An Interpretable Artificial Intelligence Model Based on CT for Prognosis of Intracerebral Hemorrhage: a Multicenter Study

Overview

Journal BMC Med Imaging

Publisher Biomed Central

Specialty Radiology

Date 2024 Jul 9

PMID 38982357

Authors

Hao Zhang

Yun-Feng Yang

Xue-Lin Song

Hai-Jian Hu

Yuan-Yuan Yang

Xia Zhu

Chao Yang

Affiliations

Soon will be listed here.

Abstract

Objectives: To develop and validate a novel interpretable artificial intelligence (AI) model that integrates radiomic features, deep learning features, and imaging features at multiple semantic levels to predict the prognosis of intracerebral hemorrhage (ICH) patients at 6 months post-onset.

Materials And Methods: Retrospectively enrolled 222 patients with ICH for Non-contrast Computed Tomography (NCCT) images and clinical data, who were divided into a training cohort (n = 186, medical center 1) and an external testing cohort (n = 36, medical center 2). Following image preprocessing, the entire hematoma region was segmented by two radiologists as the volume of interest (VOI). Pyradiomics algorithm library was utilized to extract 1762 radiomics features, while a deep convolutional neural network (EfficientnetV2-L) was employed to extract 1000 deep learning features. Additionally, radiologists evaluated imaging features. Based on the three different modalities of features mentioned above, the Random Forest (RF) model was trained, resulting in three models (Radiomics Model, Radiomics-Clinical Model, and DL-Radiomics-Clinical Model). The performance and clinical utility of the models were assessed using the Area Under the Receiver Operating Characteristic Curve (AUC), calibration curve, and Decision Curve Analysis (DCA), with AUC compared using the DeLong test. Furthermore, this study employs three methods, Shapley Additive Explanations (SHAP), Grad-CAM, and Guided Grad-CAM, to conduct a multidimensional interpretability analysis of model decisions.

Results: The Radiomics-Clinical Model and DL-Radiomics-Clinical Model exhibited relatively good predictive performance, with an AUC of 0.86 [95% Confidence Intervals (CI): 0.71, 0.95; P < 0.01] and 0.89 (95% CI: 0.74, 0.97; P < 0.01), respectively, in the external testing cohort.

Conclusion: The multimodal explainable AI model proposed in this study can accurately predict the prognosis of ICH. Interpretability methods such as SHAP, Grad-CAM, and Guided Grad-Cam partially address the interpretability limitations of AI models. Integrating multimodal imaging features can effectively improve the performance of the model.

Clinical Relevance Statement: Predicting the prognosis of patients with ICH is a key objective in emergency care. Accurate and efficient prognostic tools can effectively prevent, manage, and monitor adverse events in ICH patients, maximizing treatment outcomes.

References

Goldstein J, Fazen L, SNIDER R, Schwab K, Greenberg S, Smith E . Contrast extravasation on CT angiography predicts hematoma expansion in intracerebral hemorrhage. Neurology. 2007; 68(12):889-94. DOI: 10.1212/01.wnl.0000257087.22852.21. View

Naidech A, Bernstein R, Bassin S, Garg R, Liebling S, Bendok B . How patients die after intracerebral hemorrhage. Neurocrit Care. 2009; 11(1):45-9. DOI: 10.1007/s12028-009-9186-z. View

Yu Q, Ning Y, Wang A, Li S, Gu J, Li Q . Deep learning-assisted diagnosis of benign and malignant parotid tumors based on contrast-enhanced CT: a multicenter study. Eur Radiol. 2023; 33(9):6054-6065. DOI: 10.1007/s00330-023-09568-2. View

Feigin V, Roth G, Naghavi M, Parmar P, Krishnamurthi R, Chugh S . Global burden of stroke and risk factors in 188 countries, during 1990-2013: a systematic analysis for the Global Burden of Disease Study 2013. Lancet Neurol. 2016; 15(9):913-924. DOI: 10.1016/S1474-4422(16)30073-4. View

Song Z, Tang Z, Liu H, Guo D, Cai J, Zhou Z . A clinical-radiomics nomogram may provide a personalized 90-day functional outcome assessment for spontaneous intracerebral hemorrhage. Eur Radiol. 2021; 31(7):4949-4959. DOI: 10.1007/s00330-021-07828-7. View

Qi X, Hu G, Sun H, Chen Z, Yang C . Machine Learning-Based Perihematomal Tissue Features to Predict Clinical Outcome after Spontaneous Intracerebral Hemorrhage. J Stroke Cerebrovasc Dis. 2022; 31(6):106475. DOI: 10.1016/j.jstrokecerebrovasdis.2022.106475. View

Lin R, Lin J, Xu Y, Yu Y, Foster E, Lin M . Development and validation of a novel radiomics-clinical model for predicting post-stroke epilepsy after first-ever intracerebral haemorrhage. Eur Radiol. 2023; 33(7):4526-4536. DOI: 10.1007/s00330-023-09429-y. View

Barras C, Tress B, Christensen S, MacGregor L, Collins M, Desmond P . Density and shape as CT predictors of intracerebral hemorrhage growth. Stroke. 2009; 40(4):1325-31. DOI: 10.1161/STROKEAHA.108.536888. View

Dowlatshahi D, Demchuk A, Flaherty M, Ali M, Lyden P, Smith E . Defining hematoma expansion in intracerebral hemorrhage: relationship with patient outcomes. Neurology. 2011; 76(14):1238-44. PMC: 3068004. DOI: 10.1212/WNL.0b013e3182143317. View

10.

Wada R, Aviv R, Fox A, Sahlas D, Gladstone D, Tomlinson G . CT angiography "spot sign" predicts hematoma expansion in acute intracerebral hemorrhage. Stroke. 2007; 38(4):1257-62. DOI: 10.1161/01.STR.0000259633.59404.f3. View

11.

Qureshi A, Mendelow A, Hanley D . Intracerebral haemorrhage. Lancet. 2009; 373(9675):1632-44. PMC: 3138486. DOI: 10.1016/S0140-6736(09)60371-8. View

12.

Gillies R, Kinahan P, Hricak H . Radiomics: Images Are More than Pictures, They Are Data. Radiology. 2015; 278(2):563-77. PMC: 4734157. DOI: 10.1148/radiol.2015151169. View

13.

Wei X, Tang X, You D, Ding E, Pan C . A clinical-radiomics based nomogram to predict progressive intraparenchymal hemorrhage in mild to moderate traumatic injury patients. Eur J Radiol. 2023; 163:110785. DOI: 10.1016/j.ejrad.2023.110785. View

14.

Keep R, Hua Y, Xi G . Intracerebral haemorrhage: mechanisms of injury and therapeutic targets. Lancet Neurol. 2012; 11(8):720-31. PMC: 3884550. DOI: 10.1016/S1474-4422(12)70104-7. View

15.

Heo J, Yoon J, Park H, Kim Y, Nam H, Heo J . Machine Learning-Based Model for Prediction of Outcomes in Acute Stroke. Stroke. 2019; 50(5):1263-1265. DOI: 10.1161/STROKEAHA.118.024293. View

16.

Li H, Xie Y, Liu H, Wang X . Non-Contrast CT-Based Radiomics Score for Predicting Hematoma Enlargement in Spontaneous Intracerebral Hemorrhage. Clin Neuroradiol. 2021; 32(2):517-528. DOI: 10.1007/s00062-021-01062-w. View

17.

Li Q, Zhang G, Huang Y, Dong M, Lv F, Wei X . Blend Sign on Computed Tomography: Novel and Reliable Predictor for Early Hematoma Growth in Patients With Intracerebral Hemorrhage. Stroke. 2015; 46(8):2119-23. DOI: 10.1161/STROKEAHA.115.009185. View

18.

Nawabi J, Kniep H, Elsayed S, Friedrich C, Sporns P, Rusche T . Imaging-Based Outcome Prediction of Acute Intracerebral Hemorrhage. Transl Stroke Res. 2021; 12(6):958-967. PMC: 8557152. DOI: 10.1007/s12975-021-00891-8. View

19.

Hemphill 3rd J, Greenberg S, Anderson C, Becker K, Bendok B, Cushman M . Guidelines for the Management of Spontaneous Intracerebral Hemorrhage: A Guideline for Healthcare Professionals From the American Heart Association/American Stroke Association. Stroke. 2015; 46(7):2032-60. DOI: 10.1161/STR.0000000000000069. View

20.

Chen Y, Qin C, Chang J, Lyu Y, Zhang Q, Ye Z . A machine learning approach for predicting perihematomal edema expansion in patients with intracerebral hemorrhage. Eur Radiol. 2022; 33(6):4052-4062. DOI: 10.1007/s00330-022-09311-3. View