Table 3.
Signatures derived from imaging data
| Reference | Cancer | Signatures | Notes |
|---|---|---|---|
| Nishino et al.132 | melanoma, NSCLC, advanced-stage solid tumors | PD-L1 | – |
| Berry et al.135 | melanoma | CD8+FoxP3+PD-1 | – |
| – | CD163+PD-L1− | – | |
| Chen et al.136 | gastric cancer | TIIC signature | TIIC signature: CD4+FoxP3−PD-L1+, CD8+PD-1−LAG3−, and CD68+STING+ cell density + the effective score of CD8+PD-1+LAG3− T cells; effective score = proportion of immune cells within a specific distance from the tumor cells |
| Lopez de Rodas et al.137 | NSCLC | spatial heterogeneity score | spatial heterogeneity score uses Rao's Q index to measure diversity based on pairwise distances between cell types (tumor, CD4+, CD8+, CD20+, and stromal cells) and relative abundance of each cell type |
| Wu et al.138 | head and neck cancer, colorectal cancer | graphical embeddings of spatial relationships between cells | delineates graph neural network spatial motifs associated with cancer recurrence and response |
| Patwa et al.139 | TNBC | scoring of interactions between cells expressing PD-1, PD-L1, IDO, and LAG-3 | – |
| Zugazagoitia et al.140 | NSCLC | immune-stromal CD56 and CD4 protein expression | – |
| tumor VISTA and CD127 protein expression | – | ||
| Larroquette et al.141 | NSCLC | high CD163+ cell infiltration (possibly high expression of ITGAM, CD27, and CCL5) | – |
| high CSF1R expression in tumor cells | higher CSF1R in tumors of responders | ||
| Johannet et al.148 | metastatic melanoma | DCNN-derived response classification + clinical variables | ECOG performance score and immunotherapy category |
| Khorrami et al.149 | NSCLC | changes in a machine-learning-derived radiomic feature set | – |
| Vaidya et al.150 | advanced NSCLC | CT-scan radiomic features | – |
| Trebeschi et al.151 | advanced melanoma and NSCLC | CT-scan radiomic features | only borderline significant for melanoma |