%0 Journal Article %1 Wessels2022-jg %A Wessels, Frederik %A Schmitt, Max %A Krieghoff-Henning, Eva %A Kather, Jakob N %A Nientiedt, Malin %A Kriegmair, Maximilian C %A Worst, Thomas S %A Neuberger, Manuel %A Steeg, Matthias %A Popovic, Zoran V %A Gaiser, Timo %A von Kalle, Christof %A Utikal, Jochen S %A Fröhling, Stefan %A Michel, Maurice S %A Nuhn, Philipp %A Brinker, Titus J %D 2022 %J PLoS One %K topic_lifescience %N 8 %P e0272656 %T Deep learning can predict survival directly from histology in clear cell renal cell carcinoma %V 17 %X For clear cell renal cell carcinoma (ccRCC) risk-dependent diagnostic and therapeutic algorithms are routinely implemented in clinical practice. Artificial intelligence-based image analysis has the potential to improve outcome prediction and thereby risk stratification. Thus, we investigated whether a convolutional neural network (CNN) can extract relevant image features from a representative hematoxylin and eosin-stained slide to predict 5-year overall survival (5y-OS) in ccRCC. The CNN was trained to predict 5y-OS in a binary manner using slides from TCGA and validated using an independent in-house cohort. Multivariable logistic regression was used to combine of the CNNs prediction and clinicopathological parameters. A mean balanced accuracy of 72.0\% (standard deviation SD = 7.9\%), sensitivity of 72.4\% (SD = 10.6\%), specificity of 71.7\% (SD = 11.9\%) and area under receiver operating characteristics curve (AUROC) of 0.75 (SD = 0.07) was achieved on the TCGA training set (n = 254 patients / WSIs) using 10-fold cross-validation. On the external validation cohort (n = 99 patients / WSIs), mean accuracy, sensitivity, specificity and AUROC were 65.5\% (95\%-confidence interval CI: 62.9-68.1\%), 86.2\% (95\%-CI: 81.8-90.5\%), 44.9\% (95\%-CI: 40.2-49.6\%), and 0.70 (95\%-CI: 0.69-0.71). A multivariable model including age, tumor stage and metastasis yielded an AUROC of 0.75 on the TCGA cohort. The inclusion of the CNN-based classification (Odds ratio = 4.86, 95\%-CI: 2.70-8.75, p < 0.01) raised the AUROC to 0.81. On the validation cohort, both models showed an AUROC of 0.88. In univariable Cox regression, the CNN showed a hazard ratio of 3.69 (95\%-CI: 2.60-5.23, p < 0.01) on TCGA and 2.13 (95\%-CI: 0.92-4.94, p = 0.08) on external validation. The results demonstrate that the CNN's image-based prediction of survival is promising and thus this widely applicable technique should be further investigated with the aim of improving existing risk stratification in ccRCC.

@article{Wessels2022-jg, abstract = {For clear cell renal cell carcinoma (ccRCC) risk-dependent diagnostic and therapeutic algorithms are routinely implemented in clinical practice. Artificial intelligence-based image analysis has the potential to improve outcome prediction and thereby risk stratification. Thus, we investigated whether a convolutional neural network (CNN) can extract relevant image features from a representative hematoxylin and eosin-stained slide to predict 5-year overall survival (5y-OS) in ccRCC. The CNN was trained to predict 5y-OS in a binary manner using slides from TCGA and validated using an independent in-house cohort. Multivariable logistic regression was used to combine of the CNNs prediction and clinicopathological parameters. A mean balanced accuracy of 72.0\% (standard deviation [SD] = 7.9\%), sensitivity of 72.4\% (SD = 10.6\%), specificity of 71.7\% (SD = 11.9\%) and area under receiver operating characteristics curve (AUROC) of 0.75 (SD = 0.07) was achieved on the TCGA training set (n = 254 patients / WSIs) using 10-fold cross-validation. On the external validation cohort (n = 99 patients / WSIs), mean accuracy, sensitivity, specificity and AUROC were 65.5\% (95\%-confidence interval [CI]: 62.9-68.1\%), 86.2\% (95\%-CI: 81.8-90.5\%), 44.9\% (95\%-CI: 40.2-49.6\%), and 0.70 (95\%-CI: 0.69-0.71). A multivariable model including age, tumor stage and metastasis yielded an AUROC of 0.75 on the TCGA cohort. The inclusion of the CNN-based classification (Odds ratio = 4.86, 95\%-CI: 2.70-8.75, p < 0.01) raised the AUROC to 0.81. On the validation cohort, both models showed an AUROC of 0.88. In univariable Cox regression, the CNN showed a hazard ratio of 3.69 (95\%-CI: 2.60-5.23, p < 0.01) on TCGA and 2.13 (95\%-CI: 0.92-4.94, p = 0.08) on external validation. The results demonstrate that the CNN's image-based prediction of survival is promising and thus this widely applicable technique should be further investigated with the aim of improving existing risk stratification in ccRCC.}, added-at = {2024-09-10T11:56:37.000+0200}, author = {Wessels, Frederik and Schmitt, Max and Krieghoff-Henning, Eva and Kather, Jakob N and Nientiedt, Malin and Kriegmair, Maximilian C and Worst, Thomas S and Neuberger, Manuel and Steeg, Matthias and Popovic, Zoran V and Gaiser, Timo and von Kalle, Christof and Utikal, Jochen S and Fr{\"o}hling, Stefan and Michel, Maurice S and Nuhn, Philipp and Brinker, Titus J}, biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/2ccf338dbc6d9124d3b0380cada7c9570/scadsfct}, interhash = {6a7fdbecf4a313af5bd5488c6dc27769}, intrahash = {ccf338dbc6d9124d3b0380cada7c9570}, journal = {PLoS One}, keywords = {topic_lifescience}, language = {en}, month = aug, number = 8, pages = {e0272656}, timestamp = {2024-11-22T15:48:48.000+0100}, title = {Deep learning can predict survival directly from histology in clear cell renal cell carcinoma}, volume = 17, year = 2022 }