Exploring the State of Cancer Imaging Research in Africa.

INTRODUCTION: The growing cancer burden in Africa demands urgent action. Medical imaging is crucial for cancer diagnosis and management and is an essential enabler of precision medicine. To understand the readiness for quantitative imaging analysis to support cancer management in Africa, we analyzed the utilization patterns of imaging modalities for cancer research across the continent. METHODS: We retrieved articles by systematically searching PubMed, using a combination of search terms {"Neoplasm"} AND {"Radiology" or "Diagnostic imaging" or "Radiography" or "Interventional Radiology" or "Radiotherapy" or "Radiation Oncology"} AND {Africa∗ or 54 African countries}. Articles describing cancer diagnosis or management in humans with the utilization of imaging were included. Exclusion criteria were review articles, non-English articles, publications before 2000, noncancer diagnoses, and studies conducted outside Africa. RESULTS: The analysis of diagnostic imaging in Africa revealed a diverse utilization pattern across different cancer types and regions. The literature search identified 107 publications on cancer imaging in Africa. The studies were carried out in 19 African countries on 12 different cancer types with 6 imaging modalities identified. Most cancer imaging research studies used multiple imaging modalities. Ultrasound was the most used distinct imaging modality and MRI was the least frequently used. Most research studies originated from Nigeria, South Africa, and Egypt. CONCLUSION: We demonstrate substantial variability in the presence of imaging modalities, widespread utilization of ultrasonography, and limited availability of advanced imaging modalities for cancer research.

COVID-19 mortality prediction in the intensive care unit with deep learning based on longitudinal chest X-rays and clinical data.

OBJECTIVES: We aimed to develop deep learning models using longitudinal chest X-rays (CXRs) and clinical data to predict in-hospital mortality of COVID-19 patients in the intensive care unit (ICU). METHODS: Six hundred fifty-four patients (212 deceased, 442 alive, 5645 total CXRs) were identified across two institutions. Imaging and clinical data from one institution were used to train five longitudinal transformer-based networks applying five-fold cross-validation. The models were tested on data from the other institution, and pairwise comparisons were used to determine the best-performing models. RESULTS: A higher proportion of deceased patients had elevated white blood cell count, decreased absolute lymphocyte count, elevated creatine concentration, and incidence of cardiovascular and chronic kidney disease. A model based on pre-ICU CXRs achieved an AUC of 0.632 and an accuracy of 0.593, and a model based on ICU CXRs achieved an AUC of 0.697 and an accuracy of 0.657. A model based on all longitudinal CXRs (both pre-ICU and ICU) achieved an AUC of 0.702 and an accuracy of 0.694. A model based on clinical data alone achieved an AUC of 0.653 and an accuracy of 0.657. The addition of longitudinal imaging to clinical data in a combined model significantly improved performance, reaching an AUC of 0.727 (p = 0.039) and an accuracy of 0.732. CONCLUSIONS: The addition of longitudinal CXRs to clinical data significantly improves mortality prediction with deep learning for COVID-19 patients in the ICU. KEY POINTS: • Deep learning was used to predict mortality in COVID-19 ICU patients. • Serial radiographs and clinical data were used. • The models could inform clinical decision-making and resource allocation.