Prediction of postoperative lung function after major lung resection for lung cancer using volumetric computed tomography

Clinical application of computed tomographic volumetric imaging in postoperative lung function assessment in patients with lung cancer

BACKGROUND

To evaluate the effectiveness of the computed tomographic (CT) volumetric analysis in postoperative lung function assessment and the predicting value for postoperative complications in patients who had segmentectomy for lung cancer.

METHODS

CT scanning and pulmonary function examination were performed for 100 patients with lung cancer. CT volumetric analyses were performed by specific software, for the volume of the inspiratory phase (Vin), the mean inspiratory lung density (MLDin), the volume of expiratory phase (Vex), and the mean lung density at expiratory phase (MLDex). Pulmonary function examination results and CT volumetric analysis results were used to predict postoperative lung function. The concordance and correlations of these values were assessed by Bland-Altman analysis and Pearson correlation analysis, respectively. Multivariate binomial logistic regression analysis was executed to assess the associations of CT data with complication occurrence.

RESULTS

Correlations between CT scanning data and pulmonary function examination results were significant in both pre- and post-operation (0.8083 ≤ r ≤ 0.9390). Forced vital capacity (FVC), forced expiratory volume in the first second (FEV1), and the ratio of FVC and FEV1 estimated by CT volumetric analyses showed high concordance with those detected by pulmonary function examination. Preoperative (Vin-Vex) and (MLDex- MLDin) values were identified as predictors for post-surgery complications, with hazard ratios of 5.378 and 6.524, respectively.

CONCLUSIONS

CT volumetric imaging analysis has the potential to determine the pre- and post-operative lung function, as well as to predict post-surgery complication occurrence in lung cancer patients with pulmonary lobectomy.

Estimating lung function from computed tomography at the patient and lobe level using machine learning

BACKGROUND

Automated estimation of Pulmonary function test (PFT) results from Computed Tomography (CT) could advance the use of CT in screening, diagnosis, and staging of restrictive pulmonary diseases. Estimating lung function per lobe, which cannot be done with PFTs, would be helpful for risk assessment for pulmonary resection surgery and bronchoscopic lung volume reduction.

PURPOSE

To automatically estimate PFT results from CT and furthermore disentangle the individual contribution of pulmonary lobes to a patient's lung function.

METHODS

We propose I3Dr, a deep learning architecture for estimating global measures from an image that can also estimate the contributions of individual parts of the image to this global measure. We apply it to estimate the separate contributions of each pulmonary lobe to a patient's total lung function from CT, while requiring only CT scans and patient level lung function measurements for training. I3Dr consists of a lobe-level and a patient-level model. The lobe-level model extracts all anatomical pulmonary lobes from a CT scan and processes them in parallel to produce lobe level lung function estimates that sum up to a patient level estimate. The patient-level model directly estimates patient level lung function from a CT scan and is used to re-scale the output of the lobe-level model to increase performance. After demonstrating the viability of the proposed approach, the I3Dr model is trained and evaluated for PFT result estimation using a large data set of 8 433 CT volumes for training, 1 775 CT volumes for validation, and 1 873 CT volumes for testing.

RESULTS

First, we demonstrate the viability of our approach by showing that a model trained with a collection of digit images to estimate their sum implicitly learns to assign correct values to individual digits. Next, we show that our models can estimate lobe-level quantities, such as COVID-19 severity scores, pulmonary volume (PV), and functional pulmonary volume (FPV) from CT while only provided with patient-level quantities during training. Lastly, we train and evaluate models for producing spirometry and diffusion capacity of carbon mono-oxide (DLCO) estimates at the patient and lobe level. For producing Forced Expiratory Volume in one second (FEV1), Forced Vital Capacity (FVC), and DLCO estimates, I3Dr obtains mean absolute errors (MAE) of 0.377 L, 0.297 L, and 2.800 mL/min/mm Hg respectively. We release the resulting algorithms for lung function estimation to the research community at https://grand-challenge.org/algorithms/lobe-wise-lung-function-estimation/ CONCLUSIONS: I3Dr can estimate global measures from an image, as well as the contributions of individual parts of the image to this global measure. It offers a promising approach for estimating PFT results from CT scans and disentangling the individual contribution of pulmonary lobes to a patient's lung function. The findings presented in this work may advance the use of CT in screening, diagnosis, and staging of restrictive pulmonary diseases as well as in risk assessment for pulmonary resection surgery and bronchoscopic lung volume reduction.

Robust imaging approach for precise prediction of postoperative lung function in lung cancer patients prior to curative operation

BACKGROUND

To create a combined variable integrating both ventilation and perfusion as measured by preoperative dual-energy computed tomography (DECT), compare the results with predicted postoperative (PPO) lung function as estimated using conventional methods, and assess agreement with actual postoperative lung function.

METHODS

A total of 33 patients with lung cancer who underwent curative surgery after DECT and perfusion scan were selected. Ventilation and perfusion values were generated from DECT data. In the "combined variable method," these two variables and clinical variables were linearly regressed to estimate PPO lung function. Six PPO lung function parameters (segment counting, perfusion scan, volume analysis, ventilation map, perfusion map, and combined variable) were compared with actual postoperative lung function using an intraclass correlation coefficient (ICC).

RESULTS

The segment counting method produced the highest ICC for forced vital capacity (FVC) at 0.93 (p < 0.05), while the segment counting and perfusion map methods produced the highest ICC for forced expiratory volume in 1 second (FEV1 ; both 0.89, p < 0.05). The highest ICC value when using the combined variable method was for FEV1 /FVC (0.75, p < 0.05) and diffusing capacity of the lung for carbon monoxide (DLco; 0.80, p < 0.05) when using the perfusion map method. Overall, the perfusion map and ventilation map provided the best performance, followed by volume analysis, segment counting, perfusion scan, and the combined variable.

CONCLUSIONS

Use of DECT image processing to predict postoperative lung function produced better agreement with actual postoperative lung function than conventional methods. The combined variable method produced ICC values of 0.8 or greater for FVC and FEV1 .

Risk factors for long-term decline in post-operative pulmonary function after lung resection

OBJECTIVES

The study aimed to examine the risk factors for long-term decline in pulmonary function after anatomical resection for lung cancer and the effects of the decrease on survival.

METHODS

We retrospectively examined 489 patients who underwent anatomical resection for lung cancer between 2010 and 2020. Pulmonary function tests were performed preoperatively and at 1, 3, 6 and 12 months after surgery. The lower interquartile medians of the reduction rates of forced expiratory volume in 1 s and vital capacity at 12 months after surgery were taken as the cut-off values of risk factors for the decrease in post-operative pulmonary function.

RESULTS

Forced expiratory volume in 1 s and vital capacity decreased the most in the first month after surgery and then gradually recovered. Vital capacity continued to increase even after 6 months post-surgery, whereas forced expiratory volume in 1 s stabilized. Multivariable logistic analysis showed that the number of resected segments (odds ratio, 2.09; 95% confidence interval, 1.12-3.89; P = 0.019) was a risk factor for the decrease in forced expiratory volume in 1 s at 12 months, and the numbers of resected segments (odds ratio, 1.36; 95% confidence interval, 1.13-1.63; P < 0.001) and post-operative complications (odds ratio, 2.32; 95% confidence interval, 1.01-5.35; P = 0.047) were independent risk factors for decrease in vital capacity. Multivariate cox regression analysis showed that the decrease in vital capacity at 12 months was significantly associated with overall survival (hazard ratio, 2.02; 95% confidence interval, 1.24-3.67; P = 0.004).

CONCLUSIONS

Long-term decrease in vital capacity, which was influenced by the number of resected segments and post-operative complications, adversely affected survival.

Comparison between functional lung volume measurement and segment counting for predicting postoperative pulmonary function after pulmonary resection in lung cancer patients

BACKGROUND

Functional lung volume (FLV) obtained from computed tomography images was a breakthrough for lung imaging and functional assessment. We compared the accuracy of the FLV measurement method and the segment-counting (SC) method in predicting postoperative pulmonary function.

METHODS

A total of 113 patients who underwent two thoracoscopic surgeries were enrolled in our study. We predicted postoperative pulmonary function by the FLV measurement method and the SC method. Novel formulas based on the FLV measurement method were established using linear regression equations between the factors affecting pulmonary function and the measured values.

RESULTS

The predicted postoperative forced vital capacity (ppoFVC) and forced expiratory volume in 1 s (ppoFEV1) measured by the 2 methods showed high concordance between the actual postoperative forced vital capacity (postFVC) and the forced expiratory volume in 1 s (postFEV1) [r = 0.762, P < 0.001 (FLV method) and r = 0.759, P < 0.001 (SC method) for FVC; r = 0.790, P < 0.001 (FLV method) and r = 0.795, P < 0.001 (SC method) for FEV1]. Regression analysis showed that the measured preoperative pulmonary function parameters (FVC, FEV1) and the ratio of reduced FLV to preoperative FLV were significantly associated with the actual postoperative values and could predict these parameters (all P < 0.001). The feasibility of using these equations [postFVC = 0.8 × FVC - 0.784 × ΔFLV/FLV + 0.283 (R² = 0.677, RSD = 0.338), postFEV1 = 0.766 × FEV1 - 0.694 × ΔFLV/FLV + 0.22 (R² = 0.743, RSD = 0.265)] to predict the pulmonary function parameters after wedge resection was also verified.

CONCLUSIONS

The new FLV measurement method is valuable for predicting postoperative pulmonary function in patients undergoing lung resection surgery, with accuracy and consistency similar to those of the conventional SC method.

Pulmonary function changes after sublobar resection in patients with peripheral non-subpleural nodules

Background

In the treatment of peripheral early-staged lung cancer and benign lesions, segmentectomy and wedge resection are both reliable treatment methods. It is debatable that how much pulmonary function will be lost after different sublobar resection in the treatment of early-staged deep-located peripheral NSCLC (non-small cell lung cancer). The purpose of this study was to explore postoperative pulmonary function changes of sublobar resection in enrolled patients with non-subpleural peripheral nodules.

Methods

We collected clinical data of patients undergoing VATS (video-assisted thoracoscopic surgery) segmentectomy or wedge resection for single nodule. These nodules were confirmed as peripheral non-subpleural nodules by preoperative 3D imaging. Patients were divided into two groups according to the operation procedure. Demographic characteristics, pulmonary function, postoperative outcomes, and others were collected. All data was gathered at the First Affiliated Hospital of Soochow University. Outcomes after wedge resection were compared with those after segmentectomy resection.

Results

A total of 88 patients were included in this study, including 46 patients with VATS wedge resection and 42 patients with VATS segmentectomy. No difference was detected when comparing FEV1 (forced expiratory volume in 1 s) loss between these two groups (17.6 ± 2.1%, wedge resection vs. 19.4 ± 5.4%, segmentectomy, P = 0.176). FVC (forced vital capacity) loss (8.7 ± 2.3%, wedge resection vs. 17.1 ± 2.2%, segmentectomy, P < 0.001) and MVV (maximum ventilatory volume) loss (11.5 ± 3.1%, wedge resection vs. 20.6 ± 7.8%, segmentectomy, P < 0.001) in segmentectomy group was significantly higher than those in wedge resection group. Discrepancies were investigated when comparing duration of surgery (70 ± 22 min, wedge resection vs. 111 ± 52 min, segmentectomy, P = 0.0002), postoperative drainage (85 ± 45 mL, wedge resection vs. 287 ± 672 mL, segmentectomy, P = 0.0123), and treatment hospitalization expenses [35148 ± 889CNY, wedge resection vs. 52,502 (38,276–57,772) CNY, segmentectomy, P < 0.0002]. No significant difference was found between air leak time (1.7 ± 0.7 days, wedge resection vs. 2.5 ± 1.7 days, segmentectomy, P = 0.062) and hospitalization time (2.7 ± 0.7 days, wedge resection vs. 3.5 ± 1.7 days, segmentectomy, P = 0.051).

Conclusions

For patients with peripheral non-subpleural nodules, we observed that patients who underwent wedge resection had less lung function loss than those who underwent segmentectomy when their lung function was reviewed at the 6th month after surgery. Patients undergoing wedge resection had partial advantages over patients with segmental resection in terms of hospitalization cost, operation time and postoperative drainage, etc. Wedge resection, as a treatment for peripheral non-subpleural pulmonary nodules, seemed to have more advantages in preserving patients’ pulmonary function.

Comparison of Predicted Postoperative Lung Function in Pneumonectomy Using Computed Tomography and Lung Perfusion Scans

Background

Predicting postoperative lung function after pneumonectomy is essential. We retrospectively compared postoperative lung function to predicted postoperative lung function based on computed tomography (CT) volumetry and perfusion scintigraphy in patients who underwent pneumonectomy.

Methods

Predicted postoperative lung function was calculated based on perfusion scintigraphy and CT volumetry. The predicted function was compared to the postoperative lung function in terms of forced vital capacity (FVC) and forced expiratory volume in 1 second (FEV₁), using 4 parameters FVC, FVC%, FEV₁, and FEV₁%.

Results

The correlations between postoperative function and predicted function based on CT volumetry were r=0.632 (p=0.003) for FVC% and r=0.728 (p<0.001) for FEV₁%. The correlations between postoperative function and predicted postoperative function based on perfusion scintigraphy were r=0.654 (p=0.002) for FVC% and r=0.758 (p<0.001) for FEV₁%. The preoperative Eastern Cooperative Oncology Group (ECOG) scores were significantly higher in the group in which the gap between postoperative FEV₁ and predicted postoperative FEV₁ analyzed by CT was smaller than the gap analyzed by perfusion scintigraphy (1.2±0.62 vs. 0.4±0.52, p=0.006).

Conclusion

This study affirms that CT volumetry can replace perfusion scintigraphy for preoperative evaluation of patients needing pneumonectomy. In particular, it was found to be a better predictor of postoperative lung function for poor-performance patients (i.e., those with high ECOG scores).

Pulmonary function changes after thoracoscopic lobectomy versus intentional thoracoscopic segmentectomy for early-stage non-small cell lung cancer

BACKGROUND

Thoracoscopic segmentectomy is increasingly used in the surgical treatment of early-stage non-small cell lung cancer. However, it remains unclear whether pulmonary function loss after thoracoscopic lung resection is in direct proportion to the number of resected segments, and thus intentional thoracoscopic segmentectomy has the function-preserving advantage over thoracoscopic lobectomy.

METHODS

In this prospective observational study, spirometry tests were performed preoperatively and 6 months postoperatively. The observed functional loss was compared with the expected loss estimated by the segment counting method. Resection extent index was introduced as the number of resected segments to total number of segments in the corresponding lobe. Spirometry changes after thoracoscopic lobectomy and intentional thoracoscopic segmentectomy were compared using propensity score matching.

RESULTS

There were 338 thoracoscopic lobectomies and 321 thoracoscopic segmentectomies. Overall, the observed pulmonary function loss after segmentectomy was significantly less than after lobectomy. But the observed functional loss was significantly greater than the expected loss after segmentectomy. And pulmonary function loss per segment resected was almost doubled after segmentectomy comparing to lobectomy. For segmentectomies with a resection extent index less than 0.5, especially single segmentectomies, pulmonary function loss was significantly less than after corresponding lobectomies. Otherwise, no significant differences in spirometry changes between lobectomies and segmentectomies were detected.

CONCLUSIONS

Pulmonary function loss after thoracoscopic lung resection cannot be accurately evaluated by the number of resected segments. According to the resection extent index, intentional thoracoscopic segmentectomy may help preserve more pulmonary function than thoracoscopic lobectomy only when less than half of the corresponding lobe are resected.

Quantitative analysis based on chest CT classifies common and severe patients with coronavirus disease 2019 pneumonia in Wuhan, China

Objective

This study aimed to compare quantifiable radiologic findings and their dynamic change throughout the clinical course of common and severe coronavirus disease 2019 (COVID-19), and to provide valuable evidence for radiologic classification of the two types of this disease.

Methods

112 patients with laboratory-confirmed COVID-19 were retrospectively analyzed. Volumetric percentage of infection and density of the lung were measured by a computer-aided software. Clinical parameters were recorded to reflect disease progression. Baseline data and dynamic change were compared between two groups and a decision-tree algorithm was developed to determine the cut-off value for classification.

Results

93 patients were finally included and were divided into common group (n = 76) and severe group (n = 17) based on current criteria. Compared with common patients, severe patients experienced shorter advanced stage, peak time and plateau, but longer absorption stage. The dynamic change of volume and density coincided with the clinical course. The interquartile range of volumetric percentage of the two groups were 1.0–7.2% and 11.4–31.2%, respectively. Baseline volumetric percentage of infection was significantly higher in severe group, and the cut-off value of it was 10.10%.

Conclusions

Volumetric percentage between severe and common patients was significantly different. Because serial CT scans are systemically performed in patients with COVID-19 pneumonia, this quantitative analysis can simultaneously provide valuable information for physicians to evaluate their clinical course and classify common and severe patients accurately.