Artificial intelligence in interventional pulmonology.

PURPOSE OF REVIEW: In recent years, there has been remarkable progress in the field of artificial intelligence technology. Artificial intelligence applications have been extensively researched and actively implemented across various domains within healthcare. This study reviews the current state of artificial intelligence research in interventional pulmonology and engages in a discussion to comprehend its capabilities and implications. RECENT FINDINGS: Deep learning, a subset of artificial intelligence, has found extensive applications in recent years, enabling highly accurate identification and labeling of bronchial segments solely from intraluminal bronchial images. Furthermore, research has explored the use of artificial intelligence for the analysis of endobronchial ultrasound images, achieving a high degree of accuracy in distinguishing between benign and malignant targets within ultrasound images. These advancements have become possible due to the increased computational power of modern systems and the utilization of vast datasets, facilitating detections and predictions with greater precision and speed. SUMMARY: Artificial intelligence integration into interventional pulmonology has the potential to enhance diagnostic accuracy and patient safety, ultimately leading to improved patient outcomes. However, the clinical impacts of artificial intelligence enhanced procedures remain unassessed. Additional research is necessary to evaluate both the advantages and disadvantages of artificial intelligence in the field of interventional pulmonology.

Investigating the effects of a temperature dependent photodynamic dose: A numerical study.

SIGNIFICANCE: Photodynamic therapy (PDT) and photothermal therapy (PTT) show promise as cancer treatments, but challenges in generating large ablative volumes for deep-seated tumours persist. Using simulations, this study investigates combined PDT and PTT to increase treatment volumes, including the impact of a temperature-dependent PDT dose on the treatment volume radius. APPROACH: A finite-element model, using the open-source SfePy package, was developed to simulate combined interstitial photothermal and photodynamic treatments. Results compared an additive dose model to a temperature-dependent dose model with enhanced PDT dosimetry and examined typical clinical scenarios for possible synergistic effects. RESULTS: Findings revealed that the temperature-dependent dose model could significantly expand the damage radius compared to the additive model, depending on the tissue and drug properties. CONCLUSIONS: Characterizing synergistic effects of PDT and PTT could enhance treatment planning. Future work is ongoing to implement additional variables, such as photosensitizer photobleaching, and spatial and temporally varying oxygenation.

The 2023 American Association for Thoracic Surgery (AATS) Expert Consensus Document: Management of subsolid lung nodules.

OBJECTIVE: Lung cancers that present as radiographic subsolid nodules represent a subtype with distinct biological behavior and outcomes. The objective of this document is to review the existing literature and report consensus among a group of multidisciplinary experts, providing specific recommendations for the clinical management of subsolid nodules. METHODS: The American Association for Thoracic Surgery Clinical Practice Standards Committee assembled an international, multidisciplinary expert panel composed of radiologists, pulmonologists, and thoracic surgeons with established expertise in the management of subsolid nodules. A focused literature review was performed with the assistance of a medical librarian. Expert consensus statements were developed with class of recommendation and level of evidence for each of 4 main topics: (1) definitions of subsolid nodules (radiology and pathology), (2) surveillance and diagnosis, (3) surgical interventions, and (4) management of multiple subsolid nodules. Using a modified Delphi method, the statements were evaluated and refined by the entire panel. RESULTS: Consensus was reached on 17 recommendations. These consensus statements reflect updated insights on subsolid nodule management based on the latest literature and current clinical experience, focusing on the correlation between radiologic findings and pathological classifications, individualized subsolid nodule surveillance and surgical strategies, and multimodality therapies for multiple subsolid lung nodules. CONCLUSIONS: Despite the complex nature of the decision-making process in the management of subsolid nodules, consensus on several key recommendations was achieved by this American Association for Thoracic Surgery expert panel. These recommendations, based on evidence and a modified Delphi method, provide guidance for thoracic surgeons and other medical professionals who care for patients with subsolid nodules.

Clinical and pathological predictors of engraftment for patient-derived xenografts in lung adenocarcinoma.

Patient-derived xenografts (PDXs) are increasingly utilized in preclinical drug efficacy studies due to their ability to retain the molecular, histological, and drug response characteristics of patient tumors. This study aimed to investigate the factors influencing the successful engraftment of PDXs. Lung adenocarcinoma PDXs were established using freshly resected tumor tissues obtained through surgery. Radiological data of pulmonary nodules from this PDX cohort were analyzed, categorizing them into solid tumors and tumors with ground-glass opacity (GGO) based on preoperative CT images. Gene mutation status was obtained from next generation sequencing data and MassARRAY panel. A total of 254 resected primary lung adenocarcinomas were utilized for PDX establishment, with successful initial engraftment in 58 cases (22.8 %); stable engraftment defined as at least three serial passages was observed in 43 cases (16.9 %). The stable engraftment rates of PDXs from solid tumors and tumors with GGO were 22.1 % (42 of 190 cases) and 1.6 % (1 of 64 cases), respectively (P < 0.001). Adenocarcinomas with advanced stage, poor differentiation, solid histologic subtype, and KRAS or TP53 gene mutations were associated with stable PDX engraftment. Avoiding tumors with GGO features could enhance the cost-effectiveness of establishing PDX models from early-stage resected lung adenocarcinomas.

Systematic endoscopic staging of mediastinum to guide radiotherapy planning in patients with locally advanced non-small-cell lung cancer (SEISMIC): an international, multicentre, single-arm, clinical trial.

BACKGROUND: Systematic mediastinal lymph node staging by endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) improves accuracy of staging in patients with early-stage non-small-cell lung cancer (NSCLC). However, patients with locally advanced NSCLC commonly undergo only selective lymph node sampling. This study aimed to determine the proportion of patients with locally advanced NSCLC in whom systematic endoscopic mediastinal staging identified PET-occult lymph node metastases, and to describe the consequences of PET-occult disease on radiotherapy planning. METHODS: This prospective, international, multicentre, single-arm, international study was conducted at seven tertiary lung cancer centres in four countries (Australia, Canada, the Netherlands, and the USA). Patients aged 18 years or older with suspected or known locally advanced NSCLC underwent systematic endoscopic mediastinal lymph node staging before combination chemoradiotherapy or high-dose palliative radiotherapy. The primary endpoint was the proportion of participants with PET-occult mediastinal lymph node metastases shown following systematic endoscopic staging. The study was prospectively registered with Australian New Zealand Clinical Trials Registry, ACTRN12617000333314. FINDINGS: From Jan 30, 2018, to March 23, 2022, 155 patients underwent systematic endoscopic mediastinal lymph node staging and were eligible for analysis. 58 (37%) of patients were female and 97 (63%) were male. Discrepancy in extent of mediastinal disease identified by PET and EBUS-TBNA was observed in 57 (37% [95% CI 29-44]) patients. PET-occult lymph node metastases were identified in 18 (12% [7-17]) participants, including 16 (13% [7-19]) of 123 participants with clinical stage IIIA or cN2 NSCLC. Contralateral PET-occult N3 disease was identified in nine (7% [2-12]) of 128 participants staged cN0, cN1, or cN2. Identification of PET-occult disease resulted in clinically significant changes to treatment in all 18 patients. In silico dosimetry studies showed the median volume of PET-occult lymph nodes receiving the prescription dose of 60 Gy was only 10·1% (IQR 0·1-52·3). No serious adverse events following endoscopic staging were reported. INTERPRETATION: Our findings suggests that systematic endoscopic mediastinal staging in patients with locally advanced or unresectable NSCLC is more accurate than PET alone in defining extent of mediastinal involvement. Standard guideline-recommended PET-based radiotherapy planning results in suboptimal tumour coverage. Our findings indicate that systematic endoscopic staging should be routinely performed in patients with locally advanced NSCLC being considered for radiotherapy to accurately inform radiation planning and treatment decision making in patients with locally advanced NSCLC. FUNDING: None.

Recurrence of Non-Small Cell Lung Cancer With Visceral Pleural Invasion: A Seconday Analysis of a Randomized Clinical Trial.

Importance: The randomized clinical trial Cancer and Leukemia Group B (CALGB) 140503 showed that for patients with clinically staged T1N0 non-small cell lung cancer (NSCLC; ≤2 cm), sublobar resections were associated with similar oncological outcomes to those after lobar resection. The association of the extent of parenchymal resection with recurrence and survival in patients with tumors pathologically upstaged to T2 based on visceral pleural invasion (VPI) is controversial. Objective: To determine survival and recurrence rates in patients with small peripheral pT2 NSCLC (≤2 cm) that was treated by either lobar or sublobar resection in CALGB 140503. Design, Participants, and Setting: CALGB 140503, a randomized multicenter noninferiority trial, included 697 patients with small peripheral NSCLC that was clinically staged as T1N0. Enrollment was from June 2007 through March 2017 at 83 participating institutions, and after a median follow-up of 7 years, the primary outcome of disease-free survival after sublobar resection was noninferior to that after lobar resection. Intervention: Lobar or sublobar resection. Main Outcomes and Measures: Survival end points were estimated by the Kaplan-Meier estimator. Hazard ratios and 95% CIs were estimated using stratified Cox proportional hazard models. Results: Of 679 participants, 390 (57.4%) were female, and the median (range) age was 67.8 (37.8-89.7) years. Among 697 patients randomized, 566 (81.2%) had pT1 tumors (no VPI) and 113 (16.2%) had pT2 tumors (VPI). Five-year disease-free survival was 65.9% (95% CI, 61.9%-70.2%) in patients with pT1 compared with 53.3% (95% CI, 44.3%-64.1%) in patients with pT2 tumors (stratified log-rank: P = .02). Disease recurrence developed in 27.6% of patients with pT1 (locoregional only: 60 [10.8%]; distant only: 81 [14.6%]) and 41.6% of those with pT2 (locoregional only: 17 [15.0%]; distant only: 27 [23.9%]). Five-year recurrence-free survival was 73.1% (95% CI, 69.2%-77.1%) for pT1 tumors and 58.2% (95% CI, 49.2%-68.8%) for pT2 tumors (stratified log-rank: P = .01). There were no intergroup differences in disease-free or recurrence-free survival based on the extent of parenchymal resection. Conclusions and Relevance: The results of this secondary analysis suggest that compared with patients with tumors without VPI, patients who had tumors with VPI had worse disease-free and recurrence-free survival and a higher rate of local and distant disease recurrence. These high rates of recurrence were independent of the extent of parenchymal resection, and these data support the inclusion of these patients in adjuvant therapy trials. Trial Registration: ClinicalTrials.gov Identifier: NCT0049933.

Extension of Cold Static Donor Lung Preservation at 10°C.

BACKGROUND: Lung transplantation is performed on a 24/7 schedule to minimize organ ischemic time. Recent preclinical studies demonstrated superior graft preservation at 10°C compared with storage in an ice cooler (gold standard). METHODS: In this prospective, multicenter, nonrandomized clinical trial, we studied transplants from donors with overnight cross-clamp times (6:00 p.m. to 4:00 a.m.) that had an earliest allowed starting time of 6:00 a.m. Lungs meeting criteria for transplantation were retrieved, transported, and immediately transferred to a 10°C temperature-controlled incubator until implantation; 70 patients and 140 matched controls were included in this study. RESULTS: Total preservation times for lungs in the study group were 12 hours, 28 minutes (interquartile range, 10 hours, 14 minutes to 14 hours, 12 minutes) and 14 hours, 9 minutes (interquartile range, 12 hours, 3 minutes to 15 hours, 45 minutes) for the first and second lung implanted, respectively. Primary graft dysfunction grade 3 at 72 hours (primary outcome) was 5.7% in the study group versus 9.3% in matched controls (difference, −3.6; 95% confidence interval [CI], −10.5 to 5.3). No meaningful differences were observed in the need for postoperative extracorporeal membrane oxygenation (5.7 vs. 9.3%), median intensive care unit stay (5 vs. 5 days), or median hospital stay (25 vs. 30 days) between the two groups. One-year Kaplan­Meier survival was similar between the two groups (94 vs. 87%; hazard ratio, 0.65; 95% CI, 0.26 to 1.6). CONCLUSIONS: Extension of cold static preservation times at 10°C appears to be safe and has the potential to improve transplantation logistics and performance. (Funded by the UHN Foundation; Clinicaltrials.gov number, NCT04616365).

Assessment of effectiveness and safety of thrombolytic therapy to pulmonary emboli by endobronchial ultrasound-guided transbronchial needle injection.

Objective: Endobronchial ultrasound-guided transbronchial needle injection (EBUS-TBNI) may effectively treat acute pulmonary embolisms (PEs). Here, we assessed the effectiveness of clot dissolution and safety of tissue plasminogen activator (t-PA) injection using EBUS-TBNI in a 1-week survival study of a porcine PE model. Methods: Six pigs with bilateral PEs were used: 3 for t-PA injection using EBUS-TBNI (TBNI group) and 3 for systemic administration of t-PA (systemic group). Once bilateral PEs were created, each 25 mg of t-PA injection using EBUS-TBNI for bilateral PEs (a total of 50 mg t-PA) and 100 mg of t-PA systemic administration was performed on day 1. Hemodynamic parameters, blood tests, and contrast-enhanced computed tomography scans were carried out at several time points. On day 7, pigs were humanely killed to evaluate the residual clot volume in the pulmonary arteries. Results: The average of percent change of residual clot volumes was significantly lower in the TBNI group than in the systemic group (%: systemic group 36.6 ± 22.6 vs TBNI group 9.6 ± 6.1, P < .01) on day 3. Considering the elapsed time, the average decrease of clot volume per hour at pre-t-PA to post t-PA was significantly greater in the TBNI group than in the systemic group (mm3/hour: systemic 68.1 ± 68.1 vs TBNI 256.8 ± 148.1, P < .05). No hemorrhage was observed intracranially, intrathoracically, or intraperitoneally on any contrast-enhanced computed tomography images. Conclusions: This study revealed that t-PA injection using EBUS-TBNI is an effective and safe way to dissolve clots.