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.
ABSTRACT
Vaccination-associated adenopathy is a frequent imaging finding after administration of COVID-19 vaccines that may lead to a diagnostic conundrum in patients with manifest or suspected cancer, in whom it may be indistinguishable from malignant nodal involvement. To help the medical community address this concern in the absence of studies and evidence-based guidelines, this special report offers recommendations developed by a multidisciplinary panel of experts from three of the leading tertiary care cancer centers in the United States. According to these recommendations, some routine imaging examinations, such as those for screening, should be scheduled before or at least 6 weeks after the final vaccination dose to allow for any reactive adenopathy to resolve. However, there should be no delay of other clinically indicated imaging (eg, for acute symptoms, short-interval treatment monitoring, urgent treatment planning or complications) due to prior vaccination. The vaccine should be administered on the side contralateral to the primary or suspected cancer, and both doses should be administered in the same arm. Vaccination information-date(s) administered, injection site(s), laterality, and type of vaccine-should be included in every preimaging patient questionnaire, and this information should be made readily available to interpreting radiologists. Clear and effective communication between patients, radiologists, referring physician teams, and the general public should be considered of the highest priority when managing adenopathy in the setting of COVID-19 vaccination.