Frederik Wessels1,2, Max Schmitt1, Eva Krieghoff-Henning1, Tanja Jutzi1, Thomas S Worst2, Frank Waldbillig2, Manuel Neuberger2, Roman C Maron1, Matthias Steeg3, Timo Gaiser3, Achim Hekler1, Jochen S Utikal4,5, Christof von Kalle6, Stefan Fröhling7, Maurice S Michel2, Philipp Nuhn2, Titus J Brinker1. 1. Digital Biomarkers for Oncology Group, National Center for Tumor Diseases (NCT), German Cancer Research Center (DKFZ), Heidelberg, Germany. 2. Department of Urology and Urological Surgery, Medical Faculty Mannheim of Heidelberg University, University Medical Center Mannheim, Mannheim, Germany. 3. Institute of Pathology, Medical Faculty Mannheim of Heidelberg University, University Medical Center Mannheim, Mannheim, Germany. 4. Skin Cancer Unit, German Cancer Research Center (DKFZ), Heidelberg, Germany. 5. Department of Dermatology, Venereology and Allergology, University Medical Center Mannheim, University of Heidelberg, Heidelberg, Germany. 6. Department of Clinical-Translational Sciences, Berlin Institute of Health (BIH), Charité University Medicine, Berlin, Germany. 7. National Center for Tumor Diseases, German Cancer Research Center, Heidelberg, Germany.
Abstract
OBJECTIVE: To develop a new digital biomarker based on the analysis of primary tumour tissue by a convolutional neural network (CNN) to predict lymph node metastasis (LNM) in a cohort matched for already established risk factors. PATIENTS AND METHODS: Haematoxylin and eosin (H&E) stained primary tumour slides from 218 patients (102 N+; 116 N0), matched for Gleason score, tumour size, venous invasion, perineural invasion and age, who underwent radical prostatectomy were selected to train a CNN and evaluate its ability to predict LN status. RESULTS: With 10 models trained with the same data, a mean area under the receiver operating characteristic curve (AUROC) of 0.68 (95% confidence interval [CI] 0.678-0.682) and a mean balanced accuracy of 61.37% (95% CI 60.05-62.69%) was achieved. The mean sensitivity and specificity was 53.09% (95% CI 49.77-56.41%) and 69.65% (95% CI 68.21-71.1%), respectively. These results were confirmed via cross-validation. The probability score for LNM prediction was significantly higher on image sections from N+ samples (mean [SD] N+ probability score 0.58 [0.17] vs 0.47 [0.15] N0 probability score, P = 0.002). In multivariable analysis, the probability score of the CNN (odds ratio [OR] 1.04 per percentage probability, 95% CI 1.02-1.08; P = 0.04) and lymphovascular invasion (OR 11.73, 95% CI 3.96-35.7; P < 0.001) proved to be independent predictors for LNM. CONCLUSION: In our present study, CNN-based image analyses showed promising results as a potential novel low-cost method to extract relevant prognostic information directly from H&E histology to predict the LN status of patients with prostate cancer. Our ubiquitously available technique might contribute to an improved LN status prediction.
OBJECTIVE: To develop a new digital biomarker based on the analysis of primary tumour tissue by a convolutional neural network (CNN) to predict lymph node metastasis (LNM) in a cohort matched for already established risk factors. PATIENTS AND METHODS: Haematoxylin and eosin (H&E) stained primary tumour slides from 218 patients (102 N+; 116 N0), matched for Gleason score, tumour size, venous invasion, perineural invasion and age, who underwent radical prostatectomy were selected to train a CNN and evaluate its ability to predict LN status. RESULTS: With 10 models trained with the same data, a mean area under the receiver operating characteristic curve (AUROC) of 0.68 (95% confidence interval [CI] 0.678-0.682) and a mean balanced accuracy of 61.37% (95% CI 60.05-62.69%) was achieved. The mean sensitivity and specificity was 53.09% (95% CI 49.77-56.41%) and 69.65% (95% CI 68.21-71.1%), respectively. These results were confirmed via cross-validation. The probability score for LNM prediction was significantly higher on image sections from N+ samples (mean [SD] N+ probability score 0.58 [0.17] vs 0.47 [0.15] N0 probability score, P = 0.002). In multivariable analysis, the probability score of the CNN (odds ratio [OR] 1.04 per percentage probability, 95% CI 1.02-1.08; P = 0.04) and lymphovascular invasion (OR 11.73, 95% CI 3.96-35.7; P < 0.001) proved to be independent predictors for LNM. CONCLUSION: In our present study, CNN-based image analyses showed promising results as a potential novel low-cost method to extract relevant prognostic information directly from H&E histology to predict the LN status of patients with prostate cancer. Our ubiquitously available technique might contribute to an improved LN status prediction.
Authors: Jaakko S Knuutila; Pilvi Riihilä; Antti Karlsson; Mikko Tukiainen; Lauri Talve; Liisa Nissinen; Veli-Matti Kähäri Journal: Sci Rep Date: 2022-06-14 Impact factor: 4.996
Authors: Karl-Friedrich Kowalewski; Luisa Egen; Chanel E Fischetti; Stefano Puliatti; Gomez Rivas Juan; Mark Taratkin; Rivero Belenchon Ines; Marie Angela Sidoti Abate; Julia Mühlbauer; Frederik Wessels; Enrico Checcucci; Giovanni Cacciamani Journal: Asian J Urol Date: 2022-06-18