (Yandex, Russia), which ensured a convenient and standardized transfer of images (see Fig. 1).

 

Fig. 1. Form layout. All fields are mandatory. Supported image upload formats include the Joint Photographic Experts Group (JPEG) and the Portable Network Graphics (PNG).

 

Inclusion criteria:

  • Participants over 18 years of age. Participation of minors was permitted only through legal representatives (e.g., parents);
  • Image submission via a dedicated form on Yandex.Forms® (Yandex, Russia), with mandatory informed consent for personal data processing;
  • Anonymized medical images (containing no patient-identifying information) accompanied by a brief description.

Exclusion criteria:

  • Images containing patient-identifying information, not corresponding to the topic of the competition, or violating the legislation of the Russian Federation or principles of humanity and morality;
  • Images submitted by participants under the age of 18 or submitted on behalf of minors without the involvement of legal representatives;
  • Images with insufficient resolution or poor quality that impeded recognition of pareidolic illusions;
  • Images lacking a clear indication of the associated anatomical region or object;
  • Images borrowed from open Internet sources.

DATA ANALYSIS

Images were selected by members of the competition jury using a 5-point scale:

  • Image quality: up to 1 point;
  • Originality: up to 2 points;
  • Degree of associative similarity: up to 2 points.

Subsequently, the images were categorized into groups according to visual features.

ETHICAL CONSIDERATIONS

No approval from an ethics committee was obtained within this project. All participants were informed about the purpose of the project and participated voluntarily. Participants were free to leave the project at any time.

RESULTS

As a result of the competition, a dataset comprising 71 images containing pareidolic illusions was collected. A detailed breakdown of the dataset is presented in Table 2.

Examples of the most illustrative and noteworthy images are shown in Figures 2–10.

 

Table 2. Visual features identified in pareidolic images

Visual feature

Number of images, n

Imaging modality

Face

15

Computed tomography

Animal face

10

Computed tomography

Heart

11

Computed tomography, ultrasound

Swan

4

Computed tomography

Virus

3

Computed tomography

Ink blot

2

Computed tomography

Star

2

Magnetic resonance imaging

Mandarin orange

2

Computed tomography

Eye

1

Computed tomography

Layered cake

1

Computed tomography

Mercedes sign

1

Computed tomography

Pomegranate seeds

1

Computed tomography

Ghost

1

Computed tomography

Sunset

1

Computed tomography

Eyelashes

1

Computed tomography

Avocado

1

Magnetic resonance imaging

Bat

1

Computed tomography

Mushroom

1

Computed tomography

Footprint

1

Magnetic resonance imaging

Penguin

1

Computed tomography

Question mark

1

Computed tomography

Sun

1

Computed tomography

Fire

1

Computed tomography

Explosion

1

Computed tomography

Hedgehog

1

Computed tomography

Clock (infinity) sign

1

Magnetic resonance imaging

Dogs

1

Computed tomography (reconstruction)

Maple leaf

1

Computed tomography

Spider legs

1

Computed tomography (reconstruction)

Ink in water

1

Magnetic resonance imaging

 

Fig. 2. Magnetic resonance image of the cerebral ventricular system, T2-weighted image, coronal plane: ventricular dilatation is noted (visually resembling a bunny asking for a hug). From the archive of L.R. Abuladze. Published for the first time with permission of the copyright holder.

 

Fig. 3. Abdominal computed tomography, axial plane: an inferior vena cava filter is visualized (visually resembling a maple leaf). From the archive of V.A. Gombolevskiy. Published for the first time with permission of the copyright holder.

 

Fig. 4. Magnetic resonance image of the shoulder joint, T2-weighted image: massive immature synovial chondromatosis (visually resembling pomegranate seeds). From the archive of A.Yu. Popov. Published for the first time with permission of the copyright holder.

 

Fig. 5. Computed tomography of the brain, frontal plane: narrowing of the convexital sulci, dilatation of the lateral and third ventricles (on the visible image), and blurring of gray–white matter differentiation, consistent with cerebral edema and internal hydrocephalus (visually resembling the face of a raccoon [panda]). From the archive of V.S. Somov. Published for the first time with permission of the copyright holder.

 

Fig. 6. Magnetic resonance image of the sacrum, T2-weighted image: normal findings (visually resembling a hyena). From the archive of Yu.A. Tsybulskaya. Published for the first time with permission of the copyright holder.

 

Fig. 7. Magnetic resonance image of the pelvis, T2-weighted image, sagittal plane: dermoid cyst (visually resembling an avocado). From the archive of D.U. Shikhmuradov. Published for the first time with permission of the copyright holder.

 

Fig. 8. Magnetic resonance image of the pelvis, T1-weighted image, axial plane: congenital anomaly of the male urogenital system—seminal vesicle cyst (visually resembling a human footprint). From the archive of P.A. Chastoyedov. Published for the first time with permission of the copyright holder.

 

Fig. 9. Computed tomography of the maxilla, axial plane: dental cusps and interdental fossae of molars (visually resembling smiley faces). From the archive of O.A. Yaroslavtseva. Published for the first time with permission of the copyright holder.

 

Fig. 10. Computed tomography of the head, coronal plane: hydrocephalus (visually resembling a heart). From the archive of E.A. Slavushcheva. Published for the first time with permission of the copyright holder.

 

Analysis of the collected images revealed a predominance of face-like pareidolic patterns, which is consistent with a social perceptual mechanism acquired by humans during evolution [32]. The second most frequent category included animal faces (e.g., resembling rabbits, dogs, raccoons, hyenas, squids, etc.). Moreover, a considerable number of images resembling a “heart” were identified (not as an anatomical structure on medical images, but as a symbolic representation). This warrants further investigation, as no scientific publications explaining this phenomenon were identified. Animal silhouettes (e.g., penguins, hedgehogs, dogs, swans) were also frequently observed on medical images.

Most pareidolic patterns were represented by single instances, which precludes in-depth analysis of interrelationships in their current form and necessitates further identification of similar pathologies and anatomical localizations. Nevertheless, the obtained results may be applied for several purposes. First, they may serve as a basis for the development of neural networks for radiological image analysis aimed at automating the detection of similar patterns.

The identified images should be annotated for the presence of pareidolia and organized into datasets according to the described methodology [33], including the anonymization process.4 Such datasets can then be analyzed to identify associations between pareidolic patterns and pathological features or anatomical characteristics. Ultimately, this approach may facilitate the systematization of such visual signs and enable their use in medical education and in improving diagnostic accuracy [2, 34, 35].

Moreover, this work may be further extended from psychological, educational, and even psychiatric perspectives by using the collected images to explore associations between various visual features, states, and personality characteristics. Such associations have already been identified in several domains. For example, pareidolia is used in psychological testing, most notably in the Rorschach inkblot test for personality assessment, which allows detecting certain mental disorders. Pareidolia may induce altered states of consciousness, accompany various forms of delirium, contribute to the diagnosis of Alzheimer disease [36–39], and may even be a marker of schizophrenia [40, 41]. Furthermore, associations have been reported between face recognition ability and prematurity in children [42]. Pareidolia, as an element of associative thinking, can also be applied in education, for instance, to promote psychological openness, facilitate the development of verbal and emotional skills [43], foster creative thinking [30, 44], and be utilized in art therapy [29].

Finally, this phenomenon is studied in fields far removed from medicine and pedagogy. For example, relationships have been explored between the ability to perceive pareidolia and levels of creativity [45], as well as the role of optical illusions in design [46] and architecture [47]. Pareidolia has also been discussed in the context of interpreting ancient rock art [48]. The monograph Thoracoabdominal Computed Tomography: Images and Symptoms by Yudin [49] describes numerous illusory signs identified during computed tomography image analysis. The author highlights pareidolia as metaphorical symptoms and provides illustrative examples demonstrating the challenges of visual data interpretation in diagnostic practice. Nevertheless, scientific publications on pareidolia remain scarce (searches for the term pareidolia yielded 57, 28, and 124 publications in eLibrary, CyberLeninka, and PubMed, respectively). At the same time, pareidolia is more frequently mentioned in popular science sources, where it attracts broad public interest, evokes emotional responses, and stimulates the desire to document and share such observations. For this reason, the present project was conceived to enable not only a comprehensive scientific investigation in radiology but also the extrapolation of its findings to other fields and their dissemination to a wider audience, thereby fostering interest in science.

CONCLUSION

As part of the further development of the project, several key steps are envisaged. Based on the collected images, artificial intelligence models will be trained to identify and analyze the underlying mechanisms and associations between pareidolia and diagnostic as well as educational processes. The resulting data may contribute to improving the training of radiologists (when integrated into educational programs), as well as to enhancing the performance of artificial intelligence–based models in recognizing pathological features on medical images, thereby increasing diagnostic accuracy and efficiency in clinical practice.

We also plan to continue collecting images containing pareidolic patterns to expand the dataset used both for artificial intelligence training and for scientific research. This will enable the identification of new aspects of pareidolia application in medicine and education.

In addition, we intend to develop educational programs for medical students and clinicians that incorporate pareidolia-based examples to improve visual perception and diagnostic skills. These programs may also be adapted for use in general education settings, contributing to the development of creative and associative thinking in children.

Special emphasis will be placed on encouraging young people to pursue a career in radiology and promoting medicine and science through educational activities, such as visits to medical institutions and workshops conducted by practicing specialists.

Notably, at the current stage, the number of collected images is insufficient to fully implement all planned objectives, which is related to a limited audience reach and low participant motivation. Therefore, we plan to scale the project to a broader audience. Furthermore, through the phenomenon of pareidolia, the project aims to promote scientific interest among young people, including awareness of modern data analysis methods and the development of artificial intelligence models.

ADDITIONAL INFORMATION

Author contributions: A.V. Solovev, T.M. Bobrovskaya, M.A. Zelenova: conceptualization, methodology, writing—original draft, writing—review & editing; O.V. Omelyanskaya: conceptualization, writing—review & editing, supervision. All the authors approved the version of the manuscript to be published and agreed to be accountable for all aspects of the work, ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.

Acknowledgments: The authors express their gratitude to all the project participants who sent pareidolic images: Kirill Arzamasov, Aleksey Petryaikin, Natalya Pukhova, Elena Kozlitina, Pavel Drozhzha, Anna Gofman, Veronika Kazarinova, Elena Lomakina, Maria Akhlebinina, Vardan Bakhchoyan, Islam Gerandokov, Olga Demina, Natalia Zabavina, Ksenia Sherman, Ekaterina Bychkova, Vladimir Guryev, David Shikhmuradov, Serafim Semenov, Marina Cherkasskaya, Ksenia Klokotina, Dmitry Koshurnikov, Valentina Mikhailova, Aleksey Popov, Vladislav Somov, Galina Stakhanova, Yulia Tsybulskaya, Petr Chastoyedov, Olga Yaroslavtseva, Elena Astapenko , Liya Abuladze, Evgeniya Korochkina, Ekaterina Slavushcheva, Viktor Gombolevsky, Ekaterina Bakhteeva, Sofia Purkina, Egor Syrkashev, Svetlana Starovoitova.

Ethics approval: No approval from an ethics committee was obtained for the study within this project. All participants were informed about the aim of the project and participated voluntarily. Participants were free to leave the project at any time.

Funding sources: This article was prepared as part of the Development of a Preparation Platform for Radiology Datasets research and development project (Unified State Information Accounting System No. 123031500003-8).

Disclosure of interests: The authors have no relationships, activities, or interests for the last three years related to for-profit or not-for-profit third parties whose interests may be affected by the content of the article.

Statement of originality: No previously obtained or published material (text, images, or data) was used in this study or article.

Data availability statement: The editorial policy regarding data sharing does not apply to this work.

Generative AI: No generative artificial intelligence technologies were used to prepare this article.

Provenance and peer-review: This article was submitted unsolicited and reviewed following the standard procedure. The peer review process involved a member of the Editorial Board.

 

1 Pareidolia, face detection on grains of sand, installation [Internet]. Den Burg: Driessens & Verstappen; 2019–. Available at: https://notnot.home.xs4all.nl/pareidolia/pareidolia.html. Accessed on: September 15, 2024.

2 How to create hidden face portraits on MidJourney: Optical illusions: Making double images with AI art. [In Russ.]; [approximately 10 pages] In: Midjourney [Internet]. St. Petersburg: vc.ru, 2023–2024. Available at: https://vc.ru/midjourney/945132-kak-sozdat-zamaskirovannye-v-izobrazheniyah-portrety-opticheskie-illyuzii-v-midjourney. Accessed on: September 15, 2024.

3 DeepDream Algorithmic Pareidolia Or the Hallucinatory Code of Perception [Internet]. In: The Door of Perception. Berlin: Ben Roth, 2015–2014. Available at: https://doorofperception.com/2015/10/google-deep-dream-inceptionism/. Accessed on: September 15, 2024.

4 Certificate of state registration of computer software No. 2024680469 of August 29, 2024. Bull. No. 9. Vadilyev Yu.A., Arzamasov K. M., Omelyanskaya O.V. et al. A Software Module to Upload, Select, and De-identify Studies in DICOM Format Stored in the Unified Radiological Information System of Moscow. Available at: https://www.elibrary.ru/download/elibrary_69596606_86670510.PDF. Accessed on: September 15, 2024.

×

About the authors

Alexander V. Solovev

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies; Morozov Children's City Clinical Hospital

Author for correspondence.
Email: atlantis.92@mail.ru
ORCID iD: 0000-0003-4485-2638
SPIN-code: 9654-4005

MD

Russian Federation, Moscow; Moscow

Tatiana M. Bobrovskaya

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: BobrovskayaTM@zdrav.mos.ru
ORCID iD: 0000-0002-2746-7554
SPIN-code: 3400-8575
Russian Federation, Moscow

Maria A. Zelenova

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: maria_zelenova@yahoo.com
ORCID iD: 0000-0001-7458-5396
SPIN-code: 3823-6872

Cand. Sci. (Biology)

Russian Federation, Moscow

Olga V. Omelyanskaya

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: OmelyanskayaOV@zdrav.mos.ru
ORCID iD: 0000-0002-0245-4431
SPIN-code: 8948-6152
Russian Federation, Moscow

References

  1. Voss JL, Federmeier KD, Paller KA. The Potato Chip Really Does Look Like Elvis! Neural Hallmarks of Conceptual Processing Associated with Finding Novel Shapes Subjectively Meaningful. Cerebral Cortex. 2011;22(10):2354–2364. doi: 10.1093/cercor/bhr315
  2. Gibney B, Kassab GH, Redmond CE, et al. Pareidolia in Radiology Education: A Randomized Controlled Trial of Metaphoric Signs in Medical Student Teaching. Academic Radiology. 2021;28(10):1426–1432. doi: 10.1016/j.acra.2020.08.017 EDN: FBKOXV
  3. Waite S, Scott J, Gale B, et al. Interpretive Error in Radiology. American Journal of Roentgenology. 2017;208(4):739–749. doi: 10.2214/AJR.16.16963
  4. Imanzadeh A, Pourjabbar S, Mezrich J. Medicolegal Training in Radiology; an Overlooked Component of the Non-Interpretive Skills Curriculum. Clinical Imaging. 2020;65:138–142. doi: 10.1016/j.clinimag.2020.04.002 EDN: DZBGWK
  5. Slater A, Taylor SA, Tam E, et al. Reader Error During CT Colonography: Causes and Implications for Training. European Radiology. 2006;16(10):2275–2283. doi: 10.1007/s00330-006-0299-x EDN: VRUNXL
  6. McGurk S, Brauer K, Macfarlane TV, Duncan KA. The Effect of Voice Recognition Software on Comparative Error Rates in Radiology Reports. The British Journal of Radiology. 2008;81(970):767–770. doi: 10.1259/bjr/20698753
  7. Maskell G. Error in radiology—where are we now? The British Journal of Radiology. 2018;92(1096): 20180845. doi: 10.1259/bjr.20180845
  8. Buckle CE, Udawatta V, Straus CM. Now You See It, Now You Don’t: Visual Illusions in Radiology. RadioGraphics. 2013;33(7):2087–2102. doi: 10.1148/rg.337125204
  9. Maranhão-Filho P, Vincent MB. Neuropareidolia: diagnostic clues apropos of visual illusions. Arquivos de Neuro-Psiquiatria. 2009;67(4):1117–1123. doi: 10.1590/s0004-282x2009000600033
  10. Ridley LJ. The Use of Animal Signs in Radiology: Lessons in Image Interpretation from Art Theory, Patternicity and Analogy. Journal of Medical Imaging and Radiation Oncology. 2018;62(S1):3–6. doi: 10.1111/1754-9485.12782
  11. Ridley LJ, Xiang H, Han J, Ridley WE. Animal signs in Radiology: Method of Creating a Compendium. Journal of Medical Imaging and Radiation Oncology. 2018;62(S1):7–11. doi: 10.1111/1754-9485.12783 EDN: QHFEHY
  12. Hess CP, Dillon WP. Imaging the Pituitary and Parasellar Region. Neurosurgery Clinics of North America. 2012;23(4):529–542. doi: 10.1016/j.nec.2012.06.002
  13. Shams S, Fällmar D, Schwarz S, et al. MRI of the Swallow Tail Sign: A Useful Marker in the Diagnosis of Lewy Body Dementia? American Journal of Neuroradiology. 2017;38(9):1737–1741. doi: 10.3174/ajnr.a5274
  14. Maria BL, Quisling RG, Rosainz LC, et al. Molar Tooth Sign in Joubert Syndrome: Clinical, Radiologic, and Pathologic Significance. Journal of Child Neurology. 1999;14(6):368–376. doi: 10.1177/088307389901400605 EDN: CZSNXD
  15. Poretti A, Snow J, Summers AC, et al; NISC Comparative Sequencing Program. Joubert syndrome: neuroimaging findings in 110 patients in correlation with cognitive function and genetic cause. Journal of Medical Genetics. 2017;54(8):521–529. doi: 10.1136/jmedgenet-2016-104425
  16. Kato N, Arai K, Hattori T. Study of the Rostral Midbrain Atrophy in Progressive Supranuclear Palsy. Journal of the Neurological Sciences. 2003;210(1-2):57–60. doi: 10.1016/s0022-510x(03)00014-5
  17. Verma R, Gupta M. Hummingbird Sign in Progressive Supranuclear Palsy. Annals of Saudi Medicine. 2012;32(6):663–664. doi: 10.5144/0256-4947.2012.663
  18. Das SK, Ray K. Wilson's disease: an update. Nature Clinical Practice. Neurology. 2006;2(9):482–493. doi: 10.1038/ncpneuro0291 EDN: XUFSAZ
  19. Sethi KD, Adams RJ, Loring DW, El Gammal T. Hallervorden-Spatz Syndrome: Clinical and Magnetic Resonance Imaging Correlations. Annals of Neurology. 1988;24(5):692–694. doi: 10.1002/ana.410240519
  20. Guillerman RP. The Eye-of-the-Tiger Sign. Radiology. 2000;217(3):895–896. doi: 10.1148/radiology.217.3.r00dc31895
  21. van den Bogaard SJA, Kruit MC, Dumas EM, Roos RAC. Eye-of-the-Tiger-Sign in a 48 year Healthy Adult. Journal of the Neurological Sciences. 2014;336(1-2):254–256. doi: 10.1016/j.jns.2013.10.005
  22. Graff-Radford J, Schwartz K, Gavrilova RH, et al. Neuroimaging and Clinical Features in type II (late-onset) Alexander disease. Neurology. 2014;82(1):49–56. doi: 10.1212/01.wnl.0000438230.33223.bc
  23. Alexander RG, Yazdanie F, Waite S, et al. Visual Illusions in Radiology: Untrue Perceptions in Medical Images and Their Implications for Diagnostic Accuracy. Frontiers in Neuroscience. 2021;15:629469. doi: 10.3389/fnins.2021.629469 EDN: WBGAFH
  24. Mulroy E, Balint B, Adams ME, et al. Animals in the Brain. Movement Disorders Clinical Practice. 2019;6(3):189–198. doi: 10.1002/mdc3.12734
  25. Ponkin IV, Kupriyanovsky VP, Moreva SL, Lapteva AI. Computer Vision: Concept, Functionalpurpose, Structure, Related Regulatory Developments. International Journal of Open Information Technologies. 2024;12(5):57–66. EDN: WDFAPU
  26. Vladzimirskyy AV, Vasilev YuA, Arzamasov KM, et al. Computer Vision in Radiation Diagnostics: The First Stage of the Moscow Experiment. Moscow: Izdatel'skie resheniya; 2023. (In Russ.) ISBN: 978-5-0059-3043-9 EDN: FOYLXK
  27. Vasilev YA, Bobrovskaya TM, Arzamasov KM, et al. Medical Datasets for Machine Learning: Fundamental Principles of Standartization and Systematization. Manager Zdravookhranenia. 2023;(4):28–41. doi: 10.21045/1811-0185-2023-4-28-41 EDN: EPGAMD
  28. De la Torre GG. Does Artificial Intelligence Dream of Non-Terrestrial Techno-Signatures? Acta Astronautica. 2020;167:280–285. doi: 10.1016/j.actaastro.2019.11.013 EDN: UKHIMV
  29. Lebedeva LD. Art Therapy Resources in Overcoming Emotional Trauma. In: Anthology of Russian Psychotherapy and Psychology. Proceedings of the II World Congress of Russian-Speaking Psychotherapists and Psychologists. Moscow; 2023. P. 161–163. EDN: VHGNTM
  30. Linnik YuV, Linnik NV. Educational Potential of Polimusion in Work With Children of Preschool and Young School Age. Obshchestvo. 2018;(1):13–17. EDN: VTHZVW
  31. Moshnina VA, Lobkova EV. Pareidolias in our Life. In: Contemporary Problems of Science, Society and Culture. Proceedings of the VIII International Scientific and Practical Conference. Omsk: Siberian State Automobile and Highway University; 2023. P. 400–407. (In Russ.) EDN: BRSNHU
  32. Palmer CJ, Clifford CWG. Face Pareidolia Recruits Mechanisms for Detecting Human Social Attention. Psychological Science. 2020;31(8):1001–1012. doi: 10.1177/0956797620924814 EDN: CIJRZL
  33. Vasilev YuA, Arzamasov KM, Vladzimirskyy AV, et al. Preparing a Dataset for Training and Testing Software Based on Artificial Intelligence Technology: A Tutorial. Moscow: Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies; 2023. (In Russ.) EDN: OGKFGM
  34. Foye P, Abdelshahed D, Patel S. Musculoskeletal Pareidolia in Medical Education. The Clinical Teacher. 2014;11(4):251–253. doi: 10.1111/tct.12143
  35. Gusev AV, Vladzymyrskyy AV, Sharova DE, et al. Evolution of Research and Development in the Field of Artificial Intelligence Technologies for Healthcare in the Russian Federation: Results of 2021. Digital Diagnostics. 2022;3(3):178–194. doi: 10.17816/DD107367 EDN: KHWQWZ
  36. Gordeeva OV. Consideration of Mechanisms of Transition from the Ordinary to the Altered State of Consciousness from the Point of View of A.N. Leontiev’s Theory About the Structure of Consciousness (Research of Phenomena of Analytical Introspection). Moscow University Psychology Bulletin. 2015;(1):4–19. EDN: TJOVER
  37. Zavyalova NE, Salmina-Khvostova OI. Thiapride in the Treatment of Alcohol Withdrawal Delirium. Russian Journal of Psychiatry. 2012;(5):82–87. EDN: PJPIQV
  38. Kambarov ZG, Muminov BE. Modern Concepts on the Etiology and Pathogenesis of Postoperative Cognitive Disorders, Postoperative Deliria, Methods of Diagnosis, Prevention and Treatment (Review of Literature). Ekonomika i sotsium. 2023;(2):669–681. EDN: VHEUNF
  39. Hamilton CA, Matthews FE, Allan LM, et al. Utility of the Pareidolia Test in Mild Cognitive Impairment With Lewy Bodies and Alzheimer's Disease. International Journal of Geriatric Psychiatry. 2021;36(9):1407–1414. doi: 10.1002/gps.5546 EDN: TEHWBG
  40. Назимова С. В., Баранов П. А. Psychopathological Structure of Schizophrenia Attacks Formed Under Conditions of Exogenous Influences. Sovremennaya terapiya v psikhiatrii i nevrologii. 2013;(2):5–9. EDN: QJGMKL
  41. Abo Hamza EG, Keri S, Csigó K, et al. Pareidolia in Schizophrenia and Bipolar Disorder. SSRN Electronic Journal. 2021;12:746734. doi: 10.2139/ssrn.3868726 EDN: BWTBPU
  42. Pavlova MA, Galli J, Zanetti F, et al. Social Cognition in Individuals Born Preterm. Scientific Reports. 2021;11(1):1–11. doi: 10.1038/s41598-021-93709-4 EDN: PBAWRR
  43. Surmenelyan ME. Once Again About Associative Thinking. Innovatsionnaya nauka. 2020;(9):71–75. (In Russ.) EDN: DQZZER
  44. Taubert J, Wardle SG, Flessert M, et al. Face Pareidolia in the Rhesus Monkey. Current Biology. 2017;27(16):2505–2509.e2. doi: 10.1016/j.cub.2017.06.075 EDN: YHFUMN
  45. Kostrigina AA, Ivanov AS. The Study of the Relationship of a Creativity Level and a Pareidolic Illusion Indication Ability. Vestnik po pedagogike i psikhologii Yuzhnoi Sibiri. 2018;(2):84–100. EDN: YOIQKD
  46. Chuntonov DA, Bystrova TYu. Applying Gestalt Principles to Design Using Optical Illusions. Akademicheskij vestnik uralniiproekt RAASN. 2022;(2):108–114. doi: 10.25628/UNIIP.2022.53.2.017 EDN: RLACNA
  47. Wang C, Yu L, Mo Y, et al. Pareidolia in a Built Environment as a Complex Phenomenological Ambiguous Stimuli. International Journal of Environmental Research and Public Health. 2022;19(9):5163. doi: 10.3390/ijerph19095163 EDN: LWDQQZ
  48. Murashko A. “White Nut” or “ Headless Beast”? On the Rock Art of Wadi Sura. State Religion and Church in Russia and Worldwide. 2022;40(4):255–272. doi: 10.22394/2073-7203-2022-40-4-255-272 EDN: KIYNMD
  49. Yudin AL. Metaphorical Signs in Computed Tomography of Chest and Abdomen. Мoscow: Pirogov Russian National Research Medical University; 2012. ISBN: 978-5-88458-288-0 EDN: ZBDXAT

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 2. Magnetic resonance imaging of the ventricular system of the brain, T2-weighted image, coronal projection: dilation of the ventricular system is noted (visually resembling a "bunny who wants to be hugged"). From the archive of L.R. Abuladze. Image published for the first time with permission of the copyright holder.

Download (138KB)
Indexing metadata
3. Fig. 3. Computed tomography of the abdominal cavity, axial projection: a cava filter (visually resembling a "maple leaf") is installed in the inferior vena cava. From the archive of V.A. Gombolevsky. The image is published for the first time with permission of the copyright holder.

Download (111KB)
Indexing metadata
4. Fig. 4. Magnetic resonance imaging of the shoulder joint, T2-weighted image: massive immature synovial chondromatosis (visually resembling "pomegranate seeds"). From the archive of A. Yu. Popov. Image published for the first time with permission of the copyright holder.

Download (92KB)
Indexing metadata
5. Fig. 5. Computed tomography of the brain, frontal projection: narrowing of the convexital sulci, dilation of the lateral and third ventricles (on the visible image), smoothing of the differentiation of gray and white matter - cerebral edema and internal hydrocephalus [visually reminiscent of a "raccoon (panda) face"]. From the archive of V.S. Somov. The image is published for the first time with the permission of the copyright holder.

Download (146KB)
Indexing metadata
6. Fig. 6. Magnetic resonance imaging of the sacrum, T2-weighted image: normal condition (visually resembles a "hyena"). From the archive of Yu. A. Tsybulskaya. Image published for the first time with permission of the copyright holder.

Download (116KB)
Indexing metadata
7. Fig. 7. Magnetic resonance imaging of the pelvis, T1-weighted image, axial projection: developmental anomaly of the male genitourinary system – a seminal cyst (visually resembling a "human footprint"). From the archive of P.A. Chastoyedov. Image published for the first time with permission of the copyright holder.

Download (89KB)
Indexing metadata
8. Fig. 8. Magnetic resonance imaging of the pelvis, T2-weighted image, sagittal projection: dermoid cyst (visually resembles an "avocado"). From the archive of D.U. Shikhmuradov. Image published for the first time with permission of the copyright holder.

Download (141KB)
Indexing metadata
9. Fig. 9. Computed tomography scan of the upper jaw, axial projection: dental cusps and depressions between them on the molars (visually reminiscent of "smiley faces"). From the archive of O.A. Yaroslavtseva. The image is published for the first time with permission of the copyright holder.

Download (108KB)
Indexing metadata
10. Fig. 10. CT scan of the head, coronal view: hydrocephalus (visually resembles a "heart"). From the archive of E.A. Slavushcheva. Image published for the first time with permission of the copyright holder.

Download (185KB)
Indexing metadata
11. Fig. 1. Form layout. All fields are mandatory. Supported image upload formats include the Joint Photographic Experts Group (JPEG) and the Portable Network Graphics (PNG).

Download (180KB)
Indexing metadata

Copyright (c) 2025 Eco-Vector

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
СМИ зарегистрировано Федеральной службой по надзору в сфере связи, информационных технологий и массовых коммуникаций (Роскомнадзор).
Регистрационный номер и дата принятия решения о регистрации СМИ: серия ПИ № ФС 77 - 79539 от 09 ноября 2020 г.