A deep learning model adjusting for infant gender, age, height, and weight to determine whether the individual infant suit ultrasound examination of developmental dysplasia of the hip (DDH)

Recurrent neural networks (RNNs) have been widely adopted in research areas concerned with sequential data, such as text, audio, and video. However, RNNs consisting of sigma cells or tanh cells are unable to learn the relevant information of input data when the input gap is large. By introducing gate functions into the cell structure, the long short-term memory (LSTM) could handle the problem of long-term dependencies well. Since its introduction, almost all the exciting results based on RNNs have been achieved by the LSTM. The LSTM has become the focus of deep learning. We review the LSTM cell and its variants to explore the learning capacity of the LSTM cell. Furthermore, the LSTM networks are divided into two broad categories: LSTM-dominated networks and integrated LSTM networks. In addition, their various applications are discussed. Finally, future research directions are presented for LSTM networks.

Developmental dysplasia of the hip (DDH) describes a broad spectrum of developmental abnormalities of the hip joint that are traditionally diagnosed during infancy. Because the development of the hip joint is a dynamic process, optimal treatment depends not only on the severity of the dysplasia, but also on the age of the child. Various imaging modalities are routinely used to confirm suspected diagnosis, to assess severity, and to monitor treatment response. For infants younger than 4 months, screening hip ultrasound (US) is recommended only for those with risk factors, equivocal or positive exam findings, whereas for infants older than 4-6 months, pelvis radiography is preferred. Following surgical hip reduction, magnetic resonance (MR) imaging is preferred over computed tomography (CT) because MR can not only confirm concentric hip joint reduction, but also identify the presence of soft-tissue barriers to reduction and any unexpected postoperative complications. The routine use of contrast-enhanced MR remains controversial because of the relative paucity of well-powered and validated literature. The main objectives of this article are to review the normal and abnormal developmental anatomy of the hip joint, to discuss the rationale behind the current recommendations on the most appropriate selection of imaging modalities for screening and diagnosis, and to review routine and uncommon findings that can be identified on post-reduction MR, using an evidence-based approach. A basic understanding of the physiology and the pathophysiology can help ensure the selection of optimal imaging modality and reduce equivocal diagnoses that can lead to unnecessary treatment.

Background Acetabular dysplasia (AD) is a well-known cause of osteoarthritis (OA) of the hip, with its prevalence previously determined on plain radiography. The prevalence of preexisting AD was reported as 7.3% in a patient-based Asian population. Although computed tomography (CT) could evaluate AD in multiple planes, its prevalence using multiplanar CT images has not been reported. We investigated its prevalence with CT on coronal, axial, and sagittal planes and then determined if adding the axial and sagittal planes enhanced the investigation. Methods We retrospectively examined 52 consecutive Japanese individuals (mean age 59.4 years) who had undergone CT for conditions unrelated to hip disorders. The inclusion criteria of CT images were (1) reconstructed axial slice thickness of ≤1 mm and (2) normal pelvic rotations and tilt. Exclusion criteria were (1) age <20 years, (2) neither hip center could be clearly detected, (3) evidence of hip OA. The parameters used to define AD on the coronal plane were the center–edge angle, Sharp angle, acetabular index, acetabular depth ratio, and acetabulum head index. The anterior and posterior acetabular sector angles were used as axial parameters and the vertical-center-anterior margin angle as the sagittal parameter. AD prevalence was calculated using multiplanar images and then compared with the previously reported Asian prevalence using 95% confidence intervals (CI). In this study, we defined “prevalence” as the proportion of subjects who had AD in at least one hip. Results The mean prevalence of AD on coronal, axial, and sagittal planes was 16.9, 15.4, and 7.7%, respectively. The lowest prevalence found by combining the three planes was 25.0% (95% CI 15.2–38.2%). This prevalence was significantly higher than that in the previously reported Asian population (7.3%). Conclusions At the lowest estimate, the prevalence of AD evaluated in three planes was more than twice as high as the previously reported prevalence in Asians when we investigated its prevalence using multiplanar images. The prevalence of AD in the axial and sagittal planes was not negligible. We therefore suggest that it is important to add axial and sagittal planes’ data when investigating the prevalence of AD.