Aorta and main pulmonary artery segmentation using stacked U-Net and localization on non-contrast-enhanced computed tomography images.

BACKGROUND: The contact between the aorta, main pulmonary artery (MPA), main pulmonary vein, vena cava (VC), and esophagus affects segmentation of the aorta and MPA in non-contrast-enhanced computed tomography (NCE-CT) images. PURPOSE: A two-stage stacked U-Net and localization of the aorta and MPA were developed for the segmentation of the aorta and MPA in NCE-CT images. METHODS: Normal-dose NCE-CT images of 24 subjects with chronic thromboembolic pulmonary hypertension (CTEPH) and low-dose NCE-CT images of 100 subjects without CTEPH were used in this study. The aorta is in contact with the ascending aorta (AA) and MPA, the AA with the VC, the aortic arch (AR) with the VC and esophagus, and the descending aorta (DA) with the esophagus. These contact surfaces were manually annotated. The contact surfaces were quantified using the contact surface ratio (CSR). Segmentation of the aorta and MPA in NCE-CT images was performed by localization of the aorta and MPA and a two-stage stacked U-Net. Localization was performed by extracting and processing the trachea and main bronchus. The first stage of the stacked U-Net consisted of a 2D U-Net, 2D U-Net with a pre-trained VGG-16 encoder, and 2D attention U-Net. The second stage consisted of a 3D U-Net with four input channels: the CT volume and three segmentation results of the first stage. The model was trained and tested using 10-fold cross-validation. Segmentation of the entire volume was evaluated using the Dice similarity coefficient (DSC). Segmentation of the contact area was also assessed using the mean surface distance (MSD). The statistical analysis of the evaluation underwent a multi-comparison correction. CTEPH and non-CTEPH cases were classified based on the vessel diameters measured from the segmented MPA. RESULTS: For the noncontact surfaces of AA, the MSD of stacked U-Net was 0.31 ± 0.10 mm (p < 0.05) and 0.32 ± 0.13 mm (p < 0.05) for non-CTEPH and CTEPH cases, respectively. For contact surfaces with a CSR of 0.4 or greater in AA, the MSD was 0.52 ± 0.23 mm (p < 0.05), and 0.68 ± 0.29 mm (p > 0.05) for non-CTEPH and CTEPH cases, respectively. MSDs were lower than those of 2D and 3D U-Nets for contact and noncontact surfaces; moreover, MSDs increased slightly with larger CSRs. However, the stacked U-Net achieved MSDs of approximately 1 pixel for a wide contact surface. The area under the receiver operating characteristic curve for CTEPH and non-CTEPH classification using the right main pulmonary artery (RMPA) diameter was 0.97 (95% confidence interval [CI]: 0.94-1.00). CONCLUSIONS: Segmentation of the aorta and MPA on NCE-CT images were affected by vascular and esophageal contact. The application of stacked U-Net and localization techniques for non-CTEPH and CTEPH cases mitigated the impact of contact, suggesting its potential for diagnosing CTEPH.

Educating patients with upper limb dysfunction on self-adjustment of the CPAP/NPPV mask: A case series.

We share our experiences of instructing three patients with severe upper limb dysfunction on how to self-adjust CPAP/NPPV masks. In Case 1, we simplified the procedure by suturing a part of the headband as the left forearm was amputated. In Case 2, the patient had congenitally short limbs with short stature; thus, we provided an additional belt to the headband to maintain the headband's configuration while wearing the mask. In Case 3, the patient had left hemiplegia due to stroke and, repetitive coaching was conducted during the recovery phase rehabilitation program. Difficulties with self-adjusting NPPV/CPAP masks can occur whenever there is limited hand mobility above the head, including upper limb dysfunction. Simplifying procedures and providing sufficient time for instruction could help achieve independence. There have been no previous reports describing similar training details. We believe that sharing this knowledge will be helpful to both patients and healthcare professionals.

Respiratory symptoms as extraesophageal manifestation of gastroesophageal reflux disease (GERD).

It is common in clinical setting for physician to meet the patient with respiratory symptoms such as cough. But, we seldom know whether it is extraesophageal manifestation of gastroe- sophageal reflux disease (GERD) or not. Irritation of upper respiratory tract, invasion to lower respiratory tract(macro- or micro-aspiration) and esophagobronchial reflex by refluxate are suspected to be major cause or co-factor of GERD-related respiratory symptoms. Each of these co-factors will happen independently and interacts with others in diverse way. Interdisciplinary approach is essential, however, we have to acknowledge the lack of data and take notice of what we know and what we don' t know about this complicated issue.

Survey to determine the efficacy and safety of guideline-based pharmacological therapy for chronic obstructive pulmonary disease patients not previously receiving maintenance treatment.

OBJECTIVE: To investigate the potential beneficial effects of guideline-based pharmacological therapy on pulmonary function and quality of life (QOL) in Japanese chronic obstructive pulmonary disease (COPD) patients without prior treatment. RESEARCH DESIGN AND METHODS: Multicenter survey, open-label study of 49 Japanese COPD patients aged ≥ 40 years; outpatients with >10 pack years of smoking history; ratio of forced expiratory volume in 1 s (FEV1)/forced vital capacity (FVC) < 70%; predicted FEV1 < 80%; treated with bronchodilators and/or inhaled corticosteroids as maintenance therapy until week 48. MAIN OUTCOME MEASURES: The primary endpoint was change in pulmonary function (trough FEV1, trough FVC); secondary endpoints were QOL and physical activity at 48 weeks after initiation of therapy. RESULTS: Airway reversibility was confirmed in untreated patients. Significant changes over time were not observed for FEV1 and FVC, indicating lung function at initiation of treatment was maintained during the observation period. COPD assessment test scores showed statistical and clinical improvements. Cough, sputum, breathlessness, and shortness of breath were significantly improved. CONCLUSIONS: Lung function and QOL of untreated Japanese COPD patients improved and improvements were maintained by performing a therapeutic intervention that conformed to published guidelines.

[Role of gastro-esophageal reflux (GER) and swallowing latency in aspiration pulmonary diseases].

We evaluated the role of gastro-esophageal reflux (GER) in aspiration pulmonary disease. To explore swallowing function, we measured the latent time (LT) on the swallowing provocation test in patient with non-aspiration pneumonia (PN, n=5), aspiration pneumonia (AP, n=8), post-gastrectomy aspiration pneumonia (PGAP, n=8), gastro-esophageal reflux disease (GERD, n=12) and normal group (NR, n=7). LT was prolonged in the AP (2.83 +/- 1.66 sec p < 0.01), PGAP (2.58 +/- 1.40 sec p < 0.05) and GERD (2.40 +/- 1.70 sec p < 0.05) groups compared with NR (1.04 +/- 0.56 sec) group, but not prolonged in PN (1.46 +/- 0.75 sec) group. LT was also prolonged when swallowing was provoked during inspiration both in AP (3.61 +/- 2.60 sec vs. 2.73 +/- 2.19 sec, p < 0.05) and NR (2.13 -/+ 1.12 sec vs. 1.49 +/- 1.30 sec, p < 0.01). Protected specimen brushing (PSB) was employed to detect pathogenic organisms in the PN (n=70), AP (AP, n=27) and PGAP (n=15) groups. Gram-negative rods were most frequently detected in the PGAP (p=0.008) group. We conclude that GER plays an important role in aspiration pulmonary disease not only as a source of aspirating agent but also as a disturbing factor of swallowing function.

[Drug susceptibility of Trichosporon beigelii isolated from urine and clinical features of their hosts].

We investigated of Trichosporon beigelii by a surveillance study for two years in the Tokyo Metropolitan Police Hospital. T. beigelii was frequently found in the urine in aged patients with indwelled urethral catheter and in serious stage patients associated with malignancy. T. beigelii was in all cases isolated from the samples of patients in a hospital stay over 5 days. Minimum inhibitory concentrations (MICs) of anti-fungal agents against T. beigelii were determined by agar-dilution method. Fluconazole resistant strains of T. beigelii were found by this method. Microscopic examination revealed phagocyted T. beigelii in multinucleated neutrophils in some cases. In conclusion, T. beigelii might be suggested a causative organism of opportunistic infection in urinary diseases.