Refining diagnosis of Parkinson's disease with deep learning-based interpretation of dopamine transporter imaging.
Refining diagnosis of Parkinson's disease with deep learning-based interpretation of dopamine transporter imaging.
复制标题
DOI：
10.1016/j.nicl.2017.09.010
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Lee DS
中科院分区：
文献类型：
--
作者：
Choi H;Ha S;Im HJ;Paek SH;Lee DS
多巴胺能变性是帕金森病 (PD) 的病理标志，可通过多巴胺转运蛋白成像（如 FP-CIT SPECT）进行评估。到目前为止，成像技术已被人类常规解读，尽管它可以显示观察者之间的差异并导致诊断不一致。在本研究中，我们开发了一种基于深度学习的 FP-CIT SPECT 判读系统，以完善帕金森病的影像诊断。该系统经过PD患者和正常对照的SPECT图像训练，显示出与专家评估参考量化结果相当的高分类精度。其高精度在由帕金森病和非帕金森病震颤患者组成的独立队列中得到了验证。此外，我们还表明，一些临床诊断为 PD 的患者，其扫描结果没有多巴胺能缺陷 (SWEDD)（PD 的非典型亚组）证据，可以通过我们的自动化系统重新分类。我们的结果表明，基于深度学习的模型可以准确解释 FP-CIT SPECT 并克服人类评估的可变性。它可以帮助不确定帕金森症患者的影像诊断，并在进一步的临床研究中提供客观的患者组分类，特别是 SWEDD。开发了基于深度学习的 FP-CIT SPECT 解释模型。基于深度学习的模型可以克服观察者间的变异性。其区分 PD 与正常的准确性与临床标准相当。它还显示出区分帕金森病和非帕金森病震颤的高精度。临床随访结果显示我们的模型可以将 SWEDD 重新分类为 PD。
Dopaminergic degeneration is a pathologic hallmark of Parkinson's disease (PD), which can be assessed by dopamine transporter imaging such as FP-CIT SPECT. Until now, imaging has been routinely interpreted by human though it can show interobserver variability and result in inconsistent diagnosis. In this study, we developed a deep learning-based FP-CIT SPECT interpretation system to refine the imaging diagnosis of Parkinson's disease. This system trained by SPECT images of PD patients and normal controls shows high classification accuracy comparable with the experts' evaluation referring quantification results. Its high accuracy was validated in an independent cohort composed of patients with PD and nonparkinsonian tremor. In addition, we showed that some patients clinically diagnosed as PD who have scans without evidence of dopaminergic deficit (SWEDD), an atypical subgroup of PD, could be reclassified by our automated system. Our results suggested that the deep learning-based model could accurately interpret FP-CIT SPECT and overcome variability of human evaluation. It could help imaging diagnosis of patients with uncertain Parkinsonism and provide objective patient group classification, particularly for SWEDD, in further clinical studies. Deep learning-based FP-CIT SPECT interpretation model was developed. Deep learning-based model could overcome interobserver variability. Its accuracy for discriminating PD from normal was comparable to the clinical standard. It also showed high accuracy for differentiating PD from nonparkinsonian tremor. Clinical follow-up results showed SWEDD could be reclassified to PD by our model.
登录
查看更多内容
影响因子：
3.7
作者：
Brahim A;Ramírez J;Górriz JM;Khedher L;Salas-Gonzalez D
通讯作者：
Salas-Gonzalez D
DOI：
10.1007/s00259-015-3304-2
发表时间：
2016-07-01
影响因子：
9.1
作者：
Albert, Nathalie L.;Unterrainer, Marcus;la Fougere, Christian
通讯作者：
la Fougere, Christian
影响因子：
8.5
作者：
Prashanth, R.;Roy, Sumantra Dutta;Ghosh, Shantanu
通讯作者：
Ghosh, Shantanu
DOI：
10.1007/978-3-319-19992-4_46
发表时间：
2015-01-01
期刊：
Information processing in medical imaging : proceedings of the ... conference
影响因子：
--
作者：
Shen, Wei;Zhou, Mu;Tian, Jie
通讯作者：
Tian, Jie
影响因子：
4.1
作者：
Nicastro, Nicolas;Garibotto, Valentina;Burkhard, Pierre R.
通讯作者：
Burkhard, Pierre R.