Saliency-based 3D convolutional neural network for categorising common focal liver lesions on multisequence MRI
Abstract Background The imaging features of focal liver lesions (FLLs) are diverse and complex. Diagnosing FLLs with imaging alone remains challenging. We developed and validated an interpretable deep learning model for the classification of seven categories of FLLs on multisequence MRI and compared...
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
SpringerOpen
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/d040028a424a4073bc8776acf614b66e |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:d040028a424a4073bc8776acf614b66e |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:d040028a424a4073bc8776acf614b66e2021-11-28T12:08:47ZSaliency-based 3D convolutional neural network for categorising common focal liver lesions on multisequence MRI10.1186/s13244-021-01117-z1869-4101https://doaj.org/article/d040028a424a4073bc8776acf614b66e2021-11-01T00:00:00Zhttps://doi.org/10.1186/s13244-021-01117-zhttps://doaj.org/toc/1869-4101Abstract Background The imaging features of focal liver lesions (FLLs) are diverse and complex. Diagnosing FLLs with imaging alone remains challenging. We developed and validated an interpretable deep learning model for the classification of seven categories of FLLs on multisequence MRI and compared the differential diagnosis between the proposed model and radiologists. Methods In all, 557 lesions examined by multisequence MRI were utilised in this retrospective study and divided into training–validation (n = 444) and test (n = 113) datasets. The area under the receiver operating characteristic curve (AUC) was calculated to evaluate the performance of the model. The accuracy and confusion matrix of the model and individual radiologists were compared. Saliency maps were generated to highlight the activation region based on the model perspective. Results The AUC of the two- and seven-way classifications of the model were 0.969 (95% CI 0.944–0.994) and from 0.919 (95% CI 0.857–0.980) to 0.999 (95% CI 0.996–1.000), respectively. The model accuracy (79.6%) of the seven-way classification was higher than that of the radiology residents (66.4%, p = 0.035) and general radiologists (73.5%, p = 0.346) but lower than that of the academic radiologists (85.4%, p = 0.291). Confusion matrices showed the sources of diagnostic errors for the model and individual radiologists for each disease. Saliency maps detected the activation regions associated with each predicted class. Conclusion This interpretable deep learning model showed high diagnostic performance in the differentiation of FLLs on multisequence MRI. The analysis principle contributing to the predictions can be explained via saliency maps.Shu-Hui WangXin-Jun HanJing DuZhen-Chang WangChunwang YuanYinan ChenYajing ZhuXin DouXiao-Wei XuHui XuZheng-Han YangSpringerOpenarticleDeep learningMRIClassificationFocal liver lesionModel interpretationMedical physics. Medical radiology. Nuclear medicineR895-920ENInsights into Imaging, Vol 12, Iss 1, Pp 1-12 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Deep learning MRI Classification Focal liver lesion Model interpretation Medical physics. Medical radiology. Nuclear medicine R895-920 |
| spellingShingle |
Deep learning MRI Classification Focal liver lesion Model interpretation Medical physics. Medical radiology. Nuclear medicine R895-920 Shu-Hui Wang Xin-Jun Han Jing Du Zhen-Chang Wang Chunwang Yuan Yinan Chen Yajing Zhu Xin Dou Xiao-Wei Xu Hui Xu Zheng-Han Yang Saliency-based 3D convolutional neural network for categorising common focal liver lesions on multisequence MRI |
| description |
Abstract Background The imaging features of focal liver lesions (FLLs) are diverse and complex. Diagnosing FLLs with imaging alone remains challenging. We developed and validated an interpretable deep learning model for the classification of seven categories of FLLs on multisequence MRI and compared the differential diagnosis between the proposed model and radiologists. Methods In all, 557 lesions examined by multisequence MRI were utilised in this retrospective study and divided into training–validation (n = 444) and test (n = 113) datasets. The area under the receiver operating characteristic curve (AUC) was calculated to evaluate the performance of the model. The accuracy and confusion matrix of the model and individual radiologists were compared. Saliency maps were generated to highlight the activation region based on the model perspective. Results The AUC of the two- and seven-way classifications of the model were 0.969 (95% CI 0.944–0.994) and from 0.919 (95% CI 0.857–0.980) to 0.999 (95% CI 0.996–1.000), respectively. The model accuracy (79.6%) of the seven-way classification was higher than that of the radiology residents (66.4%, p = 0.035) and general radiologists (73.5%, p = 0.346) but lower than that of the academic radiologists (85.4%, p = 0.291). Confusion matrices showed the sources of diagnostic errors for the model and individual radiologists for each disease. Saliency maps detected the activation regions associated with each predicted class. Conclusion This interpretable deep learning model showed high diagnostic performance in the differentiation of FLLs on multisequence MRI. The analysis principle contributing to the predictions can be explained via saliency maps. |
| format |
article |
| author |
Shu-Hui Wang Xin-Jun Han Jing Du Zhen-Chang Wang Chunwang Yuan Yinan Chen Yajing Zhu Xin Dou Xiao-Wei Xu Hui Xu Zheng-Han Yang |
| author_facet |
Shu-Hui Wang Xin-Jun Han Jing Du Zhen-Chang Wang Chunwang Yuan Yinan Chen Yajing Zhu Xin Dou Xiao-Wei Xu Hui Xu Zheng-Han Yang |
| author_sort |
Shu-Hui Wang |
| title |
Saliency-based 3D convolutional neural network for categorising common focal liver lesions on multisequence MRI |
| title_short |
Saliency-based 3D convolutional neural network for categorising common focal liver lesions on multisequence MRI |
| title_full |
Saliency-based 3D convolutional neural network for categorising common focal liver lesions on multisequence MRI |
| title_fullStr |
Saliency-based 3D convolutional neural network for categorising common focal liver lesions on multisequence MRI |
| title_full_unstemmed |
Saliency-based 3D convolutional neural network for categorising common focal liver lesions on multisequence MRI |
| title_sort |
saliency-based 3d convolutional neural network for categorising common focal liver lesions on multisequence mri |
| publisher |
SpringerOpen |
| publishDate |
2021 |
| url |
https://doaj.org/article/d040028a424a4073bc8776acf614b66e |
| work_keys_str_mv |
AT shuhuiwang saliencybased3dconvolutionalneuralnetworkforcategorisingcommonfocalliverlesionsonmultisequencemri AT xinjunhan saliencybased3dconvolutionalneuralnetworkforcategorisingcommonfocalliverlesionsonmultisequencemri AT jingdu saliencybased3dconvolutionalneuralnetworkforcategorisingcommonfocalliverlesionsonmultisequencemri AT zhenchangwang saliencybased3dconvolutionalneuralnetworkforcategorisingcommonfocalliverlesionsonmultisequencemri AT chunwangyuan saliencybased3dconvolutionalneuralnetworkforcategorisingcommonfocalliverlesionsonmultisequencemri AT yinanchen saliencybased3dconvolutionalneuralnetworkforcategorisingcommonfocalliverlesionsonmultisequencemri AT yajingzhu saliencybased3dconvolutionalneuralnetworkforcategorisingcommonfocalliverlesionsonmultisequencemri AT xindou saliencybased3dconvolutionalneuralnetworkforcategorisingcommonfocalliverlesionsonmultisequencemri AT xiaoweixu saliencybased3dconvolutionalneuralnetworkforcategorisingcommonfocalliverlesionsonmultisequencemri AT huixu saliencybased3dconvolutionalneuralnetworkforcategorisingcommonfocalliverlesionsonmultisequencemri AT zhenghanyang saliencybased3dconvolutionalneuralnetworkforcategorisingcommonfocalliverlesionsonmultisequencemri |
| _version_ |
1718408226167324672 |