Combining deep learning with 3D stereophotogrammetry for craniosynostosis diagnosis
Open accessAbstract
Craniosynostosis is a condition in which cranial sutures fuse prematurely, causing problems in normal brain and skull growth in infants. To limit the extent of cosmetic and functional problems, swift diagnosis is needed. The goal of this study is to investigate if a deep learning algorithm is capable of correctly classifying the head shape of infants as either healthy controls, or as one of the following three craniosynostosis subtypes; scaphocephaly, trigonocephaly or anterior plagiocephaly. In order to acquire cranial shape data, 3D stereophotographs were made during routine pre-operative appointments of scaphocephaly (n = 76), trigonocephaly (n = 40) and anterior plagiocephaly (n = 27) patients. 3D Stereophotographs of healthy infants (n = 53) were made between the age of 3–6 months. The cranial shape data was sampled and a deep learning network was used to classify the cranial shape data as either: healthy control, scaphocephaly patient, trigonocephaly patient or anterior plagiocephaly patient. For the training and testing of the deep learning network, a stratified tenfold cross validation was used. During testing 195 out of 196 3D stereophotographs (99.5%) were correctly classified. This study shows that trained deep learning algorithms, based on 3D stereophotographs, can discriminate between craniosynostosis subtypes and healthy controls with high accuracy.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
De Jong et al. (2020) found that 3D stereophotogrammetry combined with a deep learning algorithm classified 195/196 cases (99.5%) exactly, with sensitivity 100% and specificity 96% for scaphocephaly.
“The accuracy of this method is clearly demonstrated by the exact classification of 195/196 cases (99.5%), with a sensitivity of 100% and a specificity of 96% for scaphocephaly [8].”
From Developments in diagnostic and surgical techniques in children with sagittal suture craniosynostosis: a systematic review spanning the last 30 years (2025) · cites this paper as [8]
The Results > Deep learning network passage reports that 195 of 196 subjects (99.5%) were correctly classified. It reports 100% sensitivity and specificity for scaphocephaly, not 96% specificity; the approximately 96% figure is the sensitivity for anterior plagiocephaly. (LLM, conf=0.94)
Experimental — accuracy not yet measuredDiagnosis of craniosynostosis is typically based on clinical examination focused on skull shape, with additional methods such as head circumference, cranial ultrasound, and 3D stereophotography, and CT or MRI reserved for complex cases.
“The diagnosis of craniosynostosis is typically based on a clinical examination focused on skull shape. Additional methods, such as head circumference measurement, cranial ultrasound (CUS), and 3D stereophotography, may be used, with computed tomography (CT) or magnet resonance imaging (MRI) reserved for complex cases [2, 7, 8].”
From Developments in diagnostic and surgical techniques in children with sagittal suture craniosynostosis: a systematic review spanning the last 30 years (2025) · cites this paper as [8]
The Introduction (page unavailable) says experts can diagnose craniosynostosis by examining head shape, and the Discussion (page unavailable) identifies ultrasound, MRI, and 3D stereophotogrammetry as diagnostic options. The copy does not substantiate head-circumference measurement or reserving CT and MRI for complex cases. Instead, the Introduction calls CT the primary imaging technique, and Methods says CT confirmation was part of the study center’s standard treatment protocol. (LLM, conf=0.88)
Experimental — accuracy not yet measuredToday the most common approach for evaluating suspected craniosynostosis is a detailed clinical examination by skilled professionals, where characteristic skull morphology serves as the primary indicator for provisional diagnosis.
“Today the most common approach for evaluating suspected craniosynostosis is a detailed clinical examination by skilled professionals, where characteristic skull morphology serves as the primary indicator for provisional diagnosis.”
From Developments in diagnostic and surgical techniques in children with sagittal suture craniosynostosis: a systematic review spanning the last 30 years (2025) · cites this paper as [8]
The Introduction (page unavailable) says specialists at tertiary centers can diagnose craniosynostosis accurately by visually examining head shape, supporting the role of skilled examination and skull morphology. It does not establish that clinical examination is the most common approach or that morphology is the primary indicator for a provisional diagnosis; it identifies CT as the primary imaging technique. (LLM, conf=0.85)
Experimental — accuracy not yet measuredDiagnostic confirmation typically involves measurement of head circumference, ultrasonography and, if required and technically possible, three-dimensional stereophotography.
“Diagnostic confirmation typically involves the use of methods such as measurement of the head circumference, ultrasonography and if required and technically possible three-dimensional stereophotography.”
From Developments in diagnostic and surgical techniques in children with sagittal suture craniosynostosis: a systematic review spanning the last 30 years (2025) · cites this paper as [8]
The Discussion (page not supplied) identifies ultrasound and 3D stereophotogrammetry as methods that can be used in craniosynostosis diagnosis. It does not mention head-circumference measurement or describe the claimed typical sequence of diagnostic confirmation. The Introduction and Methods > Data acquisition instead identify CT as the primary imaging technique and the method used to confirm cases in this study. (LLM, conf=0.86)
Experimental — accuracy not yet measuredIn more challenging or atypical cases, additional imaging techniques like CT and MRI may be employed.
“In more challenging or atypical cases, additional imaging techniques like CT and MRI may be employed [2, 7, 8, 37].”
From Developments in diagnostic and surgical techniques in children with sagittal suture craniosynostosis: a systematic review spanning the last 30 years (2025) · cites this paper as [8]
The Introduction (page not provided) calls CT the primary imaging technique for craniosynostosis diagnosis, and the Discussion (page not provided) says MRI can also be used. The paper does not say that CT or MRI is reserved for challenging or atypical cases; its description of CT as the primary technique does not establish that condition. (LLM, conf=0.84)
Experimental — accuracy not yet measured
De Jong et al. presented a radiation-free alternative combining 3D stereophotogrammetry with a deep learning algorithm to assess deviations in skull shape.
“De Jong et al. presented a radiation-free alternative that combines 3D stereophotogrammetry with a deep learning algorithm to assess deviations in skull shape.”
From Developments in diagnostic and surgical techniques in children with sagittal suture craniosynostosis: a systematic review spanning the last 30 years (2025) · cites this paper as [8]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126 · see citing works
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016 · see citing works
(2014) · Cited by 33,419 · see citing works
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · see citing works
TensorFlow: A system for large-scale machine learningPreprint
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al. (2016) · arXiv (Cornell University) · doi:10.5555/3026877.3026899 · Cited by 16,369 · see citing works
A survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332 · see citing works
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362 · see citing works
(2010) · International Conference on Machine Learning · Cited by 13,995 · see citing works
A survey on Image Data Augmentation for Deep Learning
Shorten, C., & Khoshgoftaar, T. M. (2019) · Journal of Big Data · doi:10.1186/s40537-019-0197-0 · Cited by 13,203 · see citing works
Algorithms for Clustering Data
Sarle, W. S., Jain, A. K., & Dubes, R. C. (1990) · Technometrics · doi:10.2307/1268876 · Cited by 7,893 · see citing works
Algorithms for clustering data
Flury, B. N. (1989) · Journal of Statistical Planning and Inference · doi:10.1016/0378-3758(89)90033-5 · Cited by 6,493 · see citing works
Deep learning in medical image analysis
Shen, D., Wu, G., & Suk, H.-I. (2017) · Annual Review of Biomedical Engineering · doi:10.1146/annurev-bioeng-071516-044442 · Cited by 4,968 · see citing works
Generative Adversarial Networks
Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1406.2661 · Cited by 4,477 · see citing works
Text Data Augmentation for Deep Learning
Shorten, C., Khoshgoftaar, T. M., & Furht, B. (2021) · Journal Of Big Data · doi:10.1186/s40537-021-00492-0 · Cited by 1,798 · see citing works
Shin, H.-C., Tenenholtz, N., Rogers, J. K., Schwarz, C. G., Senjem, M. L., Gunter, J. L., Andriole, K. P., & Michalski, M. H. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00536-8_1 · Cited by 695 · see citing works
Neural representations of events arise from temporal community structure
Schapiro, A. C., Rogers, T. T., Cordova, N. I., Turk-Browne, N. B., & Botvinick, M. M. (2013) · Nature Neuroscience · doi:10.1038/nn.3331 · Cited by 556 · see citing works
GANs for medical image analysis
Kazeminia, S., Baur, C., Kuijper, A., van Ginneken, B., Navab, N., Albarqouni, S., & Mukhopadhyay, A. (2020) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2020.101938 · Cited by 548 · see citing works
GAN Augmentation: Augmenting Training Data using Generative Adversarial NetworksPreprint
Bowles, C. T., Chen, L., Guerrero, R., Bentley, P., Gunn, R. N., Hammers, A., Dickie, D. A., Hernández, M. D. C. V., Wardlaw, J. M., & Rueckert, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.10863 · Cited by 347 · see citing works
3D digital stereophotogrammetry: a practical guide to facial image acquisition
Heike, C. L., Upson, K., Stuhaug, E., & Weinberg, S. M. (2010) · Head & Face Medicine · doi:10.1186/1746-160x-6-18 · Cited by 273 · see citing works
Mathijssen, I. M. J. (2015) · Journal of Craniofacial Surgery · doi:10.1097/scs.0000000000002016 · Cited by 232 · see citing works
Vangelisti, A., Natali, L., Bernardi, R., Sbrana, C., Turrini, A., Hassani‐Pak, K., Hughes, D., Cavallini, A., Giovannetti, M., & Giordani, T. (2018) · Scientific Reports · doi:10.1038/s41598-017-18445-0 · Cited by 213 · see citing works
Cranial vault growth in craniosynostosis
Delashaw, J. B., Persing, J. A., Broaddus, W. C., & Jane, J. A. (1989) · Journal of neurosurgery · doi:10.3171/jns.1989.70.2.0159 · Cited by 185 · see citing works
Revising the evolutionary computation abstraction
Lehman, J., & Stanley, K. O. (2010) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/1830483.1830503 · Cited by 182 · see citing works
Biomedical Data Augmentation Using Generative Adversarial Neural Networks
Calimeri, F., Marzullo, A., Stamile, C., et al. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68612-7_71 · Cited by 148 · see citing works
Eley, K. A., Watt-Smith, S. R., Sheerin, F., & Golding, S. J. (2014) · European Radiology · doi:10.1007/s00330-014-3286-7 · Cited by 136 · see citing works
The Incidence of Isolated Craniosynostosis in the Newborn Infant
Shuper, A. (1985) · Archives of Pediatrics and Adolescent Medicine · doi:10.1001/archpedi.1985.02140030091038 · Cited by 129 · see citing works
The Diagnosis and Treatment of Single-Sutural Synostoses: Are Computed Tomographic Scans Necessary?
Fearon, J. A., Singh, D. J., Beals, S. P., & Yu, J. C. (2007) · Plastic and Reconstructive Surgery · doi:10.1097/01.prs.0000279477.56044.55 · Cited by 119 · see citing works
Changing Epidemiology of Nonsyndromic Craniosynostosis and Revisiting the Risk Factors
Lee, H. Q., Hutson, J. M., Wray, A. C., Lo, P. A., Chong, D. K., Holmes, A. D., & Greensmith, A. L. (2012) · Journal of Craniofacial Surgery · doi:10.1097/scs.0b013e318252d893 · Cited by 116 · cited 2× · see citing works
“The prevalence of isolated, non-syndromic cranio-synostosis is 3.14 to 6 per 10,000 live births 3,4 .”
BackgroundInfluentialThe effects of craniosynostosis on the brain with respect to intracranial pressure
Bristol, R. E., Leković, G. P., & Rekate, H. L. (2004) · Seminars in Pediatric Neurology · doi:10.1016/j.spen.2004.11.001 · Cited by 104 · see citing works
Risk of Brain Tumor Induction from Pediatric Head CT Procedures: A Systematic Literature Review
Sheppard, J. P., Nguyen, T., Alkhalid, Y., Beckett, J. S., Salamon, N., & Yang, I. (2018) · Brain Tumor Research and Treatment · doi:10.14791/btrt.2018.6.e4 · Cited by 90 · see citing works
Avoiding CT scans in children with single-suture craniosynostosis
Schweitzer, T., Böhm, H., Meyer‐Marcotty, P., Collmann, H., Ernestus, R., & Krauß, J. (2012) · Child s Nervous System · doi:10.1007/s00381-012-1721-0 · Cited by 88 · see citing works
Bailo, O., Ham, D., & Shin, Y. M. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00136 · Cited by 87 · see citing works
Bhalodia, R., Dvoracek, L. A., Ayyash, A. M., Kavan, L., Whitaker, R., & Goldstein, J. A. (2020) · Journal of Craniofacial Surgery · doi:10.1097/scs.0000000000006215 · Cited by 78 · see citing works
Evaluation of the infant with an abnormal skull shape
Cunningham, M. L., & Heike, C. L. (2007) · Current Opinion in Pediatrics · doi:10.1097/mop.0b013e3282f1581a · Cited by 71 · see citing works
Craniosynostosis : Updates in Radiologic Diagnosis
Kim, H. J., Roh, H. G., & Lee, I. W. (2016) · Journal of Korean Neurosurgical Society · doi:10.3340/jkns.2016.59.3.219 · Cited by 66 · see citing works
Meulstee, J. W., Verhamme, L. M., Borstlap, W. A., Van der Heijden, F., De Jong, G. A., Xi, T., Bergé, S. J., Delye, H., & Maal, T. J. J. (2017) · International Journal of Oral and Maxillofacial Surgery · doi:10.1016/j.ijom.2017.03.017 · Cited by 66 · see citing works
Self-citationLow-Cost Smartphone-Based Photogrammetry for the Analysis of Cranial Deformation in Infants
Barbero-García, I., Lerma, J. L., Marqués‐Mateu, Á., & Miranda, P. (2017) · World Neurosurgery · doi:10.1016/j.wneu.2017.03.015 · Cited by 65 · see citing works
Cranial Ultrasound as a First-Line Imaging Examination for Craniosynostosis
Rozovsky, K., Udjus, K., Wilson, N., Barrowman, N. J., Simanovsky, N., & Miller, E. (2016) · Pediatrics · doi:10.1542/peds.2015-2230 · Cited by 64 · see citing works
Porras, A. R., Tu, L., Tsering, D., Mantilla‐Rivas, E., Oh, A. K., Enquobahrie, D. A., Keating, R., Rogers, G. F., & Linguraru, M. G. (2019) · Plastic & Reconstructive Surgery · doi:10.1097/prs.0000000000006260 · Cited by 62 · see citing works
Cho, M., Hallac, R. R., Effendi, M., Seaward, J. R., & Kane, A. A. (2018) · Scientific Reports · doi:10.1038/s41598-018-24756-7 · Cited by 46 · see citing works
Barbero-García, I., Lerma, J. L., Miranda, P., & Marqués‐Mateu, Á. (2018) · Measurement · doi:10.1016/j.measurement.2018.08.059 · Cited by 30 · see citing works
de Jong, G., Tolhuisen, M. L., Meulstee, J. W., van der Heijden, F., van Lindert, E., Borstlap, W. A., Maal, T., & Delye, H. (2017) · Journal of Cranio-Maxillofacial Surgery · doi:10.1016/j.jcms.2017.02.007 · Cited by 24 · see citing works
Self-citationGenerative adversarial networks and adversarial methods in biomedical image analysisPreprint
Wolterink, J. M., Kamnitsas, K., Ledig, C., & Išgum, I. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.10352 · Cited by 19 · see citing works
The normal evolution of the cranium in three dimensions
Meulstee, J. W., de Jong, G., Borstlap, W. A., Koerts, G., Maal, T., & Delye, H. (2019) · International Journal of Oral and Maxillofacial Surgery · doi:10.1016/j.ijom.2019.10.012 · Cited by 17 · see citing works
Self-citationThe computed cranial focal point
de Jong, G., Maal, T., & Delye, H. (2015) · Journal of Cranio-Maxillofacial Surgery · doi:10.1016/j.jcms.2015.08.023 · Cited by 14 · see citing works
Self-citationISCFS 2019 Abstract Supplement
(2019) · Plastic & Reconstructive Surgery Global Open · doi:10.1097/01.gox.0000582696.10862.92 · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Photogrammetry Applied to Neurosurgery: A Literature Review
Trandzhiev, M., Vezirska, D. I., Maslarski, I., Milev, M. D., Laleva, L., Nakov, V., Cornelius, J. F., & Spiriev, T. (2023) · Cureus · doi:10.7759/cureus.46251 · Cited by 23 · see citing works
Moderne Behandlung von Kraniosynostosen
Schmidt, L., Fassl, V., Erhardt, L., Winter, J., Lollert, A., Heider, J., & Ottenhausen, M. (2023) · Monatsschrift Kinderheilkunde · doi:10.1007/s00112-022-01683-6 · Cited by 2 · see citing works
Hermann, J., Raak, C. K., Ostermann, T., & Scharbrodt, W. (2025) · Orphanet Journal of Rare Diseases · doi:10.1186/s13023-025-03978-9 · Cited by 2 · see citing works
“Additional methods, such as head circumference measurement, cranial ultrasound (CUS), and 3D stereophotography, may be used, with computed tomography (CT) or magnet resonance imaging (MRI) reserved for complex cases [2, 7, 8].”
Influential
- Authors
- de Jong, G., Bijlsma, E., Meulstee, J., Wennen, M., van Lindert, E., Maal, T., Aquarius, R., & Delye, H.
- Affiliations
- Radboud University Medical Center (NL)
- Radboud University Nijmegen (NL)
- Venue
- Scientific Reports
- Published
- 2020-09-18
- Volume
- 10
- Issue
- 1
- Pages
- 15346-15346
- ISSN
- 2045-2322 (ISSN-L)
- PMC
- PMC7501225
- OpenAlex
- W3087269353
- Cited by
- 62
- References
- 47
- Citations by year
- 2026: 5 · 2025: 10 · 2024: 9 · 2023: 15 · 2022: 18 · 2021: 4
- FWCI
- 5.42
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Scientific Reports (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Pure Amsterdam UMC (acceptedVersion, cc-by)
- Data Archiving and Networked Services (DANS) (submittedVersion, other-oa)
- Radboud Repository (Radboud University) (submittedVersion)
- Radboud Repository (Radboud University) (submittedVersion, other-oa)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Craniofacial Disorders and Treatments
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Social Sciences › Arts and Humanities › Archeology › Forensic Anthropology and Bioarchaeology Studies
- Keywords
- craniosynostosis, scaphocephaly, trigonocephaly, anterior plagiocephaly, deep learning, infant head shape, cranial sutures
- MeSH terms
- Deep Learning, Craniosynostoses, Facial Bones, Head, Humans, Infant, Photogrammetry, Case-Control Studies, Imaging, Three-Dimensional
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
