Evaluation of the efficacy of pretreatment chest CT markers in predicting response to neoadjuvant chemoradiotherapy in locally advanced non-small cell lung cancer (NSCLC)

Introduction

Lung cancer is the most common cause of cancer-related death worldwide1. Non-small cell lung cancer (NSCLC) accounts for approximately 85% of all types of lung cancer, with lung adenocarcinoma and lung squamous cell carcinoma (SCC) accounting for 60% and 15% of histologic subtypes, respectively1. With the advent of new developments in neoadjuvant therapy and immunotherapy,

Corresponding Author: Hüseyin Akkaya, dr.hsynakkaya@gmail.com, Received: 30.01.2024, Accepted: 08.03.2024, Available Online Date: 11.03.2024 Cite this article as: Akkaya H, Dilek O, Saygılı RAR, et al. Evaluation of the efficacy of pretreatment chest CT markers in predicting response to neoadjuvant chemoradiotherapy in locally advanced non-small cell lung cancer. J Cukurova Anesth Surg. 2024; 7(1): 32-41.

https://doi.org/10.36516/jocass.1427896 Copyright © 2024 This is an open access article distributed under the terms of the Creative Commons Attribution-Non-Commercial-No Derivatives License 4.0 (CC-BY-NC-ND), where it is permissible to download and share the work provided it is properly cited. The work cannot be changed in any way or used commercially without permission from the journal.

the overall survival (OS) of patients with NSCLC has improved significantly. For patients with locally advanced NSCLC, neoadjuvant therapy plays an important role in both staging of lung cancer and providing an opportunity for surgery that effectively improves prognosis2. Neoadjuvant chemoradiotherapy (CRT) followed by surgical resection improves survival compared to surgery alone in patients with locally advanced non-small cell lung cancer, especially in patients with a complete pathological response or major pathological response (MPR) (classically defined as a residual tumor burden of <10%)1. Neoadjuvant CRT has become a vital strategy to reduce tumor size and facilitate surgical resection3. Neoadjuvant CRT also allows interim assessments of response to treatment and prevents the development of micrometastases4.

Traditional neoadjuvant therapy includes chemotherapy and chemoradiation, and revolutionary neoadjuvant therapies for NSCLC are evolving4. However, tools and predictive models to estimate the prognosis of patients receiving neoadjuvant therapy followed by lung surgery are still limited5. The aim of this study was to evaluate whether chest CT findings can predict neoadjuvant treatment response in patients with locally advanced non-small cell lung cancer.

Materials and methods

2.1. Patient Selection and Study Design

This retrospective study was approved by our institutional ethical committee and carried out in accordance with the Declaration of Helsinki and the Good Clinical Practice Guidelines. The requirement for informed consent from the patients was waived due to the retrospective nature of the study.

The American Joint Committee on Cancer (AJCC) TNM staging system is the most commonly used tool to predict recurrence and survival. For the N descriptor, the lymph node (LN) is based on the lymphatic territory involved without any information on the number of dissected LNs (NDLN) and the number of positive LNs (NPLN). Since January 2017, the 8th edition of TNM in Lung Cancer has been used as the standard for non-small cell lung cancer staging. This staging system was used in our study. In this study, all findings that could be obtained from chest enhanced CT examination of patients with locally advanced lung cancer were included in the investigation. For neoadjuvant treatment response, 3rd and 6th month control chest CT scans were performed and changes around the tumor and changes in tumor size were noted. Tumors in remission and operable tumors were operated. Patients who were not operable after neoadjuvant treatment were excluded from the study (Figure 1).

Individuals with diffuse or multiple nodules were excluded. Subsolid, ground glass and cavitary non-solid masses were excluded.

2.2. Chemoradiotherapy Protocols

Although there was previously no standard treatment management in locally advanced lung cancer, treatment algorithms have recently changed with the integration of immunotherapy into neoadjuvant treatment 6. To the best of our previous knowledge, neoadjuvant therapy may improve resectability by decreasing the T stage and nodal disease stage and increasing local regional control by removing residual tumor and nodal disease 7. Data from phase II trials show that neoadjuvant chemoradiotherapy is well tolerated in active patients with good performance status. In contrast, the survival benefit of neoadjuvant chemoradiation compared with induction chemotherapy has not been clearly established due to inconsistent results of Phase III trials.

The initial overall number of patients, together with the number of patients included in the study, is demonstrated. The number of patients excluded from the study and exclusion criteria of the study are shown.

There are 2 different chemotherapies commonly used with concurrent chemoradiotherapy. The first one is the weekly administration of paclitaxel and carboplatin, while the other is the combination of cisplatin and Etoposide. These two chemotherapy combinations have been compared in a previous clinical trial. Although there was no statistical significance in overall survival, there was a numerical improvement in the cisplatin and Etoposide arm. However, this numerical improvement was associated with an increased toxicity profile 8. All of the patients included in this study were patients who received neoadjuvant chemoradiotherapy and then underwent surgery. The combination of carboplatin and paclitaxel is the chemotherapy protocol used simultaneously with radiotherapy in our center because of its easy tolerability. Therefore, weekly carboplatin and paclitaxel treatment was used in all patients in the study. Radiologic response evaluation was performed 4-6 weeks after completion of chemoradiotherapy and operable patients in remission were operated.

Imaging Technique

Thorax CT scans were performed in a 128-detector scanner (Philips Ingenuity 128; Philips, Eindhoven, The Netherlands). All scans were completed in a single breath-hold in the supine position. The standard scanning area was designated as the space between the apex of the lungs and the costophrenic angles. The CT parameters were designated as follows: 80-120 kVp; 100-200 mAs; gantry rotation time = 0.4 s; pitch = 0.8 or 1; slice thickness = 1 mm; and slice reconstruction = 3 mm; FOV :350 mm. Axial, sagittal, and coronal reformatted images were acquired from the raw slices. The radiation dose received by the patients was calculated as 3-5.5 mSv. The enhanced scan was performed using a high-pressure syringe, injecting non-ionic iodine (iohexol; 350 mg/mL; injection amount, 1.5-2 mL/kg; injection rate, 3 mL/s) intravenously through the elbow. The mediastinum window was set [width, 350 Hounsfield units (HU); level, 40 HU], and the lung window was also set (width, 1,200 HU; level, -600 HU). All raters performed their evaluations using separate individual Intellispace Service Healthcare (IPS) workstations.

CT Evaluation

The pathology results of the tumor tissue, presence or absence of additional comorbidities, smoking history, age and gender were completely concealed from the readers. The readers evaluated the localization of the tumor tissue in two ways: central and peripheral. They noted the segments in which the lesion was located and the longest dimension of the lesions. Readers noted the lesion contours under 4 main headings; 1) round smooth 2) macrolobulated 3) microlobulated 4) spiculated. Readers noted the types of calcification of the lesions under 4 headings; 1) no calcification 2) central calcification 3) eccentric calcification 4) coarse calcification. Necrosis status was categorized under 3 headings; 1) no necrosis 2) <50% necrosis 3) >50% necrosis. The types of atelectasis adjacent to the lesion were noted by the readers under 5 headings. 1) no atelectasis 2) subsegmental 3) segmental 4) lobar 5) total atelectasis.

In the mediastinal window of contrast-enhanced thorax CT examination; Coronal (a) and axial (b) section examination shows a mass lesion in the lower lobe of the left lung. Infracarinal lymph node (solid arrow) , pericardial invasion and accompanying pericardial effusion are seen (hollow arrow) (a, b). After neoadjuvant treatment, it was observed that the mass shrank significantly and pericardial invasion and pericardial effusion decreased (c).

In the mediastinal window of contrast-enhanced thorax CT examination; (a) It is seen that the mass located in the upper lobe ( solid arrow) of the right lung infiltrated the posterior bronchus of the right upper lobe (marked with asterisks) and caused thrombus in the superior vena cava and bronchial artery(marked with asterisks), (b). Lymph nodes located at stations 7 and 4L are also seen(hollow arrow). In the thorax CT examination obtained after neoadjuvant treatment; It shows that the thrombus in the superior vena cava has regressed, but there is no change in the size of the mass (c).

parenchymal changes around the tumor tissue were noted by the readers under 7 headings; 1) normal parenchyma 2) ground glass 3) reticular changes (lymphatic) 4) ground glass + reticular changes 5) mosaic attenuation 6) consolidation 7) bronchiectasis. The stage of vascular infiltration of the masses was noted by the readers under 6 headings. 1) absent 2) pulmonary trunk 3) main 4) lobar 5) segmental 6) VCS (Figure 2,3).

The stage at which the masses had respiratory tract infiltration was noted by the readers under 5 headings. 1) no airway infiltration 2) trachea 3) main bronchi 4) intermediate bronchus 5) lobar bronchus ( Figure 2,3). The presence or absence of cardiac infiltration of tumor tissue was noted under 4 headings; 1) absent 2) pericardial infiltration 3) infiltration up to myocardium 4) presence of intra-chamber thrombus( Figure 2).

Readers noted which lymph node stations had pathologic lymph nodes (lymph nodes with a short axis >10 mm). The presence of distant metastasis on CT scan before neoadjuvant treatment was noted. The presence or absence of pleural effusion in the hemithorax of the lesion was noted ( Figure 2,3).

Lung tumours were contoured by three expert readers on the Workstation (Intelli SpacePhilips [IPS], The Netherlands) using a freehand tool to manually segment the lesion. The readers were blinded to the actual histopathologic diagnosis of all cases.

Statistical Analysis

SPSS (Statistical Package for the Social Sciences) 25.0 package program was used for statistical analysis of the data. Categorical measurements were summarized as number and percentage, and continuous measurements were summarized as mean and standard deviation (median (median) and minimum-maximum where necessary). The Kolmogorov-Smirnov test was used to determine whether the parameters in the study were normally distributed. Mann Whitney U test was used for parameters that did not show normal distribution. Chi-square test was used to compare categorical expressions. Cox Regression test was used to analyze the factors affecting remission and progression. Kaplan Meier test was used in survival analysis. Statistical significance level was taken as 0.05 in all tests.

Results

The enhanced chest CT scans, demographic data and number of comorbidities evaluated in the patient groups included in the study are given in Table 1.

Progression and mortality rates were found to be low in patients with remission (p<0.001). No significant difference was found between the other parameters in Table 2 (p>0.05).

The rate of progression was higher in cases with n2 and n3 in TNM staging (p<0.001). The rate of calcification was higher in patients with progression (p=0.005) and the rate of pericardial invasion was higher (p=0.008). In addition, vascular invasion rate was high in patients who developed progression (p=0.003). The mean age of patients with progression was low (p=0.038). No significant difference was found between the other parameters in Table 3 (p>0.05).

The factors affecting progression were analyzed with Cox regression model in Table 4. Univariate analysis revealed a statistically significant difference between lymph node station, calcification, presence of pericardial invasion, presence of vascular invasion and age variables. In the multivariate cox regression analysis, parameters that were found to be significant in the univariate analysis results were included. According to the results of the analysis, patients with lymph node station 3 had a 3.69 -fold efect [odds ratio (OR)=3.693, [95% confdence interval (CI)= 1.875–7.274, p=0.041] effect on progression (p<0.001), (Table 4).

Overall survival was 40.1 (months) and progression free survival was 14.8 (months) ( Figure 4).

Discussion

The aim of this study was to investigate which of the findings on pretreatment chest enhanced CT scan is more successful in predicting histologic response to neoadjuvant therapy in patients with locally advanced NSCLC. Neoadjuvant therapy followed by surgery has recently been applied as a multimodal treatment for locally advanced NSCLC6. Accurate patient stratification is becoming increasingly important. Pathological tumor-lymph node-metastasis (pTNM) classification is the most important and routinely applied prognosis prediction tool for malignant disease. MPR or complete pathologic response has been associated with long-term overall survival (OS) in NSCLC patients undergoing neoadjuvant therapy7,8. Prognostic information to predict response to treatment in the setting of neoadjuvant therapy can help establish criteria for selecting appropriate surgical candidates 9.

In the study, lymph node stage grouping was performed in patients with lung tumors. It was observed that lymph node stage was not significant in terms of response to neoadjuvant treatment. However, lymph node stage was shown to be effective in progression. Especially in the multivariant analysis, N0 and/or N3 stage group was found to be effective on the progression time. In lung cancer TNM staging 8th edition, N stage varies according to the localisation of lymph nodes. In this study, T stage in TNM staging and lymph node stage and metastasis were investigated separately in terms of both progression and response to treatment. The study showed that N stage was more effective in progression than both T and M stage. In other words, advanced N stage is a poor prognosis in terms of progression independent of TNM staging.

There are many previous studies on whether the contours of lung tumors affect the response to radiotherapy10. However, there is no consensus on this issue8-12. In our study, tumor contours were not associated with response to neoadjuvant treatment. Similarly, tumor contours were not associated with the time of progression.

There was no significant difference between the subgroups of non-small cell lung tumors in terms of response to neoadjuvant treatment or progression times. These results obtained in our study were consistent with the literature 12,13. As a matter of fact, lung tumors are divided into two groups as small cell and non-small cell in terms of treatment protocol 8,13.

Localization and infiltrating localization of lung tumors are very important in terms of surgery 14,15. In the literature, the relationship between postoperative response and localization has been examined 16-18. In our study, regardless of the areas infiltrated by tumor tissue, the lobe in which the tumor tissue was located, whether it was in a single lobe or extended to more than one lobe, and whether the lesion was centrally or peripherally localized were noted separately. It was observed that the localization of tumor tissue in the lung parenchyma had no effect on neoadjuvant treatment response or progression time.

Recently, the number of studies investigating the relationship between tumor contours in the lung and other localizations and tumor subtypes and grades has increased19-22. Tumor contour is one of the most frequently used parameters in tumor analysis, especially in studies performed with artificial intelligence19,23,24. It is an accepted fact that spiculated and microlobule lesions suggest malignant tumors 24,25. In this study, tumor contours were divided into 4 groups by the readers and the relationship between tumor contour and response to neoadjuvant treatment and progression times were examined, but no significant relationship was found.

Number of parameters analyzed in the patients included in the study

Distribution of the analyzed parameters of the patients with and without remission

DM: diabetes mellitus, HT: hypertension, VCS: vena cava superior

Distribution of analyzed parameters of progressing and non-progressing patients

DM: diabetes mellitus, HT: hypertension, VCS: vena cava superior, *p<0.05, **p<0.01, †: Chi-square, ‡: Mann Whitney U

Graph of progression free survival and overall survival times of patients.

Cox regression model of factors affecting progression

**p<0.01, Cox regression

Necrosis and cavity are not uncommon findings in lung tumors 9,26. Lesions with cavities were not included in the study. The presence of necrosis (0, <50%, >50%) on the baseline enhanced CT scan before neoadjuvant treatment was analyzed by the readers. In addition, necrosis rates at the 3rd and 6th month of the treatment follow-up were noted. The presence or absence of necrosis before treatment or necrosis developing during treatment was not associated with neoadjuvant treatment response or time to progression.

Calcification is not uncommon in both benign and malignant lung tumors 27,28. While eccentric calcification is more common in malignant lesions, coarse and central calcification is more common in benign lesions29-31. Our aim in this study was to evaluate whether calcification can predict response to treatment or progression. In the study, there was no significant difference in response to neoadjuvant treatment in cases with and without calcification , but progression was more common in cases with calcification (especially eccentric calcification).

We examined whether the presence of atelectasis in the neighborhood of the mass was associated with response to neoadjuvant treatment. Atelectasis was classified as 4 types by the readers. Both the baseline enhanced CT scan at the time of diagnosis and the presence of atelectasis at 3 and 6 months during treatment follow-up were noted. However, atelectasis both at baseline enhanced CT scan and during treatment was not associated with neoadjuvant treatment response or time to progression.

The presence of pleural effusion in the hemithorax with tumor tissue was examined both at baseline enhanced chest CT examination and at 3 and 6 months during the treatment period. However, pleural effusion at any period was not associated with neoadjuvant treatment response or time to progression.

Density changes other than atelectasis around the tumor tissue were examined both at baseline enhanced chest CT examination and at 3 and 6 months during the treatment period. However, peritumoral density changes in any period were not correlated with neoadjuvant treatment response or time to progression.

There was no significant difference in response to neoadjuvant treatment in patients with bronchial invasion, vascular invasion and pericardial invasion compared to patients without these invasions. However, progression was observed earlier in patients with bronchial, vascular and pericardial invasion compared to those without. Especially vascular invasion had a greater effect on progression compared to the others. It is not surprising that progression is seen earlier in cases with vascular invasion. The ease of spread of micrometastases and/or tumour cells via haematogenous route especially in cases with vascular invasion is already known in other tumours1,8,13. We think that the fact that the lymph node stage is another effective factor in the progression of lung tumours supports this idea.

Previous studies have shown that neoadjuvant treatment has a positive effect on both progression free survival and overall survival2,8,27. In this study, both progression times were longer and mortality was lower in patients in remission.

Limitations

Our study has some limitations. The main ones are; 1) Using artificial intelligence and obtaining quantitative data, especially in the evaluation of tumor heterogeneity and tumor contours, would have made our study much more valuable. 2) The fact that metabolic tumor volume (MTV) was not evaluated from PET CT examinations before neoadjuvant treatment can be considered one of the limitations of our study. However, due to the retrospective nature of the study, most of the patients did not have a PET CT scan after neoadjuvant treatment. 3) Since the study was not interobserver, the concordance of the chest CT findings between the readers and their usability in routine clinical practice could not be examined.

Conclusion

None of the findings on chest CT examination before neoadjuvant therapy have been shown to be successful in predicting response to neoadjuvant therapy. The findings that can predict progression on a baseline chest CT scan are vascular invasion, lymph node staging and pericardial invasion. Vascular invasion, lymph node stage advanced cases, pericardial invasion and calcification during baseline chest CT scan are findings that can predict progression. Lymph node is the most valuable of these in predicting progression.

Statement of ethics

The ethical approval was provided by the Clinical Research Ethics Committee of the Adana City Training and Research Hospital on 2023, with decision number 2767.

Conflict of interest statement

The authors declare that they have no financial conflict of interest with regard to the content of this report.

Funding source

The authors received no financial support for the research, authorship, and/or publication of this article.

Author contributions

1. substantial contributions to conception and design, acquisition of data: Hüseyin Akkaya, Okan Dilek, Bozkurt Gülek, Rukiye Aysu Revanlı Saygılı, Hatice Coşkun, Zeynel Abidin Taş

2. revising it critically for important intellectual content: Hüseyin Akkaya , Okan Dilek , Bozkurt Gülek,Ahmet Gülmez

3. final approval of the version to be published , analysis: Hüseyin Akkaya , Okan Dilek , Bozkurt Gülek, Ahmet Gülmez, Hatice Coşkun

4. agree to be accountable for all aspects of the work if questions : Hüseyin Akkaya , Okan Dilek , Bozkurt Gülek, Rukiye Aysu Revanlı Saygılı, Zeynel Abidin Taş

References

1. Siegel RL, Miller KD, Fuchs HE, Jemal A Cancer statistics, 2021. CA Cancer J Clin. 2021;71:7-33.

https://doi.org/10.3322/caac.21654

2. Wang Q, Wang S, Sun Z, Cao M, Zhao X. Evaluation of log odds of positive lymph nodes in predicting the survival of patients with non-small cell lung cancer treated with neoadjuvant therapy and surgery: a SEER cohort-based study. BMC Cancer. 2022;22:801.

https://doi.org/10.1186/s12885-022-09908-3

3. Shen J, Sun N, Zens P et al. Spatial metabolomics for evaluating response to neoadjuvant therapy in non-small cell lung cancer patients. Cancer Commun (Lond). 2022;42:517-535.

https://doi.org/10.1002/cac2.12310

4. Saw SPL, Ong BH, Chua KLM et al. Revisiting neoadjuvant therapy in non-small-cell lung cancer. Lancet Oncol. 2021;22:e501-e516.

https://doi.org/10.1016/S1470-2045(21)00383-1

5. Rosner S, Liu C, Forde PM et al. Association of Pathologic Complete Response and Long-Term Survival Outcomes Among Patients Treated with Neoadjuvant Chemotherapy or Chemoradiotherapy for NSCLC: A Meta-Analysis. JTO Clin Res Rep. 2022 Jul 31;3(9):100384.

https://doi.org/10.1016/j.jtocrr.2022.100384

6. Godoy LA, Chen J, Ma W P et al. Emerging precision neoadjuvant systemic therapy for patients with resectable non-small cell lung cancer: current status and perspectives. Biomark Res 2023;11:7.

https://doi.org/10.1186/s40364-022-00444-7

7. Blumenthal GM, Bunn PA Jr, Chaft JE et al. Current Status and Future Perspectives on Neoadjuvant Therapy in Lung Cancer. J Thorac Oncol 2018;13:1818-31.

https://doi.org/10.1016/j.jtho.2018.09.017

8. Liang J, Bi N, Wu S et al. Etoposide and cisplatin versus paclitaxel and carboplatin with concurrent thoracic radiotherapy in unresectable stage III non-small cell lung cancer: a multicenter randomized phase III trial. Ann Oncol. 2017;28):777-783.

https://doi.org/10.1093/annonc/mdx009

9. Cheng Y, Chen ZY, Huang JJ et al. Efficacy evaluation of neoadjuvant immunotherapy plus chemotherapy for non-small-cell lung cancer: comparison of PET/CT with postoperative pathology. Eur Radiol. 2023;33:6625-6635.

https://doi.org/10.1007/s00330-023-09922-4

10. Khorrami M, Jain P, Bera K et al. Predicting pathologic response to neoadjuvant chemoradiation in resectable stage III non-small cell lung cancer patients using computed tomography radiomic features. Lung Cancer. 2019;135:1-9.

https://doi.org/10.1016/j.lungcan.2019.06.020

11. Yue D, Liu W, Chen C et al. Circulating tumor DNA predicts neoadjuvant immunotherapy efficacy and recurrence-free survival in surgical non-small cell lung cancer patients. Transl Lung Cancer Res. 2022;11:263-276.

https://doi.org/10.21037/tlcr-22-106

12. Bao Y, Gu C, Xie H et al. Comprehensive study of neoadjuvant targeted therapy for resectable non-small cell lung cancer. Ann Transl Med. 2021;9:493.

https://doi.org/10.21037/atm-21-1134

13. Tanahashi M, Suzuki E, Yoshii N et al. Role of fluorodeoxyglucose-positron emission tomography in predicting the pathological response and prognosis after neoadjuvant chemoradiotherapy for locally advanced non-small-cell lung cancer. Interact Cardiovasc Thorac Surg. 2022;35:113.

https://doi.org/10.1093/icvts/ivac113

14. Zhang J, Zhao X, Zhao Y et al. Value of pre-therapy 18F-FDG PET/CT radiomics in predicting EGFR mutation status in patients with non-small cell lung cancer. Eur J Nucl Med Mol Imaging. 2020;47:1137-1146.

https://doi.org/10.1007/s00259-019-04592-1

15. Chetan MR, Gleeson FV. Radiomics in predicting treatment response in non-small-cell lung cancer: current status, challenges and future perspectives. Eur Radiol. 2021;31:1049-1058.

https://doi.org/10.1007/s00330-020-07141-9

16. Dissaux G, Visvikis D, Da-Ano R et al. Pretreatment 18F-FDG PET/CT Radiomics Predict Local Recurrence in Patients Treated with Stereotactic Body Radiotherapy for Early-Stage Non-Small Cell Lung Cancer: A Multicentric Study. J Nucl Med. 2020;61:814-820.

https://doi.org/10.2967/jnumed.119.228106

17. Nestle U, Schimek-Jasch T, Kremp S et al. Imaging-based target volume reduction in chemoradiotherapy for locally advanced non-small-cell lung cancer (PET-Plan): a multicentre, open-label, randomized, controlled trial. Lancet Oncol. 2020;21:581-592.

https://doi.org/10.1016/S1470-2045(20)30013-9

18. Khorrami M, Prasanna P, Gupta A, Patil P et al. Changes in CT Radiomic Features Associated with Lymphocyte Distribution Predict Overall Survival and Response to Immunotherapy in Non-Small Cell Lung Cancer. Cancer Immunol Res. 2020;8:108-119.

https://doi.org/10.1158/2326-6066.CIR-19-0476

19. Bortolotto C, Lancia A, Stelitano C et al. Radiomics features as predictive and prognostic biomarkers in NSCLC. Expert Rev Anticancer Ther. 2021;21:257-266.

https://doi.org/10.1080/14737140.2021.1852935

20. Liberini V, Mariniello A, Righi L et al. NSCLC Biomarkers to Predict Response to Immunotherapy with Checkpoint Inhibitors (ICI): From the Cells to In Vivo Images. Cancers (Basel). 2021;13:4543.

https://doi.org/10.3390/cancers13184543

21. Seban RD, Mezquita L, Berenbaum A et al. Baseline metabolic tumor burden on FDG PET/CT scans predicts outcome in advanced NSCLC patients treated with immune checkpoint inhibitors. Eur J Nucl Med Mol Imaging. 2020;47:1147-1157.

https://doi.org/10.1007/s00259-019-04615-x

22. Rosner S, Liu C, Forde PM et al. Association of Pathologic Complete Response and Long-Term Survival Outcomes Among Patients Treated With Neoadjuvant Chemotherapy or Chemoradiotherapy for NSCLC: A Meta-Analysis. JTO Clin Res Rep. 2022;3:100384.

https://doi.org/10.1016/j.jtocrr.2022.100384

23. Zarogoulidis P, Matthaios D, Kosmidis C et al. Effective early diagnosis for NSCLC: an algorithm. Expert Rev Respir Med. 2021;15:1437-1445.

https://doi.org/10.1080/17476348.2021.1969916

24. Han Y, Ma Y, Wu Z et al. Histologic subtype classification of non-small cell lung cancer using PET/CT images. Eur J Nucl Med Mol Imaging. 2021;48:350-360.

https://doi.org/10.1007/s00259-020-04771-5

25. Koyasu S, Nishio M, Isoda H et al. Usefulness of gradient tree boosting for predicting histological subtype and EGFR mutation status of non-small cell lung cancer on 18F FDG-PET/CT. Ann Nucl Med. 2020;34:49-57.

https://doi.org/10.1007/s12149-019-01414-0

26. Dissaux G, Visvikis D, Da-Ano R et al. Pretreatment 18F-FDG PET/CT Radiomics Predict Local Recurrence in Patients Treated with Stereotactic Body Radiotherapy for Early-Stage Non-Small Cell Lung Cancer: A Multicentric Study. J Nucl Med. 2020;61:814-820.

https://doi.org/10.2967/jnumed.119.228106

27. Leader AM, Grout JA, Maier BB et al. Single-cell analysis of human non-small cell lung cancer lesions refines tumor classification and patient stratification. Cancer Cell. 2021;39:1594-1609.

https://doi.org/10.1016/j.ccell.2021.10.009

28. Kan CFK, Unis GD, Li LZ et al. Circulating Biomarkers for Early Stage Non-Small Cell Lung Carcinoma Detection: Supplementation to Low-Dose Computed Tomography. Front Oncol. 2021;11:555331.

https://doi.org/10.3389/fonc.2021.555331

29. Hattori A, Suzuki K, Takamochi K et al. Japan Clinical Oncology Group Lung Cancer Surgical Study Group. Prognostic impact of a ground-glass opacity component in clinical stage IA non-small cell lung cancer. J Thorac Cardiovasc Surg. 2021;161:1469-1480.

https://doi.org/10.1016/j.jtcvs.2020.01.107

30. Akinci D'Antonoli T, Farchione A, Lenkowicz J et al. CT Radiomics Signature of Tumor and Peritumoral Lung Parenchyma to Predict Nonsmall Cell Lung Cancer Postsurgical Recurrence Risk. Acad Radiol. 2020;27:497-507.

https://doi.org/10.1016/j.acra.2019.05.019

31. Nakanishi Y, Masuda T, Yamaguchi K et al. Pre-existing interstitial lung abnormalities are risk factors for immune checkpoint inhibitor-induced interstitial lung disease in non-small cell lung cancer. Respir Investig. 2019;57:451-459.

https://doi.org/10.1016/j.resinv.2019.05.002