Best imaging signs identified by radiomics could outperform the model: application to differentiating lung carcinoid tumors from atypical hamartomas

• Published in: Insights into imaging Vol. 14; no. 1; p. 148
• Main Authors: Habert, Paul, Decoux, Antoine, Chermati, Lilia, Gibault, Laure, Thomas, Pascal, Varoquaux, Arthur, Le Pimpec-Barthes, Françoise, Arnoux, Armelle, Juquel, Loïc, Chaumoitre, Kathia, Garcia, Stéphane, Gaubert, Jean-Yves, Duron, Loïc, Fournier, Laure
• Format: Journal Article
• Language: English
• Published: Vienna Springer Vienna 19-09-2023; Springer Nature B.V; Springer; SpringerOpen
• Subjects: Algorithms; Attenuation; Bias; Carcinoid tumors; Chest; Computed tomography; Computer Science; Criteria; Datasets; Density; Diagnostic Radiology; Hamartomas; Imaging; Internal Medicine; Interventional Radiology; Lung cancer; Lungs; Machine learning; Median (statistics); Medical Imaging; Medicine; Medicine & Public Health; Neuroradiology; Original; Original Article; Pulmonary neoplasms; Radiology; Radiomics; Semantics; Tumors; Ultrasound; X-ray; Carcinoid tumors; X-ray; Computed tomography; Hamartomas; Pulmonary neoplasms; Radiomics
• ISSN: 1869-4101; 1869-4101
• DOI: 10.1186/s13244-023-01484-9

Objectives
Lung carcinoids and atypical hamartomas may be difficult to differentiate but require different treatment. The aim was to differentiate these tumors using contrast-enhanced CT semantic and radiomics criteria.
Methods
Between November 2009 and June 2020, consecutives patient operated for hamartomas or carcinoids with contrast-enhanced chest-CT were retrospectively reviewed. Semantic criteria were recorded and radiomics features were extracted from 3D segmentations using Pyradiomics. Reproducible and non-redundant radiomics features were used to training a random forest algorithm with cross-validation. A validation-set from another institution was used to evaluate of the radiomics signature, the 3D ‘median’ attenuation feature (3D-median) alone and the mean value from 2D-ROIs.
Results
Seventy-three patients (median 58 years [43‒70]) were analyzed (16 hamartomas; 57 carcinoids). The radiomics signature predicted hamartomas vs carcinoids on the external dataset (22 hamartomas; 32 carcinoids) with an AUC = 0.76. The 3D-median was the most important in the model. Density thresholds < 10 HU to predict hamartoma and > 60 HU to predict carcinoids were chosen for their high specificity > 0.90. On the external dataset, sensitivity and specificity of the 3D-median and 2D-ROIs were, respectively, 0.23, 1.00 and 0.13, 1.00 < 10 HU; 0.63, 0.95 and 0.69, 0.91 > 60 HU. The 3D-median was more reproducible than 2D-ROIs (ICC = 0.97 95% CI [0.95‒0.99]; bias: 3 ± 7 HU limits of agreement (LoA) [− 10‒16] vs. ICC = 0.90 95% CI [0.85‒0.94]; bias: − 0.7 ± 21 HU LoA [− 4‒40], respectively).
Conclusions
A radiomics signature can distinguish hamartomas from carcinoids with an AUC = 0.76. Median density < 10 HU and > 60 HU on 3D or 2D-ROIs may be useful in clinical practice to diagnose these tumors with confidence, but 3D is more reproducible.
Critical relevance statement
Radiomic features help to identify the most discriminating imaging signs using random forest. ‘Median’ attenuation value (Hounsfield units), extracted from 3D-segmentations on contrast-enhanced chest-CTs, could distinguish carcinoids from atypical hamartomas (AUC = 0.85), was reproducible (ICC = 0.97), and generalized to an external dataset.
Key points
• 3D-‘Median’ was the best feature to differentiate carcinoids from atypical hamartomas (AUC = 0.85).
• 3D-‘Median’ feature is reproducible (ICC = 0.97) and was generalized to an external dataset.
• Radiomics signature from 3D-segmentations differentiated carcinoids from atypical hamartomas with an AUC = 0.76.
• 2D-ROI value reached similar performance to 3D-‘median’ but was less reproducible (ICC = 0.90).
Graphical Abstract