Characterizing tumor heterogeneity is a challenge in oncology. As explained by Marusyk and Polyak [1], the coexistence of different clones in a tumor affects the evolution of cancer and should be accounted for in patient management. Measuring the extent of clonal heterogeneity could therefore be extremely useful to select the most promising therapeutic approach. Several groups have characterized tumor heterogeneity using textural indices in 18F-FDG PET [2–12] but contradictory results have been reported. For instance, in head and neck cancer, Cheng et al [8] showed that a tumor uniformity index (also called energy in other papers) calculated in pretreatment 18F-FDG PET images was a prognostic factor in advanced T-stage, while El Naqa [3] could not predict patient response using this index. Moreover, most analyses used a univariate approach and did not actually assess the incremental value of textural metrics over conventional indices such as tumor metabolic volume or FDG uptake. Also, it has been pointed out that textural metrics should be used with caution, as some metrics are substantially variable with respect to the acquisition mode and reconstruction parameters [13], are strongly correlated with the tumor metabolic volume [14,15] and/or are redundant [14]. Misconceptions regarding the meaning of textural indices derived from PET images have been recently underlined, especially given the instrumental limitations encountered in PET [16,17]. In a recent study using 18F-FDG PET data, Brooks and Grigsby [15] demonstrated that below a tumor volume of 45 cm³ (corresponding to 700 voxels in their work), the entropy metrics mostly reflected the tumor volume and not the heterogeneity of tracer uptake in the tumor. This result therefore questions the use of textural metrics for a broad range of tumors and casts doubt upon previous conclusions obtained in tumors for which the volume was not reported. Last, many studies that demonstrated the ability of TI to distinguish between tumor groups did actually not properly control the false positive rate caused by the large number of hypotheses tested simultaneously [18]. Moreover, the fact that FDG-PET images can depict tissue-specific textural pattern, meaning that different tissues might be characterized by different TI values, has received little attention in the literature. Similarly, the meaning and actual variation of TI as a function of tissue type has not been thoroughly investigated in FDG-PET.

TI calculation requires an initial resampling of the tumor voxel intensities that sets voxels with similar uptake to the same value hence reduces the impact of noise. The usual resampling method consists in rescaling the tumor voxel values between 0 and 1 using a fixed number of bins (typically 64), so that the maximum voxel value in the tumor is set to 1 while the minimum is set to 0. Alternative resampling schemes have been proposed [19,20]. By definition, this resampling step affects the value of TI. Yet, the impact of this resampling on the ability of TI to reflect useful information regarding the uptake spatial distribution has been overlooked. The goal of our study was therefore to investigate the impact of this resampling step on TI values and on the ability of TI to reflect tissue-specific pattern of metabolic activity. For that purpose, we first used a uniform FDG-filled phantom to characterize the behavior of TI as a function of the region volume when no biological texture is present for two resampling approaches. Second, we analyzed images from patients with non-small cell lung cancer (NSCLC) to confirm the findings obtained using the phantom and to determine whether the regional FDG uptake pattern measured using different TI could distinguish between tissue types and whether this distinction depended on the resampling scheme.

In this study, we showed that TI computed using an AR method were less correlated to MV than those calculated with a RR method and demonstrated that AR-based TI were significantly different in healthy and tumor tissue or in two subtypes of lung tumors. These differences were higher than those observed with SUVmax, MV and RR-based TI. We found that lung tumor tissue exhibited more heterogeneous texture than healthy tissue, corresponding to lower homogeneity and higher entropy (Table 3). Similarly, we observed that squamous cell carcinomas yielded a more heterogeneous tumor metabolism than adenocarcinomas.

The first objective of our study was to determine the impact of the resampling method on the resulting TI and on their correlation with the region volume and SUVs. Unlike Brooks and Grigsby [15], we used PET images of a phantom uniformly filled with FDG for our experiments. For that phantom, the texture of the FDG distribution was only that of the PET signal which is spatially correlated in the reconstructed images [22], as there was no “physiological” texture in the phantom. The behavior of TI as a function of the volume of the region used to calculate it could thus be investigated without any confounding factor potentially introduced by an underlying physiological signal. When using the usual RR resampling, we found that change in entropy (Fig 3C) with the VOI volume was very similar to that previously reported in [15], demonstrating the relevance of our phantom study to characterize the relationship between TI and region volume. In addition, we found that most TI actually behave like entropy with respect to their dependency on the tumor volume, with high dependency on volume for small volume and then stable TI values beyond a certain volume. Still, the volume from which the plateau was reached varied from one TI to another (see Fig 3A and 3C and S1A, S1C and S1G Fig). We also observed that some TI never reached a plateau, confirming that these indices were poor descriptors of texture (RLNU, see [14]).

We also found that the relationship between TI and MV was similar in phantom data and in clinical data (Fig 3), demonstrating for the first time that the phantom approach was appropriate to characterize the TI dependency on volume as observed in patients, in spite of differences in SUV distribution (Fig 3) and signal-to-noise ratios between the phantom and clinical data (phantom: 11 kBq/mL at scan time scanned for 3 min; patient: 3–3.5 kBq/mL at scan time scanned for 1.45 min per bed position).

In their conclusion, Brooks and Grigsby [15] recommended calculating entropy only in regions greater than 45 cm³, which significantly limits the use of TI. The alternative AR resampling scheme we propose actually overcome this limitation and enable calculation of TI without introducing a large bias associated with the tumor volume. The rationale for the AR method is that the range of SUV in a given tumor actually already provides information regarding the tumor heterogeneity, regardless of the spatial arrangement of these values within a tumor. Indeed, it is expected that if a tumor region includes a broad range of SUV values, the tumor will be more heterogeneous than if all SUV are similar. Therefore, removing the SUV range information by using Eq (1) in the resampling step does not appear to be relevant for assessing the tumor texture. On the contrary, the fact that TI are correlated with SUV (Fig 4) does not appear counterintuitive since the range of SUV in a tumor actually already reflects some tumor heterogeneity: for instance, if SUV varies from 2 to 10 in a tumor, it is expected to be more heterogeneous than a tumor in which SUV varies only from 2 to 3.

Resampling between fixed low and high SUV bounds therefore preserves this useful SUV information in the TI calculation. We arbitrarily chose 0 as a low bound and 20 as a high bound, as this is typically the range of SUV encountered in the clinics. To assess the impact of the arbitrary high bound value, we investigated the robustness of our results when changing the higher bound to 15 or 25 SUV units (Tables 2 and 4) and found that the conclusions remained unchanged, demonstrating that the choice of this high bound is not critical.

Using AR-based TI, it is possible to determine whether textural features are different as a function of the tissue type, without being affected by differences in the volume of the analyzed tissue. As a first in vivo model that could serve as a toy model, we first investigated whether TI were significantly different in healthy and tumor tissue. Although it is obvious that this distinction is not clinically meaningful, TI should enable the distinction between healthy and tumoral tissues if they are expected to be useful to distinguish between subtle differences in tissue types. Using this toy model, we demonstrated that all 7 TI were significantly different between these two tissue types when using the AR method, while this was not the case when using the RR method. Healthy tissue was more homogeneous than tumor tissue (Table 3) as shown by higher homogeneity and lower entropy values in the liver compared to the tumor in our NSCLC patients. Similarly, we observed that tumors contained less “low gray-level” and more “high gray-level” voxels than healthy tissue (Table 3), corresponding to lower LGZE and higher HGZE in tumors, which is again what could be intuitively expected. To the best of our knowledge, only two studies compared the range of TI across tissue types so far. Using 103 untreated patients with bone and soft-tissue lesions, Xu et al [23] showed that TI from PET and CT images could differentiate between malignant and benign lesions. They found that entropy from FDG-PET images was higher in malignant tumors than in benign lesions. The second study [24] reported that the contrast TI (from CM) was greater in the liver compared to tumors for 11 patients with breast cancer who underwent a fluorothymidine (FLT) PET scan before treatment. In our study, we found that the same contrast index (data not shown) was higher in lung tumors (median 26.0, range: [1.2–219.7]) than in liver tissue (median 1.1, range: [0.5–2.8]). These discrepant results might be explained by the use of different tracers, by the low number of patients in [24], by the inclusion of tumors with very heterogeneous volumes (2.65 to 540.99 mL) without accounting for these differences in volumes and by the use of RR instead of AR. It is important to underline that when using RR, none of the TI yielded a pvalue lower than that of SUVmax, while when using the AR method, 4 out of the 7 TI did better than SUVmax at distinguishing between tumor and healthy tissue, demonstrating the relevance of the AR method. Given that AR-based TI also reflect some SUV information, we checked how the pvalues of Wicoxon’s tests of AR-based TI compared with the pvalues of the combination between RR-based TI and SUVmax (S3 Table). We found that the AR-based TI led to very similar results compared to RR-based TI associated with SUVmax using a logistic regression with lower pvalues for homogeneity, entropy, SRE and LGZE to differentiate tumor and healthy tissue. An advantage of using AR-based TI is that it consistently includes TI and SUV information into a single index, which might facilitate its use in a clinical setting compared to the co-analysis of two indices (RR-based TI and SUV).

When determining whether TI were different between tumor subtypes, we again observed that with the AR method, tumor subtypes were better distinguished than with the RR method (Table 4). TI reflected differences between FDG uptake pattern in adenocarcinomas and squamous cell carcinomas: the adenocarcinomas were more homogeneous, with higher homogeneity and lower entropy, and had less “high gray-level” voxels than the squamous cell carcinomas (Table 3). Chi-2 Pearson tests showed that only the presence of necrosis measured on the resected specimen was significantly different between the two subtypes of cancer (pvalue<0.01), unlike T stage, N stage and the level of differentiation (Table 5). We can thus hypothesize that AR-based TI could capture the presence of histologic necrosis. In their study, Asamura et al [25] demonstrated that patients with squamous cell carcinomas had a poorer prognosis than those with adenocarcinomas, after surgical resection, based on 11,939 patients. Moreover the squamous cell carcinomas exhibit a high proliferative index compared to the adenocarcinomas [26]. Altogether, these results suggest than AR-based TI might assist in objectively assessing tumor aggressiveness by efficiently combining texture information and SUV in a single index. For three TI (homogeneity, entropy and LGZE), the use of AR-based TI led to a better distinction between the tumor types than combining RR-based indices with SUVmax (S3 Table).

The AR method is close to the resampling method used by Leijenaar et al [19], where the authors resampled voxel intensities with fixed bin width of 0.5 SUV units. Their approach actually corresponds to using AR with the maximum bound of 32 SUV units. With a maximum bound of 20 SUV units and 64 discrete values, the bin-width is approximately of 0.3 SUV units, which makes the TI sensitive to smaller variations in voxel SUV compared to a bin width of 0.5 SUV units. The optimal bin size could be further investigated, but we already demonstrated that our results did not strongly depend on it (Tables 2 and 4).

Our results should be confirmed using larger cohorts, since we only studied the distinction of subtypes between 28 adenocarcinomas and 13 squamous cell carcinomas. Moreover, our conclusions should be validated using different cancer types, and a next step will be to establish expected normal TI values as a function of the tissue type, so that TI could be used prospectively on an individual patient basis to assess the tumor homogeneity, instead of being only used in retrospective studies as has been reported so far.

On-going standardization of PET imaging protocols should make it easier to later define some common rules for TI interpretation, also accounting for TI variability as a function of the PET acquisition mode and reconstruction parameters previously described by Galavis et al [13]. Moreover, as previously underlined [14], the relevance of TI should always be studied by measuring its incremental value for tumor characterization with respect to the widely used SUV and MV.

To conclude, textural patterns of metabolic activity can be measured without being biased by the region volume by using an absolute resampling method identical for all tumors and preserving the SUV information that already reflect some tumor heterogeneity. We demonstrated that AR-based TI were significantly different in lung tumors and healthy tissue and also in squamous cell carcinoma and adenocarcinoma, and that these differences were greater than those observed with SUVmax or MV. These results show that AR-based TI capture relevant information regarding the amplitude and spatial distribution of SUV and might be of interest to enrich the tumor profiling in radiomic analyses [27] that aim at a comprehensive characterization of tumors based on image features.