Transperineal volumetric ultrasound (TPUS) imaging has become routine practice for diagnosing anorectal dysfunction, a lifechallenging pelvic floor dysfunction (PFD). To assess the integrity of the whole length of the anal sphincter from three-dimensional (3D) ultrasound (US) data, sonographers first extract a tomographic US imaging (TUI) sequence from the TPUS recording. TUI sequences consist of eight equally spaced and properly oriented two-dimensional (2D) coronalview slices of the anal sphincter complex. TUI sequences are visually assessed by a sonographer to diagnose anal sphincter injury. Obtaining TUI sequences is performed manually in clinical practice, which is labour-intensive and requires expert knowledge of pelvic floor anatomy. To the best of our knowledge, this work is the first to report an automatic method to aid this medical imaging acquisition task. We propose a novel, convolutional neural network (CNN) approach for the automatic extraction of the TUI sequences from a TPUS. The method utilises a CNN to segment the external anal sphincter (EAS), and the desired TUI sequences are subsequently extracted after several automatic post-processing steps. The proposed method is evaluated on 30 TPUS recordings and compared against manually acquired gold standard TUI sequences. One expert evaluated the quality of the automatically detected TUI sequences in terms of their clinical acceptability for diagnosis. The automatic method performs with an overall clinical acceptability of 90.00%. The method reduces the time required to extract the anal sphincter complex TUI sequence of a TPUS by 52.36 seconds and may reduce the need for high-level expertise in anorectal dysfunction analysis.