Optical mesoscopy, machine learning, and computational microscopy enable high information content diagnostic imaging of blood films

Abstract

Automated image‐based assessment of blood films has tremendous potential to support clinical haematology within overstretched healthcare systems. To achieve this, efficient and reliable digital capture of the rich diagnostic information contained within a blood film is a critical first step. However, this is often challenging, and in many cases entirely unfeasible, with the microscopes typically used in haematology due to the fundamental trade‐off between magnification and spatial resolution. To address this, we investigated three state‐of‐the‐art approaches to microscopic imaging of blood films which leverage recent advances in optical and computational imaging and analysis to increase the information capture capacity of the optical microscope: optical mesoscopy, which uses a giant microscope objective (Mesolens) to enable high‐resolution imaging at low magnification; Fourier ptychographic microscopy, a computational imaging method which relies on oblique illumination with a series of LEDs to capture high‐resolution information; and deep neural networks which can be trained to increase the quality of low magnification, low resolution images. We compare and contrast the performance of these techniques for blood film imaging for the exemplar case of Giemsa‐stained peripheral blood smears. Using computational image analysis and shape‐based object classification, we demonstrate their use for automated analysis of red blood cell morphology and visualization and detection of small blood‐borne parasites such as the malarial parasite Plasmodium falciparum. Our results demonstrate that these new methods greatly increase the information capturing capacity of the light microscope, with transformative potential for haematology and more generally across digital pathology. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons, Ltd. on behalf of The Pathological Society of Great Britain and Ireland.

Challenges and advances in optical 3D mesoscale imaging

“…This is in line with microscopy, where AI and related techniques have found broad use for image segmentation 141–143 . Likewise, we expect this to become increasingly relevant for mesoscale imaging 144 …”

“…[141][142][143] Likewise, we expect this to become increasingly relevant for mesoscale imaging. 144 Additionally, for medical imaging, dosage reduction takes an important role. 145 OPT can take advantage of these CT strategies from medical imaging, such as compressed sensing and DL approaches, to reconstruct 3D volumes from fewer projection images to reduce the light dose and accelerate 3D image data acquisition.…”

Light-sheet mesoscopy with the Mesolens provides fast sub-cellular resolution imaging throughout large tissue volumes.

“…Nyquist sampling for the Mesolens FOV in widefield (and therefore light-sheet) modality corresponds to a 224 nm pixel size, for a total of 260MP. There are no commercially available cameras with said resolution, but the Mesolens camera detector (VNP-29MC, Vieworks) is equipped with a chip-shifting mechanism that by shifting the image by 1/3 of a pixel in a 3x3 square allows Nyquist sampling (Schniete et al, 2018, Shaw et al, 2021.…”

“…According to equations (1) and (2), a light-sheet 6 mm wide cannot have a thickness of less than approximately 50 µm (Born & Wolf, 2019). We cannot reduce the Rayleigh length of the beam to reduce the beam diameter and use a scanned light-sheet method because the sensor-shifting cameras required to image the Mesolens FOV with Nyquist sampled resolution are global shutter only (Schniete et al, 2018; Shaw et al, 2021). Although the Mesolens has a usable FOV 6 mm in diameter, our sensor-shifting camera restricts the FOV to 4.4 mm × 3 mm.…”

Paving the Way: Contributions of Big Data to Apicomplexan and Kinetoplastid Research

“…Beyond diagnosis, the field of parasitology has successfully generated multiple automated image analysis tools. This includes tools developed specifically for Apicomplexan ( Kudella et al., 2016 ; Perez-Guaita et al., 2016 ; Touquet et al., 2018 ; Fisch et al., 2019 ; Bauman et al., 2020 ; Fisch et al., 2020 ; Hung et al., 2020 ; Dey et al., 2021 ; Shaw et al., 2021 ; Yoon et al., 2021 ) and Kinetoplastid research ( Wheeler et al., 2012 ; Moon et al., 2014 ; Yazdanparast et al., 2014 ; Gomes-Alves et al., 2018 ; Moraes et al., 2019 ; Wheeler, 2020 ) and applied to a range of questions, from micrograph analysis, subcellular landmark investigation and parasite motility, to insect vector behavior. Many of these parameters are common outputs from ‘omics’ and large screen studies.…”