Innovations in thoracic imaging: CT, radiomics, AI and x-ray velocimetry

Study rationale and design of the PEOPLHE trial

PURPOSE

Lung cancer screening (LCS) by low-dose computed tomography (LDCT) demonstrated a 20-40% reduction in lung cancer mortality. National stakeholders and international scientific societies are increasingly endorsing LCS programs, but translating their benefits into practice is rather challenging. The "Model for Optimized Implementation of Early Lung Cancer Detection: Prospective Evaluation Of Preventive Lung HEalth" (PEOPLHE) is an Italian multicentric LCS program aiming at testing LCS feasibility and implementation within the national healthcare system. PEOPLHE is intended to assess (i) strategies to optimize LCS workflow, (ii) radiological quality assurance, and (iii) the need for dedicated resources, including smoking cessation facilities.

METHODS

PEOPLHE aims to recruit 1.500 high-risk individuals across three tertiary general hospitals in three different Italian regions that provide comprehensive services to large populations to explore geographic, demographic, and socioeconomic diversities. Screening by LDCT will target current or former (quitting < 10 years) smokers (> 15 cigarettes/day for > 25 years, or > 10 cigarettes/day for > 30 years) aged 50-75 years. Lung nodules will be volumetric measured and classified by a modified PEOPLHE Lung-RADS 1.1 system. Current smokers will be offered smoking cessation support.

CONCLUSION

The PEOPLHE program will provide information on strategies for screening enrollment and smoking cessation interventions; administrative, organizational, and radiological needs for performing a state-of-the-art LCS; collateral and incidental findings (both pulmonary and extrapulmonary), contributing to the LCS implementation within national healthcare systems.

Systematic Review on Learning-based Spectral CT

Spectral computed tomography (CT) has recently emerged as an advanced version of medical CT and significantly improves conventional (single-energy) CT. Spectral CT has two main forms: dual-energy computed tomography (DECT) and photon-counting computed tomography (PCCT), which offer image improvement, material decomposition, and feature quantification relative to conventional CT. However, the inherent challenges of spectral CT, evidenced by data and image artifacts, remain a bottleneck for clinical applications. To address these problems, machine learning techniques have been widely applied to spectral CT. In this review, we present the state-of-the-art data-driven techniques for spectral CT.

Systematic Review on Learning-based Spectral CT

Spectral computed tomography (CT) has recently emerged as an advanced version of medical CT and significantly improves conventional (single-energy) CT. Spectral CT has two main forms: dual-energy computed tomography (DECT) and photon-counting computed tomography (PCCT), which offer image improvement, material decomposition, and feature quantification relative to conventional CT. However, the inherent challenges of spectral CT, evidenced by data and image artifacts, remain a bottleneck for clinical applications. To address these problems, machine learning techniques have been widely applied to spectral CT. In this review, we present the state-of-the-art data-driven techniques for spectral CT.

Innovations in Chest Imaging: How Can Patients Benefit?

This Special Issue of Diagnostics entitled "Leading Diagnosis on Chest Imaging" provides an overview of recent technical developments in chest imaging and their clinical relevance, with a special focus on dual-energy CT (DECT) imaging [...].

Computed tomography-based radiomics improves non-invasive diagnosis of Pneumocystis jirovecii pneumonia in non-HIV patients: a retrospective study

BACKGROUND

Pneumocystis jirovecii pneumonia (PCP) could be fatal to patients without human immunodeficiency virus (HIV) infection. Current diagnostic methods are either invasive or inaccurate. We aimed to establish an accurate and non-invasive radiomics-based way to identify the risk of PCP infection in non-HIV patients with computed tomography (CT) manifestation of pneumonia.

METHODS

This is a retrospective study including non-HIV patients hospitalized for suspected PCP from January 2010 to December 2022 in one hospital. The patients were randomized in a 7:3 ratio into training and validation cohorts. Computed tomography (CT)-based radiomics features were extracted automatically and used to construct a radiomics model. A diagnostic model with traditional clinical and CT features was also built. The area under the curve (AUC) were calculated and used to evaluate the diagnostic performance of the models. The combination of the radiomics features and serum β-D-glucan levels was also evaluated for PCP diagnosis.

RESULTS

A total of 140 patients (PCP: N = 61, non-PCP: N = 79) were randomized into training (N = 97) and validation (N = 43) cohorts. The radiomics model consisting of nine radiomic features performed significantly better (AUC = 0.954; 95% CI: 0.898-1.000) than the traditional model consisting of serum β-D-glucan levels (AUC = 0.752; 95% CI: 0.597-0.908) in identifying PCP (P = 0.002). The combination of radiomics features and serum β-D-glucan levels showed an accuracy of 95.8% for identifying PCP infection (positive predictive value: 95.7%, negative predictive value: 95.8%).

CONCLUSIONS

Radiomics showed good diagnostic performance in differentiating PCP from other types of pneumonia in non-HIV patients. A combined diagnostic method including radiomics and serum β-D-glucan has the potential to provide an accurate and non-invasive way to identify the risk of PCP infection in non-HIV patients with CT manifestation of pneumonia.

TRIAL REGISTRATION

ClinicalTrials.gov (NCT05701631).

Environmental and occupational bronchiolitis obliterans: new reality

Patients diagnosed with environmental/occupational bronchiolitis obliterans (BO) over the last 2 decades often present with an indolent evolution of respiratory symptoms without a history of high-level, acute exposure to airborne toxins. Exertional dyspnea is the most common symptom and standard clinical and radiographic evaluation can be non-diagnostic. Lung biopsies often reveal pathological abnormalities affecting all distal lung compartments. These modern cases of BO typically exhibit the constrictive bronchiolitis phenotype of small airway remodeling, along with lymphocytic inflammation. In addition, hypertensive-type remodeling of intrapulmonary vasculature, diffuse fibroelastosis of alveolar tissue, and fibrous thickening of visceral pleura are frequently present. The diagnosis of environmental/occupational BO should be considered in patients who present with subacute onset of exertional dyspnea and a history compatible with prolonged or recurrent exposure to environmental toxins. Important areas for future studies include development of less invasive diagnostic approaches and testing of novel agents for disease prevention and treatment.

Quantifying ventilation by X-ray velocimetry in healthy adults

RATIONALE

X-ray velocimetry (XV) has been utilized in preclinical models to assess lung motion and regional ventilation, though no studies have compared XV-derived physiologic parameters to measures derived through conventional means.

OBJECTIVES

To assess agreement between XV-analysis of fluoroscopic lung images and pitot tube flowmeter measures of ventilation.

METHODS

XV- and pitot tube-derived ventilatory parameters were compared during tidal breathing and with bilevel-assisted breathing. Levels of agreement were assessed using the Bland-Altman analysis. Mixed models were used to characterize the association between XV- and pitot tube-derived values and optimize XV-derived values for higher ventilatory volumes.

MEASUREMENTS AND MAIN RESULTS

Twenty-four healthy volunteers were assessed during tidal breathing and 11 were reassessed with increased minute ventilation with bilevel-assisted breathing. No clinically significant differences were observed between the two methods for respiratory rate (average Δ: 0.58; 95% limits of agreement: -1.55, 2.71) or duty cycle (average Δ: 0.02; 95% limits of agreement: 0.01, 0.03). Tidal volumes and flow rates measured using XV were lower than those measured using the pitot tube flowmeter, particularly at the higher volume ranges with bilevel-assisted breathing. Under these conditions, a mixed-model based adjustment was applied to the XV-derived values of tidal volume and flow rate to obtain closer agreement with the pitot tube-derived values.

CONCLUSION

Radiographically obtained measures of ventilation with XV demonstrate a high degree of correlation with parameters of ventilation. If the accuracy of XV were also confirmed for assessing the regional distribution of ventilation, it would provide information that goes beyond the scope of conventional pulmonary function tests or static radiographic assessments.

Association of x-ray velocimetry (XV) ventilation analysis compared to spirometry

Introduction

X-ray Velocimetry (XV) ventilation analysis is a 4-dimensional imaging-based method for quantifying regional ventilation, aiding in the assessment of lung function. We examined the performance characteristics of XV ventilation analysis by examining correlation to spirometry and measurement repeatability.

Methods

XV analysis was assessed in 27 patients receiving thoracic radiotherapy for non-lung cancer malignancies. Measurements were obtained pre-treatment and at 4 and 12-months post-treatment. XV metrics such as ventilation defect percent (VDP) and regional ventilation heterogeneity (VH) were compared to spirometry at each time point, using correlation analysis. Repeatability was assessed between multiple runs of the analysis algorithm, as well as between multiple breaths in the same patient. Change in VH and VDP in a case series over 12 months was used to determine effect size and estimate sample sizes for future studies.

Results

VDP and VH were found to significantly correlate with FEV₁ and FEV₁/FVC (range: -0.36 to -0.57; p < 0.05). Repeatability tests demonstrated that VDP and VH had less than 2% variability within runs and less than 8% change in metrics between breaths. Three cases were used to illustrate the advantage of XV over spirometry, where XV indicated a change in lung function that was either undetectable or delayed in detection by spirometry. Case A demonstrated an improvement in XV metrics over time despite stable spirometric values. Case B demonstrated a decline in XV metrics as early as 4-months, although spirometric values did not change until 12-months. Case C demonstrated a decline in XV metrics at 12 months post-treatment while spirometric values remained normal throughout the study. Based on the effect sizes in each case, sample sizes ranging from 10 to 38 patients would provide 90% power for future studies aiming to detect similar changes.

Conclusions

The performance and safety of XV analysis make it ideal for both clinical and research applications across most lung indications. Our results support continued research and provide a basis for powering future studies using XV as an endpoint to examine lung health and determine therapeutic efficacy.

Functional imaging for assessing regional lung ventilation in preclinical and clinical research

Dynamic heterogeneity in lung ventilation is an important measure of pulmonary function and may be characteristic of early pulmonary disease. While standard indices like spirometry, body plethysmography, and blood gases have been utilized to assess lung function, they do not provide adequate information on regional ventilatory distribution nor function assessments of ventilation during the respiratory cycle. Emerging technologies such as xenon CT, volumetric CT, functional MRI and X-ray velocimetry can assess regional ventilation using non-invasive radiographic methods that may complement current methods of assessing lung function. As a supplement to current modalities of pulmonary function assessment, functional lung imaging has the potential to identify respiratory disease phenotypes with distinct natural histories. Moreover, these novel technologies may offer an optimal strategy to evaluate the effectiveness of novel therapies and therapies targeting localized small airways disease in preclinical and clinical research. In this review, we aim to discuss the features of functional lung imaging, as well as its potential application and limitations to adoption in research.

Deep learning radiomics-based preoperative prediction of recurrence in chronic rhinosinusitis

Chronic rhinosinusitis (CRS) is characterized by poor prognosis and propensity for recurrence even after surgery. Identification of those CRS patients with high risk of relapse preoperatively will contribute to personalized treatment recommendations. In this paper, we proposed a multi-task deep learning network for sinus segmentation and CRS recurrence prediction simultaneously to develop and validate a deep learning radiomics-based nomogram for preoperatively predicting recurrence in CRS patients who needed surgical treatment. 265 paranasal sinuses computed tomography (CT) images of CRS from two independent medical centers were analyzed to build and test models. The sinus segmentation model achieved good segmentation results. Furthermore, the nomogram combining a deep learning signature and clinical factors also showed excellent recurrence prediction ability for CRS. Our study not only facilitates a technique for sinus segmentation but also provides a noninvasive method for preoperatively predicting recurrence in patients with CRS.