PurposeThe purpose of this study was to determine whether computed tomography (CT)-based machine learning of radiomics features could help distinguish autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma (PDAC).Materials and MethodsEighty-nine patients with AIP (65 men, 24 women; mean age, 59.7 ± 13.9 [SD] years; range: 21–83 years) and 93 patients with PDAC (68 men, 25 women; mean age, 60.1 ± 12.3 [SD] years; range: 36–86 years) were retrospectively included. All patients had dedicated dual-phase pancreatic protocol CT between 2004 and 2018. Thin-slice images (0.75/0.5 mm thickness/increment) were compared with thick-slices images (3 or 5 mm thickness/increment). Pancreatic regions involved by PDAC or AIP (areas of enlargement, altered enhancement, effacement of pancreatic duct) as well as uninvolved parenchyma were segmented as three-dimensional volumes. Four hundred and thirty-one radiomics features were extracted and a random forest was used to distinguish AIP from PDAC. CT data of 60 AIP and 60 PDAC patients were used for training and those of 29 AIP and 33 PDAC independent patients were used for testing.ResultsThe pancreas was diffusely involved in 37 (37/89; 41.6%) patients with AIP and not diffusely in 52 (52/89; 58.4%) patients. Using machine learning, 95.2% (59/62; 95% confidence interval [CI]: 89.8–100%), 83.9% (52:67; 95% CI: 74.7–93.0%) and 77.4% (48/62; 95% CI: 67.0–87.8%) of the 62 test patients were correctly classified as either having PDAC or AIP with thin-slice venous phase, thin-slice arterial phase, and thick-slice venous phase CT, respectively. Three of the 29 patients with AIP (3/29; 10.3%) were incorrectly classified as having PDAC but all 33 patients with PDAC (33/33; 100%) were correctly classified with thin-slice venous phase with 89.7% sensitivity (26/29; 95% CI: 78.6–100%) and 100% specificity (33/33; 95% CI: 93–100%) for the diagnosis of AIP, 95.2% accuracy (59/62; 95% CI: 89.8–100%) and area under the curve of 0.975 (95% CI: 0.936–1.0).ConclusionsRadiomic features help differentiate AIP from PDAC with an overall accuracy of 95.2%. 相似文献
Background: Previous genome-wide association study (GWAS) has revealed the association between MYP10 at 8p23 and MYP15 at 10q21.1 and high myopia (HM) in a French population. This study is managed to discover the connection between some single nucleotide polymorphism (located at MYP10 and MYP15) and Han Chinese HM.
Methods and Results: This case-control association study contained 1673 samples, including 869 ophthalmic patients and 804 controls. Twelve tag SNPs have been selected from the MYP10 and MYP15 loci and genotyped by SNaPshot method. Among 12 SNPs, rs4840437 and rs6989782 in TNKS gene were found significant association with HM. Carriers of rs4840437G allele and rs4840437GG genotype created a low risk of high myopia (P = .036, OR = 0.81, 95%CI = 0.71–0.93; P = .016, OR = 0.73, 95%CI = 0.56–0.96; respectively). Carriers of rs6989782T allele and rs6989782TT+CT genotype also had a decreased risk of high myopia (P = .048, OR = 0.82, 95%CI = 0.71–0.94; P = .006, OR = 0.74, 95%CI = 0.59–0.92; respectively). Other 10 SNPs displaced nonsignificant association with HM. Additionally, the risk haplotype AC and the protective haplotype GT, generated by two SNPs in TNKS, were considerably more likely to be association with HM (for AC, P = .002 and OR = 1.26; for GT, P = .027 and OR = 0.84).
Conclusions: Our results demonstrated that some heritable variants in the TNKS gene are associated with HM in the Han population. The possible functions of TNKS in the development and pathogenesis of hereditary high myopia still require further researches to identify. 相似文献
BACKGROUND: An augmented reality tool for computer assisted surgery named X-Scope allows visual tracking of real anatomical structures in superposition with volume rendered CT or MRI scans and thus can be used for navigated translocation of bony segments. METHODS: In a feasibility study X-Scope was used in orthognathic surgery to control the translocation of the maxilla after Le Fort I osteotomy within a bimaxillary procedure. The situation achieved was compared with the pre-operative situation by means of cephalometric analysis on lateral and frontal cephalograms. RESULTS: The technique was successfully utilized in 5 patients. Maxillary positioning using X-Scope was accomplished accurately within a range of 1mm. The tool was used in all cases in addition to the usual intra-operative splints. A stand-alone application without conventional control does not yet seem reasonable. CONCLUSION: Augmented reality tools like X-Scope may be helpful for controlling maxillary translocation in orthognathic surgery. The application to other interventions in cranio-maxillofacial surgery such as Le Fort III osteotomy, fronto-orbital advancement, and cranial vault reshaping or repair may also be considered. 相似文献
Our group have studied a patient affected by a malignant schwannoma in the posterior tibial nerve. Schwannomas are uncommon neoplasms that originate from the Schwann cells of the peripheral nerves: the most common forms are benign. Malignant transformation is rarer. The therapy is surgical and the operation undertaken, if possible, should be the amputation. Alternatively, where amputation is not possible due to the specific localisation or due to patient refusal, the alternative must be the largest and most radical excision possible. 相似文献