Evaluating Urine Cytology Slide Digitization Efficiency: A Comparative Study Using an Artificial Intelligence-Based Heuristic Scanning Simulation and Multiple Z-Plane Scanning.

INTRODUCTION: Digitizing cytology slides presents challenges because of their three-dimensional features and uneven cell distribution. While multi-Z-plane scan is a prevalent solution, its adoption in clinical digital cytopathology is hindered by prolonged scanning times, increased image file sizes, and the requirement for cytopathologists to review multiple Z-plane images. METHODS: This study presents heuristic scan as a novel solution, using an artificial intelligence (AI)-based approach specifically designed for cytology slide scanning as an alternative to the multi-Z-plane scan. Both the 21 Z-plane scan and the heuristic scan simulation methods were used on 52 urine cytology slides from three distinct cytopreparations (Cytospin, ThinPrep, and BD CytoRich™ [SurePath]), generating whole-slide images (WSIs) via the Leica Aperio AT2 digital scanner. The AI algorithm inferred the WSI from 21 Z-planes to quantitate the total number of suspicious for high-grade urothelial carcinoma or more severe cells (SHGUC+) cells. The heuristic scan simulation calculated the total number of SHGUC+ cells from the 21 Z-plane scan data. Performance metrics including SHGUC+ cell coverage rates (calculated by dividing the number of SHGUC+ cells identified in multiple Z-planes or heuristic scan simulation by the total SHGUC+ cells in the 21 Z-planes for each WSI), scanning time, and file size were analyzed to compare the performance of each scanning method. The heuristic scan's metrics were linearly estimated from the 21 Z-plane scan data. Additionally, AI-aided interpretations of WSIs with scant SHGUC+ cells followed The Paris System guidelines and were compared with original diagnoses. RESULTS: The heuristic scan achieved median SHGUC+ cell coverage rates similar to 5 Z-plane scans across three cytopreparations (0.78-0.91 vs. 0.75-0.88, p = 0.451-0.578). Notably, it substantially reduced both scanning time (137.2-635.0 s vs. 332.6-1,278.8 s, p < 0.05) and image file size (0.51-2.10 GB vs. 1.16-3.10 GB, p < 0.05). Importantly, the heuristic scan yielded higher rates of accurate AI-aided interpretations compared to the single Z-plane scan (62.5% vs. 37.5%). CONCLUSION: We demonstrated that the heuristic scan offers a cost-effective alternative to the conventional multi-Z-plane scan in digital cytopathology. It achieves comparable SHGUC+ cell capture rates while reducing both scanning time and image file size, promising to aid digital urine cytology interpretations with a higher accuracy rate compared to the conventional single (optimal) plane scan. Further studies are needed to assess the integration of this new technology into compatible digital scanners for practical cytology slide scanning.

Comparative evaluation of slide scanners, scan settings, and cytopreparations for digital urine cytology.

Background: Acquiring well-focused digital images of cytology slides with scanners can be challenging due to the 3-dimensional nature of the slides. This study evaluates performances of whole-slide images (WSIs) obtained from 2 different cytopreparations by 2 distinct scanners with 3 focus modes. Methods: Fourteen urine specimens were collected from patients with urothelial carcinoma. Each specimen was equally divided into 2 portions, prepared with Cytospin and ThinPrep methods and scanned for WSIs using Leica (Aperio AT2) and Hamamatsu (NanoZoomer S360) scanners, respectively. The scan settings included 3 focus modes (default, semi-auto, and manual) for single-layer scanning, along with a manual focus mode for 21 Z-layers scanning. Performance metrics were evaluated including scanning success rate, artificial intelligence (AI) algorithm-inferred atypical cell numbers and coverage rate (atypical cell numbers in single or multiple Z-layers divided by the total atypical cell numbers in 21 Z-layers), scanning time, and image file size. Results: The default mode had scanning success rates of 85.7% or 92.9%, depending on the scanner used. The semi-auto mode increased success to 92.9% or 100%, and manual even further to 100%. However, these changes did not affect the standardized median atypical cell numbers and coverage rates. The selection of scanners, cytopreparations, and Z-stacking influenced standardized median atypical cell numbers and coverage rates, scanning times, and image file sizes. Discussion: Both scanners showed satisfactory scanning. We recommend using semi-auto or manual focus modes to achieve a scanning success rate of up to 100%. Additionally, a minimum of 9-layer Z-stacking at 1 µm intervals is required to cover 80% of atypical cells. These advanced focus methods do not impact the number of atypical cells or their coverage rate. While Z-stacking enhances the AI algorithm's inferred quantity and coverage rates of atypical cells, it simultaneously results in longer scanning times and larger image file sizes.

Evaluation of an artificial intelligence algorithm for assisting the Paris System in reporting urinary cytology: A pilot study.

BACKGROUND: The Paris System for Reporting Urinary Cytology (TPS) has been shown to improve bladder cancer diagnosis. Advances in artificial intelligence (AI) may assist and improve the clinical workflow by applying TPS in routine diagnostic services. METHODS: A deep-learning-based algorithm was developed to identify urothelial cancer candidate cells using whole-slide images (WSIs). In the testing cohort, 131 urine cytology slides were retrospectively retrieved and analyzed using this AI algorithm. The authors compared the performance of one cytopathologist and two cytotechnologists using AI-assisted digital urine cytology. Then, the AI-assisted WSIs were evaluated in the clinical workflow. The cytopathologist first made a diagnosis by reviewing the AI-inferred WSIs and quantitative data (nuclear-to-cytoplasmic ratio and nuclear size) for each sample. After a washout period, the same cytopathologist made a diagnosis for the same samples using direct microscopy. All diagnosis results were compared with the expert panel consensus. RESULTS: The AI-assisted diagnosis by the two cytotechnologists and the one cytopathologist demonstrated performance results that were comparable to the expert panel consensus (sensitivity, 79.5% and 82.1% vs. 92.3%, respectively; specificity, 100% and 98.9% vs. 100%, respectively). Furthermore, the performance of the AI-assisted WSIs compared with the microscopic diagnosis by the cytopathologist demonstrated superior sensitivity (92.3% vs. 87.2%) and negative predictive value (96.8% vs. 94.8%). In addition, the AI-assisted reporting demonstrated near perfect agreement with the expert panel consensus (κ = 0.944) and the microscopic diagnosis (κ = 0.862). CONCLUSIONS: The AI algorithm developed by the authors effectively assisted TPS-based reporting by providing AI-inferred WSIs and quantitative data.

EGFR in enterocytes & endothelium and HIF1α in enterocytes are dispensable for massive small bowel resection induced angiogenesis.

BACKGROUND: Short bowel syndrome (SBS) results from significant loss of small intestinal length. In response to this loss, adaptation occurs, with Epidermal Growth Factor Receptor (EGFR) being a key driver. Besides enhanced enterocyte proliferation, we have revealed that adaptation is associated with angiogenesis. Further, we have found that small bowel resection (SBR) is associated with diminished oxygen delivery and elevated levels of hypoxia-inducible factor 1-alpha (HIF1α). METHODS: We ablated EGFR in the epithelium and endothelium as well as HIF1α in the epithelium, ostensibly the most hypoxic element. Using these mice, we determined the effects of these genetic manipulations on intestinal blood flow after SBR using photoacoustic microscopy (PAM), intestinal adaptation and angiogenic responses. Then, given that endothelial cells require a stromal support cell for efficient vascularization, we ablated EGFR expression in intestinal subepithelial myofibroblasts (ISEMFs) to determine its effects on angiogenesis in a microfluidic model of human small intestine. RESULTS: Despite immediate increased demand in oxygen extraction fraction measured by PAM in all mouse lines, were no differences in enterocyte and endothelial cell EGFR knockouts or enterocyte HIF1α knockouts by POD3. Submucosal capillary density was also unchanged by POD7 in all mouse lines. Additionally, EGFR silencing in ISEMFs did not impact vascular network development in a microfluidic device of human small intestine. CONCLUSIONS: Overall, despite the importance of EGFR in facilitating intestinal adaptation after SBR, it had no impact on angiogenesis in three cell types-enterocytes, endothelial cells, and ISEMFs. Epithelial ablation of HIF1α also had no impact on angiogenesis in the setting of SBS.

Direct measurement of hypoxia in a xenograft multiple myeloma model by optical-resolution photoacoustic microscopy.

Using photoacoustic microscopy (PAM), we evaluated non-invasively oxygenation and vascularization in vivo due to multiple myeloma (MM) progression. Mice injected with MM.1S-GFP were monitored with a fluorescence microscope for tumor progression. In vivo PAM of the cerebral bone marrow quantified the total oxygen saturation (sO2). At 28 days after the MM cell injection, the total sO2 had decreased by half in the developing tumor regions, while in the non-tumor regions it had decreased by 20% compared with the value at one day post MM injection. The blood vessel density was reduced by 35% in the developing tumor regions, while in the non-tumor regions it was reduced by 8% compared with the value at one day post MM injection. Hence, PAM corroborated the development of hypoxia due to MM progression and demonstrated decreased vascularization surrounding the tumor areas.

Optical-resolution photoacoustic endomicroscopy in vivo.

Optical-resolution photoacoustic microscopy (OR-PAM) has become a major experimental tool of photoacoustic tomography, with unique imaging capabilities for various biological applications. However, conventional imaging systems are all table-top embodiments, which preclude their use in internal organs. In this study, by applying the OR-PAM concept to our recently developed endoscopic technique, called photoacoustic endoscopy (PAE), we created an optical-resolution photoacoustic endomicroscopy (OR-PAEM) system, which enables internal organ imaging with a much finer resolution than conventional acoustic-resolution PAE systems. OR-PAEM has potential preclinical and clinical applications using either endogenous or exogenous contrast agents.

In vivo optically encoded photoacoustic flowgraphy.

We present an optically encoded photoacoustic (PA) flow imaging method based on optical-resolution PA microscopy. An intensity-modulated continuous-wave laser photothermally encodes the flowing medium, and a pulsed laser generates PA waves to image the encoded heat pattern. Flow speeds can be calculated by cross correlation. The method was validated in phantoms at flow speeds ranging from 0.23 to 11 mm/s. Venous blood flow speed in a mouse ear was also measured.

Urogenital photoacoustic endoscope.

Photoacoustic (PA) endoscopy for human urogenital imaging has the potential to diagnose many important diseases, such as endometrial and prostate cancers. We have specifically developed a 12.7 mm diameter, rigid, side-scanning PA endoscopic probe for such applications. The key features of this endoscope are the streamlined structure for smooth cavity introduction and the proximal actuation mechanism for fast scanning. Here we describe the probe's composition and scanning mechanism and present in vivo experimental results suggesting its potential for comprehensive clinical applications.

Characterization of mechanical and geometrical properties of a tube with axial and circumferential guided waves.

Guided waves propagating in cylindrical tubes are frequently applied for the characterization of material or geometrical properties of tubes. In a tube, guided waves can propagate in the axial direction and called axial guided waves, or in the circumferential direction called circumferential guided waves. Dispersion spectra for the axial and circumferential guided waves share some common behaviors and however exhibit some particular behaviors of their own. This study provides an investigation with theoretical modeling, experimental measurements, and a simplex-based inversion procedure to explore the similarity and difference between the axial guided waves and circumferential guided waves, aiming at providing useful information while axial and circumferential guided waves are applied in the area of material characterization. The sensitivity to the radius curvature for the circumferential guided waves dispersion spectra is a major point that makes circumferential guided waves different from axial guided waves. For the purpose of material characterization, both axial and circumferential guided waves are able to extract an elastic moduli and wall-thickness information from the dispersion spectra, however, radius information can only be extracted from the circumferential guided waves spectra.