External validation study on the value of deep learning algorithm for the prediction of hematoma expansion from noncontrast CT scans

• Published in: BMC medical imaging Vol. 22; no. 1; pp. 45 - 9
• Main Authors: Guo, Dong Chuang, Gu, Jun, He, Jian, Chu, Hai Rui, Dong, Na, Zheng, Yi Feng
• Format: Journal Article
• Language: English
• Published: London BioMed Central 14.03.2022; BioMed Central Ltd; BMC
• Subjects: Algorithms; Artificial Intelligence; Care and treatment; Cerebral Hemorrhage - diagnostic imaging; CT imaging; Data mining; Deep Learning; Diagnostic imaging; Early diagnosis; Health aspects; Hematoma; Hematoma - diagnostic imaging; Hematoma expansion; Humans; Hypertension; Hypertensive intracerebral hemorrhage; Imaging; Medical care; Medicine; Medicine & Public Health; Mortality; Prognosis; Quality management; Radiology; Retrospective Studies; Tomography, X-Ray Computed - methods; Early diagnosis; Hematoma expansion; Artificial intelligence; Hypertensive intracerebral hemorrhage
• ISSN: 1471-2342; 1471-2342
• DOI: 10.1186/s12880-022-00772-y

Background Hematoma expansion is an independent predictor of patient outcome and mortality. The early diagnosis of hematoma expansion is crucial for selecting clinical treatment options. This study aims to explore the value of a deep learning algorithm for the prediction of hematoma expansion from non-contrast computed tomography (NCCT) scan through external validation. Methods 102 NCCT images of hypertensive intracerebral hemorrhage (HICH) patients diagnosed in our hospital were retrospectively reviewed. The initial computed tomography (CT) scan images were evaluated by a commercial Artificial Intelligence (AI) software using deep learning algorithm and radiologists respectively to predict hematoma expansion and the corresponding sensitivity, specificity and accuracy of the two groups were calculated and compared. Comparisons were also conducted among gold standard hematoma expansion diagnosis time, AI software diagnosis time and doctors’ reading time. Results Among 102 HICH patients, the sensitivity, specificity, and accuracy of hematoma expansion prediction in the AI group were higher than those in the doctor group(80.0% vs 66.7%, 73.6% vs 58.3%, 75.5% vs 60.8%), with statistically significant difference ( p  < 0.05). The AI diagnosis time (2.8 ± 0.3 s) and the doctors’ diagnosis time (11.7 ± 0.3 s) were both significantly shorter than the gold standard diagnosis time (14.5 ± 8.8 h) ( p  < 0.05), AI diagnosis time was significantly shorter than that of doctors ( p  < 0.05). Conclusions Deep learning algorithm could effectively predict hematoma expansion at an early stage from the initial CT scan images of HICH patients after onset with high sensitivity and specificity and greatly shortened diagnosis time, which provides a new, accurate, easy-to-use and fast method for the early prediction of hematoma expansion.