Table 1.
Description of studies using different radiomics features to determine the malignancy/benignancy of lung nodules.
| Year | References | Number of Cases * | Imaging Modality | Group a | Validation ** | Combined Model b | Diagnostic Performance |
|---|---|---|---|---|---|---|---|
| 2019 | Liting Mao [33] | (294) | CT | SPN | Yes (internal) | No | AUC = 0.97 (Sensitivity = 81%, Specificity = 92.2%, Accuracy = 89.8%) |
| 2019 | Johanna Uthoff [29] | 363 | CT | SPN | Yes (internal) | No | AUC = 0.965 (Sensitivity = 100%, Specificity = 96%) |
| 2019 | Diego Ardila [27] | 10306 | CT | SPN | Yes (internal) | No | AUC = 0.95 |
| 2018 | Tobias Peikert [24] | (726) | CT | SPN | Yes (internal) | No | AUC = 0.939 |
| 2021 | Mehdi Astaraki [37] | (1297) | CT | SPN | Yes (internal) | No | AUC = 0.938 |
| 2021 | Mehdi Astaraki [38] | (1927) | CT | SPN | Yes (internal) | No | AUC = 0.936 |
| 2018 | Wookjin Choi [25] | (72) | CT | SPN | Yes (internal) | No | AUC = 0.89 (Sensitivity = 87.2%, Specificity = 81.2%, Accuracy = 84.6%) |
| 2016 | Ying Liu [21] | 172 | CT | SPN | Yes (internal) | No | AUC = 0.88 (Sensitivity = 76.2%, Specificity = 91.7%, Accuracy = 81.1%) |
| 2020 | Qin Liu [35] | 197 (210) | CT | SPN | Yes (internal) | No | AUC = 0.877 (Sensitivity = 81.8%, Specificity = 77.4%, Accuracy = 80%) |
| 2019 | Yan Xu [31] | (373) | CT | SPN | No | No | AUC = 0.84 (Sensitivity = 89%, Specificity = 74%, Accuracy = 77%) |
| 2016 | Samuel Hawkins [22] | (185) | CT | SPN | Yes (internal) | No | AUC = 0.83 (Accuracy = 80.12%) |
| 2019 | Niha Beig [32] | 290 | CT | SPN | Yes (internal) | No | AUC = 0.80 |
| 2019 | Darcie A P Delzell [28] | 200 | CT | SPN | No | No | AUC = 0.72 |
| 2016 | Lan He [23] | (240) | CT | SPN | Yes (internal) | No | AUC = 0.682 |
| 2019 | Subba R Digumarthy [30] | 36 (108) | CT | SSN | No | No | AUC = 0.624 |
| 2016 | Jun Wang [39] | 593 | CT | SPN | Yes (internal) | No | (Sensitivity = 82.5%, Specificity = 89.5%, Accuracy = 86%) |
| 2018 | Chia-Hung Chen [26] | 72 (75) | CT | SPN | No | No | (Sensitivity = 92.85%, Specificity = 72.73%, Accuracy = 84%) |
| 2021 | Rui Jing [36] | 116 | CT | SPN | Yes (internal) | Yes | AUC = 0.9406 |
| 2014 | Sang Hwan Lee [40] | (86) | CT | PSN | No | Yes | AUC = 0.929 |
| 2020 | Ailing Liu [34] | 875 | CT | SPN | Yes (internal) | Yes | AUC = 0.836 |
SPN: solitary pulmonary nodule; SSN: subsolid nodule; PSN: part-solid nodule; AUC: area under the curve. a Group: refers to the type of lung nodules analyzed in this study. b Combined model: refers to whether there has been clinical or semantic information added to the model. * Number of people (number of nodules). ** Internal stands for internal validation; external stands for external validation. Internal validation was defined as a prediction method drawn from a similar population as the original training cohort; external validation is the action of testing the developed prediction model in a set of the population independent of the original training cohort.