Development and Validation of a Deep Learning Algorithm for Improving Gleason Scoring of Prostate Cancer
arXiv:1811.06497 · doi:10.1038/s41746-019-0112-2
Abstract
For prostate cancer patients, the Gleason score is one of the most important prognostic factors, potentially determining treatment independent of the stage. However, Gleason scoring is based on subjective microscopic examination of tumor morphology and suffers from poor reproducibility. Here we present a deep learning system (DLS) for Gleason scoring whole-slide images of prostatectomies. Our system was developed using 112 million pathologist-annotated image patches from 1,226 slides, and evaluated on an independent validation dataset of 331 slides, where the reference standard was established by genitourinary specialist pathologists. On the validation dataset, the mean accuracy among 29 general pathologists was 0.61. The DLS achieved a significantly higher diagnostic accuracy of 0.70 (p=0.002) and trended towards better patient risk stratification in correlations to clinical follow-up data. Our approach could improve the accuracy of Gleason scoring and subsequent therapy decisions, particularly where specialist expertise is unavailable. The DLS also goes beyond the current Gleason system to more finely characterize and quantitate tumor morphology, providing opportunities for refinement of the Gleason system itself.
References in corpus (3)
Cited by in corpus (32)
- Deep neural network models for computational histopathology: A survey
- Automated Gleason Grading of Prostate Biopsies using Deep Learning
- Microscope 2.0: An Augmented Reality Microscope with Real-time Artificial Intelligence Integration
- Deep learning-based survival prediction for multiple cancer types using histopathology images
- PanNuke Dataset Extension, Insights and Baselines
- Predicting optical coherence tomography-derived diabetic macular edema grades from fundus photographs using deep learning
- Whole-Slide Image Focus Quality: Automatic Assessment and Impact on AI Cancer Detection
- Recommendations on test datasets for evaluating AI solutions in pathology
- Towards Label-efficient Automatic Diagnosis and Analysis: A Comprehensive Survey of Advanced Deep Learning-based Weakly-supervised, Semi-supervised and Self-supervised Techniques in Histopathological Image Analysis
- Predicting Prostate Cancer-Specific Mortality with A.I.-based Gleason Grading
- Self-learning for weakly supervised Gleason grading of local patterns
- Survey of XAI in digital pathology
- Automated Detection of Cribriform Growth Patterns in Prostate Histology Images
- Iterative Augmentation of Visual Evidence for Weakly-Supervised Lesion Localization in Deep Interpretability Frameworks: Application to Color Fundus Images
- An attention-based multi-resolution model for prostate whole slide imageclassification and localization
- Pathologist-Level Grading of Prostate Biopsies with Artificial Intelligence
- Representation Learning for Electronic Health Records
- Multimodal Multitask Representation Learning for Pathology Biobank Metadata Prediction
- Future Artificial Intelligence tools and perspectives in medicine
- Improving Prostate Cancer Detection with Breast Histopathology Images
- OpenSRH: optimizing brain tumor surgery using intraoperative stimulated Raman histology
- Computational model discovery with reinforcement learning
- Domain-Specific Pre-training Improves Confidence in Whole Slide Image Classification
- A Multi-resolution Model for Histopathology Image Classification and Localization with Multiple Instance Learning
- The State of Applying Artificial Intelligence to Tissue Imaging for Cancer Research and Early Detection
- Meta-SVDD: Probabilistic Meta-Learning for One-Class Classification in Cancer Histology Images
- Automated Prostate Cancer Diagnosis Based on Gleason Grading Using Convolutional Neural Network
- Histogram of Cell Types: Deep Learning for Automated Bone Marrow Cytology
- Deep Learning for Prostate Pathology
- 3D Reasoning for Unsupervised Anomaly Detection in Pediatric WbMRI
- Hybrid Supervision Learning for Pathology Whole Slide Image Classification
- Learning of Inter-Label Geometric Relationships Using Self-Supervised Learning: Application To Gleason Grade Segmentation