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

Simple Summary Patients with cancer are often immuno-compromised, and at a high risk of experiencing various COVID-19-associated complications compared to the general population. Additionally, COVID-19 infection and lung toxicities due to cancer treatments can present with similar radiologic abnormalities, such as ground glass opacities or patchy consolidation, which poses further challenges for developing AI algorithms. To fill the gap, we carried out the first imaging AI study to investigate the performance of habitat imaging technique for COVID-19 severity prediction and detection specifically in the cancer patient population, and further tested its performance in the general population based on multicenter datasets. The proposed COVID-19 habitat imaging models trained separately on the cancer cohort outperformed those AI models (including deep learning) trained on the multicenter general population by a significant margin. This suggests that publicly available COVID-19 AI models developed for the general population will not be optimally applied to cancer. Abstract 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.