Machine learning for predicting Plasmodium liver stage development in vitro using microscopy imaging.

Malaria, a significant global health challenge, is caused by Plasmodium parasites. The Plasmodium liver stage plays a pivotal role in the establishment of the infection. This study focuses on the liver stage development of the model organism Plasmodium berghei, employing fluorescent microscopy imaging and convolutional neural networks (CNNs) for analysis. Convolutional neural networks have been recently proposed as a viable option for tasks such as malaria detection, prediction of host-pathogen interactions, or drug discovery. Our research aimed to predict the transition of Plasmodium-infected liver cells to the merozoite stage, a key development phase, 15 hours in advance. We collected and analyzed hourly imaging data over a span of at least 38 hours from 400 sequences, encompassing 502 parasites. Our method was compared to human annotations to validate its efficacy. Performance metrics, including the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity, were evaluated on an independent test dataset. The outcomes revealed an AUC of 0.873, a sensitivity of 84.6%, and a specificity of 83.3%, underscoring the potential of our CNN-based framework to predict liver stage development of P. berghei. These findings not only demonstrate the feasibility of our methodology but also could potentially contribute to the broader understanding of parasite biology.

A weakly supervised deep learning approach for label-free imaging flow-cytometry-based blood diagnostics.

The application of machine learning approaches to imaging flow cytometry (IFC) data has the potential to transform the diagnosis of hematological diseases. However, the need for manually labeled single-cell images for machine learning model training has severely limited its clinical application. To address this, we present iCellCnn, a weakly supervised deep learning approach for label-free IFC-based blood diagnostics. We demonstrate the capability of iCellCnn to achieve diagnosis of Sézary syndrome (SS) from patient samples on the basis of bright-field IFC images of T cells obtained after fluorescence-activated cell sorting of human peripheral blood mononuclear cell specimens. With a sample size of four healthy donors and five SS patients, iCellCnn achieved a 100% classification accuracy. As iCellCnn is not restricted to the diagnosis of SS, we expect such weakly supervised approaches to tap the diagnostic potential of IFC by providing automatic data-driven diagnosis of diseases with so-far unknown morphological manifestations.

Spectral Quantification of Nonlinear Elasticity Using Acoustoelasticity and Shear-Wave Dispersion.

Tissue biomechanical properties are known to be sensitive to pathological changes. Accordingly, various techniques have been developed to estimate tissue mechanical properties. Shear-wave elastography (SWE) measures shear-wave speed (SWS) in tissues, which can be related to shear modulus. Although viscosity or stress-strain nonlinearity may act as confounder of SWE, their explicit characterization may also provide additional information about tissue composition as a contrast modality. Viscosity can be related to frequency dispersion of SWS, which can be characterized using multi-frequency measurements, herein called spectral SWE (SSWE). Additionally, nonlinear shear modulus can be quantified and parameterized based on SWS changes with respect to applied stress, a phenomenon called acoustoelasticity (AE). In this work, we characterize the nonlinear parameters of tissue as a function of excitation frequency by utilizing both AE and SSWE together. For this, we apply incremental amounts of quasi-static stress on a medium, while imaging and quantifying SWS dispersion via SSWE. Results from phantom and ex vivo porcine liver experiments demonstrate the feasibility of measuring frequency-dependent nonlinear parameters using the proposed method. SWS propagation in porcine liver tissue was observed to change from 1.8 m/s at 100 Hz to 3.3 m/s at 700 Hz, while increasing by approximately 25% from a strain of 0% to 12% across these frequencies.

Robust Reconstruction of Elasticity Using Ultrasound Imaging and Multi-Frequency Excitations.

Biomedical parameters of tissue can be important indicators for clinical diagnosis. One such parameter that reflects tissue stiffness is elasticity, the imaging of which is called elastography. In this paper, we use displacements from harmonic excitations to solve the inverse problem of elasticity based on a finite-element method (FEM) formulation. This leads to iterative solution of nonlinear and nonconvex problems. In this paper, we show the importance and selection of viable initializations in numerical simulation studies and propose techniques for the fusion of multiple initializations for ideal reconstructions of unknown tissue as well as combining information from excitations at multiple frequencies. Results show that our method leads up to 76% decrease in root-mean-squared error (RMSE) and 9.9 dB increase in contrast-to-noise ratio (CNR) in simulations with noise, when compared to conventional iterative FEM without multiple initializations and frequencies. As the wave patterns in individually selected frequencies may introduce artifacts, a joint inverse-problem solution of multi-frequency excitations is introduced as a robust solution, where CNR improvements of up to 11.9 dB are observed. We also present the methods on a tissue-mimicking gelatin phantom study using mechanical excitation and ultrafast plane-wave ultrasound imaging, where the RMSE was improved by up to 51%. An experiment of ablation via heating an ex-vivo bovine liver shows that reconstruction artifacts are reduced with our proposed method.

FEM-based elasticity reconstruction using ultrasound for imaging tissue ablation.

PURPOSE: Success of ablation treatment depends on the accurate placement of the target ablation focus and the complete destruction of the pathological tissue. Thus, monitoring the formation, location, and size of the ablated lesion is essential. As ablated tissue gets stiffer, an option for ablation monitoring is ultrasound elastography, for imaging the tissue mechanical properties. Reconstruction of elasticity distribution can be achieved by solving an inverse problem from observed displacements, based on a deformable tissue model, commonly discretized by the finite element method (FEM). However, available reconstruction techniques are prone to noise and may achieve suboptimal accuracy. METHODS: We propose a novel inverse problem formulation and elasticity reconstruction method, in which both the elasticity parameters and the model displacements are estimated as independent parameters of an unconstrained optimization problem. Total variation regularization of spatial elasticity distribution is introduced in this formulation, providing robustness to noise. RESULTS: Our approach was compared to state of the art direct and iterative harmonic elastography techniques. We employed numerical simulation studies using various noise and inclusion contrasts, given multiple excitation frequencies. Compared to alternatives, our method leads to a decrease in RMSE of up to 50% and an increase in CNR of up to 11 dB in numerical simulations. The methods were also compared on an ex vivo bovine liver sample that was locally subjected to ablation, for which improved lesion delineation was obtained with our proposed method. Our method takes [Formula: see text] for [Formula: see text] reconstruction grid. CONCLUSIONS: We present a novel FEM problem formulation that improves reconstruction accuracy and inclusion delineation compared to currently available techniques.