Preoperative CT-based radiomic prognostic index to predict the benefit of postoperative radiotherapy in patients with non-small cell lung cancer: a multicenter study.

BACKGROUND: The value of postoperative radiotherapy (PORT) for patients with non-small cell lung cancer (NSCLC) remains controversial. A subset of patients may benefit from PORT. We aimed to identify patients with NSCLC who could benefit from PORT. METHODS: Patients from cohorts 1 and 2 with pathological Tany N2 M0 NSCLC were included, as well as patients with non-metastatic NSCLC from cohorts 3 to 6. The radiomic prognostic index (RPI) was developed using radiomic texture features extracted from the primary lung nodule in preoperative chest CT scans in cohort 1 and validated in other cohorts. We employed a least absolute shrinkage and selection operator-Cox regularisation model for data dimension reduction, feature selection, and the construction of the RPI. We created a lymph-radiomic prognostic index (LRPI) by combining RPI and positive lymph node number (PLN). We compared the outcomes of patients who received PORT against those who did not in the subgroups determined by the LRPI. RESULTS: In total, 228, 1003, 144, 422, 19, and 21 patients were eligible in cohorts 1-6. RPI predicted overall survival (OS) in all six cohorts: cohort 1 (HR = 2.31, 95% CI: 1.18-4.52), cohort 2 (HR = 1.64, 95% CI: 1.26-2.14), cohort 3 (HR = 2.53, 95% CI: 1.45-4.3), cohort 4 (HR = 1.24, 95% CI: 1.01-1.52), cohort 5 (HR = 2.56, 95% CI: 0.73-9.02), cohort 6 (HR = 2.30, 95% CI: 0.53-10.03). LRPI predicted OS (C-index: 0.68, 95% CI: 0.60-0.75) better than the pT stage (C-index: 0.57, 95% CI: 0.50-0.63), pT + PLN (C-index: 0.58, 95% CI: 0.46-0.70), and RPI (C-index: 0.65, 95% CI: 0.54-0.75). The LRPI was used to categorize individuals into three risk groups; patients in the moderate-risk group benefited from PORT (HR = 0.60, 95% CI: 0.40-0.91; p = 0.02), while patients in the low-risk and high-risk groups did not. CONCLUSIONS: We developed preoperative CT-based radiomic and lymph-radiomic prognostic indexes capable of predicting OS and the benefits of PORT for patients with NSCLC.

In situ single-cell therapeutic response imaging facilitated by the TRIPODD fluorescence imaging platform.

Purpose: Small molecule drugs such as tyrosine kinase inhibitors (TKIs) targeting tumoral molecular dependencies have become standard of care for numerous cancer types. Notably, epidermal growth factor receptor (EGFR) TKIs (e.g., erlotinib, afatinib, osimertinib) are the current first-line treatment for non-small cell lung cancer (NSCLC) due to their improved therapeutic outcomes for EGFR mutated and overexpressing disease over traditional platinum-based chemotherapy. However, many NSCLC tumors develop resistance to EGFR TKI therapy causing disease progression. Currently, the relationship between in situ drug target availability (DTA), local protein expression and therapeutic response cannot be accurately assessed using existing analytical tools despite being crucial to understanding the mechanism of therapeutic efficacy. Procedure: We have previously reported development of our fluorescence imaging platform termed TRIPODD (Therapeutic Response Imaging through Proteomic and Optical Drug Distribution) that is capable of simultaneous quantification of single-cell DTA and protein expression with preserved spatial context within a tumor. TRIPODD combines two complementary fluorescence imaging techniques: intracellular paired agent imaging (iPAI) to measure DTA and cyclic immunofluorescence (cyCIF), which utilizes oligonucleotide conjugated antibodies (Ab-oligos) for spatial proteomic expression profiling on tissue samples. Herein, TRIPODD was modified and optimized to provide a downstream analysis of therapeutic response through single-cell DTA and proteomic response imaging. Results: We successfully performed sequential imaging of iPAI and cyCIF resulting in high dimensional imaging and biomarker assessment to quantify single-cell DTA and local protein expression on erlotinib treated NSCLC models. Pharmacodynamic and pharmacokinetic studies of the erlotinib iPAI probes revealed that administration of 2.5 mg/kg each of the targeted and untargeted probe 4 h prior to tumor collection enabled calculation of DTA values with high Pearson correlation to EGFR, the erlotinib molecular target, expression in the tumors. Analysis of single-cell biomarker expression revealed that a single erlotinib dose was insufficient to enact a measurable decrease in the EGFR signaling cascade protein expression, where only the DTA metric detected the presence of bound erlotinib. Conclusion: We demonstrated the capability of TRIPODD to evaluate therapeutic response imaging to erlotinib treatment as it relates to signaling inhibition, DTA, proliferation, and apoptosis with preserved spatial context.

Engineering PD-1-targeted small protein variants for in vitro diagnostics and in vivo PET imaging.

BACKGROUND: Programmed cell death 1 (PD-1) belongs to immune checkpoint proteins ensuring negative regulation of the immune response. In non-small cell lung cancer (NSCLC), the sensitivity to treatment with anti-PD-1 therapeutics, and its efficacy, mostly correlated with the increase of tumor infiltrating PD-1+ lymphocytes. Due to solid tumor heterogeneity of PD-1+ populations, novel low molecular weight anti-PD-1 high-affinity diagnostic probes can increase the reliability of expression profiling of PD-1+ tumor infiltrating lymphocytes (TILs) in tumor tissue biopsies and in vivo mapping efficiency using immune-PET imaging. METHODS: We designed a 13 kDa ß-sheet Myomedin scaffold combinatorial library by randomization of 12 mutable residues, and in combination with ribosome display, we identified anti-PD-1 Myomedin variants (MBA ligands) that specifically bound to human and murine PD-1-transfected HEK293T cells and human SUP-T1 cells spontaneously overexpressing cell surface PD-1. RESULTS: Binding affinity to cell-surface expressed human and murine PD-1 on transfected HEK293T cells was measured by fluorescence with LigandTracer and resulted in the selection of most promising variants MBA066 (hPD-1 KD = 6.9 nM; mPD-1 KD = 40.5 nM), MBA197 (hPD-1 KD = 29.7 nM; mPD-1 KD = 21.4 nM) and MBA414 (hPD-1 KD = 8.6 nM; mPD-1 KD = 2.4 nM). The potential of MBA proteins for imaging of PD-1+ populations in vivo was demonstrated using deferoxamine-conjugated MBA labeled with 68Galium isotope. Radiochemical purity of 68Ga-MBA proteins reached values 94.7-99.3% and in vitro stability in human serum after 120 min was in the range 94.6-98.2%. The distribution of 68Ga-MBA proteins in mice was monitored using whole-body positron emission tomography combined with computerized tomography (PET/CT) imaging up to 90 min post-injection and post mortem examined in 12 mouse organs. The specificity of MBA proteins was proven by co-staining frozen sections of human tonsils and NSCLC tissue biopsies with anti-PD-1 antibody, and demonstrated their potential for mapping PD-1+ populations in solid tumors. CONCLUSIONS: Using directed evolution, we developed a unique set of small binding proteins that can improve PD-1 diagnostics in vitro as well as in vivo using PET/CT imaging.

Sentinel Lymph Node Mapping in Lung Cancer: A Pilot Study for the Detection of Micrometastases in Stage I Non-Small Cell Lung Cancer.

Lymphadenectomy represents a fundamental step in the staging and treatment of non-small cell lung cancer (NSCLC). To date, the extension of lymphadenectomy in early-stage NSCLC is a debated topic due to its possible complications. The detection of sentinel lymph nodes (SLNs) is a strategy that can improve the selection of patients in which a more extended lymphadenectomy is necessary. This pilot study aimed to refine lymph nodal staging in early-stage NSCLC patients who underwent robotic lung resection through the application of innovative intraoperative sentinel lymph node (SLN) identification and the pathological evaluation using one-step nucleic acid amplification (OSNA). Clinical N0 NSCLC patients planning to undergo robotic lung resection were selected. The day before surgery, all patients underwent radionuclide computed tomography (CT)-guided marking of the primary lung lesion and subsequently Single Photon Emission Computed Tomography (SPECT) to identify tracer migration and, consequently, the area with higher radioactivity. On the day of surgery, the lymph nodal radioactivity was detected intraoperatively using a gamma camera. SLN was defined as the lymph node with the highest numerical value of radioactivity. The OSNA amplification, detecting the mRNA of CK19, was used for the detection of nodal metastases in the lymph nodes, including SLN. From March to July 2021, a total of 8 patients (3 female; 5 male), with a mean age of 66 years (range 48-77), were enrolled in the study. No complications relating to the CT-guided marking or preoperative SPECT were found. An average of 5.3 lymph nodal stations were examined (range 2-8). N2 positivity was found in 3 out of 8 patients (37.5%). Consequently, pathological examination of lymph nodes with OSNA resulted in three upstages from the clinical IB stage to pathological IIIA stage. Moreover, in 1 patient (18%) with nodal upstaging, a positive node was intraoperatively identified as SLN. Comparing this protocol to the usual practice, no difference was found in terms of the operating time, conversion rate, and complication rate. Our preliminary experience suggests that sentinel lymph node detection, in association with the accurate pathological staging of cN0 patients achieved using OSNA, is safe and effective in the identification of metastasis, which is usually undetected by standard diagnostic methods.

Prognostic and predictive value of interstitial lung abnormalities and EGFR mutation status in patients with non-small cell lung cancer.

BACKGROUND: To determine the predictive value of interstitial lung abnormalities (ILA) for epidermal growth factor receptor (EGFR) mutation status and assess the prognostic significance of EGFR and ILA in patients with non-small cell lung cancer (NSCLC). METHODS: We reviewed 797 consecutive patients with a histologically proven diagnosis of primary NSCLC from January 2013 to October 2018. Of these, 109 patients with NSCLC were found to have concomitant ILA. Multivariate logistic regression analysis was used to identify the significant clinical and computed tomography (CT) findings in predicting EGFR mutations. Cox proportional hazard models were used to identify significant prognostic factors. RESULTS: EGFR mutations were identified in 22 of 109 tumors (20.2%). Multivariate analysis showed that the models incorporating clinical, tumor CT and ILA CT features yielded areas under the receiver operating characteristic curve (AUC) values of 0.749, 0.838, and 0.849, respectively. When combining the three models, the independent predictive factors for EGFR mutations were non-fibrotic ILA, female sex, and small tumor size, with an AUC value of 0.920 (95% confidence interval[CI]: 0.861-0.978, p < 0.001). In the multivariate Cox model, EGFR mutations (hazard ratio = 0.169, 95% CI = 0.042-0.675, p = 0.012; 692 days vs. 301 days) were independently associated with extended overall survival compared to the wild-type. CONCLUSION: Non-fibrotic ILA independently predicts the presence of EGFR mutations, and the presence of EGFR mutations rather than non-fibrotic ILA serves as an independent good prognostic factor for patients with NSCLC.

[18F]fluorodeoxyglucose positron emission tomography/computed tomography in combination with clinical data in predicting overall survival in non-small-cell lung cancer patients: A retrospective study.

INTRODUCTION: Positron emission tomography/computed tomography (PET/CT) has an established role in evaluating patients with lung cancer. The aim of this work was to assess the predictive capability of [18F]Fluorodeoxyglucose ([18F]FDG) PET/CT parameters on overall survival (OS) in lung cancer patients using an artificial neural network (ANN) in parallel with conventional statistical analysis. METHODS: Retrospective analysis was performed on a group of 165 lung cancer patients (98M, 67F). PET features associated with the primary tumor: maximum and mean standardized uptake value (SUVmax, SUVmean), total lesion glycolysis (TLG) metabolic tumor volume (MTV) and area under the curve-cumulative SUV histogram (AUC-CSH) and metastatic lesions (SUVmaxtotal, SUVmeantotal, TLGtotal, and MTVtotal) were evaluated. In parallel with conventional statistical analysis (Chi-Square analysis for nominal data, Student's t test for continuous data), the data was evaluated using an ANN. There were 97 input variables in 165 patients using a binary classification of either below, or greater than/equal to median survival post primary diagnosis. Additionally, phantom study was performed to assess the most optimal contouring method. RESULTS: Males had statistically higher SUVmax (mean: 10.7 vs 8.9; p = 0.020), MTV (mean: 66.5 cm3 vs. 21.5 cm3; p = 0.001), TLG (mean 404.7 vs. 115.0; p = 0.003), TLGtotal (mean: 946.7 vs. 433.3; p = 0.014) and MTVtotal (mean: 242.0 cm3 vs. 103.7 cm3; p = 0.027) than females. The ANN after training and validation was optimised with a final architecture of 4 scaling layer inputs (TLGtotal, SUVmaxtotal, SUVmeantotal and disease stage) and receiving operator characteristic (ROC) analysis demonstrated an AUC of 0.764 (sensitivity of 92.3%, specificity of 57.1%). CONCLUSION: Conventional statistical analysis and the ANN provided concordant findings in relation to variables that predict decreased survival. The ANN provided a weighted algorithm of the 4 key features to predict decreased survival. IMPLICATION FOR PRACTICE: Identification of parameters which can predict survival in lung cancer patients might be helpful in choosing the group of patients who require closer look during the follow-up.

Prognostic significance of ground-glass areas within tumours in non-small-cell lung cancer.

OBJECTIVES: To validate or refute the hypothesis that non-small-cell lung cancers (NSCLC) with ground-glass areas (GGA+) within the tumour on high-resolution computed tomography are associated with a more favourable prognosis than those without GGA (GGA-). METHODS: We analysed data from a multicentre observational cohort study in Japan including 5005 patients with completely resected pathological stage I NSCLC, who were excluded from the Japan Clinical Oncology Group (JCOG) 0707 trial on oral adjuvant treatment during the enrolment period. The patients' medical and pathological records were assessed retrospectively by physicians and re-staged according to the 8th tumour, node, metastasis edition. RESULTS: Of the 5005 patients, 2388 (48%) were ineligible for the JCOG0707 trial and 2617 (52%) were eligible but were not enrolled. A total of 958 patients (19.1%) died. Patients with GGA+ NSCLC and pathological invasion ≤3 cm showed significantly better overall survival than others. In patients with tumours with an invasive portion ≤4 cm, GGA+ was associated with better survival. The prognoses of patients with GGA+ T2a and GGA- T1c tumours were similar (5-year overall survival: 84.6% vs 83.1%, respectively). The survival with T2b or more tumours appeared unaffected by GGA, and GGA was not prognostic in these larger tumours. CONCLUSIONS: Patients with GGA+ NSCLC on high-resolution computed tomography and ≤4 cm invasion size may have a better prognosis than patients with solid GGA- tumours of the same T-stage. However, the presence or absence of radiological GGA has little impact on the prognosis of patients with NSCLC with greater (>4 cm) pathological invasion.

Preoperative nomogram for predicting spread through air spaces in clinical-stage IA non-small cell lung cancer using 18F-fluorodeoxyglucose positron emission tomography/computed tomography.

PURPOSE: This study aims to assess the predictive value of 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) radiological features and the maximum standardized uptake value (SUVmax) in determining the presence of spread through air spaces (STAS) in clinical-stage IA non-small cell lung cancer (NSCLC). METHODS: A retrospective analysis was conducted on 180 cases of NSCLC with postoperative pathological assessment of STAS status, spanning from September 2019 to September 2023. Of these, 116 cases from hospital one comprised the training set, while 64 cases from hospital two formed the testing set. The clinical information, tumor SUVmax, and 13 related CT features were analyzed. Subgroup analysis was carried out based on tumor density type. In the training set, univariable and multivariable logistic regression analyses were employed to identify the most significant variables. A multivariable logistic regression model was constructed and the corresponding nomogram was developed to predict STAS in NSCLC, and its diagnostic efficacy was evaluated in the testing set. RESULTS: SUVmax, consolidation-to-tumor ratio (CTR), and lobulation sign emerged as the best combination of variables for predicting STAS in NSCLC. Among these, SUVmax and CTR were identified as independent predictors for STAS prediction. The constructed prediction model demonstrated area under the curve (AUC) values of 0.796 and 0.821 in the training and testing sets, respectively. Subgroup analysis revealed a 2.69 times higher STAS-positive rate in solid nodules compared to part-solid nodules. SUVmax was an independent predictor for predicting STAS in solid nodular NSCLC, while CTR and an emphysema background were independent predictors for STAS in part-solid nodular NSCLC. CONCLUSION: Our nomogram based on preoperative 18F-FDG PET/CT radiological features and SUVmax effectively predicts STAS status in clinical-stage IA NSCLC. Furthermore, our study highlights that metabolic parameters and CT variables associated with STAS differ between solid and part-solid nodular NSCLC.

Non-invasive prediction for pathologic complete response to neoadjuvant chemoimmunotherapy in lung cancer using CT-based deep learning: a multicenter study.

Neoadjuvant chemoimmunotherapy has revolutionized the therapeutic strategy for non-small cell lung cancer (NSCLC), and identifying candidates likely responding to this advanced treatment is of important clinical significance. The current multi-institutional study aims to develop a deep learning model to predict pathologic complete response (pCR) to neoadjuvant immunotherapy in NSCLC based on computed tomography (CT) imaging and further prob the biologic foundation of the proposed deep learning signature. A total of 248 participants administrated with neoadjuvant immunotherapy followed by surgery for NSCLC at Ruijin Hospital, Ningbo Hwamei Hospital, and Affiliated Hospital of Zunyi Medical University from January 2019 to September 2023 were enrolled. The imaging data within 2 weeks prior to neoadjuvant chemoimmunotherapy were retrospectively extracted. Patients from Ruijin Hospital were grouped as the training set (n = 104) and the validation set (n = 69) at the 6:4 ratio, and other participants from Ningbo Hwamei Hospital and Affiliated Hospital of Zunyi Medical University served as an external cohort (n = 75). For the entire population, pCR was obtained in 29.4% (n = 73) of cases. The areas under the curve (AUCs) of our deep learning signature for pCR prediction were 0.775 (95% confidence interval [CI]: 0.649 - 0.901) and 0.743 (95% CI: 0.618 - 0.869) in the validation set and the external cohort, significantly superior than 0.579 (95% CI: 0.468 - 0.689) and 0.569 (95% CI: 0.454 - 0.683) of the clinical model. Furthermore, higher deep learning scores correlated to the upregulation for pathways of cell metabolism and more antitumor immune infiltration in microenvironment. Our developed deep learning model is capable of predicting pCR to neoadjuvant chemoimmunotherapy in patients with NSCLC.

Preclinical development of novel PD-L1 tracers and first-in-human study of [68Ga]Ga-NOTA-RW102 in patients with lung cancers.

BACKGROUND: The programmed cell death protein-1 (PD-1)/programmed death receptor ligand 1 (PD-L1) axis critically facilitates cancer cells' immune evasion. Antibody therapeutics targeting the PD-1/PD-L1 axis have shown remarkable efficacy in various tumors. Immuno-positron emission tomography (ImmunoPET) imaging of PD-L1 expression may help reshape solid tumors' immunotherapy landscape. METHODS: By immunizing an alpaca with recombinant human PD-L1, three clones of the variable domain of the heavy chain of heavy-chain only antibody (VHH) were screened, and RW102 with high binding affinity was selected for further studies. ABDRW102, a VHH derivative, was further engineered by fusing RW102 with the albumin binder ABD035. Based on the two targeting vectors, four PD-L1-specific tracers ([68Ga]Ga-NOTA-RW102, [68Ga]Ga-NOTA-ABDRW102, [64Cu]Cu-NOTA-ABDRW102, and [89Zr]Zr-DFO-ABDRW102) with different circulation times were developed. The diagnostic efficacies were thoroughly evaluated in preclinical solid tumor models, followed by a first-in-human translational investigation of [68Ga]Ga-NOTA-RW102 in patients with non-small cell lung cancer (NSCLC). RESULTS: While RW102 has a high binding affinity to PD-L1 with an excellent KD value of 15.29 pM, ABDRW102 simultaneously binds to human PD-L1 and human serum albumin with an excellent KD value of 3.71 pM and 3.38 pM, respectively. Radiotracers derived from RW102 and ABDRW102 have different in vivo circulation times. In preclinical studies, [68Ga]Ga-NOTA-RW102 immunoPET imaging allowed same-day annotation of differential PD-L1 expression with specificity, while [64Cu]Cu-NOTA-ABDRW102 and [89Zr]Zr-DFO-ABDRW102 enabled longitudinal visualization of PD-L1. More importantly, a pilot clinical trial shows the safety and diagnostic value of [68Ga]Ga-NOTA-RW102 immunoPET imaging in patients with NSCLCs and its potential to predict immune-related adverse effects following PD-L1-targeted immunotherapies. CONCLUSIONS: We developed and validated a series of PD-L1-targeted tracers. Initial preclinical and clinical evidence indicates that immunoPET imaging with [68Ga]Ga-NOTA-RW102 holds promise in visualizing differential PD-L1 expression, selecting patients for PD-L1-targeted immunotherapies, and monitoring immune-related adverse effects in patients receiving PD-L1-targeted treatments. TRIAL REGISTRATION NUMBER: NCT06165874.

Development and validation of an MRI-Based nomogram to predict the effectiveness of immunotherapy for brain metastasis in patients with non-small cell lung cancer.

Introduction: The variability and unpredictability of immune checkpoint inhibitors (ICIs) in treating brain metastases (BMs) in patients with advanced non-small cell lung cancer (NSCLC) is the main concern. We assessed the utility of novel imaging biomarkers (radiomics) for discerning patients with NSCLC and BMs who would derive advantages from ICIs treatment. Methods: Data clinical outcomes and pretreatment magnetic resonance images (MRI) were collected on patients with NSCLC with BMs treated with ICIs between June 2019 and June 2022 and divided into training and test sets. Metastatic brain lesions were contoured using ITK-SNAP software, and 3748 radiomic features capturing both intra- and peritumoral texture patterns were extracted. A clinical radiomic nomogram (CRN) was built to evaluate intracranial progression-free survival, progression-free survival, and overall survival. The prognostic value of the CRN was assessed by Kaplan-Meier survival analysis and log-rank tests. Results: In the study, a total of 174 patients were included, and 122 and 52 were allocated to the training and validation sets correspondingly. The intratumoral radiomic signature, peritumoral radiomic signature, clinical signature, and CRN predicted intracranial objective response rate. Kaplan-Meier analyses showed a significantly longer intracranial progression-free survival in the low-CRN group than in the high-CRN group (p < 0.001). The CRN was also significantly associated with progression-free survival (p < 0.001) but not overall survival. Discussion: Radiomics biomarkers from pretreatment MRI images were predictive of intracranial response. Pretreatment radiomics may allow the early prediction of benefits.

Total metabolic tumor volume on 18F-FDG PET/CT is a game-changer for patients with metastatic lung cancer treated with immunotherapy.

PURPOSE: Because of atypical response imaging patterns in patients with metastatic non-small cell lung cancer (NSCLC) treated with immune checkpoint inhibitors (ICPIs), new biomarkers are needed for a better monitoring of treatment efficacy. The aim of this prospective study was to evaluate the prognostic value of volume-derived positron-emission tomography (PET) parameters on baseline and follow-up 18F-fluoro-deoxy-glucose PET (18F-FDG-PET) scans and compare it with the conventional PET Response Criteria in Solid Tumors (PERCIST). METHODS: Patients with metastatic NSCLC were included in two different single-center prospective trials. 18F-FDG-PET studies were performed before the start of immunotherapy (PETbaseline), after 6-8 weeks (PETinterim1) and after 12-16 weeks (PETinterim2) of treatment, using PERCIST criteria for tumor response assessment. Different metabolic parameters were evaluated: absolute values of maximum standardized uptake value (SUVmax) of the most intense lesion, total metabolic tumor volume (TMTV), total lesion glycolysis (TLG), but also their percentage changes between PET studies (ΔSUVmax, ΔTMTV and ΔTLG). The median follow-up of patients was 31 (7.3-31.8) months. Prognostic values and optimal thresholds of PET parameters were estimated by ROC (Receiver Operating Characteristic) curve analysis of 12-month overall survival (12M-OS) and 6-month progression-free survival (6M-PFS). Tumor progression needed to be confirmed by a multidisciplinary tumor board, considering atypical response patterns on imaging. RESULTS: 110 patients were prospectively included. On PETbaseline, TMTV was predictive of 12M-OS [AUC (Area Under Curve) =0.64; 95% CI: 0.61 to 0.66] whereas SUVmax and TLG were not. On PETinterim1 and PETinterim2, all metabolic parameters were predictive for 12M-OS and 6M-PFS, the residual TMTV on PETinterim1 (TMTV1) being the strongest prognostic biomarker (AUC=0.83 and 0.82; 95% CI: 0.74 to 0.91, for 12M-OS and 6M-PFS, respectively). Using the optimal threshold by ROC curve to classify patients into three TMTV1 subgroups (0 cm3; 0-57 cm3; >57 cm3), TMTV1 prognostic stratification was independent of PERCIST criteria on both PFS and OS, and significantly outperformed them. Subgroup analysis demonstrated that TMTV1 remained a strong prognostic biomarker of 12M-OS for non-responding patients (p=0.0003) according to PERCIST criteria. In the specific group of patients with PERCIST progression on PETinterim1, low residual tumor volume (<57 cm3) was still associated with a very favorable patients' outcome (6M-PFS=73%; 24M-OS=55%). CONCLUSION: The absolute value of residual metabolic tumor volume, assessed 6-8 weeks after the start of ICPI, is an optimal and independent prognostic measure, exceeding and complementing conventional PERCIST criteria. Oncologists should consider it in patients with first tumor progression according to PERCIST criteria, as it helps identify patients who benefit from continued treatment. TRIAL REGISTRATION NUMBER: 2018-A02116-49; NCT03584334.

Machine learning for differentiating lung squamous cell cancer from adenocarcinoma using Clinical-Metabolic characteristics and 18F-FDG PET/CT radiomics.

Noninvasive differentiation between the squamous cell carcinoma (SCC) and adenocarcinoma (ADC) subtypes of non-small cell lung cancer (NSCLC) could benefit patients who are unsuitable for invasive diagnostic procedures. Therefore, this study evaluates the predictive performance of a PET/CT-based radiomics model. It aims to distinguish between the histological subtypes of lung adenocarcinoma and squamous cell carcinoma, employing four different machine learning techniques. A total of 255 Non-Small Cell Lung Cancer (NSCLC) patients were retrospectively analyzed and randomly divided into the training (n = 177) and validation (n = 78) sets, respectively. Radiomics features were extracted, and the Least Absolute Shrinkage and Selection Operator (LASSO) method was employed for feature selection. Subsequently, models were constructed using four distinct machine learning techniques, with the top-performing algorithm determined by evaluating metrics such as accuracy, sensitivity, specificity, and the area under the curve (AUC). The efficacy of the various models was appraised and compared using the DeLong test. A nomogram was developed based on the model with the best predictive efficiency and clinical utility, and it was validated using calibration curves. Results indicated that the logistic regression classifier had better predictive power in the validation cohort of the radiomic model. The combined model (AUC 0.870) exhibited superior predictive power compared to the clinical model (AUC 0.848) and the radiomics model (AUC 0.774). In this study, we discovered that the combined model, refined by the logistic regression classifier, exhibited the most effective performance in classifying the histological subtypes of NSCLC.

Enhancing NSCLC recurrence prediction with PET/CT habitat imaging, ctDNA, and integrative radiogenomics-blood insights.

While we recognize the prognostic importance of clinicopathological measures and circulating tumor DNA (ctDNA), the independent contribution of quantitative image markers to prognosis in non-small cell lung cancer (NSCLC) remains underexplored. In our multi-institutional study of 394 NSCLC patients, we utilize pre-treatment computed tomography (CT) and 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) to establish a habitat imaging framework for assessing regional heterogeneity within individual tumors. This framework identifies three PET/CT subtypes, which maintain prognostic value after adjusting for clinicopathologic risk factors including tumor volume. Additionally, these subtypes complement ctDNA in predicting disease recurrence. Radiogenomics analysis unveil the molecular underpinnings of these imaging subtypes, highlighting downregulation in interferon alpha and gamma pathways in the high-risk subtype. In summary, our study demonstrates that these habitat imaging subtypes effectively stratify NSCLC patients based on their risk levels for disease recurrence after initial curative surgery or radiotherapy, providing valuable insights for personalized treatment approaches.

Identification of CT radiomic features robust to acquisition and segmentation variations for improved prediction of radiotherapy-treated lung cancer patient recurrence.

The primary objective of the present study was to identify a subset of radiomic features extracted from primary tumor imaged by computed tomography of early-stage non-small cell lung cancer patients, which remain unaffected by variations in segmentation quality and in computed tomography image acquisition protocol. The robustness of these features to segmentation variations was assessed by analyzing the correlation of feature values extracted from lesion volumes delineated by two annotators. The robustness to variations in acquisition protocol was evaluated by examining the correlation of features extracted from high-dose and low-dose computed tomography scans, both of which were acquired for each patient as part of the stereotactic body radiotherapy planning process. Among 106 radiomic features considered, 21 were identified as robust. An analysis including univariate and multivariate assessments was subsequently conducted to estimate the predictive performance of these robust features on the outcome of early-stage non-small cell lung cancer patients treated with stereotactic body radiation therapy. The univariate predictive analysis revealed that robust features demonstrated superior predictive potential compared to non-robust features. The multivariate analysis indicated that linear regression models built with robust features displayed greater generalization capabilities by outperforming other models in predicting the outcomes of an external validation dataset.

A distributed feature selection pipeline for survival analysis using radiomics in non-small cell lung cancer patients.

Predictive modelling of cancer outcomes using radiomics faces dimensionality problems and data limitations, as radiomics features often number in the hundreds, and multi-institutional data sharing is ()often unfeasible. Federated learning (FL) and feature selection (FS) techniques combined can help overcome these issues, as one provides the means of training models without exchanging sensitive data, while the other identifies the most informative features, reduces overfitting, and improves model interpretability. Our proposed FS pipeline based on FL principles targets data-driven radiomics FS in a multivariate survival study of non-small cell lung cancer patients. The pipeline was run across datasets from three institutions without patient-level data exchange. It includes two FS techniques, Correlation-based Feature Selection and LASSO regularization, and Cox Proportional-Hazard regression with Overall Survival as endpoint. Trained and validated on 828 patients overall, our pipeline yielded a radiomic signature comprising "intensity-based energy" and "mean discretised intensity". Validation resulted in a mean Harrell C-index of 0.59, showcasing fair efficacy in risk stratification. In conclusion, we suggest a distributed radiomics approach that incorporates preliminary feature selection to systematically decrease the feature set based on data-driven considerations. This aims to address dimensionality challenges beyond those associated with data constraints and interpretability concerns.

Ultrasound-based radiomics machine learning models for diagnosing cervical lymph node metastasis in patients with non-small cell lung cancer: a multicentre study.

BACKGROUND: Cervical lymph node metastasis (LNM) is an important prognostic factor for patients with non-small cell lung cancer (NSCLC). We aimed to develop and validate machine learning models that use ultrasound radiomic and descriptive semantic features to diagnose cervical LNM in patients with NSCLC. METHODS: This study included NSCLC patients who underwent neck ultrasound examination followed by cervical lymph node (LN) biopsy between January 2019 and January 2022 from three institutes. Radiomic features were extracted from the ultrasound images at the maximum cross-sectional areas of cervical LNs. Logistic regression (LR) and random forest (RF) models were developed. Model performance was assessed by the area under the curve (AUC) and accuracy, validated internally and externally by fivefold cross-validation and hold-out method, respectively. RESULTS: In total, 313 patients with a median age of 64 years were included, and 276 (88.18%) had cervical LNM. Three descriptive semantic features, including long diameter, shape, and corticomedullary boundary, were selected by multivariate analysis. Out of the 474 identified radiomic features, 9 were determined to fit the LR model, while 15 fit the RF model. The average AUCs of the semantic and radiomics models were 0.876 (range: 0.781-0.961) and 0.883 (range: 0.798-0.966), respectively. However, the average AUC was higher for the semantic-radiomics combined LR model (0.901; range: 0.862-0.927). When the RF algorithm was applied, the average AUCs of the radiomics and semantic-radiomics combined models were improved to 0.908 (range: 0.837-0.966) and 0.922 (range: 0.872-0.982), respectively. The models tested by the hold-out method had similar results, with the semantic-radiomics combined RF model achieving the highest AUC value of 0.901 (95% CI, 0.886-0.968). CONCLUSIONS: The ultrasound radiomic models showed potential for accurately diagnosing cervical LNM in patients with NSCLC when integrated with descriptive semantic features. The RF model outperformed the conventional LR model in diagnosing cervical LNM in NSCLC patients.

Clinical Utility of a CT-based AI Prognostic Model for Segmentectomy in Non-Small Cell Lung Cancer.

Background Currently, no tool exists for risk stratification in patients undergoing segmentectomy for non-small cell lung cancer (NSCLC). Purpose To develop and validate a deep learning (DL) prognostic model using preoperative CT scans and clinical and radiologic information for risk stratification in patients with clinical stage IA NSCLC undergoing segmentectomy. Materials and Methods In this single-center retrospective study, transfer learning of a pretrained model was performed for survival prediction in patients with clinical stage IA NSCLC who underwent lobectomy from January 2008 to March 2017. The internal set was divided into training, validation, and testing sets based on the assignments from the pretraining set. The model was tested on an independent test set of patients with clinical stage IA NSCLC who underwent segmentectomy from January 2010 to December 2017. Its prognostic performance was analyzed using the time-dependent area under the receiver operating characteristic curve (AUC), sensitivity, and specificity for freedom from recurrence (FFR) at 2 and 4 years and lung cancer-specific survival and overall survival at 4 and 6 years. The model sensitivity and specificity were compared with those of the Japan Clinical Oncology Group (JCOG) eligibility criteria for sublobar resection. Results The pretraining set included 1756 patients. Transfer learning was performed in an internal set of 730 patients (median age, 63 years [IQR, 56-70 years]; 366 male), and the segmentectomy test set included 222 patients (median age, 65 years [IQR, 58-71 years]; 114 male). The model performance for 2-year FFR was as follows: AUC, 0.86 (95% CI: 0.76, 0.96); sensitivity, 87.4% (7.17 of 8.21 patients; 95% CI: 59.4, 100); and specificity, 66.7% (136 of 204 patients; 95% CI: 60.2, 72.8). The model showed higher sensitivity for FFR than the JCOG criteria (87.4% vs 37.6% [3.08 of 8.21 patients], P = .02), with similar specificity. Conclusion The CT-based DL model identified patients at high risk among those with clinical stage IA NSCLC who underwent segmentectomy, outperforming the JCOG criteria. © RSNA, 2024 Supplemental material is available for this article.

A comparison between centralized and asynchronous federated learning approaches for survival outcome prediction using clinical and PET data from non-small cell lung cancer patients.

BACKGROUND AND OBJECTIVE: Survival analysis plays an essential role in the medical field for optimal treatment decision-making. Recently, survival analysis based on the deep learning (DL) approach has been proposed and is demonstrating promising results. However, developing an ideal prediction model requires integrating large datasets across multiple institutions, which poses challenges concerning medical data privacy. METHODS: In this paper, we propose FedSurv, an asynchronous federated learning (FL) framework designed to predict survival time using clinical information and positron emission tomography (PET)-based features. This study used two datasets: a public radiogenic dataset of non-small cell lung cancer (NSCLC) from the Cancer Imaging Archive (RNSCLC), and an in-house dataset from the Chonnam National University Hwasun Hospital (CNUHH) in South Korea, consisting of clinical risk factors and F-18 fluorodeoxyglucose (FDG) PET images in NSCLC patients. Initially, each dataset was divided into multiple clients according to histological attributes, and each client was trained using the proposed DL model to predict individual survival time. The FL framework collected weights and parameters from the clients, which were then incorporated into the global model. Finally, the global model aggregated all weights and parameters and redistributed the updated model weights to each client. We evaluated different frameworks including single-client-based approach, centralized learning and FL. RESULTS: We evaluated our method on two independent datasets. First, on the RNSCLC dataset, the mean absolute error (MAE) was 490.80±22.95 d and the C-Index was 0.69±0.01. Second, on the CNUHH dataset, the MAE was 494.25±40.16 d and the C-Index was 0.71±0.01. The FL approach achieved centralized method performance in PET-based survival time prediction and outperformed single-client-based approaches. CONCLUSIONS: Our results demonstrated the feasibility and effectiveness of employing FL for individual survival prediction in NSCLC patients, using clinical information and PET-based features.