Explore the vast range of titles available.

PurposeTo evaluate the performance of a deep learning-based computer-aided diagnosis (CAD) system at detecting pulmonary nodules on CT by comparing radiologists’ readings with and without CAD.Materials and methodsA total of 120 chest CT images were randomly selected from patients with suspected lung cancer. The gold standard of nodules ≥ 3 mm was established by a panel of three expert radiologists. Two less experienced radiologists read the images without and afterward with CAD system. Their reading times were recorded.ResultsThe radiologists’ sensitivity increased from 20.9% to 38.0% with the introduction of CAD. The positive predictive value (PPV) decreased from 70.5% to 61.8%, and the F1-score increased from 32.2% to 47.0%. The sensitivity significantly increased from 13.7% to 32.4% for small nodules (3–6 mm) and from 33.3% to 47.6% for medium nodules (6–10 mm). CAD alone showed a sensitivity of 70.3%, a PPV of 57.9%, and an F1-score of 63.5%. Reading time decreased by 11.3% with the use of CAD.ConclusionCAD improved the less experienced radiologists’ sensitivity in detecting pulmonary nodules of all sizes, especially including a significant improvement in the detection of clinically important-sized medium nodules (6–10 mm) as well as small nodules (3–6 mm) and reduced their reading time.

Background Induction or adjuvant therapies are not always beneficial for thoracic esophageal squamous cell carcinoma (ESCC) patients, and it is thus important to identify patients at high risk for postoperative ESCC recurrence. We investigated the usefulness of the total metabolic tumor volume (TMTV) for predicting the postoperative recurrence of thoracic ESCC. Methods We retrospectively analyzed the cases of 163 thoracic ESCC patients (135 men, 28 women; median age of 66 [range 34–82] years) treated at our hospital in 2007–2012. The TMTV was calculated from the fluorine-18 fluorodeoxyglucose ( 18 F-FDG) uptake in the primary lesion and lymph node metastases. The optimal cut-off values for relapse and non-relapse were obtained by the time-dependent receiver operating curve analyses. Relapse-free survival (RFS) was evaluated by the Kaplan-Meier method, and between-subgroup differences in survival were analyzed by log-rank test. The prognostic significance of metabolic parameters and clinicopathological variables was assessed by a Cox proportional hazard regression analysis. The difference in the failure patterns after surgical resection was evaluated using the χ 2 -test. Results The optimal cut-off value of TMTV for discriminating relapse from non-relapse was 3.82. The patients with a TMTV ≥3.82 showed significantly worse prognoses than those with low values ( p  < 0.001). The TMTV was significantly related to RFS (model 1 for preoperative risk factors: TMTV: hazard ratio [HR] =2.574, p =  0.004; model 2 for preoperative and postoperative risk factors: HR = 1.989, p =  0.044). The combination of the TMTV and cN0–1 or pN0–1 stage significantly stratified the patients into low-and high-risk recurrence groups (TMTV cN0–1, p  < 0.001; TMTV pN0–1, p =  0.004). The rates of hematogenous and regional lymph node metastasis were significantly higher in the patients with TMTV ≥3.82 than those with low values (hematogenous metastasis, p  < 0.001, regional lymph node metastasis, p =  0.011). Conclusions The TMTV was a more significantly independent prognostic factor for RFS than any other PET parameter in patients with resectable thoracic ESCC. The TMTV may be useful for the identifying thoracic ESCC patients at high risk for postoperative recurrence and for deciding the patient management.

Introduction The aim of this study was to investigate the prevalence of intravertebral pneumatocyst (IVP) of the cervical spine by age group, compared with that of intradiscal vacuum (IDV). Methods We investigated 500 consecutive patients who underwent cervical computed tomography (CT) from May 2012 to May2013 for various indications. CT datasets were assessed for the presence of IVPs and IDVs with stratification by age. Results IVPs of the cervical spine were detected in 8 % (7 of 86 subjects) of patients in their forties or below, 30 % (23 of 75) in their fifties, 49 % (67 of 136) in their sixties, 55 % (76 of 137) in their seventies, and 60 % (40 of 66) in their eighties or over. IDVs of the cervical spine were detected in 6, 25, 48, 54, and 57 %, respectively. Coexistence of both phenomena was identified in 4, 17, 33, 40, and 43 %, respectively. Conclusion IVPs of the cervical spine are a common incidental finding, increasing in prevalence with age and more common than IDV in all age groups.