Table 2.
Description of studies using different radiomics features to determine the invasiveness of lung adenocarcinoma spectrum lesions.
| Year | References | Number of Cases | Imaging Modality | Group a | Validation * | Combined Model b | Diagnostic Performance |
|---|---|---|---|---|---|---|---|
| 2014 | Hee-Dong Chae [42] | 86 | CT | PSN | No | No | AUC = 0.981 |
| 2017 | Takuya Yagi [59] | 101 | CT | SSN | No | No | AUC = 0.85–0.90 (Sensitivity = 75–83.3%, Specificity = 83.6–85.1%) |
| 2021 | Yining Jiang [46] | 100 | CT | pGGN | Yes (internal) | No | AUC = 0.892 (Sensitivity = 81.1%, Specificity = 71.9%) |
| 2019 | Hwan-ho Cho [43] | 236 | CT | GGN | Yes (internal) | No | AUC = 0.8419 |
| 2019 | Bin Yang [60] | 192 | CT | SSN | Yes (internal) | No | AUC = 0.83 (Sensitivity = 84%, Specificity = 78%, Accuracy = 82%) |
| 2018 | Wei Li [47] | 109 | CT | GGN | No | No | AUC = 0.665–0.775 |
| 2018 | Xing Xue [58] | 599 | CT | GGN | Yes (internal) | No | AUC = 0.76 |
| 2020 | Guangyao Wu [53] | 291 | CT | PSN | Yes (external) | Yes | AUC = 0.98 (Sensitivity = 98%, Specificity = 78%, Accuracy = 93%) |
| 2018 | Yunlang She [49] | 402 | CT | SSN | Yes (internal) | Yes | AUC = 0.95 |
| 2019 | B Feng [45] | 100 | CT | SSN | Yes (internal) | Yes | AUC = 0.943 (Sensitivity = 84%, Specificity = 88%) |
| 2022 | Yong Li [48] | 147 | CT | pGGN | Yes (internal) | Yes | AUC = 0.879–0.941 |
| 2020 | Lan Song [50] | 187 | CT | GGN | Yes (internal) | Yes | AUC = 0.934 (Sensitivity = 80.5%, Specificity = 87.5%, Accuracy = 83.8%) |
| 2018 | Li Fan [44] | 208 | CT | GGN | Yes (internal) | Yes | AUC = 0.917 (Sensitivity = 83.1%, Specificity = 89.6%) |
| 2020 | Linyu Wu [54] | 120 | CT | GGN | Yes (internal) | Yes | AUC = 0.896 |
| 2019 | Q Weng [52] | 119 | CT | PSN | Yes (internal) | Yes | AUC = 0.888 (Sensitivity = 73.5%, Specificity = 94.1%) |
| 2021 | Ziqi Xiong [56] | 198 | CT | pGGN | Yes (internal) | Yes | AUC = 0.879 (Sensitivity = 75%, Specificity = 89.3%) |
| 2021 | Yun-Ju Wu [55] | 236 | CT | SSN | Yes (internal) | Yes | AUC = 0.878 (Sensitivity = 84.8%, Specificity = 79.2%) |
| 2020 | Fangyi Xu [57] | 275 | CT | pGGN | Yes (internal) | Yes | AUC = 0.824 |
| 2020 | Yingli Sun [51] | 395 | CT | GGN | Yes (internal) | Yes | AUC = 0.77 |
| 2019 | WeiZhao [61] | 542 | CT | GGN | Yes (internal) | Yes | AUC = 0.716 |
pGGN: pure ground-glass nodules; PSN: part-solid nodule; SSN: subsolid 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 the model has had clinical or semantic information added it. * 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.