Radiomics and artificial intelligence for precision medicine in lung cancer treatment.

Lung cancer is the leading cause of cancer-related deaths worldwide. It exhibits, at the mesoscopic scale, phenotypic characteristics that are generally indiscernible to the human eye but can be captured non-invasively on medical imaging as radiomic features, which can form a high dimensional data space amenable to machine learning. Radiomic features can be harnessed and used in an artificial intelligence paradigm to risk stratify patients, and predict for histological and molecular findings, and clinical outcome measures, thereby facilitating precision medicine for improving patient care. Compared to tissue sampling-driven approaches, radiomics-based methods are superior for being non-invasive, reproducible, cheaper, and less susceptible to intra-tumoral heterogeneity. This review focuses on the application of radiomics, combined with artificial intelligence, for delivering precision medicine in lung cancer treatment, with discussion centered on pioneering and groundbreaking works, and future research directions in the area.

Lung Parenchymal and Tracheal CT Morphology: Evaluation before and after Bariatric Surgery.

Background There is significant pulmonary functional deficit related to obesity, but no prospective CT studies have evaluated the effects of obesity on the lungs and trachea. Purpose To evaluate lung parenchymal and tracheal CT morphology before and 6 months after bariatric surgery, with functional and symptomatic correlation. Materials and Methods A prospective longitudinal study of 51 consecutive individuals referred for bariatric surgery was performed (from November 2011 to November 2013). All individuals had undergone limited (three-location) inspiratory and end-expiratory thoracic CT before and after surgery, with concurrent pulmonary function testing, body mass index calculation, and modified Medical Research Council (mMRC) dyspnea scale and Epworth scoring. Two thoracic radiologists scored the CT extent of mosaic attenuation, end-expiratory air trapping, and tracheal shape. The inspiratory and end-expiratory cross-sectional areas of the trachea were measured. The paired t test or Wilcoxon signed-rank test was used for pre- and postsurgical comparisons. Spearman correlation and logistic regression were used to evaluate correlations between CT findings and functional and symptom indexes. Results A total of 51 participants (mean age, 52 years ± 8 [standard deviation]; 20 men) were evaluated. Before surgery, air trapping extent correlated most strongly with decreased total lung capacity (Spearman rank correlation coefficient [rs] = -0.40, P = .004). After surgery, there were decreases in percentage mosaic attenuation (0% [interquartile range {IQR}: 0%-2.5%] vs 0% [IQR: 0%-0%], P < .001), air trapping (9.6% [IQR: 5.8%-15.8%] vs 2.5% [IQR: 0%-6.7%], P < .001), and tracheal collapse (201 mm2 [IQR: 181-239 mm2] vs 229 mm2 [186-284 mm2], P < .001). After surgery, mMRC dyspnea score change correlated positively with air trapping extent change (rs = 0.46, P = .001) and end-expiratory tracheal shape change (rs = 0.40, P = .01). At multivariable analysis, air trapping was the main determinant for decreased dyspnea after surgery (odds ratio, 1.2; 95% confidence interval: 1.1, 1.2; P = .03). Conclusion Dyspnea improved in obese participants after weight reduction, which correlated with less tracheal collapse and air trapping at end-expiration chest CT. © RSNA, 2020 Online supplemental material is available for this article.

Tracheal CT morphology: correlation with distribution and extent of thoracic adipose tissue.

OBJECTIVE: To evaluate the relationship between adipose tissue measurements and anterior bowing of the posterior tracheal wall in a large nonselected group of patients undergoing CT pulmonary angiography (CTPA). METHODS: Consecutive patients undergoing CTPA over a 4-month period were analyzed retrospectively. Using an adapted scoring system (posterior bowing, flattening, mild/moderate or severe anterior bowing of the posterior tracheal membrane), the axial morphology and cross-sectional area of the trachea at the narrowest point and 1 cm above the aortic arch were evaluated. Measurements of adipose tissue were taken (anterior mediastinal fat width, sagittal upper abdominal diameter and subcutaneous fat thickness at the level of the costophrenic angle). Relationships between tracheal morphology and measurements of adipose tissue were analyzed. RESULTS: 296 patients were included (120 males, 176 females, mean age 59 years, range 19-90). Severe anterior bowing of the posterior tracheal wall correlated with increasing sagittal upper abdominal diameter (p = 0.002). Mild/moderate and severe anterior bowing of the posterior tracheal wall correlated with increasing mediastinal fat width (p = 0.000 and p = 0.031, respectively). Tracheal cross-sectional area was inversely correlated with increasing subcutaneous fat thickness (p = 0.022). CONCLUSION: The findings demonstrate a statistically significant relationship between CT tracheal morphology and adipose tissue measurements in a large nonselected population. KEY POINTS: • There is increasing interest in the effects of obesity on the airways. • A relationship between anterior bowing of the posterior tracheal wall and adipose tissue measurements is demonstrated. • This is of clinical relevance in an increasingly obese population. • Further studies with functional correlation are required.

A Novel Radiogenomics Biomarker for Predicting Treatment Response and Pneumotoxicity From Programmed Cell Death Protein or Ligand-1 Inhibition Immunotherapy in NSCLC.

INTRODUCTION: Patient selection for checkpoint inhibitor immunotherapy is currently guided by programmed death-ligand 1 (PD-L1) expression obtained from immunohistochemical staining of tumor tissue samples. This approach is susceptible to limitations resulting from the dynamic and heterogeneous nature of cancer cells and the invasiveness of the tissue sampling procedure. To address these challenges, we developed a novel computed tomography (CT) radiomic-based signature for predicting disease response in patients with NSCLC undergoing programmed cell death protein 1 (PD-1) or PD-L1 checkpoint inhibitor immunotherapy. METHODS: This retrospective study comprises a total of 194 patients with suitable CT scans out of 340. Using the radiomic features computed from segmented tumors on a discovery set of 85 contrast-enhanced chest CTs of patients diagnosed with having NSCLC and their CD274 count, RNA expression of the protein-encoding gene for PD-L1, as the response vector, we developed a composite radiomic signature, lung cancer immunotherapy-radiomics prediction vector (LCI-RPV). This was validated in two independent testing cohorts of 66 and 43 patients with NSCLC treated with PD-1 or PD-L1 inhibition immunotherapy, respectively. RESULTS: LCI-RPV predicted PD-L1 positivity in both NSCLC testing cohorts (area under the curve [AUC] = 0.70, 95% confidence interval [CI]: 0.57-0.84 and AUC = 0.70, 95% CI: 0.46-0.94). In one cohort, it also demonstrated good prediction of cases with high PD-L1 expression exceeding key treatment thresholds (>50%: AUC = 0.72, 95% CI: 0.59-0.85 and >90%: AUC = 0.66, 95% CI: 0.45-0.88), the tumor's objective response to treatment at 3 months (AUC = 0.68, 95% CI: 0.52-0.85), and pneumonitis occurrence (AUC = 0.64, 95% CI: 0.48-0.80). LCI-RPV achieved statistically significant stratification of the patients into a high- and low-risk survival group (hazard ratio = 2.26, 95% CI: 1.21-4.24, p = 0.011 and hazard ratio = 2.45, 95% CI: 1.07-5.65, p = 0.035). CONCLUSIONS: A CT radiomics-based signature developed from response vector CD274 can aid in evaluating patients' suitability for PD-1 or PD-L1 checkpoint inhibitor immunotherapy in NSCLC.

Chest CT features and functional correlates of COVID-19 at 3 months and 12 months follow-up.

Long-term pulmonary sequelae of Coronavirus 2019 (COVID-19) remain unclear. Thus, we aimed to establish post-COVID-19 temporal changes in chest computed tomography (CT) features of pulmonary fibrosis and to investigate associations with respiratory symptoms and physiological parameters at 3 and 12 months' follow-up. Adult patients who attended our initial COVID-19 follow-up service and developed chest CT features of interstitial lung disease, in addition to cases identified using British Society of Thoracic Imaging codes, were evaluated retrospectively. Clinical data were gathered on respiratory symptoms and physiological parameters at baseline, 3 months, and 12 months. Corresponding chest CT scans were reviewed by two thoracic radiologists. Associations between CT features and functional correlates were estimated using random effects logistic or linear regression adjusted for age, sex and body mass index. In total, 58 patients were assessed. No changes in reticular pattern, honeycombing, traction bronchiectasis/bronchiolectasis index or pulmonary distortion were observed. Subpleural curvilinear lines were associated with lower odds of breathlessness over time. Parenchymal bands were not associated with breathlessness or impaired lung function overall. Based on our results, we conclude that post-COVID-19 chest CT features of irreversible pulmonary fibrosis remain static over time; other features either resolve or remain unchanged. Subpleural curvilinear lines do not correlate with breathlessness. Parenchymal bands are not functionally significant. An awareness of the different potential functional implications of post-COVID-19 chest CT changes is important in the assessment of patients who present with multi-systemic sequelae of COVID-19 infection.

Tumor and local lymphoid tissue interaction determines prognosis in high-grade serous ovarian cancer.

Tertiary lymphoid structure (TLS) is associated with prognosis in copy-number-driven tumors, including high-grade serous ovarian cancer (HGSOC), although the function of TLS and its interaction with copy-number alterations in HGSOC are not fully understood. In the current study, we confirm that TLS-high HGSOC patients show significantly better progression-free survival (PFS). We show that the presence of TLS in HGSOC tumors is associated with B cell maturation and cytotoxic tumor-specific T cell activation and proliferation. In addition, the copy-number loss of IL15 and CXCL10 may limit TLS formation in HGSOC; a list of genes that may dysregulate TLS function is also proposed. Last, a radiomics-based signature is developed to predict the presence of TLS, which independently predicts PFS in both HGSOC patients and immune checkpoint inhibitor (ICI)-treated non-small cell lung cancer (NSCLC) patients. Overall, we reveal that TLS coordinates intratumoral B cell and T cell response to HGSOC tumor, while the cancer genome evolves to counteract TLS formation and function.

Chronic lung disease in adolescents with delayed diagnosis of vertically acquired HIV infection.

BACKGROUND: Long-term survivors of vertically acquired human immunodeficiency virus (HIV) infection are reaching adolescence in large numbers in Africa and are at high risk of delayed diagnosis and chronic complications of untreated HIV infection. Chronic respiratory symptoms are more common than would be anticipated based on the HIV literature. METHODS: Consecutive adolescents with presumed vertically acquired HIV attending 2 HIV care clinics in Harare, Zimbabwe, were recruited and assessed with clinical history and examination, CD4 count, pulmonary function tests, Doppler echocardiography, and chest radiography (CXR). Those with suspected nontuberculous chronic lung disease (CLD) were scanned using high-resolution computed tomography (HRCT). RESULTS: Of 116 participants (43% male; mean age, 14 ± 2.6 years, mean age at HIV diagnosis, 12 years), 69% were receiving antiretroviral therapy. Chronic cough and reduced exercise tolerance were reported by 66% and 21% of participants, respectively; 41% reported multiple respiratory tract infections in the previous year, and 10% were clubbed. More than 40% had hypoxemia at rest (13%) or on exercise (29%), with pulmonary hypertension (mean pulmonary artery pressure >25 mm Hg) in 7%. Forced expiratory volume in 1 second (FEV(1)) was <80% predicted in 45%, and 47% had subtle CXR abnormalities. The predominant HRCT pattern was decreased attenuation as part of a mosaic attenuation pattern (31 of 56 [55%]), consistent with small airway disease and associated with bronchiectasis (Spearman correlation coefficient (r(2) = 0.8) and reduced FEV(1) (r(2) = -0.26). CONCLUSIONS: Long-term survivors of vertically acquired HIV in Africa are at high risk of a previously undescribed small airway disease, with >40% of unselected adolescent clinic attendees meeting criteria for severe hypoxic CLD. This condition is not obvious at rest. Etiology, prognosis, and response to treatment are currently unknown.

Symptomatic, biochemical and radiographic recovery in patients with COVID-19.

BACKGROUND: The symptoms, radiography, biochemistry and healthcare utilisation of patients with COVID-19 following discharge from hospital have not been well described. METHODS: Retrospective analysis of 401 adult patients attending a clinic following an index hospital admission or emergency department attendance with COVID-19. Regression models were used to assess the association between characteristics and persistent abnormal chest radiographs or breathlessness. RESULTS: 75.1% of patients were symptomatic at a median of 53 days post discharge and 72 days after symptom onset and chest radiographs were abnormal in 47.4%. Symptoms and radiographic abnormalities were similar in PCR-positive and PCR-negative patients. Severity of COVID-19 was significantly associated with persistent radiographic abnormalities and breathlessness. 18.5% of patients had unscheduled healthcare visits in the 30 days post discharge. CONCLUSIONS: Patients with COVID-19 experience persistent symptoms and abnormal blood biomarkers with a gradual resolution of radiological abnormalities over time. These findings can inform patients and clinicians about expected recovery times and plan services for follow-up of patients with COVID-19.

Towards nationally curated data archives for clinical radiology image analysis at scale: Learnings from national data collection in response to a pandemic.

The prevalence of the coronavirus SARS-CoV-2 disease has resulted in the unprecedented collection of health data to support research. Historically, coordinating the collation of such datasets on a national scale has been challenging to execute for several reasons, including issues with data privacy, the lack of data reporting standards, interoperable technologies, and distribution methods. The coronavirus SARS-CoV-2 disease pandemic has highlighted the importance of collaboration between government bodies, healthcare institutions, academic researchers and commercial companies in overcoming these issues during times of urgency. The National COVID-19 Chest Imaging Database, led by NHSX, British Society of Thoracic Imaging, Royal Surrey NHS Foundation Trust and Faculty, is an example of such a national initiative. Here, we summarise the experiences and challenges of setting up the National COVID-19 Chest Imaging Database, and the implications for future ambitions of national data curation in medical imaging to advance the safe adoption of artificial intelligence in healthcare.

Biopsy-proved idiopathic pulmonary fibrosis: spectrum of nondiagnostic thin-section CT diagnoses.

PURPOSE: To document the spectrum of misleading thin-section computed tomographic (CT) diagnoses in patients with biopsy-proved idiopathic pulmonary fibrosis (IPF). MATERIALS AND METHODS: This study had institutional review board approval, and patient consent was not required. Three observers, blinded to any clinical information and the purpose of the study, recorded thin-section CT differential diagnoses and assigned a percentage likelihood to each for a group of 123 patients (79 men, 44 women; age range, 27-82 years) with various chronic interstitial lung diseases, including a core group of 55 biopsy-proved cases of IPF. Patients with IPF in the core group, in whom IPF was diagnosed as low-grade probability (<30%) by at least two observers, were considered to have atypical IPF cases, and the alternative diagnoses were analyzed further. RESULTS: Thirty-four (62%) of 55 biopsy-proved IPF cases were regarded as alternative diagnoses. In these atypical IPF cases, the first-choice diagnoses, expressed with high degree of probability, were nonspecific interstitial pneumonia (NSIP; 18 [53%] of 34), chronic hypersensitivity pneumonitis (HP; four [12%] of 34), sarcoidosis (three [9%] of 34), and organizing pneumonia (one [3%] of 34); in eight (23%) of 34 cases, no single diagnosis was favored by more than one observer. Frequent differential diagnoses, although not always the first-choice diagnosis, were NSIP (n = 29), chronic HP (n = 23), and sarcoidosis (n = 9). CONCLUSION: In the correct clinical setting, a diagnosis of IPF is not excluded by thin-section CT appearances more suggestive of NSIP, chronic HP, or sarcoidosis. (c) RSNA, 2010.

Lung morphology in the elderly: comparative CT study of subjects over 75 years old versus those under 55 years old.

PURPOSE: To describe thin-section pulmonary computed tomographic (CT) features in asymptomatic elderly individuals. MATERIALS AND METHODS: Institutional review board approval was given, and informed consent was obtained. Two study groups (older group, over 75 years of age; younger group, under 55 years) were prospectively identified from outpatient requests for CT of the abdomen or brain. Fifty-six consecutive volunteers (older group: n = 40, 18 men, 22 women; younger group: n = 16, eight men, eight women) with no known respiratory disease were included. Prone thin-section CT imaging was performed, and two observers independently scored images for the presence and extent of CT features (including reticular pattern, ground glass opacity, and thin-walled cystic air spaces). Group comparisons were made, and logistic regression analysis was used to assess relationships between CT findings and age and smoking history. RESULTS: A limited predominantly subpleural basal reticular pattern was identified in the majority (24 of 40, 60%) of individuals in the older group and was absent (zero of 16) in the younger group (P < .001). Cysts were seen in 10 (25%) of the 40 subjects in the older group but were seen in none of the subjects in the younger group (P = .02). Bronchial dilation and wall thickening were also seen significantly more frequently (P < .001) in the older group (24 [60%] and 22 [55%] of 40, respectively) than in the younger group (both one [6%] of 16). All findings were independent of pack-year smoking history with multiple logistic regression analysis. CONCLUSION: Thin-section CT findings usually associated with interstitial lung disease are frequently seen in asymptomatic elderly individuals and are absent in younger subjects. Therefore, these findings may not necessarily represent clinically relevant disease.

Interstitial lung disease in systemic sclerosis: a simple staging system.

RATIONALE: In interstitial lung disease complicating systemic sclerosis (SSc-ILD), the optimal prognostic use of baseline pulmonary function tests (PFTs) and high-resolution computed tomography (HRCT) is uncertain. OBJECTIVES: To construct a readily applicable prognostic algorithm in SSc-ILD, integrating PFTs and HRCT. METHODS: The prognostic value of baseline PFT and HRCT variables was quantified in patients with SSc-ILD (n = 215) against survival and serial PFT data. MEASUREMENTS AND MAIN RESULTS: Increasingly extensive disease on HRCT was a powerful predictor of mortality (P < 0.0005), with an optimal extent threshold of 20%. In patients with HRCT extent of 10-30% (termed indeterminate disease), an FVC threshold of 70% was an adequate prognostic substitute. On the basis of these observations, SSc-ILD was staged as limited disease (minimal disease on HRCT or, in indeterminate cases, FVC >or= 70%) or extensive disease (severe disease on HRCT or, in indeterminate cases, FVC < 70%). This system (hazards ratio [HR], 3.46; 95% confidence interval [CI], 2.19-5.46; P < 0.0005) was more discriminatory than an HRCT threshold of 20% (HR, 2.48; 95% CI, 1.57-3.92; P < 0.0005) or an FVC threshold of 70% (HR, 2.11; 95% CI, 1.34-3.32; P = 0.001). The system was evaluated by four trainees and four practitioners, with minimal and severe disease on HRCT defined as clearly < 20% or clearly > 20%, respectively, and the use of an FVC threshold of 70% in indeterminate cases. The staging system was predictive of mortality for all scorers, with prognostic separation higher for practitioners (HR, 3.39-3.82) than trainees (HR, 1.87-2.60). CONCLUSIONS: An easily applicable limited/extensive staging system for SSc-ILD, based on combined evaluation with HRCT and PFTs, provides discriminatory prognostic information.

Morphology of the Aging Lung on Computed Tomography.

As the population becomes older, recognition of the pulmonary computed tomography (CT) features of "normal" aging is likely to become increasingly important to differentiate from clinically significant disease. Several studies have evaluated the appearances of the lung parenchyma and large and small airways in asymptomatic older individuals and found increased prevalence of cysts, reticular pattern, air trapping, bronchial dilation, and bronchial wall thickening in older individuals compared with younger individuals. Objective differences in CT lung parenchymal attenuation and complexity have also been described. The CT appearances of the aging lung are illustrated, and the histopathologic and functional changes are discussed.

Unilateral lymphangioleiomyomatosis.

Pulmonary involvement in tuberous sclerosis complex (TSC) resembles lymphangioleiomyomatosis (LAM) in its clinical, radiologic, and histopathological features. Typical high-resolution computed tomography (HRCT) findings are of bilateral thin-walled cysts symmetrically throughout both lungs, with associated increase in lung volumes. Atypical cases have been described; and we report a case of biopsy proven, focal unilateral disease. The presence of nodules has been reported in association with TSC that histologically are composed of proliferated type II pneumocytes. We discuss other atypical cases of TSC and sporadic LAM and review current concepts of the pathogenesis of the 2 diseases, with reference to our case.

Imaging appearance of thoracic amyloidosis.

Amyloidosis is a disease caused by the deposition of abnormal proteins within extracellular soft tissues, and affects the respiratory tract in 50% of cases. Pulmonary involvement may be secondary to systemic disease or due to the accumulation of locally produced amyloid, and this differentiation has important prognostic and therapeutic implications. This pictorial essay, using cases of biopsy-proven respiratory tract amyloidosis, aims to depict the spectrum of imaging findings, and those of CT in particular, that can be of use in distinguishing between the 2 typical patterns of the disease.

Prolonged B cell depletion with rituximab is effective in treating refractory pulmonary granulomatous inflammation in granulomatosis with polyangiitis (GPA).

Pulmonary nodule formation is a frequent feature of granulomatosis with polyangiitis (GPA). Traditional induction therapy includes methotrexate or cyclophosphamide, however, pulmonary nodules generally respond slower than vasculitic components of disease. Efficacy of rituximab (RTX) solely for the treatment of pulmonary nodules has not been assessed. In this observational cohort study, we report patient outcomes with RTX in GPA patients with pulmonary nodules who failed to achieve remission following conventional immunosuppression. Patients (n = 5) with persistent pulmonary nodules were identified from our clinic database and retrospectively evaluated. Systemic manifestations, inflammatory markers, disease activity, concurrent immunosuppression, and absolute B cell numbers were recorded pre-RTX and at 6 monthly intervals following treatment. Chest radiographs at each time point were scored by an experienced radiologist, blinded to clinical details. Five patients with GPA and PR3-ANCA were evaluated (2 male, 3 female), mean age 34 (22-52) years. Pulmonary nodules (median 4, range 2-6), with or without cavitation were present in all patients. RTX induced initial B cell depletion (<5 cells/µL) in all patients but re-population was observed in 3 patients. Repeated RTX treatment in these 3 and persistent B cell depletion in the whole cohort was associated with further significant radiological improvement. Radiographic scoring at each time interval showed reduction in both number of nodules (P =  <0.0001) and largest nodule diameter (P =  <0.0001) in all patients for at least 18 months following B cell depletion. In summary, RTX therapy induces resolution of pulmonary granulomatous inflammation in GPA following prolonged B cell depletion.