Cascaded deep transfer learning on thoracic CT in COVID-19 patients treated with steroids

Abstract

. Purpose: Given the recent COVID-19 pandemic and its stress on global medical resources, presented here is the development of a machine intelligent method for thoracic computed tomography (CT) to inform management of patients on steroid treatment. Approach: Transfer learning has demonstrated strong performance when applied to medical imaging, particularly when only limited data are available. A cascaded transfer learning approach extracted quantitative features from thoracic CT sections using a fine-tuned VGG19 network. The extracted slice features were axially pooled to provide a CT-scan-level representation of thoracic characteristics and a support vector machine was trained to distinguish between patients who required steroid administration and those who did not, with performance evaluated through receiver operating characteristic (ROC) curve analysis. Least-squares fitting was used to assess temporal trends using the transfer learning approach, providing a preliminary method for monitoring disease progression. Results: In the task of identifying patients who should receive steroid treatments, this approach yielded an area under the ROC curve of and demonstrated significant separation between patients who received steroids and those who did not. Furthermore, temporal trend analysis of the prediction score matched expected progression during hospitalization for both groups, with separation at early timepoints prior to convergence near the end of the duration of hospitalization. Conclusions: The proposed cascade deep learning method has strong clinical potential for informing clinical decision-making and monitoring patient treatment.

Lessons learned in transitioning to AI in the medical imaging of COVID-19

“… 95 A severity score derived from lung images can be used for triaging the patient to decide home discharge, regular hospital admission, or intensive care unit admission. 96 The imaging characteristics can be used for prognosis assessment 97 and evaluation of the extent of disease, 11 and it has potential to predict the length of hospital stay. 98 …”

“…The temporal changes can be used to monitor the patients’ response to the treatment and to inform the decision for discharge. 97 Lung ultrasound has also been suggested as the imaging tool for COVID-19 pandemic in disease triage, diagnosis, prognosis, severity assessment, and monitoring the treatment response. 13 …”

“…95 A severity score derived from lung images can be used for triaging the patient to decide home discharge, regular hospital admission, or intensive care unit admission. 96 The imaging characteristics can be used for prognosis assessment 97 and evaluation of the extent of disease, 11 and it has potential to predict the length of hospital stay. 98 Although COVID-19 is seen as a disease that primarily affects the lungs, it may also damage other organs, including heart 93,99 and brain, 93,[99][100][101][102] and many long-term COVID-19 effects are still unknown.…”

Usage of Compromised Lung Volume in Monitoring Steroid Therapy on Severe COVID-19

“…In our preliminary study, we found that quantitative parameters of QCT may serve as a useful endpoint in evaluating treatment e cacy in patients with COVID-19 [13]. Further, we found that patients with severe COVID-19 receiving steroid therapy showed a signi cant different recovery pattern compared to those not receiving steroid therapy using a deep learning method [14]. However, due to the black-box brought by deep networks, we were not able to further interpret the difference we have observed.…”

“…This may be particularly valuable in circumstance of minor effect as new therapies are developed and evaluated [7] .We hypothesize that QCT can serve as a tool for monitoring steroid treatment response during the course of disease. Our preliminary studies have con rmed the value of QCT in monitoring the progression and clinical decision-making in patients with 14]. However, the effect of steroids on quantitative chest CT parameters during the treatment process remains unknown.…”