Table 3.
Computationally extracted imaging features from radiogenomics studies
| Study | Modality | Cancer | Computer-extracted features |
|---|---|---|---|
| Jain et al32 | CT | GBM | CBV, PS |
| Aerts et al9 | CT | NSCLC | Tumour intensity, shape, texture, wavelet features |
| Jamshidi et al28 | CT | CCRCC | None |
| Kuo et al18 | CT | HCC | None |
| Segal et al20 | CT | HCC | None |
| Carlson et al30 | CT | HGG | None |
| Osburne et al36 | PET | Breast cancer | SUV |
| Palaskas et al37 | PET | Breast cancer | SUV |
| Nair et al19 | PET | NSCLC | SUV intensity metrics, SUV distribution metrics, SUV spatial metrics |
| Gevaert et al15 | PET/CT | NSCLC | Histogram, texture, edge sharpness, edge shape, ROI size, SUV |
| Yamamoto et al21 | MRI | Breast cancer | T1 intrinsic signal,T2intrinsic signal strength, contrast kinetic pattern, median peak signal strength at different times, nadir signal strength at different times |
| Yamamoto et al22 | MRI | Breast cancer | Largest tumour volume, tumour roundness, entropy, skewness, kurtosis, GLCM contrast, GLCM homogeneity, GLCM energy, Hu’s seven moment invariants, average of wash-in slope, average of washout slope, plateau fraction, persistent fraction, heterogeneity of time intensity, ERF |
| Zhu et al38 | MRI | Breast cancer | Size phenotypes, shape phenotypes, morphological phenotypes, enhancement texture phenotypes, kinetic curve assessment, enhancement-variance kinetics |
| Barajas et al24 | MRI | GBM | CBV, PH, PSR, ADC |
| Gevaert et al16 | MRI | GBM | Necrotic, enhancing, oedema ROIs |
| Zinn et al23 | MRI | GBM | FLAIR volume |
| Zinn et al27 | MRI | GBM | Volume |
| Colen et al29 | MRI | GBM | Necrosis volume |
| Naeini et al33 | MRI | GBM | Contrast-enhancing volume, necrotic volume, contrast enhancement+necrotic volume, T2hyperintense volume, the ratio of oedema/(necrosis+contrast) |
| Pope et al35 | MRI | GBM | ADC |
| Jamshidi et al17 | MRI | GBM | None |
| Diehn et al25 | MRI | GBM | None |
| Pope et al26 | MRI | GBM | None |
| Colen et al31 | MRI | GBM | None |
| Nicolasjilwan et al34 | MRI | GBM | None |
| Halle et al40 | MRI | Cervical cancer | Abrix (enhancement-variance kinetics) |
| Miura et al39 | MRI | HCC | None |
ADC, apparent diffusion coefficient; C : N ratio, contrast:necrosis ratio; CBV, cerebral blood volume; CCRCC, clear-cell renal cell carcinoma; CNV, copy number variation; EFR, enhancing rim fraction; FLAIR, fluid-attenuated inversion recovery; GBM, glioblastoma multiforme; GLCM, gray-level concurrence matrix; HCC, hepatocellular carcinoma; HGG, high-grade glioma; NSCLC, non-small-cell lung cancer; PET, positron emission tomography; PH, peak height; PSR, percentage of signal intensity recovery; PS, permeability surface; ROI, region of interest; SUV, standardized uptake value; SVZ, subventricular zone.
Bold type means significant relationship of imaging feature with genomic data.