전산화 단층 촬영 (Computed tomography, CT) 이미지에 대한 EfficientNet 기반 두개내출혈 진단 및 가시화 모델 개발
Diagnosis and Visualization of Intracranial Hemorrhage on Computed Tomography Images Using EfficientNet-based Model
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Intracranial hemorrhage (ICH) refers to acute bleeding inside the intracranial vault. Not only does this devastating disease record a very high mortality rate, but it can also cause serious chronic impairment of sensory, motor, and cognitive functions. Therefore, a prompt and professional diagnosis of the disease is highly critical. Non- invasive brain imaging data are essential for clinicians to efficiently diagnose the locus of brain lesion, volume of bleeding, and subsequent cortical damage, and to take clinical interventions. In particular, computed tomography (CT) images are used most often for the diagnosis of ICH. In order to diagnose ICH through CT images, not only medical specialists with a sufficient number of diagnosis experiences are required, but even when this condition is met, there are many cases where bleeding cannot be successfully detected due to factors such as low signal ratio and artifacts of the image itself. In addition, discrepancies between interpretations or even misinterpretations might exist causing critical clinical consequences. To resolve these clinical problems, we developed a diagnostic model predicting intra- cranial bleeding and its subtypes (intraparenchymal, intraventricular, subarachnoid, subdural, and epidural) by apply- ing deep learning algorithms to CT images. We also constructed a visualization tool highlighting important regions in a CT image for predicting ICH. Specifically, 1) 27,758 CT brain images from RSNA were pre-processed to minimize the computational load. 2) Three different CNN-based models (ResNet, EfficientNet-B2, and EfficientNet-B7) were trained based on a training image data set. 3) Diagnosis performance of each of the three models was evaluated based on an independent test image data set: As a result of the model comparison, EfficientNet-B7’s performance (clas- sification accuracy = 91%) was a way greater than the other models. 4) Finally, based on the result of EfficientNet-B7, we visualized the lesions of internal bleeding using the Grad-CAM. Our research suggests that artificial intelligence- based diagnostic systems can help diagnose and treat brain diseases resolving various problems in clinical situations.
Abstract
Intracranial hemorrhage (ICH) refers to acute bleeding inside the intracranial vault. Not only does this devastating disease record a very high mortality rate, but it can also cause serious chronic impairment of sensory, motor, and cognitive functions. Therefore, a prompt and professional diagnosis of the disease is highly critical. Non- invasive brain imaging data are essential for clinicians to efficiently diagnose the locus of brain lesion, volume of bleeding, and subsequent cortical damage, and to take clinical interventions. In particular, computed tomography (CT) images are used most often for the diagnosis of ICH. In order to diagnose ICH through CT images, not only medical specialists with a sufficient number of diagnosis experiences are required, but even when this condition is met, there are many cases where bleeding cannot be successfully detected due to factors such as low signal ratio and artifacts of the image itself. In addition, discrepancies between interpretations or even misinterpretations might exist causing critical clinical consequences. To resolve these clinical problems, we developed a diagnostic model predicting intra- cranial bleeding and its subtypes (intraparenchymal, intraventricular, subarachnoid, subdural, and epidural) by apply- ing deep learning algorithms to CT images. We also constructed a visualization tool highlighting important regions in a CT image for predicting ICH. Specifically, 1) 27,758 CT brain images from RSNA were pre-processed to minimize the computational load. 2) Three different CNN-based models (ResNet, EfficientNet-B2, and EfficientNet-B7) were trained based on a training image data set. 3) Diagnosis performance of each of the three models was evaluated based on an independent test image data set: As a result of the model comparison, EfficientNet-B7’s performance (clas- sification accuracy = 91%) was a way greater than the other models. 4) Finally, based on the result of EfficientNet-B7, we visualized the lesions of internal bleeding using the Grad-CAM. Our research suggests that artificial intelligence- based diagnostic systems can help diagnose and treat brain diseases resolving various problems in clinical situations.
참고문헌 (18)
- Davenport T, "The potential for artificial intelligence in healthcare", Future Healthcare Journal, 6(2), pp.94~98 (2019)
- Liu GD, "A Brief Review of Artificial Intelligence Applications and Algorithms for Psychiatric Disorders", Engineering, 6(4), pp.462~467 (2020)
- Marietta M, "Intracerebral haemorrhage: An often neglected medical emergency", Internal and Emergency Medicine, 2(1), pp.38~45 (2007)
- Caceres JA, "Intracranial Hemorrhage", Emergency Medicine Clinics of North America, 30(3), pp.771~794 (2012)
- Ye H, "Precise diagnosis of intracranial hemorrhage and subtypes using a three-dimensional joint convolutional and recurrent neural network", European Radiology, 29(11), pp.6191~6201 (2019)
- Alfaro D, "Accuracy of interpretation of cranial computed tomography scans in an emergency medicine residency program", Annals of Emergency Medicine, 25(2), pp.169~174 (1995)
- Lal NR, "Clinical consequences of misinterpretations of neuroradiologic CT scans by on-call radiology residents", AJNR. American Journal of Neuroradiology, 21(1), pp.124~129 (2000)
- Strub WM, "Overnight Preliminary Head CT Interpretations Provided by Residents:Locations of Misidentified Intracranial Hemorrhage", American Journal of Neuroradiology, 28(9), pp.1679~1682 (2007)
- Arbabshirani MR, "Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls", NeuroImage, 145, pp.137~165 (2017)
- "2015", ~
- "2020", ~
- Chilamkurthy S, "Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study", Lancet, 392, pp.2388~2396 (2018)
- Alfidi RJ, "Computed tomography of the thorax and abdomen: a preliminary report", Radiology, 117, pp.257~264 (1975)
- 김철환, "악골 병소의 켬퓨터 촬영상에서 Hounsfield Unit에 관한 연구", 대한구강악안면외과학회지, 32(4), pp.391~396 (2006), 대한구강악안면외과학회
- Lin T, "Focal Loss for Dense Object Detection", arXiv:1708.02002, ~ (2017)
- Selvaraju RR, "Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization", International Journal of Computer Vision, 128(2), pp.336~359 (2020)
- Pope PE, "Explainability Methods for Graph Convolutional Neural Networks", 2019 IEEE, 2019, 10764~10773
- Xie Q, "Self-Training with Noisy Student Improves ImageNet Classification", 2020 IEEE, 2020, 10687~10698