Automatic Segmentation of Intracochlear Anatomy in Conventional CT

• Published in: IEEE transactions on biomedical engineering 2011-09, Vol.58 (9), p.2625-2632
• Main Authors: Noble, Jack H., Labadie, Robert F., Majdani, Omid, Dawant, Benoit M.
• Format: Article
• Language: English
• Subjects: Active shape model; Active shape model segmentation; Algorithms; Applied sciences; Biological and medical sciences; cochlear implant; Cochlear implants; Computational modeling; Computed tomography; Computerized, statistical medical data processing and models in biomedicine; Exact sciences and technology; Hearing aids; Humans; Image processing; Image segmentation; Information, signal and communications theory; intracochlear anatomy; Medical management aid. Diagnosis aid; Medical sciences; Pattern recognition; Radiographic Image Enhancement - methods; Reproducibility of Results; scala tympani; Scala Tympani - anatomy & histology; Scala Tympani - diagnostic imaging; Scala Vestibuli - anatomy & histology; Scala Vestibuli - diagnostic imaging; Shape; Signal processing; Surgery; Telecommunications and information theory; Tomography, X-Ray Computed - methods; Training; X-Ray Microtomography
• ISSN: 0018-9294; 1558-2531
• DOI: 10.1109/TBME.2011.2160262

Cochlear implant surgery is a procedure performed to treat profound hearing loss. Clinical results suggest that implanting the electrode in the scala tympani, one of the two principal cavities inside the cochlea, may result in better hearing restoration. Segmentation of intracochlear cavities could thus aid the surgeon to choose the point of entry and angle of approach that maximize the likelihood of successful implant insertion, which may lead to more substantial hearing restoration. However, because the membrane that separates the intracochlear cavities is too thin to be seen in conventional in vivo imaging, traditional segmentation techniques are inadequate. In this paper, we circumvent this problem by creating an active shape model with micro CT (μCT) scans of the cochlea acquired ex vivo. We then use this model to segment conventional CT scans. The model is fitted to the partial information available in the conventional scans and used to estimate the position of structures not visible in these images. Quantitative evaluation of our method, made possible by the set of μCTs, results in Dice similarity coefficients averaging 0.75. Mean and maximum surface errors average 0.21 and 0.80 mm.