An Automated Deep Learning Method for Tile AO/OTA Pelvic Fracture Severity Grading from Trauma whole-Body CT.

Admission trauma whole-body CT is routinely employed as a first-line diagnostic tool for characterizing pelvic fracture severity. Tile AO/OTA grade based on the presence or absence of rotational and translational instability corresponds with need for interventions including massive transfusion and angioembolization. An automated method could be highly beneficial for point of care triage in this critical time-sensitive setting. A dataset of 373 trauma whole-body CTs collected from two busy level 1 trauma centers with consensus Tile AO/OTA grading by three trauma radiologists was used to train and test a triplanar parallel concatenated network incorporating orthogonal full-thickness multiplanar reformat (MPR) views as input with a ResNeXt-50 backbone. Input pelvic images were first derived using an automated registration and cropping technique. Performance of the network for classification of rotational and translational instability was compared with that of (1) an analogous triplanar architecture incorporating an LSTM RNN network, (2) a previously described 3D autoencoder-based method, and (3) grading by a fourth independent blinded radiologist with trauma expertise. Confusion matrix results were derived, anchored to peak Matthews correlation coefficient (MCC). Associations with clinical outcomes were determined using Fisher's exact test. The triplanar parallel concatenated method had the highest accuracies for discriminating translational and rotational instability (85% and 74%, respectively), with specificity, recall, and F1 score of 93.4%, 56.5%, and 0.63 for translational instability and 71.7%, 75.7%, and 0.77 for rotational instability. Accuracy of this method was equivalent to the single radiologist read for rotational instability (74.0% versus 76.7%, p = 0.40), but significantly higher for translational instability (85.0% versus 75.1, p = 0.0007). Mean inference time was < 0.1 s per test image. Translational instability determined with this method was associated with need for angioembolization and massive transfusion (p = 0.002-0.008). Saliency maps demonstrated that the network focused on the sacroiliac complex and pubic symphysis, in keeping with the AO/OTA grading paradigm. A multiview concatenated deep network leveraging 3D information from orthogonal thick-MPR images predicted rotationally and translationally unstable pelvic fractures with accuracy comparable to an independent reader with trauma radiology expertise. Model output demonstrated significant association with key clinical outcomes.

Plate versus sacroiliac screw fixation for treating posterior pelvic ring fracture: a Systematic review and meta-analysis.

BACKGROUND: Whether plate fixation or sacroiliac (SI) screw fixation is the better treatment for posterior pelvic ring disruption is controversial. The aim of this systematic review and meta-analysis was to compare the two fixation methods. MATERIAL AND METHODS: The MEDLINE, Embase, and Cochrane Library databases were systematically searched for studies comparing plate and SI screw fixations in posterior pelvic ring injuries. Intraoperative variables, postoperative complications, and clinical/radiological scores were compared between the techniques. RESULTS: Eleven studies were included in the qualitative synthesis, and nine in the meta-analysis. The meta-analysis included 202 patients who underwent plate fixation and 258 patients who underwent SI screw fixation. The incision length and mean blood loss were greater in the plate group than in the SI screw group (standard mean difference (SMD) = 7.29, 95% confidence interval (CI): 3.18-11.40; SMD = 5.09, 95% CI: 2.08-8.09, respectively). Patients in the SI screw group had more X-ray exposure than those in the plate group (SMD = -5.96, 95% CI: -7.95-3.97). There were no differences in operation time and intraoperative complications (SMD = -1.42, 95% CI: -3.90-1.05; OR = 0.92, 95% CI: 0.05-18.60, respectively). The duration of hospital stay was longer in the plate group (SMD = 2.21, 95% CI: 1.74-2.68). There were no differences in postoperative neurological complications, infection rate, and nonunion rate (OR = 1.62, 95% CI: 0.20-13.21; OR = 2.10, 95% CI: 0.74-5.94; OR = 1.12, 95% CI: 0.26-4.87, respectively), but implant loosening was more common in the SI screw group (OR = 0.18, 95% CI: 0.04-0.87). There was no difference in revision surgery (OR = 0.23, 95% CI: 0.02-2.14). The total excellent rating according to the postoperative Majeed functional and Matta scores was higher in the SI screw group (OR = 0.43, 95% CI: 0.20-0.91; OR = 0.24, 95% CI: 0.08-0.74, respectively). CONCLUSIONS: SI screw fixation was superior to plate fixation in the functional and radiological scores, but implant loosening was more common for the treatment posterior pelvic ring injuries.

The use of an anterior pelvic internal fixator to treat disruptions of the anterior pelvic ring: a report of technique, indications and complications.

AIMS: The anterior pelvic internal fixator is increasingly used for the treatment of unstable, or displaced, injuries of the anterior pelvic ring. The evidence for its use, however, is limited. The aim of this paper is to describe the indications for its use, how it is applied and its complications. PATIENTS AND METHODS: We reviewed the case notes and radiographs of 50 patients treated with an anterior pelvic internal fixator between April 2010 and December 2015 at a major trauma centre in the United Kingdom. The median follow-up time was 38 months (interquartile range 24 to 51). RESULTS: Three patients were excluded from the analysis leaving 47 patients with complete follow-up data. Of the 47 patients, 46 achieved radiological union and one progressed to an asymptomatic nonunion. Of the remaining patients, 45 required supplementary posterior fixation with percutaneous iliosacral screws, 2 of which required sacral plating. The incidence of injury to the lateral femoral cutaneous nerve (LFCN) was 34%. The rate of infection was 2%. There were no other significant complications. Without this treatment, 44 patients (94%) would have needed unilateral or bilateral open reduction and plate fixation extending laterally to the hip joint. CONCLUSION: The anterior pelvic internal fixator reduces the need for extensive open surgery and is a useful addition to the armamentarium for the treatment of anterior pelvic injuries. It is associated with injury to the LFCN in a third of patients. Cite this article: Bone Joint J 2017;99-B.1232-6.

Open reduction internal fixation versus percutaneous iliosacral screw fixation for unstable posterior pelvic ring disruptions.

BACKGROUND: Surgical stabilization of posterior pelvic ring fractures can be achieved by either open or closed methods. They all provide a comparable biomechanical stability. The aim of the present study is to compare the clinical results of both techniques for treating posterior pelvic ring injuries. MATERIAL AND METHODS: Seventy patients operated for unstable posterior pelvic ring disruptions were retrospectively reviewed. We compared 35 patients treated by open reduction internal fixation (ORIF group) versus 35 patients stabilized by using closed reduction and percutaneous iliosacral screw fixation (CRIF group) under fluoroscopic guidance. RESULTS: According to pelvic outcome scoring system of Pohlemann et al., 28 patients out of the ORIF group obtained good or excellent results (20 excellent and 8 good), five fair and two poor. In the CRIF group, 30 patients obtained good or excellent results (25 excellent and 5 good), four fair and one poor (P=0.64). The average intraoperative blood loss in the ORIF group was 500cc with average blood transfusion of 2units (1000cc) compared to blood loss 150cc in the CRIF group, with average blood transfusion of 1unit (500cc) (P=0.002). No intraoperative complications were reported in the ORIF group while operative guide wires were broken in two cases in the CRIF group (P=0.16). There were no neurological complications observed in the ORIF group, but one radiculopathy (L5 root palsy) occurred in the CRIF group (P=0.317). In the ORIF group, three patients had superficial wound infection and one patient had deep infection while in the CRIF group, we noted only one case of deep infection (P=0.083). CONCLUSION: No difference was noticed between ORIF and CRIF. The technical decision is variable according to time of surgery, fracture types, patient general condition, skin condition, presence of ipsilateral fractures of the acetabulum and feasibility of the closed reduction. More studies are needed to identify prognostic factors related to quality of the reduction. We need for creation of decisional algorithm for ORIF versus CRIF. LEVEL OF EVIDENCE: Level 4.

Mechanical comparison between lengthened and short sacroiliac screws in sacral fracture fixation: a finite element analysis.

OBJECTIVE: To compare the stability of lengthened sacroiliac screw and standard sacroiliac screw for the treatment of unilateral vertical sacral fractures; to provide reference for clinical applications. METHODS: A finite element model of Tile type C pelvic ring injury (unilateral Denis type II fracture of the sacrum) was produced. The unilateral sacral fractures were fixed with lengthened sacroiliac screw and sacroiliac screw in six different types of models respectively. The translation and angle displacement of the superior surface of the sacrum (in standing position on both feet) were measured and compared. RESULTS: The stability of one lengthened sacroiliac screw fixation in S1 or S2 segment is superior to that of one sacroiliac screw fixation in the same sacral segment. The stability of one lengthened sacroiliac screw fixation in S1 and S2 segments respectively is superior to that of one sacroiliac screw fixation in S1 and S2 segments respectively. The stability of one lengthened sacroiliac screw fixation in S1 and S2 segments respectively is superior to that of one lengthened sacroiliac screw fixation in S1 or S2 segment. The stability of one sacroiliac screw fixation in S1 and S2 segments respectively is markedly superior to that of one sacroiliac screw fixation in S1 or S2 segment. The vertical and rotational stability of lengthened sacroiliac screw fixation and sacroiliac screw fixation in S2 is superior to that of S1. CONCLUSION: In a finite element model of type C pelvic ring disruption, S1 and S2 lengthened sacroiliac screws should be utilized for the fixation as regularly as possible and the most stable fixation is the combination of the lengthened sacroiliac screws of S1 and S2 segments. Even if lengthened sacroiliac screws cannot be systematically used due to specific conditions, one sacroiliac screw fixation in S1 and S2 segments respectively is recommended. No matter which kind of sacroiliac screw is used, if only one screw can be implanted, the fixation in S2 segment is more recommended than that in S1. LEVEL OF EVIDENCE: Experimental study Level III.