High resolution (HR) magnetic resonance images (MRI) or computed tomography (CT) images can provide clearer anatomical details of human body, which facilitates early diagnosis of the diseases. However, due to the imaging system, imaging environment and human factors, it is difficult to obtain clear high-resolution images. In this paper, we proposed a novel medical image super resolution (SR) reconstruction method via multi-scale information distillation (MSID) network in the non-subsampled shearlet transform (NSST) domain, namely NSST-MSID network. We first proposed a MSID network that mainly consisted of a series of stacked MSID blocks to fully exploit features from images and effectively restore the low resolution (LR) images to HR images. In addition, most previous methods predict the HR images in the spatial domain, producing over-smoothed outputs while losing texture details. Thus, we viewed the medical image SR task as the prediction of NSST coefficients, which make further MSID network keep richer structure details than that in spatial domain. Finally, the experimental results on our constructed medical image datasets demonstrated that the proposed method was capable of obtaining better peak signal to noise ratio (PSNR), structural similarity (SSIM) and root mean square error (RMSE) values and keeping global topological structure and local texture detail better than other outstanding methods, which achieves good medical image reconstruction effect.
OBJECTIVE To probe the clinical results of a new designed operation-double semitendinous reconstruction of posterior cruciate ligament (PCL) with invasive mini-plate. METHODS The new surgical technique was performed on 28 patients with PCL deficient knee in our department from September 1994 to October 1997. Protection of popliteal nerves and blood vessels was emphasized in the operation, and the femoral and tibial tunnel placement was critical to the procedure’s success. RESULTS All patients were followed up 18 to 36 months, averaged 22 months, they gained stable knees. The knee function of 28 patients recovered to normal after the operation, 1 patients had a small range of limitation of the knee flexion, but no obvious dysfunction. CONCLUSION Double semitendinous reconstruction of PCL with invasive mini-plate has advantages in the operated field exposure, adequate tibial and femoral fixation and excellent results in motion, stability and function of the knee after the operation.
ObjectiveTo investigate the diagnosis and effectiveness of limited operative treatment for multi-segmental lumbar disease. MethodsBetween February 2008 and February 2011, 47 patients with multi-segmental lumbar disease were treated, including 27 males and 20 females with an average age of 60.3 years (range, 38-82 years) and a median disease duration of 21 months (range, 6 months to 7 years). Based on preoperative clinical manifestation and imaging examination results, the possibility of preliminary responsible segment was identified as two levels in 31 cases (L4, 5 and L5, S1 in 22 cases, L3, 4 and L4, 5 in 6 cases, L2, 3 and L3, 4 in 3 cases) and three levels in 16 cases (L3, 4, L4, 5, and L5, S1 in 9 cases, L1, 2, L4, 5, and L5, S1 in 4 cases, L2, 3, L4, 5, and L5, S1 in 3 cases). Selective nerve root block (SNRB) was used in all cases to identify the responsible segment. Based on the results, the patients were treated by limited operative treatment. The operation time, intra operative blood loss, postoperative drainage volume, postoperative ambulation time, and complications were recorded. The clinical outcome was evaluated according to the visual analogue scale (VAS) scores for back and leg pain, Japanese orthopaedic association (JOA) scores, and Oswestry disability index (ODI). The position of internal fixators and interbody fusion were observed through lumbar anteroposterior and lateral X-ray films. ResultsThe responsible segment was identified as single level in 33 cases (L4, 5 in 18 cases, L5, S1 in 11 cases, and L3, 4 in 4 cases) and two levels in 10 cases (L4, 5 and L5, S1 in 6 cases, L3, 4 and L4, 5 in 3 cases, L2, 3 and L4, 5 in 1 case) by SNRB. After SNRB, 4 cases did not receive surgical treatment because of a low relief rate of less than 30%. The operations were performed successfully in all 43 patients. The mean operation time was 101.9 minutes; the mean intraoperative blood loss was 164.5 mL; the mean postoperative drainage volume was 238.9 mL; and the mean postoperative ambulation time was 38.2 hours. There was no complication of nerve injury or incision infection. All 43 patients were followed up 12-36 months (mean, 19.3 months). The VAS scores, JOA scores, and ODI after operation were significantly improved when compared with preoperative ones (P<0.05). The postoperative JOA recovery rates were 62.2%±12.6%, 63.4%±12.4%, and 68.6%±14.6% at 3, 6 months, and last follow-up respectively, showing no significant difference (F=2.841, P=0.062). The postoperative X-ray films showed that the internal fixators were in good position without loosening or fracture, and the interbody fusion was good. ConclusionAfter identifying the responsible segment by SNRB in the diagnosis, limited operative treatment is safe and reliable in the treatment of multi-segmental lumbar disease. It can relieve compression effectively, decrease the range of operation, maintain the spinal stabilization, and has a good effectiveness.