Dataset Information

A mutation-based radiomics signature predicts response to imatinib in Gastrointestinal Stromal Tumors (GIST).

ABSTRACT:

Objectives

To develop a mutation-based radiomics signature to predict response to imatinib in Gastrointestinal Stromal Tumors (GISTs).

Methods

Eighty-two patients with GIST were enrolled in this retrospective study, including 52 patients from one center that were used to develop the model, and 30 patients from a second center to validate it. Reference standard was the mutational status of tyrosine-protein kinase (KIT) and platelet-derived growth factor α (PDGFRA). Patients were dichotomized in imatinib sensitive (group 0 - mutation in KIT or PDGFRA, different from exon 18-D842V), and imatinib non-responsive (group 1 - PDGFRA exon 18-D842V mutation or absence of mutation in KIT/PDGFRA). Initially, 107 texture features were extracted from the tumor masks of baseline computed tomography scans. Different machine learning methods were then implemented to select the best combination of features for the development of the radiomics signature.

Results

The best performance was obtained with the 5 features selected by the ANOVA model and the Bayes classifier, using a threshold of 0.36. With this setting the radiomics signature had an accuracy and precision for sensitive patients of 82 % (95 % CI:60-95) and 90 % (95 % CI:73-97), respectively. Conversely, a precision of 80 % (95 % CI:34-97) was obtained in non-responsive patients using a threshold of 0.9. Indeed, with the latter setting 4 patients out of 5 were correctly predicted as non-responders.

Conclusions

The results are a first step towards using radiomics to improve the management of patients with GIST, especially when tumor tissue is unavailable for molecular analysis or when molecular profiling is inconclusive.

SUBMITTER: Cappello G

PROVIDER: S-EPMC10362081 | biostudies-literature | 2023 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A mutation-based radiomics signature predicts response to imatinib in Gastrointestinal Stromal Tumors (GIST).

Cappello Giovanni G Giannini Valentina V Cannella Roberto R Tabone Emanuele E Ambrosini Ilaria I Molea Francesca F Damiani Nicolò N Landolfi Ilenia I Serra Giovanni G Porrello Giorgia G Gozzo Cecilia C Incorvaia Lorena L Badalamenti Giuseppe G Grignani Giovanni G Merlini Alessandra A D'Ambrosio Lorenzo L Bartolotta Tommaso Vincenzo TV Regge Daniele D

European journal of radiology open 20230710

<h4>Objectives</h4>To develop a mutation-based radiomics signature to predict response to imatinib in Gastrointestinal Stromal Tumors (GISTs).<h4>Methods</h4>Eighty-two patients with GIST were enrolled in this retrospective study, including 52 patients from one center that were used to develop the model, and 30 patients from a second center to validate it. Reference standard was the mutational status of tyrosine-protein kinase (KIT) and platelet-derived growth factor α (PDGFRA). Patients were di ...[more]

PMID: 37484979

Similar Datasets

Project description:Dysregulation of the fibroblast growth factor (FGF)/fibroblast growth factor receptor (FGFR) signaling pathway is frequently observed in multiple human malignancies, and thus, therapeutic strategies targeting FGFs and FGFRs in human cancer are being extensively explored. We observed the activation of the FGF/FGFR-signaling pathway in imatinib (IM)-resistant gastrointestinal stromal tumor (GIST) cells. Furthermore, we found that the activation of FGFR signaling has a significant impact on IM resistance in GISTs in vitro. Next, we tested the efficacy of BGJ398, a potent and selective FGFR1⁻3 inhibitor, in xenograft models of GISTs exhibiting secondary IM resistance due to receptor-tyrosine kinase (RTK) switch (loss of c-KIT/gain of FGFR2a). Five to eight-week-old female nu/nu mice were subcutaneously inoculated into the flank areas with GIST T-1R cells. Mice were randomized as control (untreated), IM, BGJ398, or a combination and treated orally for 12 days. IM had a moderate effect on tumor size, thus revealing GIST resistance to IM. Similarly, a minor regression in tumor size was observed in BGJ398-treated mice. Strikingly, a 90% decrease in tumor size was observed in mice treated with a combination of IM and BGJ398. Treatment with BGJ398 and IM also induced major histopathologic changes according to a previously defined histopathologic response score and resulted in massive myxoid degeneration. This was associated with increased intratumoral apoptosis as detected by immunohistochemical staining for cleaved caspase-3 on day 5 of the treatment. Furthermore, treatment with BGJ398 and IM significantly reduced the proliferative activity of tumor cells as measured by positivity for Ki-67 staining. In conclusion, inhibition of FGFR signaling substantially inhibited the growth of IM-resistant GISTs in vitro and showed potent antitumor activity in an IM-resistant GIST model via the inhibition of proliferation, tumor growth, and the induction of apoptosis, thereby suggesting that patients with advanced and metastatic GISTs exhibiting IM resistance might benefit from therapeutic inhibition of FGFR signaling.

Project description:BackgroundGastrointestinal stromal tumors (GIST) mutational status is recognized factor related to the results of tyrosine kinase inhibitors therapy such as imatinib (IM) or sunitinib (SU). Arterial hypertension (AH) is common adverse event related to SU, reported as predictive factor in renal cell carcinoma. The aim of the study was to analyze the outcomes and factors predicting results of SU therapy in inoperable/metastatic CD117(+) GIST patients after IM failure.MethodsWe identified 137 consecutive patients with advanced inoperable/metastatic GIST treated in one center with SU (2nd line treatment). Median follow-up time was 23 months. Additionally, in 39 patients there were analyzed selected constitutive single nucleotide polymorphisms (SNPs) of VEGFA and VEGFR2 genes.ResultsOne year progression-free survival (PFS; calculated from the start of SU) rate was 42% and median PFS was 43 weeks. The estimated overall survival (OS, calculated both from start of SU or IM) was 74 weeks and 51 months, respectively. One-year PFS was 65% (median 74 weeks) in 55 patients with AH vs. 22% (median 17 weeks) in patients without AH. Patients with primary tumors carrying mutations in KIT exon 9 or wild-type had substantially better 1-year PFS (68% and 57%; median 65.5 and 50.5 weeks, respectively) than patients having tumors with KIT exon 11 or PDGFRA mutations (34% and 15%; median 36.8 and 9 weeks, respectively). We identified two independent factors with significant impact on PFS and OS in univariate and multivariate analysis: primary tumor genotype and presence of AH. The most common adverse events during therapy were: fatigue, AH, hypothyroidism, hand and foot syndrome, mucositis, skin reactions, dyspepsia, and diarrhea. Two deaths were assessed as related to tumor rupture caused by reaction to SU therapy. The presence of C-allele in rs833061 and the T-allele in rs3025039 polymorphism of VEGFA were associated with significantly higher risk of hypothyroidism (OR: 10.0 p = 0.041 and OR: 10.5; p = 0.015, respectively).ConclusionsWe confirmed that many advanced GIST patients benefit from SU therapy with OS > 1.5 year. Primary tumor KIT/PDGFRA genotype and SU-induced AH, as surrogate of its antiangiogenic activity are two independent factors influencing both PFS and OS.

Dataset Information

A mutation-based radiomics signature predicts response to imatinib in Gastrointestinal Stromal Tumors (GIST).

Objectives

Methods

Results

Conclusions

Publications

A mutation-based radiomics signature predicts response to imatinib in Gastrointestinal Stromal Tumors (GIST).

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets