METHODS: In this study, we propose a multi-view secondary input residual (MV-SIR) convolutional neural network model for 3D lung nodule segmentation using the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset of chest computed tomography (CT) images. Lung nodule cubes are prepared from the sample CT images. Further, from the axial, coronal, and sagittal perspectives, multi-view patches are generated with randomly selected voxels in the lung nodule cubes as centers. Our model consists of six submodels, which enable learning of 3D lung nodules sliced into three views of features; each submodel extracts voxel heterogeneity and shape heterogeneity features. We convert the segmentation of 3D lung nodules into voxel classification by inputting the multi-view patches into the model and determine whether the voxel points belong to the nodule. The structure of the secondary input residual submodel comprises a residual block followed by a secondary input module. We integrate the six submodels to classify whether voxel points belong to nodules, and then reconstruct the segmentation image.
RESULTS: The results of tests conducted using our model and comparison with other existing CNN models indicate that the MV-SIR model achieves excellent results in the 3D segmentation of pulmonary nodules, with a Dice coefficient of 0.926 and an average surface distance of 0.072.
CONCLUSION: our MV-SIR model can accurately perform 3D segmentation of lung nodules with the same segmentation accuracy as the U-net model.
Methods: Between August 2015 to March 2019, 96 patients in our hospital underwent RALP, with 32 patients as secondary intervention for recurrent UPJO. We compared the perioperative parameters of RALP for both primary UPJO and recurrent UPJO. Patient demographics, perioperative parameters, postoperative outcomes and complications from both groups were analyzed and compared.
Results: RALP was successfully performed for all cases in both groups. The median operating time was longer for secondary RALP than for primary RALP [125 (108.5-155) vs. 151 (120-190) minutes, P=0.004]. There were no conversions to open surgery or significant perioperative complications. No difference in blood loss, transfusion rate and perioperative complication rates was noted between the two groups. The success rates were 98.44% (63/64) and 96.88% (31/32) at a median follow up of 32 and 20 months (P=0.001) for the primary and secondary groups, respectively.
Conclusions: Secondary RALP is associated with significantly longer operative time as compared to primary RALP, especially during the exposure of the UPJO, however it is a safe surgical modality for recurrent UPJO with durable outcome. RALP should be an alternative treatment modality for recurrent UPJO whenever the facility and expert are available.
METHODS: By using preoperative computed tomography, magnetic resonance imaging, and 3-dimensional image reconstruction, 5 critical components were assessed: the ratio of the sinus area occupied by the tumor in relation to the whole sinus area (R), the compression of the renal segmental vessels or collection system by the tumor (O), the anteroposterior relation of the tumor relative to the segmental vessels or collection system (A), the tumor diameter (D), and whether the tumor affects a solitary kidney (S) ("ROADS"). The ROADS score, indicating low, moderate, or high surgical complexity, was then used to guide surgical strategy planning, including cooling techniques, surgical approaches, and parenchyma incision techniques. A cohort of 134 patients with renal sinus tumors was treated based on their ROADS score and was retrospectively analyzed.
RESULTS: The authors successfully performed 113 nephron-sparing surgeries and 21 radical nephrectomies with a complication rate of 7.9%. During follow-up, 3 cases were classified according to surgical margin status because they lacked an intact tumor capsule. There was only 1 case of local recurrence, and there were no cases of metastasis. A high ROADS score was correlated with greater operative complexity, such as longer operation and ischemia times and higher estimated blood loss and complication rates. However, renal function and short-term oncologic outcomes were not related to the score.
CONCLUSIONS: The ROADS scoring system provides a standardized, quantitative, 3-dimensional anatomic classification to guide surgical strategy in renal sinus tumors.
MATERIALS AND METHODS: Eight patients with level IV inferior vena cava thrombi not extending into the atrium underwent transabdominal-transdiaphragmatic robot-assisted inferior vena cava thrombectomy obviating cardiopulmonary bypass/deep hypothermic circulatory arrest (cardiopulmonary bypass-free group) by an expert team comprising urological, hepatobiliary, and cardiovascular surgeons. The central diaphragm tendon and pericardium were transabdominally dissected until the intrapericardial inferior vena cava were exposed and looped proximal to the cranial end of the thrombi under intraoperative ultrasound guidance. As controls, 14 patients who underwent robot-assisted inferior vena cava thrombectomy with cardiopulmonary bypass (cardiopulmonary bypass group) and 25 patients who underwent open thrombectomy with cardiopulmonary bypass/deep hypothermic circulatory arrest (cardiopulmonary bypass/deep hypothermic circulatory arrest group) were included. Clinicopathological, operative, and survival outcomes were retrospectively analyzed.
RESULTS: Eight robot-assisted inferior vena cava thrombectomies were successfully performed without cardiopulmonary bypass, with 1 open conversion. The median operation time and first porta hepatis occlusion time were shorter, and estimated blood loss was lower in the cardiopulmonary bypass-free group as compared to the cardiopulmonary bypass group (540 vs 586.5 minutes, 16.5 vs 38.5. minutes, and 2,050 vs 3,500 mL, respectively). Severe complications (level IV-V) were also lower in the cardiopulmonary bypass-free group than in cardiopulmonary bypass and cardiopulmonary bypass/deep hypothermic circulatory arrest groups (25% vs 50% vs 40%). Oncologic outcomes were comparable among the 3 groups in short-term follow-up.
CONCLUSIONS: Pure transabdominal-transdiaphragmatic robot-assisted inferior vena cava thrombectomy without cardiopulmonary bypass/deep hypothermic circulatory arrest represents as an alternative minimally invasive approach for selected level IV inferior vena cava thrombi.
METHODS: Positron emission tomography (PET) and computed tomography (CT) image data from 97 patients with LC and 77 patients with TB nodules were collected. One hundred radiomic features were extracted from both PET and CT imaging using the pyradiomics platform, and 2048 deep learning features were obtained through a residual neural network approach. Four models included traditional machine learning model with radiomic features as input (traditional radiomics), a deep learning model with separate input of image features (deep convolutional neural networks [DCNN]), a deep learning model with two inputs of radiomic features and deep learning features (radiomics-DCNN) and a deep learning model with inputs of radiomic features and deep learning features and clinical information (integrated model). The models were evaluated using area under the curve (AUC), sensitivity, accuracy, specificity, and F1-score metrics.
RESULTS: The results of the classification of TB nodules and LC showed that the integrated model achieved an AUC of 0.84 (0.82-0.88), sensitivity of 0.85 (0.80-0.88), and specificity of 0.84 (0.83-0.87), performing better than the other models.
CONCLUSION: The integrated model was found to be the best classification model in the diagnosis of TB nodules and solid LC.
OBJECTIVES: We sought to establish the effects of 1 mo of intermittent fasting on the gut microbiome.
METHODS: We took advantage of intermittent fasting being voluntarily observed during the Islamic faith-associated Ramadan and sampled feces and blood, as well as collected longitudinal physiologic data in 2 cohorts, sampled in 2 different years. The fecal microbiome was determined by 16S sequencing. Results were contrasted to age- and body weight-matched controls and correlated to physiologic parameters (e.g., body mass and calorie intake).
RESULTS: We observed that Ramadan-associated intermittent fasting increased microbiome diversity and was specifically associated with upregulation of the Clostridiales order-derived Lachnospiraceae [no fasting 24.6 ± 13.67 compared with fasting 39.7 ± 15.9 in relative abundance (%); linear discriminant analysis = 4.9, P