Objective To develop a deep learning system for CT images to assist in the diagnosis of thoracolumbar fractures and analyze the feasibility of its clinical application. Methods Collected from West China Hospital of Sichuan University from January 2019 to March 2020, a total of 1256 CT images of thoracolumbar fractures were annotated with a unified standard through the Imaging LabelImg system. All CT images were classified according to the AO Spine thoracolumbar spine injury classification. The deep learning system in diagnosing ABC fracture types was optimized using 1039 CT images for training and validation, of which 1004 were used as the training set and 35 as the validation set; the rest 217 CT images were used as the test set to compare the deep learning system with the clinician’s diagnosis. The deep learning system in subtyping A was optimized using 581 CT images for training and validation, of which 556 were used as the training set and 25 as the validation set; the rest 104 CT images were used as the test set to compare the deep learning system with the clinician’s diagnosis. Results The accuracy and Kappa coefficient of the deep learning system in diagnosing ABC fracture types were 89.4% and 0.849 (P<0.001), respectively. The accuracy and Kappa coefficient of subtyping A were 87.5% and 0.817 (P<0.001), respectively. Conclusions The classification accuracy of the deep learning system for thoracolumbar fractures is high. This approach can be used to assist in the intelligent diagnosis of CT images of thoracolumbar fractures and improve the current manual and complex diagnostic process.
ObjectiveTo evaluate the effectiveness of percutaneous monoplanar screw internal fixation via injured vertebrae for treatment of thoracolumbar fracture.MethodsBetween May 2015 and August 2017, 38 cases of thoracolumbar fractures without neurological symptom were treated with percutaneous monoplanar screw internal fixation via injured vertebrae. There were 22 males and 16 females, aged 25-52 years (mean, 32.5 years). There were 23 cases of AO type A3 and 15 cases of AO type A4. The injured vertebrae located at T11 in 4 cases, T12 in 9 cases, L1 in 11 cases, L2 in 10 cases, L3 in 3 cases, and L4 in 1 case. The mean interval between injury and operation was 4.5 days (range, 3-7 days). The pre- and post-operative degrees of lumbodorsal pain were estimated by the visual analogue scale (VAS) score. The X-ray film, CT three-dimensional reconstruction, and MRI were performed, and the ratio of anterior vertebral body height and sagittal Cobb angle were measured to assess the kyphosis of the fractured area.ResultsAll operations in 38 patients successfully completed without complications such as dural sac, nerve root, or vascular injury. The operation time was (56.2±3.7) minutes and the intraoperative blood loss was (42.3±3.5) mL. All incisions healed by first intention without redness, swelling, or exudation. All patients were followed up 17-33 months, with an average of 21.5 months. The VAS score at each time point after operation significantly improved when compared with that before operation (P<0.05), and significantly improved at 3 months and last follow-up when compared with that at 1 week (P<0.05); there was no significant difference between 3 months and last follow-up (P>0.05). There was no internal fixator loosening, breakage, or delayed kyphosis in all patients. The ratio of anterior vertebral body height and sagittal Cobb angle significantly improved postoperatively (P<0.05), and no significant difference was found between the different time points after operation (P>0.05).ConclusionPercutaneous monoplanar screw internal fixation via injured vertebrae is an easy approach to treat thoracolumbar fracture without neurological symptom, which can effectively restore vertebral body height and correct kyphosis, and avoid long-term segmental kyphosis.
ObjectiveTo explore the application of different digestive system management strategies in the perioperative period of thoracolumbar fracture.MethodsThe clinical data of the patients with thoracolumbar fractures and pedicle screw fixation in Affiliated Hospital of Southwest Medical University from January 2016 to January 2018 were retrospectively analyzed. According to different perioperative management strategies of the digestive system, they were divided into two groups. Patients with careful management strategy were included in the observation group, and patients with routine management were included in the control group. The baseline conditions, the abnormalities of digestive tract function at admission and before and after surgery, the postoperative first feeding time, exhaust time, defecation time, the incidence of other postoperative complications except digestive tract complication, length of stay and patient satisfaction were compared between the two groups. At 6 months after surgery, the fracture healing, loosening or fracture of internal plants were compared between the two groups.ResultA total of 121 patients were included in the study, including 67 cases in the observation group and 54 cases in the control group. There was no significant differences in the baseline conditions between the two groups (P>0.05). There were no significant differences between the two groups in the incidences of digestive system dysfunction at admission (P>0.05). The incidences of digestive system dysfunction in the observation group before and after surgery were lower than those in the control group (29.9% vs. 53.7%, P<0.05; 35.8% vs. 61.1%, P<0.05). The first eating time [(3.7±1.1) vs. (6.7±2.6) h], exhaust time [(7.8±2.3) vs. (13.6±4.2) h], defecation time [(26.7±8.1) vs. (40.9±11.2) h] and length of stay [(6.5±2.4) vs. (9.0±2.7) d] in the observation group were shorter than those in the control group (P<0.005), and the patients’ satisfaction was better than that of the control group (8.3±1.1 vs. 7.6±1.3; t=?3.208, P=0.002). There was no statistically significant difference in the incidence of postoperative complications except digestive tract complication, and the fracture healing rate, the incidence of nail-rod breakage at6 months after surgery between the two groups (P>0.05). No internal plant loosening was found in the two groups of patients within 6 months after surgery.ConclusionThe application of the careful digestive system management strategy in patients with thoracolumbar fractures can help reduce the incidence of perioperative gastrointestinal dysfunction, promote the recovery of perioperative gastrointestinal function, shorten the length of hospital stay, and improve patient satisfaction.
A new method of anterior decompression for thoracolumbar fractures with paralysi s in six cases was reported. In a follw-up of one to five months, was shown that the neurological functions in all six cases has improved ⅡⅢ rank in Frankl classification. The author believe that the method has the following advantages, such as: less trauma from operation; the level and the limit of decompression could be made without Xray during the operation; usually only 1/5 to 1/4 of the vertebral body was excised so that the stability of the spine was not disturbed, and the obvious favourable results.
Objective To investigate the influence of spinal cord decompression on posterior surgical treatment of thoracolumbar fracture, and to provide the practical basis for the indications of posterior spinal cord decompression Methods The cl inical data were retrospectively analyzed from 170 cases of thoracolumbar fracture treated with posterior surgical treatment between January 2005 and January 2009. There were 119 males and 51 females with an average age of42.7 years (range, 17-68 years). The fracture locations included T11 in 22 cases, T12 in 30 cases, L1 in 57 cases, and L2 in 61 cases. According to Denis classification system, there were 65 cases of compression fractures, 44 cases of burst fractures, 25 cases of flexion-distraction injuries, and 36 cases of fracture-dislocations. The time from injury to operation was 3-8 days (mean, 4.4 days). All the cases were divided into 4 groups according to space-occupying rates of spinal cord: group A, ≤20% (n=32); group B, 21%-40% (n=68); group C, 41%-60% (n=37); and group D, ≥ 61% (n=33). Through statistical analysis, the correlation between space-occupying rates and spinal cord function (Frankel grade) was evaluated, and the necessities of spinal cord decompression was studied in the patients who had neurological symptoms with space-occupying rates under 40%. Results There was no positive correlation between the degree of spinal cord injury and the space-occupying rates of bone fragments broken into the spinal canal. All patients were followed up 13-41 months (mean, 23.5 months). During the follow-up period, no secondary neurological damage occurred in the patients who were not given posterior spinal cord decompression with space-occupying rates under 40% (28 cases). And also in the cohort of patients with neurological symptoms whose space-occupying rates were under 40%, the posterior spinal cord decompression (65 cases) could improve the spinal cord function significantly when compared with no decompression cohort (7 cases), (P lt; 0.05). Conclusion The relative indications of posterior spinal cord decompression for thoracolumbar fracture are as follows: the cases having neurological symptoms with space-occupying rates under 40% and the ones having the neurological symptoms or not with space-occupying rates above 40%.
Objective To study the feasibil ity and rel iabil ity of the multi-plannar reformation (MPR) of multispiral CT (MSCT) in measuring the kyphosis angle (KA) after thoracolumbar fracture. Methods From December 2007 to December 2009, 45 thoracolumbar fracture patients who underwent computed radiology (CR) and MSCT were recruited. There were 32 males and 13 females with a mean age of 48 years (range, 24-63 years), including 36 simple compression fractures and 9 burst fractures. The fracture locations were T11 in 6 cases , T12 in 11 cases, L1 in 20 cases, and L2 in 8 cases. Fracture was caused by trafffic accident in 25 cases, by fall ing from height in 12 cases, and by others in 8 cases. The imaging examination was performed after 2 hours to 7 days of injury in 22 cases and after more than 7 days in 23 cases. The KA was measured on the lateral X-ray films of CR and MPR by two observers, then the measurements were done again after three weeks. The data were statistically analyzed. Results The average KA values on CR by two observers were (20.75 ± 8.31)° and (22.49 ± 9.07)°, respectively; showing significant difference (P lt; 0.05), and the correlation was good (r=0.882, P lt; 0.05). The average KA values on MPR by two observers were (16.65 ± 8.62)° and (17.08 ± 7.88)°, respectively, showing no significant difference (P gt; 0.05), the correlation was excellent (r=0.976, P lt; 0.05). The average KA values on CR and MPR were (21.61 ± 8.43)° and (16.87 ± 8.20)°, respectively; showing significant difference (P lt; 0.05), the correlation was good (r=0.852, P lt; 0.05). Conclusion It is more feasible and rel iable in measuring the KA on MRP of MSCT than CR, but the value is larger on CR.
Objective To review the latest progress in classification system of thoracolumbar fractures and its surgical treatment with posterior approaches. Methods Recent l iterature about classification system of thoracolumbar fractures and its surgical treatment was reviewed. Results For the treatment of thoracolumbar fracture, the surgeon first should decide whether the surgical treatment was necessary. Recently, a new classification system had been developed to help the surgeon make the right decision. The surgical methods included short segment internal fixation and long segment internalfixation with or without fusion, and minimally invasive internal fixation. Conclusion The progress in the surgical treatmentof thoracolumbar fracture will help spinal surgeon decide the necessary surgery beneficial for the patients. The most appropriate and effective surgical method with the minimum damage should be used to treat the fracture. The advantages of non-fusion surgical treatment still need a further study.
ObjectiveTo explore the clinical characteristics and surgical treatment strategies of delayed spinal cord injury (SCI) caused by atypical compression of old thoracolumbar fracture.MethodsBetween January 2011 and June 2018, 32 patients with delayed SCI caused by atypical compression of old thoracolumbar fracture who met the inclusion criteria were admitted and divided into group A (20 cases, underwent anterior subtotal vertebral body resection+titanium mesh reconstruction+screw rod internal fixation) and group B (12 cases, underwent posterior 270° ring decompression of vertebral canal+titanium mesh reconstruction+screw rod internal fixation) according to the different operation approaches. There was no significant difference between the two groups in age, gender, cause of injury, fracture segment, disease duration, preoperative American Spinal Injury Association (ASIA) classification, and preoperative back pain visual analogue scale (VAS) score, lumbar Japanese Orthopaedic Association (JOA) score, kyphosis angle, and vertebral canal occupational ratio (P>0.05). The incision length, operation time, intraoperative blood loss, complications, and bone fusion time of reconstructed vertebrae were recorded and compared between the two groups; the kyphosis angle, back pain VAS score, and lumbar JOA score were used to evaluate the effectiveness.ResultsExcept that the incision length in group A was significantly shorter than that in group B (t=?4.865, P=0.000), there was no significant difference in intraoperative blood loss and operation time between the two groups (P>0.05). There was no deaths or postoperative paraplegia cases in the two groups, and no deep infection or skin infection occurred. There was 1 case of cerebrospinal fluid leakage, 1 case of inferior vena cava injury, and 1 case of chyle leakage in group A. No serious complications occurred in group B. There was no significant difference in the incidence of complications between the two groups (P=0.274). All 32 patients were followed up 12-61 months, with an average of 20.8 months. The follow-up time for groups A and B were (19.35±5.30) months and (23.25±12.20) months respectively, and the difference was not significant (t=?1.255, P=0.219). The reconstructed vertebrae in all cases obtained bony fusion postoperatively. The fusion time of groups A and B were (8.85±2.27) months and (8.50±2.50) months respectively, and the difference was not significant (t=0.406, P=0.688). The kyphosis angle, back pain VAS score, and lumbar JOA score of the two groups at each time point after operation and last follow-up were significantly improved when compared with preoperatively (P<0.05); the lumbar JOA score was further improved with time postoperatively (P<0.05), while the kyphosis angle and the VAS score of back pain remained similarly (P>0.05). Comparison of kyphosis angle, back pain VAS score, and lumbar JOA score between the two groups at various time points postoperatively showed no significant difference (P>0.05). At last follow-up, the JOA score improvement rate in groups A and B were 83.87%±0.20% and 84.50%±0.14%, respectively, and the difference was not significant (t=–0.109, P=0.914); the surgical treatment effects of the two groups were judged to be significant.ConclusionIn the later stage of treatment of old thoracolumbar fractures, even mild kyphosis and spinal canal occupying may induce delayed SCI. Surgical correction and decompression can significantly promote the recovery of damaged spinal cord function. Compared with anterior approach surgery, posterior approach surgery has the advantages of less trauma, convenient operation, and fewer complications, so it can be preferred.
ObjectiveTo systematically review the efficacy of at the fracture level (AFL) versus cross the fracture level (CFL) short-segment pedicle screw fixation for thoracolumbar fractures.
MethodsWe electronically search PubMed, The Cochrane Library (Issue 8, 2015), EMbase, CBM, CNKI, VIP and WanFang data to collect randomized controlled trials (RCTs) of AFL versus CFL short segment pedicle screw fixation for thoracolumbar fractures from inception to Aug. 2015. Two reviewers independently screened literature, extracted data and assessed the risk of bias of included studies. Meta-analysis was performed using RevMan 5.3 software.
ResultsA total of 11 RCTs involving 730 patients were included. The results of meta-analysis indicated that: compared with the CFL group, the AFL group had more blood loss (MD=9.8, 95%CI 7.40 to 12.20), less implant failure rate (RR=0.19, 95%CI 0.07 to 0.48), lower long term postoperative VAS score of thoracolumbar pain (MD=-1.20, 95%CI -1.85 to -0.56), higher correction in short term postoperative kyphotic Cobb angle (MD=3.56, 95%CI 2.25 to 4.87), smaller value in long term postoperative kyphotic Cobb angle and its loss of correction (MD=-3.95, 95%CI -7.78 to -0.12; MD=-4.65, 95%CI -6.91 to -2.40), smaller degree of anterior vertebral height compression in short and long term postoperative (MD=-3.51, 95%CI -5.23 to -1.80; MD=-8.28, 95%CI -12.22 to -4.33), better result in long term postoperative anterior vertebral height and its loss of correction (MD=8.00, 95%CI 3.85 to 12.15; MD=-6.06, 95%CI -7.68 to -4.44). There were no significant differences between two groups regarding operation time, infectious complications and short term postoperative kyphotic Cobb angle (MD=0.11, 95%CI -5.36 to 5.57; RR=0.55, 95%CI 0.11 to 2.85; MD=-0.66, 95%CI -2.19 to 0.87).
ConclusionCurrent evidence shows that AFL short-segment pedicle screw fixation for thoracolumbar fractures is superior to CFL fixation. Due to limited quality and quantity of the included studies, more high quality studies are needed to verify the above conclusion.
ObjectiveTo explore the effectiveness of pedicle screw fixation combined with non-fusion technology for the treatment of thoracolumbar fracture (AO type A) through Wiltse paraspinal approach.
MethodsBetween March 2011 and December 2012, 35 cases of thoracolumbar fractures were treated with pedicle screw fixation combined with non-fusion technology by Wiltse paraspinal approach. There were 27 males and 8 females, aged from 19 to 51 years (mean, 39.7 years). The time from injury to operation varied from 3 to 15 days (mean, 5.9 days). The causes of injury were traffic accident in 17 cases, falling from height in 11 cases, and crush trauma in 7 cases. All fractures were single-segment fracture, including T8 in 1 case, T9 in 2 cases, T10 in 2 cases, T11 in 3 cases, T12 in 12 cases, L1 in 10 cases, L2 in 4 cases, and L3 in 1 case. According to AO classification, there were 17 type A1 fractures (compression fracture), 3 type A2 fractures (splitting fracture), and 15 type A3 fractures (burst fracture). Based on American Spinal Injury Association (ASIA) spinal cord injury grade, all cases were in grade E before operation. Perioperative parameters were recorded; the anterior vertebral height and kyphotic Cobb angle of vertebral bodies were measured before and after operation to evaluate the effect of correction.
ResultsThe mean operating time was 74 minutes; the mean blood loss was 125 mL; and the mean drainage volume was 51 mL. Skin necrosis of incision occurred in 2 cases and was cured after dressing change; primary healing of incision was obtained in the others. All patients were followed up 15-24 months (mean, 17.3 months). No loosening or breakage of internal fixation was found. The internal fixator was removed at 12-19 months after operation (mean, 15 months). There were significant differences in Cobb's angle and anterior vertebral body height between before operation and immediately after operation, before internal fixator removal as well as at last follow-up (P < 0.05). There was no significant difference in anterior vertebral body height among the postoperative time points (P > 0.05). There was significant difference in Cobb's angle between immediately after operation and before internal fixator removal as well as at last follow-up (P < 0.05), but the difference was not significant between before internal fixator removal and at last follow-up (P > 0.05). The motion of fixed segment was restored after internal fixator removal.
ConclusionIt is an effective method of pedicle screw fixation combined with non-fusion technology through Wiltse paraspinal approach for the treatment of thoracolumbar fracture (AO type A). The method has the advantages of simple operation and less trauma. It can effectively rebuild the height of vertebral body and correct kyphotic deformity.
