FocusLiteNN: High Efficiency Focus Quality Assessment for Digital Pathology

TL;DR

FocusLiteNN is a highly efficient CNN-based Focus Quality Assessment model for digital pathology that achieves fast computation and high accuracy, addressing the bottleneck in high-throughput Whole Slide Image scanning.

Contribution

The paper introduces a lightweight CNN model trained on a diverse dataset, demonstrating competitive performance with minimal complexity and superior speed compared to existing methods.

Findings

The model maintains high performance even with minimal CNN complexity.

It outperforms existing FQA methods in speed and accuracy.

The comprehensive dataset enables robust evaluation across tissue types.

Abstract

Out-of-focus microscopy lens in digital pathology is a critical bottleneck in high-throughput Whole Slide Image (WSI) scanning platforms, for which pixel-level automated Focus Quality Assessment (FQA) methods are highly desirable to help significantly accelerate the clinical workflows. Existing FQA methods include both knowledge-driven and data-driven approaches. While data-driven approaches such as Convolutional Neural Network (CNN) based methods have shown great promises, they are difficult to use in practice due to their high computational complexity and lack of transferability. Here, we propose a highly efficient CNN-based model that maintains fast computations similar to the knowledge-driven methods without excessive hardware requirements such as GPUs. We create a training dataset using FocusPath which encompasses diverse tissue slides across nine different stain colors, where the stain diversity greatly helps the model to learn diverse color spectrum and tissue structures. In our attempt to reduce the CNN complexity, we find with surprise that even trimming down the CNN to the minimal level, it still achieves a highly competitive performance. We introduce a novel comprehensive evaluation dataset, the largest of its kind, annotated and compiled from TCGA repository for model assessment and comparison, for which the proposed method exhibits superior precision-speed trade-off when compared with existing knowledge-driven and data-driven FQA approaches.