Dataset Information

Combined Radiomic and Visual Assessment for Improved Detection of Lung Adenocarcinoma Invasiveness on Computed Tomography Scans: A Multi-Institutional Study.

ABSTRACT:

Objective

The timing and nature of surgical intervention for semisolid abnormalities are dependent upon distinguishing between adenocarcinoma-in-situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (INV). We sought to develop and evaluate a quantitative imaging method to determine invasiveness of small, ground-glass lesions on computed tomography (CT) chest scans.

Methods

The study comprised 268 patients from 4 institutions with resected (<=3 cm) semisolid lesions with confirmed histopathological diagnosis of MIA/AIS or INV. A total of 248 radiomic texture features from within the tumor nodule (intratumoral) and adjacent to the nodule (peritumoral) were extracted from manually annotated lung nodules of chest CT scans. The datasets were randomly divided, with 40% of patients used for training and 60% used for testing the machine classifier (Training D_Train, N=106; Testing, D_Test, N=162).

Results

The top five radiomic stable features included four intratumoral (Laws and Haralick feature families) and one peritumoral feature within 3 to 6 mm of the nodule (CoLlAGe feature family), which successfully differentiated INV from MIA/AIS nodules with an AUC of 0.917 [0.867-0.967] on D_Train and 0.863 [0.79-0.931] on D_Test. The radiomics model successfully differentiated INV from MIA cases (<1 cm AUC: 0.76 [0.53-0.98], 1-2 cm AUC: 0.92 [0.85-0.98], 2-3 cm AUC: 0.95 [0.88-1]). The final integrated model combining the classifier with the radiologists' score gave the best AUC on D_Test (AUC=0.909, p<0.001).

Conclusions

Addition of advanced image analysis via radiomics to the routine visual assessment of CT scans help better differentiate adenocarcinoma subtypes and can aid in clinical decision making. Further prospective validation in this direction is warranted.

SUBMITTER: Vaidya P

PROVIDER: S-EPMC9190758 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Combined Radiomic and Visual Assessment for Improved Detection of Lung Adenocarcinoma Invasiveness on Computed Tomography Scans: A Multi-Institutional Study.

Vaidya Pranjal P Bera Kaustav K Linden Philip A PA Gupta Amit A Rajiah Prabhakar Shantha PS Jones David R DR Bott Matthew M Pass Harvey H Gilkeson Robert R Jacono Frank F Hsieh Kevin Li-Chun KL Lan Gong-Yau GY Velcheti Vamsidhar V Madabhushi Anant A

Frontiers in oncology 20220530

<h4>Objective</h4>The timing and nature of surgical intervention for semisolid abnormalities are dependent upon distinguishing between adenocarcinoma-<i>in-situ</i> (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (INV). We sought to develop and evaluate a quantitative imaging method to determine invasiveness of small, ground-glass lesions on computed tomography (CT) chest scans.<h4>Methods</h4>The study comprised 268 patients from 4 institutions with resected (<=3 cm) ...[more]

PMID: 35707362

Similar Datasets

Project description:ObjectiveTo identify stable and discriminating radiomic features on non-contrast CT scans to develop more generalisable radiomic classifiers for distinguishing granulomas from adenocarcinomas.MethodsIn total, 412 patients with adenocarcinomas and granulomas from three institutions were retrospectively included. Segmentations of the lung nodules were performed manually by an expert radiologist in a 2D axial view. Radiomic features were extracted from intra- and perinodular regions. A total of 145 patients were used as part of the training set (Str), whereas 205 patients were used as part of test set I (Ste1) and 62 patients were used as part of independent test set II (Ste2). To mitigate the variation of CT acquisition parameters, we defined 'stable' radiomic features as those for which the feature expression remains relatively unchanged between different sites, as assessed using a Wilcoxon rank-sum test. These stable features were used to develop more generalisable radiomic classifiers that were more resilient to variations in lung CT scans. Features were ranked based on two criteria, firstly based on discriminability (i.e. maximising AUC) alone and subsequently based on maximising both feature stability and discriminability. Different machine-learning classifiers (Linear discriminant analysis, Quadratic discriminant analysis, Support vector machines and random forest) were trained with features selected using the two different criteria and then compared on the two independent test sets for distinguishing granulomas from adenocarcinomas, in terms of area under the receiver operating characteristic curve.ResultsIn the test sets, classifiers constructed using the criteria involving maximising feature stability and discriminability simultaneously achieved higher AUC compared with the discriminating alone criteria (Ste1 [n = 205]: maximum AUCs of 0.85versus . 0.80; p-value = 0.047 and Ste2 [n = 62]: maximum AUCs of 0.87 versus. 0.79; p-value = 0.021). These differences held for features extracted from scans with <3 mm slice thickness (AUC = 0.88 versus. 0.80; p-value = 0.039, n = 100) and for the ≥3 mm cases (AUC = 0.81 versus. 0.76; p-value = 0.034, n = 105). In both experiments, shape and peritumoural texture features had a higher stability compared with intratumoural texture features.ConclusionsOur study suggests that explicitly accounting for both stability and discriminability results in more generalisable radiomic classifiers to distinguish adenocarcinomas from granulomas on non-contrast CT scans. Our results also showed that peritumoural texture and shape features were less affected by the scanner parameters compared with intratumoural texture features; however, they were also less discriminating compared with intratumoural features.

Project description:BackgroundClinically differentiating preinvasive lesions (atypical adenomatous hyperplasia, AAH and adenocarcinoma in situ, AIS) from invasive lesions (minimally invasive adenocarcinomas, MIA and invasive adenocarcinoma, IA) manifesting as ground-glass opacity nodules (GGOs) is difficult due to overlap of morphological features. Hence, the current study was performed to explore the diagnostic efficiency of radiomics in assessing the invasiveness of lung adenocarcinoma manifesting as GGOs.MethodsA total of 1018 GGOs pathologically confirmed as lung adenocarcinoma were enrolled in this retrospective study and were randomly divided into a training set (n = 712) and validation set (n = 306). The nodules were delineated manually and 2446 intra-nodular and peri-nodular radiomic features were extracted. Univariate analysis and least absolute shrinkage and selection operator (LASSO) were used for feature selection. Clinical and semantic computerized tomography (CT) feature model, radiomic model and a combined nomogram were constructed and compared. Decision curve analysis (DCA) was used to evaluate the clinical value of the established nomogram.Results16 radiomic features were selected and used for model construction. The radiomic model exhibited significantly better performance (AUC = 0.828) comparing to the clinical-semantic model (AUC = 0.746). Further analysis revealed that peri-nodular radiomic features were useful in differentiating between preinvasive and invasive lung adenocarcinomas appearing as GGOs with an AUC of 0.808. A nomogram based on lobulation sign and radiomic features showed the best performance (AUC = 0.835), and was found to have potential clinical value in assessing nodule invasiveness.ConclusionsRadiomic model based on both intra-nodular and peri-nodular features showed good performance in differentiating between preinvasive lung adenocarcinoma lesions and invasive ones appearing as GGOs, and a nomogram based on clinical, semantic and radiomic features could provide clinicians with added information in nodule management and preoperative evaluation.

Project description:BackgroundPancreatic perfusion computed tomography (CT) imaging is increasingly used for neoplastic grading, predicting prognosis, and evaluating the response to therapy. To optimize the clinical pancreatic CT perfusion imaging methods, we evaluated 2 different CT scanning protocols concerning pancreas perfusion parameters.MethodsA retrospective study was conducted on 40 patients who underwent whole pancreas CT perfusion scanning in The First Affiliated Hospital of Zhengzhou University. Of these 40 patients, 20 patients in group A underwent continuous perfusion scanning, while 20 patients in group B underwent intermittent perfusion scanning. For group A, continuous axial scanning was performed 25 times, and the total scan time was 50 s. For group B, arterial phase helical perfusion scanning was performed 8 times, and then venous phase helical perfusion scanning was performed 15 times, with a total scan time of 64.6 to 70.0 s. A comprehensive list of perfusion parameters between different parts of the pancreas and the 2 groups were compared. The effective radiation dose for the 2 scanning methods was analyzed.ResultsThe parameter of the mean slope of increase (MSI) at different pancreatic parts in group A differed (P=0.028). The pancreas head had the lowest value, and the tail had the highest (about a 20% difference). In group A compared to group B, the blood volume of the pancreatic head was smaller (15.256±2.925 vs. 16.953±3.602), the positive enhanced integral was smaller (0.307±0.050 vs. 0.344±0.060) and the permeability surface was larger (34.205±9. 612 vs. 24.377±8.413); the blood volume of the pancreatic neck was smaller (13.940±2.691 vs. 17.173±3.918), the positive enhanced integral was smaller (0.304±0.088 vs. 0.361±0.051) and the permeability surface was larger (34.898±11.592 vs. 25. 794±8.149); the blood volume of the pancreatic body was smaller (16.142±4.006 vs. 18.401±2.513), the positive enhanced integral was smaller (0.305±0.093 vs. 0.342±0.048) and the permeability surface was larger (28.861±10.448 vs. 22.158±6. 017); the blood volume of the pancreatic tail was smaller (16.446±3.709 vs. 17.374±3.781), the positive enhanced integral was smaller (0.304±0.057 vs. 0.350±0.073) and the permeability surface was larger (27.823±8.228 vs. 21.509±7.768) (P<0.05). The effective radiation dose in the intermittent scan mode was slightly lower at 16.657±2.259 mSv than in the continuous scan mode (17.973±3.698 mSv).ConclusionsDifferent CT scanning intervals had a significant influence on whole pancreas blood volume, permeability surface, and positive enhanced integral. These demonstrate the high sensitivity of intermittent perfusion scanning for identifying perfusion abnormalities. Therefore, for the diagnosis of pancreatic diseases, intermittent pancreatic CT perfusion may be more advantageous.

Dataset Information

Combined Radiomic and Visual Assessment for Improved Detection of Lung Adenocarcinoma Invasiveness on Computed Tomography Scans: A Multi-Institutional Study.

Objective

Methods

Results

Conclusions

Publications

Combined Radiomic and Visual Assessment for Improved Detection of Lung Adenocarcinoma Invasiveness on Computed Tomography Scans: A Multi-Institutional Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets