Radiomics Analysis of Computed Tomography helps predict poor prognostic outcome in COVID-19

Abstract

Rationale: Given the rapid spread of COVID-19, an updated risk-stratify prognostic tool could help clinicians identify the high-risk patients with worse prognoses. We aimed to develop a non-invasive and easy-to-use prognostic signature by chest CT to individually predict poor outcome (death, need for mechanical ventilation, or intensive care unit admission) in patients with COVID-19. Methods: From November 29, 2019 to February 19, 2020, a total of 492 patients with COVID-19 from four centers were retrospectively collected. Since different durations from symptom onsets to the first CT scanning might affect the prognostic model, we designated the 492 patients into two groups: 1) the early-phase group: CT scans were performed within one week after symptom onset (0-6 days, n = 317); and 2) the late-phase group: CT scans were performed one week later after symptom onset (≥7 days, n = 175). In each group, we divided patients into the primary cohort (n = 212 in the early-phase group, n = 139 in the late-phase group) and the external independent validation cohort (n = 105 in the early-phase group, n = 36 in the late-phase group) according to the centers. We built two separate radiomics models in the two patient groups. Firstly, we proposed an automatic segmentation method to extract lung volume for radiomics feature extraction. Secondly, we applied several image preprocessing procedures to increase the reproducibility of the radiomics features: 1) applied a low-pass Gaussian filter before voxel resampling to prevent aliasing; 2) conducted ComBat to harmonize radiomics features per scanner; 3) tested the stability of the features in the radiomics signature by several image transformations, such as rotating, translating, and growing/shrinking. Thirdly, we used least absolute shrinkage and selection operator (LASSO) to build the radiomics signature (RadScore). Afterward, we conducted a Fine-Gray competing risk regression to build the clinical model and the clinic-radiomics signature (CrrScore). Finally, performances of the three prognostic signatures (clinical model, RadScore, and CrrScore) were estimated from the two aspects: 1) cumulative poor outcome probability prediction; 2) 28-day poor outcome prediction. We also did stratified analyses to explore the potential association between the CrrScore and the poor outcomes regarding different age, type, and comorbidity subgroups. Results: In the early-phase group, the CrrScore showed the best performance in estimating poor outcome (C-index = 0.850), and predicting the probability of 28-day poor outcome (AUC = 0.862). In the late-phase group, the RadScore alone achieved similar performance to the CrrScore in predicting poor outcome (C-index = 0.885), and 28-day poor outcome probability (AUC = 0.976). Moreover, the RadScore in both groups successfully stratified patients with COVID-19 into low- or high-RadScore groups with significantly different survival time in the training and validation cohorts (all P < 0.05). The CrrScore in both groups can also significantly stratify patients with different prognoses regarding different age, type, and comorbidities subgroups in the combined cohorts (all P < 0.05). Conclusions: This research proposed a non-invasive and quantitative prognostic tool for predicting poor outcome in patients with COVID-19 based on CT imaging. Taking the insufficient medical recourse into account, our study might suggest that the chest CT radiomics signature of COVID-19 is more effective and ideal to predict poor outcome in the late-phase COVID-19 patients. For the early-phase patients, integrating radiomics signature with clinical risk factors can achieve a more accurate prediction of individual poor prognostic outcome, which enables appropriate management and surveillance of COVID-19.

Keywords: COVID-19; Computed tomography; Poor outcome; Prognosis; Radiomics.

Conflict of interest statement

Competing Interests: The authors have declared that no competing interest exists.

© The author(s).

Figures

Figure 1

Radiomics framework of predicting the poor prognostic outcome in patients with COVID-19. RadScore_earlyphase and RadScore_latephase means the radiomics signature built for predicting poor outcome in the early-phase and late-phase COVID-19 patients, respectively. CrrScore_earlyphase and CrrScore_latephase means the clinic-radiomics signature built for predicting poor outcome in the early-phase and late-phase COVID-19 patients, respectively.

Figure 2

Cumulative poor outcome probability according to the risk strata defined by RadScore. A) and C) in the training cohort; B) and D) in the validation cohort. A) and B) assess the cumulative probability in the early-phase group. C) and D) assess the cumulative probability in the late-phase group.

Figure 3

Cumulative poor outcome and recovery probability according to the risk strata defined by CrrScore. Red curves mean the risk of reaching to poor outcome, and the blue curves mean the risk of reaching to recovery. A), B), E), and F) in the training cohort, and C), D), G) and H) in the validation cohort. A), C), E), and G) for the low-CrrScore group, and B), D), F) and h) for the high-CrrScore group. A), B), C) and D) assess the cumulative probability in the early-phase group. E), F), G) and H) assess the cumulative probability in the late phase group.

Figure 4

Four representative clinical high-risk patients with older age, severe type, comorbidities and different prognoses. The patient with relatively higher RadScore and CrrScore had shorter time to reach the poor outcome. Patient 1 and 2 were in the early-phase group (the time interval between initial symptom onset and the CT scan < 7 days). Patient 3 and 4 were in the late-phase group (the time interval between initial symptom onset and the CT scan ≥ 7 days).

Figure 5

Cumulative poor outcome probability according to the risk strata defined by CrrScore within age subgroup in the combined cohorts. A) and C) for the age < 60 subgroup; B) and D) for the age ≥ 60 subgroup. A) and B) assess the cumulative probability in the early-phase group. C) and D) assess the cumulative probability in the late phase group.

Figure 6

Cumulative poor outcome probability according to the risk strata defined by CrrScore within type subgroup in the combined cohorts. A) and C) for the mild type subgroup; B) and D) for the severe type subgroup. A) and B) assess the cumulative probability in the early-phase group. C) and D) assess the cumulative probability in the late-phase group.

Figure 7

Cumulative poor outcome probability according to the risk strata defined by CrrScore within comorbidity subgroup in the combined cohorts. A) and C) for the non-comorbidity subgroup; B) and D) for the comorbidity subgroup. A) and B) assess the cumulative probability in the early-phase group. C) and D) assess the cumulative probability in the late-phase group.