Tumor Characterization Using [18F]FDG PET Radiomics in a PD-L1-Positive NSCLC Cohort
<b>Background</b>: Durvalumab consolidation following radiochemotherapy is now the standard treatment for unresectable stage III non-small cell lung cancer (NSCLC). [<sup>18</sup>F]FDG PET/CT offers valuable insights not just for staging but also for tumor characterization via radiomics, which can potentially predict histology, immunophenotype, and prognosis. <b>Methods</b>: We conducted a retrospective analysis of [<sup>18</sup>F]FDG PET/CT scans from stage IIIA-IIIB NSCLC patients treated at the Clinical Centre, University of Pécs. All biopsy samples were classified histologically (squamous vs. adenocarcinoma) and tested for PD-L1. Lung tumors were segmented using MEDISO InterViewTM FUSION software (version 3.12.002.0000). with an SUVmax threshold of four. Imaging features were extracted and compared based on histology, PD-L1 status, and neutrophil-to-lymphocyte ratio (NLR)-based prognosis groups. Statistical analyses were performed with Jamovi (v2.6.44), using Shapiro-Wilk, <i>t</i>-test/ANOVA, Mann-Whitney/Kruskal-Wallis, or Chi-square tests as appropriate. <b>Results</b>: Fifty-six patients were included (38 PD-L1-positive, 18 -negative). Among PD-L1-positive cases, poor versus good NLR prognosis groups differed in maximum diameter (<i>p</i> = 0.046), short-zone emphasis (<i>p</i> = 0.026), and zone-length non-uniformity (<i>p</i> = 0.027). Focusing on PD-L1-positive squamous carcinoma, maximum diameter, metabolic tumor volume, busyness, and coarseness showed significant differences (all <i>p</i> < 0.05). SUVmax, mean SUV, SUVpeak, and complexity were higher in squamous than in adenocarcinoma subtypes. PD-L1-positive and -negative squamous tumors differed in zone percentage (<i>p</i> = 0.039) and long-zone high gray-level emphasis (<i>p</i> = 0.024), while no significant differences were observed among adenocarcinomas. <b>Conclusions</b>: [<sup>18</sup>F]FDG PET/CT radiomics showed potential for differentiating NSCLC histological subtypes and for identifying PD-L1-associated imaging patterns in squamous cell carcinoma. In addition, certain metabolic features were associated with NLR-based prognostic groups in PD-L1-positive patients.
Authors
- Zsombor Ritter (ORCID: https://orcid.org/0000-0002-2898-1571)
- Bernadett Kálmán
- Dániel Dezső
- Éva Pusztai (ORCID: https://orcid.org/0000-0002-1997-2630)
- János Girán (ORCID: https://orcid.org/0000-0002-4309-0013)
- Árpád Boronkai
- Dávid Sipos (ORCID: https://orcid.org/0000-0001-9615-1740)
- Ferenc Budán (ORCID: https://orcid.org/0000-0003-1562-9496)
- Domokos Máthé (ORCID: https://orcid.org/0009-0008-6727-1725)
- Agnieszka Bos-Liedke
- Ewelina Kaminska
- Mateusz Matusewicz
Institutions
- Semmelweis University (HU)
- Poznań University of Economics and Business (PL)
- University of Life Sciences in Poznań (PL)
- Adam Mickiewicz University in Poznań (PL)
- University of Pecs (HU)
Publication Details
- Journal
- Pharmaceuticals
- Published
- 2026-01-07
- DOI
- https://doi.org/10.3390/ph19010103
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Semmelweis Egyetem
- Pécsi Tudományegyetem
- Medical Research Council
- Nemzeti Kutatási, Fejlesztési és Innovaciós Alap
- NIH Clinical Center