Table 1.
Characteristics of studies on the current applications of radiogenomics in cancer
| Research | Cancer type | Application | Sample size | Images | Methods | Features in models | Results |
|---|---|---|---|---|---|---|---|
|
Chen et al. [85] |
ccRCC | Diagnosis | 197 | CT | LR | Radiomics; genomics | AUC: 0.864–0.900 |
|
Smedley et al. [86] |
NSCLC | Diagnosis | 351 | CT | NN | Radiomics; genomics | AUC: 0.86 (adenocarcinoma), 0.91 (squamous cell), and 0.71 (other) |
|
Shim et al. [87] |
Glioblastoma | Recurrence | 192 | MRI | NN | Radiomics; | AUC: 0.969 for local recurrence and 0.864 for distant recurrence |
|
Kirienko et al [88] |
NSCLC | Recurrence | 151 | PET/CT |
GLM; ML |
Radiomics; genomics | AUC: 0.87 |
|
Yan et al. [89] |
MB | Survival | 166 | MRI | LASSO-COX | Radiomics; clinicomolecular | C-index: 0.762 for OS and 0.697 for PFS |
|
Xie et al. [81] |
ESCC | Survival | 106 | CT | ML |
Radiomics; clinical factors |
AUC: 0.852 for 5-year DFS; Significant risk stratification for DFS (p < 0.001) |
|
Huang et al [90] |
ccRCC | Survival | 205 | Contrast-enhanced CT | RF | Radiomic; genomics | AUC: 0.84, 0.81, and 0.75 for 1, 3, and 5-year OS, respectively |
|
Liu et al. [80] |
CRC | Metastasis | 134 | CT | LR |
Radiomics; genomics; clinical factors |
AUC: 0.752 (95% CI 0.608–0.896) |
|
Kim et al [92] |
Paediatric osteosarcoma | Chemotherapy response | 73 | PET/CT | ML | Radiomics; genomics; | AUC: 0.89 |
|
Yi et al. [93] |
OC | Platinum resistance | 102 | CT | SVM |
Radiomics; genomics; clinical factors |
AUC: 0.967 (95% CI 0.83–0.98) |
|
Zeng et al. [77] |
ccRCC | Molecular subtypes | 382 | Contrast-enhanced CT | ML | Radiomics; genomics; transcriptomics; proteomics | AUC: 0.973 (m1), 0.968 (m2), 0.961 (m3), 0.953 (m4) |
|
Park et al. [94] |
Glioblastoma | Molecular characteristics | 121 | MRI | ML |
Radiomics; clinical factors |
AUC: 0.863 |
|
Li et al. [95] |
BC | Molecular subtypes | 91 | MRI | Linear classifier | Radiomics | AUC: 0.89 (ER + vs. ER −), 0.69 (PR + vs. PR −), 0.65 (HER2 + vs. HER2 −), and 0.67 (triple-negative vs. others) |
ccRCC: clear cell renal cell carcinoma; NSCLC: non-small cell lung cancer; MB: medulloblastoma; ESCC: oesophageal squamous cell carcinoma; CRC: colorectal cancer; OC: ovarian cancer; BC: breast cancer; CT: computed tomography; MRI: magnetic resonance imaging; PET: positron emission tomography; NN: neural network; GLM: generalized linear model; ML: machine learning; LASSO-COX: least absolute shrinkage and selection operator penalized Cox proportional hazards regression; RF: random forest; LR: logistic regression; SVM: support vector machine; AUC: area under the curve; OS: overall survival; PFS: progression-free survival; DFS: disease-free survival