Grading diabetic retinopathy and prostate cancer diagnostic images with deep quantum ordinal regression

• Published in: Computers in biology and medicine 2022-06, Vol.145, p.105472-105472, Article 105472
• Main Authors: Toledo-Cortés, Santiago, Useche, Diego H., Müller, Henning, González, Fabio A.
• Format: Article
• Language: English
• Subjects: Alzheimer's disease; Classification; Deep learning; Deep probabilistic learning; Density matrices; Diabetes; Diabetes Mellitus; Diabetic retinopathy; Diabetic Retinopathy - diagnostic imaging; Diagnosis; Eye fundus images; Fundus Oculi; Histopathology images; Humans; Image analysis; Image classification; Image processing; Machine learning; Male; Medical diagnosis; Medical imaging; Neural networks; Ordinal regression; Probability; Probability distribution; Prostate; Prostate cancer; Prostatic Neoplasms - diagnostic imaging; Quantum measurement; Regression models; Retinopathy; Statistical analysis; Support vector machines; Uncertainty; Uncertainty quantification
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2022.105472

Although for many diseases there is a progressive diagnosis scale, automatic analysis of grade-based medical images is quite often addressed as a binary classification problem, missing the finer distinction and intrinsic relation between the different possible stages or grades. Ordinal regression (or classification) considers the order of the values of the categorical labels and thus takes into account the order of grading scales used to assess the severity of different medical conditions. This paper presents a quantum-inspired deep probabilistic learning ordinal regression model for medical image diagnosis that takes advantage of the representational power of deep learning and the intrinsic ordinal information of disease stages. The method is evaluated on two different medical image analysis tasks: prostate cancer diagnosis and diabetic retinopathy grade estimation on eye fundus images. The experimental results show that the proposed method not only improves the diagnosis performance on the two tasks but also the interpretability of the results by quantifying the uncertainty of the predictions in comparison to conventional deep classification and regression architectures. The code and datasets are available at https://github.com/stoledoc/DQOR. •A new end-to-end neural probabilistic ordinal regression method.•Model's predictions correspond to probability distributions over the range of grades.•Probability distributions are represented as density matrices.•In addition to the prediction, the model quantifies its uncertainty.•Approaching the problem as an ordinal regression model improves binary diagnosis.