Radiomics of Tumor Heterogeneity in 18F-FDG-PET-CT for Predicting Response to Immune Checkpoint Inhibition in Therapy-Naïve Patients with Advanced Non-Small-Cell Lung Cancer

Determination of the optimal imaging protocol for [18F]PSMA-PET-CT for the detection of bone metastases in prostate cancer patients

AIM

Prostate-specific membrane antigen-positron emission tomography (PSMA-PET) is a widely used diagnostic tool in patients with prostate cancer (PC). However, due to the limited availability of PET scanners and relevant acquisition costs, it is important to consider the indications and acquisition time. The aim of this investigation was to determine whether a PET scan from the skull base to the proximal thigh is sufficient to detect the presence of bone metastases.

METHODS

A retrospective analysis was conducted on 1050 consecutive [18F]PSMA-1007-PET-CT scans from the head to the proximal lower leg. The PET scans were categorised according to the presence and amount of bone metastases: (1) 1-5, (2) 6-19 and (3) ≥20. Additionally, the PET scans were evaluated for the presence of bone metastases below the proximal thigh as well as bone metastases above the skull base. Imaging results were compared to patients PSA values.

RESULTS

Of the 391 patients with bone metastases, 146 (37.3%) exhibited metastases located below the proximal thigh and 104 (26.6%) above the skull base. The majority of bone metastases located below the proximal thigh (145, 99.3%) and above the skull base (94, 90.4%) were identified in patients with more than five bone metastases. No solitary distal metastasis was detected. The PSA value correlated significantly with number of bone metastases (e. g., 1-5 vs. ≥20 bone metastases, P < 0.001) and was significantly higher in patients with distal bone metastases (P < 0.001). ROC analysis showed that a PSA value of 11.15 ng/mL is the optimal cut-off for detecting bone metastases located below the proximal thigh, with an AUC of 0.919 (95% CI: 0.892-0.945, sensitivity 87%, specificity 86%). Similarly, the PSA value of 12.86 ng/mL is the optimal cut-off for detecting bone metastases above the skull base with an AUC of 0.904 (95% CI: 0.874-0.935, sensitivity 87%, specificity 83%).  CONCLUSION: PSMA-PET acquisition protocols from the skull base to the proximal femur may be sufficient to accurately detect bone metastatic disease in PC. PSA values can provide decision support for individual PET acquisition protocols.

Prognostic models for immunotherapy in non-small cell lung cancer: A comprehensive review

The introduction of immune checkpoint inhibitors (ICIs) has revolutionized the treatment of lung cancer. Given the limited clinical benefits of immunotherapy in patients with non-small cell lung cancer (NSCLC), various predictors have been shown to significantly influence prognosis. However, no single predictor is adequate to forecast patients' survival benefit. Therefore, it's imperative to develop a prognostic model that integrates multiple predictors. This model would be instrumental in identifying patients who might benefit from ICIs. Retrospective analysis and small case series have demonstrated the potential role of these models in prognostic prediction, though further prospective investigation is required to evaluate more rigorously their application in these contexts. This article presents and summarizes the latest research advancements on immunotherapy prognostic models for NSCLC from multiple omics perspectives and discuss emerging strategies being developed to enhance the domain.

Enhanced CT-based radiomics model to predict natural killer cell infiltration and clinical prognosis in non-small cell lung cancer

Background

Natural killer (NK) cells are crucial for tumor prognosis; however, their role in non-small-cell lung cancer (NSCLC) remains unclear. The current detection methods for NSCLC are inefficient and costly. Therefore, radiomics represent a promising alternative.

Methods

We analyzed the radiogenomics datasets to extract clinical, radiological, and transcriptome data. The effect of NK cells on the prognosis of NSCLC was assessed. Tumors were delineated using a 3D Slicer, and features were extracted using pyradiomics. A radiomics model was developed and validated using five-fold cross-validation. A nomogram model was constructed using the selected clinical variables and a radiomic score (RS). The CIBERSORTx database and gene set enrichment analysis were used to explore the correlations of NK cell infiltration and molecular mechanisms.

Results

Higher infiltration of NK cells was correlated with better overall survival (OS) (P = 0.002). The radiomic model showed an area under the curve of 0.731, with 0.726 post-validation. The RS differed significantly between high and low infiltration of NK cells (P < 0.01). The nomogram, using RS and clinical variables, effectively predicted 3-year OS. NK cell infiltration was correlated with the ICOS and BTLA genes (P < 0.001) and macrophage M0/M2 levels. The key pathways included TNF-α signaling via NF-κB and Wnt/β-catenin signaling.

Conclusions

Our radiomic model accurately predicted NK cell infiltration in NSCLC. Combined with clinical characteristics, it can predict the prognosis of patients with NSCLC. Bioinformatic analysis revealed the gene expression and pathways underlying NK cell infiltration in NSCLC.

Methodological evaluation of original articles on radiomics and machine learning for outcome prediction based on positron emission tomography (PET)

AIM

Despite a vast number of articles on radiomics and machine learning in positron emission tomography (PET) imaging, clinical applicability remains limited, partly owing to poor methodological quality. We therefore systematically investigated the methodology described in publications on radiomics and machine learning for PET-based outcome prediction.

METHODS

A systematic search for original articles was run on PubMed. All articles were rated according to 17 criteria proposed by the authors. Criteria with >2 rating categories were binarized into "adequate" or "inadequate". The association between the number of "adequate" criteria per article and the date of publication was examined.

RESULTS

One hundred articles were identified (published between 07/2017 and 09/2023). The median proportion of articles per criterion that were rated "adequate" was 65% (range: 23-98%). Nineteen articles (19%) mentioned neither a test cohort nor cross-validation to separate training from testing. The median number of criteria with an "adequate" rating per article was 12.5 out of 17 (range, 4-17), and this did not increase with later dates of publication (Spearman's rho, 0.094; p = 0.35). In 22 articles (22%), less than half of the items were rated "adequate". Only 8% of articles published the source code, and 10% made the dataset openly available.

CONCLUSION

Among the articles investigated, methodological weaknesses have been identified, and the degree of compliance with recommendations on methodological quality and reporting shows potential for improvement. Better adherence to established guidelines could increase the clinical significance of radiomics and machine learning for PET-based outcome prediction and finally lead to the widespread use in routine clinical practice.

A multitask deep learning radiomics model for predicting the macrotrabecular-massive subtype and prognosis of hepatocellular carcinoma after hepatic arterial infusion chemotherapy

BACKGROUND

The macrotrabecular-massive (MTM) is a special subtype of hepatocellular carcinoma (HCC), which has commonly a dismal prognosis. This study aimed to develop a multitask deep learning radiomics (MDLR) model for predicting MTM and HCC patients' prognosis after hepatic arterial infusion chemotherapy (HAIC).

METHODS

From June 2018 to March 2020, 158 eligible patients with HCC who underwent surgery were retrospectively enrolled in MTM related cohorts, and 752 HCC patients who underwent HAIC were included in HAIC related cohorts during the same period. DLR features were extracted from dual-phase (arterial phase and venous phase) contrast-enhanced computed tomography (CECT) of the entire liver region. Then, an MDLR model was used for the simultaneous prediction of the MTM subtype and patient prognosis after HAIC. The MDLR model for prognostic risk stratification incorporated DLR signatures, clinical variables and MTM subtype.

FINDINGS

The predictive performance of the DLR model for the MTM subtype was 0.968 in the training cohort [TC], 0.912 in the internal test cohort [ITC] and 0.773 in the external test cohort [ETC], respectively. Multivariable analysis identified portal vein tumor thrombus (PVTT) (p = 0.012), HAIC response (p < 0.001), HAIC sessions (p < 0.001) and MTM subtype (p < 0.001) as indicators of poor prognosis. After incorporating DLR signatures, the MDLR model yielded the best performance among all models (AUC, 0.855 in the TC, 0.805 in the ITC and 0.792 in the ETC). With these variables, the MDLR model provided two risk strata for overall survival (OS) in the TC: low risk (5-year OS, 44.9%) and high risk (5-year OS, 4.9%).

INTERPRETATION

A tool based on MDLR was developed to consider that the MTM is an important prognosis factor for HCC patients. MDLR showed outstanding performance for the prognostic risk stratification of HCC patients who underwent HAIC and may help physicians with therapeutic decision making and surveillance strategy selection in clinical practice.