Role of radiomics in predicting lung cancer spread through air spaces in a heterogeneous dataset

Lung Cancer Surgery in Octogenarians: Implications and Advantages of Artificial Intelligence in the Preoperative Assessment

The general world population is aging and patients are often diagnosed with early-stage lung cancer at an advanced age. Several studies have shown that age is not itself a contraindication for lung cancer surgery, and therefore, more and more octogenarians with early-stage lung cancer are undergoing surgery with curative intent. However, octogenarians present some peculiarities that make surgical treatment more challenging, so an accurate preoperative selection is mandatory. In recent years, new artificial intelligence techniques have spread worldwide in the diagnosis, treatment, and therapy of lung cancer, with increasing clinical applications. However, there is still no evidence coming out from trials specifically designed to assess the potential of artificial intelligence in the preoperative evaluation of octogenarian patients. The aim of this narrative review is to investigate, through the analysis of the available international literature, the advantages and implications that these tools may have in the preoperative assessment of this particular category of frail patients. In fact, these tools could represent an important support in the decision-making process, especially in octogenarian patients in whom the diagnostic and therapeutic options are often questionable. However, these technologies are still developing, and a strict human-led process is mandatory.

Predictive value of multiple imaging predictive models for spread through air spaces of lung adenocarcinoma: A systematic review and network meta‑analysis

Spread Through Air Spaces (STAS) is involved in lung adenocarcinoma (LUAD) recurrence, where cancer cells spread into adjacent lung tissue, impacting surgical planning and prognosis assessment. Radiomics-based models show promise in predicting STAS preoperatively, enhancing surgical precision and prognostic evaluations. The present study performed network meta-analysis to assess the predictive efficacy of imaging models for STAS in LUAD. Data were systematically sourced from PubMed, Embase, Scopus, Wiley and Web of Science, according to the Cochrane Handbook for Systematic Reviews of Interventions) and A Measurement Tool to Assess systematic Reviews 2. Using Stata software v17.0 for meta-analysis, surface under the cumulative ranking area (SUCRA) was applied to identify the most effective diagnostic method. Quality assessments were performed using Cochrane Collaboration's risk-of-bias tool and publication bias was assessed using Deeks' funnel plot. The analysis encompassed 14 articles, involving 3,734 patients, and assessed 17 predictive models for STAS in LUAD. According to comprehensive analysis of SUCRA, the machine learning (ML)_Peri_tumour model had the highest accuracy (56.5), the Features_computed tomography (CT) model had the highest sensitivity (51.9) and the positron emission tomography (pet)_CT model had the highest specificity (53.9). ML_Peri_tumour model had the highest predictive performance. The accuracy was as follows: ML_Peri_tumour vs. Features_CT [relative risk (RR)=1.14; 95% confidence interval (CI), 0.99-1.32]; ML_Peri_tumour vs. ML_Tumour (RR=1.04; 95% CI, 0.83-1.30) and ML_Peri_tumour vs. pet_CT (RR=1.04; 95% CI, 0.84-1.29). Comparative analyses revealed heightened predictive accuracy of the ML_Peri_tumour compared with other models. Nonetheless, the field of radiological feature analysis for STAS prediction remains nascent, necessitating improvements in technical reproducibility and comprehensive model evaluation.

Computed Tomography Radiomics for Preoperative Prediction of Spread Through Air Spaces in the Early Stage of Surgically Resected Lung Adenocarcinomas

PURPOSE

To assess the added value of radiomics models from preoperative chest CT in predicting the presence of spread through air spaces (STAS) in the early stage of surgically resected lung adenocarcinomas using multiple validation datasets.

MATERIALS AND METHODS

This retrospective study included 550 early-stage surgically resected lung adenocarcinomas in 521 patients, classified into training, test, internal validation, and temporal validation sets (n=211, 90, 91, and 158, respectively). Radiomics features were extracted from the segmented tumors on preoperative chest CT, and a radiomics score (Rad-score) was calculated to predict the presence of STAS. Diagnostic performance of the conventional model and the combined model, based on a combination of conventional and radiomics features, for the diagnosis of the presence of STAS were compared using the area under the curve (AUC) of the receiver operating characteristic curve.

RESULTS

Rad-score was significantly higher in the STAS-positive group compared to the STAS-negative group in the training, test, internal, and temporal validation sets. The performance of the combined model was significantly higher than that of the conventional model in the training set {AUC: 0.784 [95% confidence interval (CI): 0.722-0.846] vs. AUC: 0.815 (95% CI: 0.759-0.872), p=0.042}. In the temporal validation set, the combined model showed a significantly higher AUC than that of the conventional model (p=0.001). The combined model showed a higher AUC than the conventional model in the test and internal validation sets, albeit with no statistical significance.

CONCLUSION

A quantitative CT radiomics model can assist in the non-invasive prediction of the presence of STAS in the early stage of lung adenocarcinomas.

Preliminary exploration of the correlation between spectral computed tomography quantitative parameters and spread through air spaces in lung adenocarcinoma

Background

The invasive pattern called spread through air spaces (STAS) is linked to an unfavorable prognosis in patients with lung adenocarcinoma (LUAD). Using computed tomography (CT) signs alone to assess STAS is subjective and lacks quantitative evaluation, whereas spectral CT can provide quantitative analysis of tumors. The aim of this study was to investigate the association between spectral CT quantitative parameters and STAS in LUAD.

Methods

We retrospectively collected consecutive patients with LUAD who underwent surgical resection and preoperative spectral CT scan at our institution. The quantitative parameters included CT values at 40, 70, and 100 keV [CT40keVa/v, CT70keVa/v, and CT100keVa/v (a: arterial; v: venous)]; iodine concentration (ICa/ICv); normalized iodine concentration (NICa/NICv); and slope λHU of the spectral curve (λHUa/λHUv). Clinical and CT features of the patients were also collected. Statistical analysis was performed to identify the quantitative parameters, clinical and CT features that were significantly correlated with STAS status. We evaluated the diagnostic performance of significant factors or models which combined quantitative parameters and CT features, using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve.

Results

We enrolled a total of 47 patients, with 32 positive and 15 negative for STAS. The results revealed that CT100keVa (P=0.002), CT100keVv (P=0.007), pathologic stage (P=0.040), tumor density (P<0.001), spiculation (P=0.003), maximum solid component diameter (P=0.008), and the consolidation/tumor ratio (CTR) (P=0.001) were significantly correlated with STAS status. The tumor density demonstrated a superior diagnostic capability [AUC =0.824, 95% confidence interval (CI): 0.709-0.939, sensitivity =59.4%, specificity =100.0%] compared to other variables. CT100keVa exhibited the best diagnostic performance (AUC =0.779, 95% CI: 0.633-0.925, sensitivity =78.1%, specificity =80.0%) among the quantitative parameters. Combination models were then constructed by combining the quantitative parameters with CT features. The total combined model showed the highest diagnostic efficiency (AUC =0.952, 95% CI: 0.894-1.000, sensitivity =90.6%, specificity =86.7%).

Conclusions

Spectral CT quantitative parameters CT100keVa and CT100keVv may be potentially useful parameters in distinguishing the STAS status in LUAD.

PET/CT-based deep learning grading signature to optimize surgical decisions for clinical stage I invasive lung adenocarcinoma and biologic basis under its prediction: a multicenter study

PURPOSE

No consensus on a grading system for invasive lung adenocarcinoma had been built over a long period of time. Until October 2020, a novel grading system was proposed to quantify the whole landscape of histologic subtypes and proportions of pulmonary adenocarcinomas. This study aims to develop a deep learning grading signature (DLGS) based on positron emission tomography/computed tomography (PET/CT) to personalize surgical treatments for clinical stage I invasive lung adenocarcinoma and explore the biologic basis under its prediction.

METHODS

A total of 2638 patients with clinical stage I invasive lung adenocarcinoma from 4 medical centers were retrospectively included to construct and validate the DLGS. The predictive performance of the DLGS was evaluated by the area under the receiver operating characteristic curve (AUC), its potential to optimize surgical treatments was investigated via survival analyses in risk groups defined by the DLGS, and its biological basis was explored by comparing histologic patterns, genotypic alternations, genetic pathways, and infiltration of immune cells in microenvironments between risk groups.

RESULTS

The DLGS to predict grade 3 achieved AUCs of 0.862, 0.844, and 0.851 in the validation set (n = 497), external cohort (n = 382), and prospective cohort (n = 600), respectively, which were significantly better than 0.814, 0.810, and 0.806 of the PET model, 0.813, 0.795, and 0.824 of the CT model, and 0.762, 0.734, and 0.751 of the clinical model. Additionally, for DLGS-defined high-risk population, lobectomy yielded an improved prognosis compared to sublobectomy p = 0.085 for overall survival [OS] and p = 0.038 for recurrence-free survival [RFS]) and systematic nodal dissection conferred a superior prognosis to limited nodal dissection (p = 0.001 for OS and p = 0.041 for RFS).

CONCLUSION

The DLGS harbors the potential to predict the histologic grade and personalize the surgical treatments for clinical stage I invasive lung adenocarcinoma. Its applicability to other territories should be further validated by a larger international study.

Improving the prediction of Spreading Through Air Spaces (STAS) in primary lung cancer with a dynamic dual-delta hybrid machine learning model: a multicenter cohort study

BACKGROUND

Reliable pre-surgical prediction of spreading through air spaces (STAS) in primary lung cancer is essential for precision treatment and surgical decision-making. We aimed to develop and validate a dual-delta deep-learning and radiomics model based on pretreatment computed tomography (CT) image series to predict the STAS in patients with lung cancer.

METHOD

Six hundred seventy-four patients with pre-surgery CT follow-up scans (with a minimum interval of two weeks) and primary lung cancer diagnosed by surgery were retrospectively recruited from three Chinese hospitals. The training cohort and internal validation cohort, comprising 509 and 76 patients respectively, were selected from Shanghai Chest Hospital; the external validation cohorts comprised 36 and 53 patients from two other centers, respectively. Four imaging signatures (classic radiomics features and deep learning [DL] features, delta-radiomics and delta-DL features) reflecting the STAS status were constructed from the pretreatment CT images by comprehensive methods including handcrafting, 3D views extraction, image registration and subtraction. A stepwise optimized three-step procedure, including feature extraction (by DL and time-base radiomics slope), feature selection (by reproducibility check and 45 selection algorithms), and classification (32 classifiers considered), was applied for signature building and methodology optimization. The interpretability of the proposed model was further assessed with Grad-CAM for DL-features and feature ranking for radiomics features.

RESULTS

The dual-delta model showed satisfactory discrimination between STAS and non-STAS and yielded the areas under the receiver operating curve (AUCs) of 0.94 (95% CI, 0.92-0.96), 0.84 (95% CI, 0.82-0.86), and 0.84 (95% CI, 0.83-0.85) in the internal and two external validation cohorts, respectively, with interpretable core feature sets and feature maps.

CONCLUSION

The coupling of delta-DL model with delta-radiomics features enriches information such as anisotropy of tumor growth and heterogeneous changes within the tumor during the radiological follow-up, which could provide valuable information for STAS prediction in primary lung cancer.

CT-based radiomics model to predict spread through air space in resectable lung cancer

BACKGROUND

Spread through air space (STAS) has been identified as a pathological pattern associated with lung cancer progression. Patients with STAS were related to a worse prognosis compared with patients without STAS. The objective of this study was to establish a radiomics model capable of forecasting STAS before surgery, which can assist surgeons in selecting the most appropriate operation type for patients with STAS.

METHOD

There were 537 eligible patients retrospectively included in this study. ROI segmentation was performed manually on all CT images to identify the region of interest. From each segmented lesion, a total of 1688 features were extracted. The tumor size, maximum tumor diameters, and tumor type were also recorded. Using Spearman's correlation coefficient to calculate the correlation and redundancy of elements, and redundant features less than 0.80 were removed. In order to reduce the level of overfitting and avoid statistical biases, a dimension reduction process of the dataset was conducted to decrease the number of features. Finally, a radiomics model included 44 features was established to predict STAS. To evaluate the performance of the model, the receiver operating characteristic (ROC) curve was used, and the area under the curve (AUC) was calculated, and the accuracy of the model was verified by 10-fold cross-validation.

RESULTS

The incidence of STAS was 38.2% (205/537). The tumor type, maximum tumor diameters, and consolidation tumor ratio were significantly different between STAS group and non-STAS group. The training group included 430 patients, while the test group was consisted with 107. The training group achieved an AUC of 0.825 (sensitivity, 0.875; specificity, 0.621; and accuracy, 0.749) and the test group had an AUC of 0.802 (sensitivity, 0.797; specificity,0.688; and accuracy, 0.748). The 10-fold cross-validation had an AUC of 0.834.

CONCLUSION

CT-based radiomic model can predict STAS effectively, which is of great importance to guide the selection of operation types before surgery.

Application of radiomics based on chest CT-enhanced dual-phase imaging in the immunotherapy of non-small cell lung cancer

OBJECTIVE

To explore the value of applying computed tomography (CT) radiomics based on different CT-enhanced phases to determine the immunotherapeutic efficacy of non-small cell lung cancer (NSCLC).

METHODS

106 patients with NSCLC who underwent immunotherapy are randomly divided into training (74) and validation (32) groups. CT-enhanced arterial and venous phase images of patients before treatment are collected. Region-of-interest (ROI) is segmented on the CT-enhanced images, and the radiomic features are extracted. One-way analysis of variance and least absolute shrinkage and selection operator (LASSO) are used to screen the optimal radiomics features and analyze the association between radiomics features and immunotherapy efficacy. The area under receiver-operated characteristic curves (AUC) along with the sensitivity and specificity are computed to evaluate diagnostic effectiveness.

RESULTS

LASSO regression analysis screens and selects 6 and 8 optimal features in the arterial and venous phases images, respectively. Applying to the training group, AUCs based on CT-enhanced arterial and venous phase images are 0.867 (95% CI:0.82-0.94) and 0.880 (95% CI:0.86-0.91) with the sensitivities of 73.91% and 76.19%, and specificities of 66.67% and 72.19%, respectively, while in validation group, AUCs of the arterial and venous phase images are 0.732 (95% CI:0.71-0.78) and 0.832 (95% CI:0.78-0.91) with sensitivities of 75.00% and 76.00%, and specificities of 73.07% and 75.00%, respectively. There are no significant differences between AUC values computed from arterial phases and venous phases images in both training and validation groups (P < 0.05).

CONCLUSION

The optimally selected radiomics features computed from CT-enhanced different-phase images can provide new imaging marks to evaluate efficacy of the targeted therapy in NSCLC with a high diagnostic value.