COVID-19 Pneumonia and Lung Cancer: A Challenge for the Radiological Review of the Main Radiological Features, Differential Diagnosis and Overlapping Pathologies

A Thorough Review of the Clinical Applications of Artificial Intelligence in Lung Cancer

According to data from the World Health Organization (WHO), lung cancer is becoming a global epidemic. It is particularly high in the list of the leading causes of death not only in developed countries, but also worldwide; furthermore, it holds the leading place in terms of cancer-related mortality. Nevertheless, many breakthroughs have been made the last two decades regarding its management, with one of the most prominent being the implementation of artificial intelligence (AI) in various aspects of disease management. We included 473 papers in this thorough review, most of which have been published during the last 5-10 years, in order to describe these breakthroughs. In screening programs, AI is capable of not only detecting suspicious lung nodules in different imaging modalities-such as chest X-rays, computed tomography (CT), and positron emission tomography (PET) scans-but also discriminating between benign and malignant nodules as well, with success rates comparable to or even better than those of experienced radiologists. Furthermore, AI seems to be able to recognize biomarkers that appear in patients who may develop lung cancer, even years before this event. Moreover, it can also assist pathologists and cytologists in recognizing the type of lung tumor, as well as specific histologic or genetic markers that play a key role in treating the disease. Finally, in the treatment field, AI can guide in the development of personalized options for lung cancer patients, possibly improving their prognosis.

A non-enhanced CT-based deep learning diagnostic system for COVID-19 infection at high risk among lung cancer patients

Background

Pneumonia and lung cancer have a mutually reinforcing relationship. Lung cancer patients are prone to contracting COVID-19, with poorer prognoses. Additionally, COVID-19 infection can impact anticancer treatments for lung cancer patients. Developing an early diagnostic system for COVID-19 pneumonia can help improve the prognosis of lung cancer patients with COVID-19 infection.

Method

This study proposes a neural network for COVID-19 diagnosis based on non-enhanced CT scans, consisting of two 3D convolutional neural networks (CNN) connected in series to form two diagnostic modules. The first diagnostic module classifies COVID-19 pneumonia patients from other pneumonia patients, while the second diagnostic module distinguishes severe COVID-19 patients from ordinary COVID-19 patients. We also analyzed the correlation between the deep learning features of the two diagnostic modules and various laboratory parameters, including KL-6.

Result

The first diagnostic module achieved an accuracy of 0.9669 on the training set and 0.8884 on the test set, while the second diagnostic module achieved an accuracy of 0.9722 on the training set and 0.9184 on the test set. Strong correlation was observed between the deep learning parameters of the second diagnostic module and KL-6.

Conclusion

Our neural network can differentiate between COVID-19 pneumonia and other pneumonias on CT images, while also distinguishing between ordinary COVID-19 patients and those with white lung. Patients with white lung in COVID-19 have greater alveolar damage compared to ordinary COVID-19 patients, and our deep learning features can serve as an imaging biomarker.

Detection of subsolid nodules on chest CT scans during the COVID-19 pandemic

OBJECTIVE

To investigate the detection of subsolid nodules (SSNs) on chest CT scans of outpatients before and during the COVID-19 pandemic, as well as to correlate the imaging findings with epidemiological data. We hypothesized that (pre)malignant nonsolid nodules were underdiagnosed during the COVID-19 pandemic because of an overlap of imaging findings between SSNs and COVID-19 pneumonia.

METHODS

This was a retrospective study including all chest CT scans performed in adult outpatients (> 18 years of age) in September of 2019 (i.e., before the COVID-19 pandemic) and in September of 2020 (i.e., during the COVID-19 pandemic). The images were reviewed by a thoracic radiologist, and epidemiological data were collected from patient-filled questionnaires and clinical referrals. Regression models were used in order to control for confounding factors.

RESULTS

A total of 650 and 760 chest CT scans were reviewed for the 2019 and 2020 samples, respectively. SSNs were found in 10.6% of the patients in the 2019 sample and in 7.9% of those in the 2020 sample (p = 0.10). Multiple SSNs were found in 23 and 11 of the patients in the 2019 and 2020 samples, respectively. Women constituted the majority of the study population. The mean age was 62.8 ± 14.8 years in the 2019 sample and 59.5 ± 15.1 years in the 2020 sample (p < 0.01). COVID-19 accounted for 24% of all referrals for CT examination in 2020.

CONCLUSIONS

Fewer SSNs were detected on chest CT scans of outpatients during the COVID-19 pandemic than before the pandemic, although the difference was not significant. In addition to COVID-19, the major difference between the 2019 and 2020 samples was the younger age in the 2020 sample. We can assume that fewer SSNs will be detected in a population with a higher proportion of COVID-19 suspicion or diagnosis.

Prognostic Factors and Outcomes in Advanced Stage Lung Cancer Patients with COVID-19 Omicron Variant Infection

Background

We study the characteristics and outcomes in lung cancer patients with COVID-19 Omicron variant infection.

Methods

Hospitalized lung cancer patients with advanced-stage disease and laboratory-confirmed COVID-19 Omicron infection were included. Pneumonitis involving at least 25% of lung parenchyma on CT scans, accompanied by symptoms and oxygen saturation below 93%, were criteria for enrollment. Pneumonitis severity was graded using CTCAE v5.0. Treatment included Paxlovid, prednisolone, anticoagulation, and ventilation. Initial data, radiographic findings, and outcomes were compared. Logistic regression was employed to determine risk factors for in-hospital mortality.

Results

Fifteen patients (median age: 65 years; 80.0% males) were included. 73.3% improved and were discharged, 20.0% died, and 6.7% remained intubated. Initial symptoms included cough (100.0%), fever (73.3%), and shortness of breath (53.3%). Symptoms resolved in discharged patients. Median fever duration was 3.5 days, and respiratory symptom recovery took 26 days. Three patients died due to respiratory failure from Omicron pneumonia. Lower oxygen saturation, reduced lymphocyte/neutrophil ratio on day 7, and diffuse bilateral lung lesions were poor prognostic factors.

Conclusion

This study underscores the importance of prompt intervention and early diagnosis for lung cancer patients infected with the COVID-19 Omicron variant. Lower oxygen saturation, decreased lymphocyte/neutrophil ratio on day 7, and diffuse lung lesions on CT scans were associated with worse outcomes. Clinicians should prioritize timely and comprehensive management to improve survival rates in this population.

Immune Checkpoint Inhibitors and Tuberculosis Infection in Lung Cancer: A Case Series and Systematic Review With Pooled Analysis

The association between immune checkpoint inhibitors (ICIs) and tuberculosis (TB) infection in patients with lung cancer remains largely elusive. We performed a systematic review and conducted a retrospective analysis of TB infection in patients with lung cancer and ICI exposure to assess the clinical characteristics and outcomes using PubMed, EMBASE, and the Cochrane Library. The time interval from ICI administration to diagnosis of TB between patients with and without a history of TB was compared using Kaplan-Meier analysis. A multivariate Cox regression model was used to identify potential risk factors associated with the time interval of TB development. Twenty-four studies including 53 patients with lung cancer were included. The median age of the patients was 64 years. Eight patients had a history of TB. The median time interval from ICI administration to TB diagnosis was 3 months. In retrospective analysis, 5 (1.16%, 95%CI 0.38% to 2.68%) patients with lung cancer developed TB during ICI treatment. The median time interval was 10.4 months. In a pooled analysis, the median time interval in the without-TB and with-TB groups was 7.00 and 2.35 months, respectively (P = .034). Multivariate Cox regression analyses revealed a history of TB to be an independent factor affecting the time interval of TB activation in patients with lung cancer and ICI exposure (HR 3.59; 95%CI 1.17 to 11.02; P = .026). Therefore, TB infection should be considered in patients with lung cancer during or after ICI treatment. Moreover, we found TB history to be a positive risk factor for a shorter median time interval from ICI to TB diagnosis in patients with lung cancer receiving ICI.

Outcomes of Thoracoscopic Lobectomy after Recent COVID-19 Infection

BACKGROUND

The COVID-19 outbreak had a massive impact on lung cancer patients with the rise in the incidence and mortality of lung cancer.

METHODS

We evaluated whether a recent COVID-19 infection affected the outcome of patients undergoing thoracoscopic lobectomy for lung cancer using a retrospective observational mono-centric study conducted between January 2020 and August 2022. Postoperative complications and 90-day mortality were reported. We compared lung cancer patients with a recent history of COVID-19 infection prior to thoracoscopic lobectomy to those without recent COVID-19 infection. Univariable and multivariable analyses were performed.

RESULTS

One hundred and fifty-three consecutive lung cancer patients were enrolled. Of these 30 (19%), had a history of recent COVID-19 infection prior to surgery. COVID-19 was not associated with a higher complication rate or 90-day mortality. Patients with recent COVID-19 infection had more frequent pleural adhesions (p = 0.006). There were no differences between groups regarding postoperative complications, conversion, drain removal time, total drainage output, and length of hospital stay.

CONCLUSIONS

COVID-19 infection did not affect the outcomes of thoracoscopic lobectomy for lung cancer. The treatment of these patients should not be delayed in case of recent COVID-19 infection and should not differ from that of the general population.

Habitat Imaging Biomarkers for Diagnosis and Prognosis in Cancer Patients Infected with COVID-19

OBJECTIVES

Cancer patients have worse outcomes from the COVID-19 infection and greater need for ventilator support and elevated mortality rates than the general population. However, previous artificial intelligence (AI) studies focused on patients without cancer to develop diagnosis and severity prediction models. Little is known about how the AI models perform in cancer patients. In this study, we aim to develop a computational framework for COVID-19 diagnosis and severity prediction particularly in a cancer population and further compare it head-to-head to a general population.

METHODS

We have enrolled multi-center international cohorts with 531 CT scans from 502 general patients and 420 CT scans from 414 cancer patients. In particular, the habitat imaging pipeline was developed to quantify the complex infection patterns by partitioning the whole lung regions into phenotypically different subregions. Subsequently, various machine learning models nested with feature selection were built for COVID-19 detection and severity prediction.

RESULTS

These models showed almost perfect performance in COVID-19 infection diagnosis and predicting its severity during cross validation. Our analysis revealed that models built separately on the cancer population performed significantly better than those built on the general population and locked to test on the cancer population. This may be because of the significant difference among the habitat features across the two different cohorts.

CONCLUSIONS

Taken together, our habitat imaging analysis as a proof-of-concept study has highlighted the unique radiologic features of cancer patients and demonstrated effectiveness of CT-based machine learning model in informing COVID-19 management in the cancer population.

Dynamic change of COVID-19 lung infection evaluated using co-registration of serial chest CT images

Purpose

To evaluate the volumetric change of COVID-19 lesions in the lung of patients receiving serial CT imaging for monitoring the evolution of the disease and the response to treatment.

Materials and methods

A total of 48 patients, 28 males and 20 females, who were confirmed to have COVID-19 infection and received chest CT examination, were identified. The age range was 21-93 years old, with a mean of 54 ± 18 years. Of them, 33 patients received the first follow-up (F/U) scan, 29 patients received the second F/U scan, and 11 patients received the third F/U scan. The lesion region of interest (ROI) was manually outlined. A two-step registration method, first using the Affine alignment, followed by the non-rigid Demons algorithm, was developed to match the lung areas on the baseline and F/U images. The baseline lesion ROI was mapped to the F/U images using the obtained geometric transformation matrix, and the radiologist outlined the lesion ROI on F/U CT again.

Results

The median (interquartile range) lesion volume (cm³) was 30.9 (83.1) at baseline CT exam, 18.3 (43.9) at first F/U, 7.6 (18.9) at second F/U, and 0.6 (19.1) at third F/U, which showed a significant trend of decrease with time. The two-step registration could significantly decrease the mean squared error (MSE) between baseline and F/U images with p < 0.001. The method could match the lung areas and the large vessels inside the lung. When using the mapped baseline ROIs as references, the second-look ROI drawing showed a significantly increased volume, p < 0.05, presumably due to the consideration of all the infected areas at baseline.

Conclusion

The results suggest that the registration method can be applied to assist in the evaluation of longitudinal changes of COVID-19 lesions on chest CT.