No 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.

No abstract

Out-of-focus sections of whole slide images are a significant source of false positives and other systematic errors in clinical diagnoses. As a result, focus quality assessment (FQA) methods must be able to quickly and accurately differentiate between focus levels in a scan. Recently, deep learning methods using convolutional neural networks (CNNs) have been adopted for FQA. However, the biggest obstacles impeding their wide usage in clinical workflows are their generalizability across different test conditions and their potentially high computational cost. In this study, we focus on the transferability and scalability of CNN-based FQA approaches. We carry out an investigation on ten architecturally diverse networks using five datasets with stain and tissue diversity. We evaluate the computational complexity of each network and scale this to realistic applications involving hundreds of whole slide images. We assess how well each full model transfers to a separate, unseen dataset without fine-tuning. We show that shallower networks transfer well when used on small input patch sizes, while deeper networks work more effectively on larger inputs. Furthermore, we introduce neural architecture search (NAS) to the field and learn an automatically designed low-complexity CNN architecture using differentiable architecture search which achieved competitive performance relative to established CNNs.

The Tolmount Field is a lean gas condensate accumulation located in Block 42/28d of the UK Southern North Sea. The field was discovered in 2011 by well 42/28d-12, which encountered good-quality gas-bearing reservoir sandstones of the Permian Leman Sandstone Formation. The discovery was appraised in 2013 by wells 42/28d-13 and 42/28d-13Z, which logged the gas–water contact on the eastern flank of the field. The Tolmount structure is a four-way, dip-closed, faulted anticline, orientated NW to SE. The reservoir comprises mixed aeolian dune and fluvial sheetflood facies deposited within an arid continental basin. Dune sands display the best reservoir properties with porosities around 22% and permeabilities exceeding 100 mD. Only minor diagenetic alteration has occurred, primarily in the form of grain-coating illite. Superior reservoir quality is observed at Tolmount compared to adjacent areas, due to the preservation of dune facies, a hypothesized early gas emplacement and a relatively benign burial history. Current mapped gas initially-in-place estimates for the field are between 450 bcf and 800 bcf, with an estimated recovery factor between 70 and 90%. An initial four-well development is planned, with first gas expected in 2020.