Precise diagnosis of intracranial hemorrhage and subtypes using a three-dimensional joint convolutional and recurrent neural network.
Objectives: To evaluate the performance of a novel three-dimensional (3D) joint convolutional and recurrent neural network (CNN-RNN) for the detection of intracranial hemorrhage (ICH) and its five subtypes (cerebral parenchymal, intraventricular, subdural, epidural, and subarachnoid) in non-contrast...
| Publicado en: | European Radiology Vol. 29; no. 11; pp. 6191 - 6202 |
|---|---|
| Autores principales: | , , , , , , , , , , , , , |
| Formato: | diagnostic images research tables/charts Journal Article |
| Publicado: |
Springer Nature
Nov2019
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=139163649&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 139163649 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 09387994 NPH jtl: European Radiology issn: 09387994 maglogo: N pubinfo: dt: Nov2019 vid: 29 iid: 11 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 139163649 139163649 143921539 NLM31041565 139163649 10.1007/s00330-019-06163-2 NLM31041565 139163649 ppf: 6191 ppct: 11 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Precise diagnosis of intracranial hemorrhage and subtypes using a three-dimensional joint convolutional and recurrent neural network. aug: au: Ye, Hai Gao, Feng Yin, Youbing Guo, Danfeng Zhao, Pengfei Lu, Yi Wang, Xin Bai, Junjie Cao, Kunlin Song, Qi Zhang, Heye Chen, Wei Guo, Xuejun Xia, Jun affil: Department of Radiology, Shenzhen Second People's Hospital, Shenzhen Second Hospital Clinical Medicine College of Anhui Medical University, Shenzhen, China sug: subj: Tomography, X-Ray Computed Methods Imaging, Three-Dimensional Methods Intracranial Hemorrhage Diagnosis Recurrent Neural Networks Convolutional Neural Networks Aged Female Adolescence Child, Preschool Male Retrospective Design Middle Age Reproducibility of Results Child Young Adult Adult Aged, 80 and Over Infant Human Validation Studies Comparative Studies Evaluation Research Multicenter Studies Aged: 65+ years Adolescent: 13-18 years Child, Preschool: 2-5 years Middle Aged: 45-64 years Child: 6-12 years Adult: 19-44 years Aged, 80 & over Infant: 1-23 months Female Male ab: Objectives: To evaluate the performance of a novel three-dimensional (3D) joint convolutional and recurrent neural network (CNN-RNN) for the detection of intracranial hemorrhage (ICH) and its five subtypes (cerebral parenchymal, intraventricular, subdural, epidural, and subarachnoid) in non-contrast head CT.Methods: A total of 2836 subjects (ICH/normal, 1836/1000) from three institutions were included in this ethically approved retrospective study, with a total of 76,621 slices from non-contrast head CT scans. ICH and its five subtypes were annotated by three independent experienced radiologists, with majority voting as reference standard for both the subject level and the slice level. Ninety percent of data was used for training and validation, and the rest 10% for final evaluation. A joint CNN-RNN classification framework was proposed, with the flexibility to train when subject-level or slice-level labels are available. The predictions were compared with the interpretations from three junior radiology trainees and an additional senior radiologist.Results: It took our algorithm less than 30 s on average to process a 3D CT scan. For the two-type classification task (predicting bleeding or not), our algorithm achieved excellent values (≥ 0.98) across all reporting metrics on the subject level. For the five-type classification task (predicting five subtypes), our algorithm achieved > 0.8 AUC across all subtypes. The performance of our algorithm was generally superior to the average performance of the junior radiology trainees for both two-type and five-type classification tasks.Conclusions: The proposed method was able to accurately detect ICH and its subtypes with fast speed, suggesting its potential for assisting radiologists and physicians in their clinical diagnosis workflow.Key Points: • A 3D joint CNN-RNN deep learning framework was developed for ICH detection and subtype classification, which has the flexibility to train with either subject-level labels or slice-level labels. • This deep learning framework is fast and accurate at detecting ICH and its subtypes. • The performance of the automated algorithm was superior to the average performance of three junior radiology trainees in this work, suggesting its potential to reduce initial misinterpretations. pubtype: Academic Journal doctype: diagnostic images research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|