Towards machine learned quality control: A benchmark for sharpness quantification in digital pathology. (April 2018)

• Record Type: Journal Article
• Authors: Campanella, Gabriele; Rajanna, Arjun R.; Corsale, Lorraine; Schüffler, Peter J.; Yagi, Yukako; Fuchs, Thomas J.
• Is Part Of: Computerized medical imaging and graphics. Volume 65(2018)
• Page Start: 142
• Page End: 151
• Publication Date: 2018-04
• Subjects: Computational pathology -- Digital pathology -- Quality control -- Machine learning -- Deep learning -- Quantitative blur detection; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2017.09.001
• Languages: English
• ISSNs: 0895-6111

Abstract

Highlights: A comprehensive benchmark dataset for blur detection was created. A comprehensive performance comparison of 13 sharpness metrics was obtained. Feature engineering was compared to deep feature learning for blur detection. A blur detection software was implemented for usage in the clinic. The blur detector was validated on 3 datasets, and against human experts. The blur detector was tested in the clinical setting and compared it to the state-of-the-art joint QC pipeline of commercial scanner software and human QC experts. Abstract: Pathology is on the verge of a profound change from an analog and qualitative to a digital and quantitative discipline. This change is mostly driven by the high-throughput scanning of microscope slides in modern pathology departments, reaching tens of thousands of digital slides per month. The resulting vast digital archives form the basis of clinical use in digital pathology and allow large scale machine learning in computational pathology. One of the most crucial bottlenecks of high-throughput scanning is quality control (QC). Currently, digital slides are screened manually to detected out-of-focus regions, to compensate for the limitations of scanner software. We present a solution to this problem by introducing a benchmark dataset for blur detection, an in-depth comparison of state-of-the art sharpness descriptors and their prediction performance within a random forest framework. Furthermore, we show that convolution neural networks, like residual networks, can be used to train blur detectors from scratch. We thoroughly evaluate the accuracy of feature based and deep learning based approaches for sharpness classification (99.74% accuracy) and regression (MSE 0.004) and additionally compare them to domain experts in a comprehensive human perception study. Our pipeline outputs spacial heatmaps enabling to quantify and localize blurred areas on a slide. Finally, we tested the proposed framework in the clinical setting and demonstrate superior performance over the state-of-the-art QC pipeline comprising commercial software and human expert inspection by reducing the error rate from 17% to 4.7%.