Determination of Cranial Index in Sagittal Synostosis using Artificial Intelligent Techniques

Background: At least one main suture of skull is closed prematurely in craniosynostosis; which may lead to different skull and face deformities and various types of child developmental delay. Increased postero-anterior diameter of skull is the main characteristic of sagittal craniosynostosis. Cranial index is the most important parameter for diagnosis and monitoring of children with this deformity. This index is generally determined by direct measuring of infant’s head dimensions or using skull CT scan. Artificial intelligence-based techniques could identify the shape of head from routine digital photos of child and therefore, they may play a useful role in assisting physicians and parents for early diagnosis of skull anomaly, better intervention follow-up and reducing medical system financial costs. Materials and Methods: In this diagnostic study, by developing an executive scientific method, automatic measurement of cranial index in sagittal craniosynostotic infants based on simulated annealing algorithm was done (by using routine digital photos of their head). Pre-operative photos of 59 patients operated in Mofid children hospital (Tehran, Iran); were processed and the cranial index (normal value between 75% to 85%) was calculated with the proposed algorithm and compared with pediatric neurosurgeon measured values, using Matlab software. Findings: The proposed algorithm calculated the cranial index with acceptable accuracy. The simulated annealing algorithm determined the cranial index with mean 72.04 and standard deviation of 5.21, which have minimal differences with surgeon measured values with mean of 72.21 and standard deviation of 5.08. In statistical investigation, using paired t-test, there was no statistical significant differences between these two methods (p-value = 0.52). The values measured by this method in 55 patients out of 59 studied patients (93.2%) are in the range of optimal values determined by the specialist (p≤0.8 ). Conclusion: It seems that the proposed method could determine the cranial index from routine digital patient’s head photos with acceptable accuracy. More development of this method may assist physicians and parents in early diagnosis of this anomaly, better monitoring of treatment results and reducing medical financial costs.