Search

This presentation explores how n-grams can be used to automatically classify and learn about music. An overall discussion is provided of various ways in which n-grams can be adapted for use with digital scores, and of how musically meaningful features can be extracted from them. The jSymbolic 3.0 alpha prototype feature extractor is then used in three sets of music classification experiments investigating how n-gram features perform relative to and combined with other types of features extracted from symbolic music files., Funded by the FRQSC and SSHRC.

We present a Web application that facilitates the deep visual search of image collections using contemporary machine learning. We discuss image retrieval as a combined computer vision/human-computer interaction problem, and propose that the standardization of feature extraction is one of the main problems that digital art history faces today.

In this study, we are looking for early mentions of basic principles of sustainability in literary texts using machine learning. With a trained CRF-classifier we automatically annotated a corpus of about 70 novels from German romanticism and singled out passages with a high frequency of annotations, which we analysed in terms of a concept of sustainability. We thus test whether the application of machine learning used to operationalise high-frequency phenomena can also help uncover less frequent and highly interpretive aspects of narrative texts.

Collective sentiment plays a crucial role in financial markets. In this paper, we present our workflow for creating an index that captures the sentiment at the Berlin Stock Exchange from 1872 to 1930. Based on a historical newspaper, we train three models that provide daily aspect-level sentiment data.

The project develops an open-source machine learning platform for East Asian Studies, the first one in the United States.Our platform will be so versatile that humanists will not have to devote time to learning various digital tools. With our sample codes and tutorials, researchers can conduct computer-aided research.

What role does color play in how we imagine our own world and the world(s) of others? Using machine learning and methods from Explainable AI, we study and explain how color use shaped the geographic imaginaries of the Orient and Occident in two different media: photochromes and autochromes

This contribution deals with Dynamic Topic Modelling of Austrian historical newspapers (found in the ANNO Corpus), focusing on the time period from the 18th to the mid-20th Century. The aim of the investigation is to uncover the development of the topic surrounding migration from and via Southeast Europe to Austria.

A decade ago, Johanna Drucker asked: "Is There a 'Digital' Art History?" In this paper, we attempt to reconsider Drucker's question in the light of recent developments in computer vision by investigating the epistemic implications and methodological affordances of large-scale, transformer-based vision models.

This paper explores representations of holiness in a collection of 63.000 lantern slides. Using the multimodal model CLIP, it sheds light on the transition between the real and the imaginary, the holy and the profane. It demonstrates how CLIP can help scholars deal with complex visual concepts such as holiness.

The poster develops and discusses a new technique of modeling prototypicality in genre concepts based on the c@1-score as an uncertainty-based accuracy score and perspectival modeling within the framework of supervised machine learning. The technique is intended to provide better understanding of loosely ordered genres.

We present a modeling of document dates such that it can allow scholars to express uncertainty when annotating data, act as a differentiable loss function for training models and allow for unbiased interpretable performance evaluation under uncertainty.

Kao is a stylized signature used in East Asian cultures. Its location and size are important elements of document manners. This study explores information about their location and size in images through numerical summarization and visualization, and provides quantitative results that support existing tacit knowledge.

In large digital libraries, such as the HathiTrust, metadata is insufficient to identify items of interest. Metadata records are often incomplete and challenging for fiction, where metadata categories, when present, are too broad. This project constructs a machine learning pipeline for fiction classification using the HTRC Extracted Features Dataset, and based on previous work from Underwood et al. We will detail the methodology, early results, and planned future work in generating this dataset.

We consider the problem of estimating a signal from measurements obtained via a generalized linear model. We focus on estimators based on approximate message passing (AMP), a family of iterative algorithms with many appealing features: the performance of AMP in the high-dimensional limit can be succinctly characterized under suitable model assumptions; AMP can also be tailored to the empirical distribution of the signal entries, and for a wide class of estimation problems, AMP is conjectured to be optimal among all polynomial-time algorithms. However, a major issue of AMP is that in many models (such as phase retrieval), it requires an initialization correlated with the ground-truth signal and independent from the measurement matrix. Assuming that such an initialization is available is typically not realistic. In this paper, we solve this problem by proposing an AMP algorithm initialized with a spectral estimator. With such an initialization, the standard AMP analysis fails since the spectral estimator depends in a complicated way on the design matrix. Our main contribution is a rigorous characterization of the performance of AMP with spectral initialization in the high-dimensional limit. The key technical idea is to define and analyze a two-phase artificial AMP algorithm that first produces the spectral estimator, and then closely approximates the iterates of the true AMP. We also provide numerical results that demonstrate the validity of the proposed approach.

We consider the problem of estimating a signal from measurements obtained via a generalized linear model. We focus on estimators based on approximate message passing (AMP), a family of iterative algorithms with many appealing features: the performance of AMP in the high-dimensional limit can be succinctly characterized under suitable model assumptions; AMP can also be tailored to the empirical distribution of the signal entries, and for a wide class of estimation problems, AMP is conjectured to be optimal among all polynomial-time algorithms. However, a major issue of AMP is that in many models (such as phase retrieval), it requires an initialization correlated with the ground-truth signal and independent from the measurement matrix. Assuming that such an initialization is available is typically not realistic. In this paper, we solve this problem by proposing an AMP algorithm initialized with a spectral estimator. With such an initialization, the standard AMP analysis fails since the spectral estimator depends in a complicated way on the design matrix. Our main contribution is a rigorous characterization of the performance of AMP with spectral initialization in the high-dimensional limit. The key technical idea is to define and analyze a two-phase artificial AMP algorithm that first produces the spectral estimator, and then closely approximates the iterates of the true AMP. We also provide numerical results that demonstrate the validity of the proposed approach., Comment: 38 pages, 5 figures, AISTATS 2021

This article reports a simple and inexpensive leak-proof paper pad with an initial selection of a paper substrate on the grounds of surface morphology and fluid absorption time. Herein, a drying method is used for glucose detection on a paper pad through colorimetric analysis, and the spot detection of glucose is analyzed by optimizing the HRP concentration and volume to obtain accurate results. The rapid colorimetric method for the detection of glucose on the paper pad was developed with a limit of detection (LOD) of 2.92 mmol L−1. Furthermore, the effects of the detection conditions were investigated and discussed comprehensively with the help of chemometric methods. Paper pads were developed for glucose detection with a range of 0.5–20 mM (apropos to the normal glucose level in the human body) and 0.1–0.5 M (to test the excessive intake of glucose). The developed concept has huge potential in the healthcare sector, and its extension could be envisioned to develop the reported paper pad as a point-of-care testing device for the initial screening of a variety of diseases.

Adverse outcome pathways have shown themselves to be useful ways of understanding and expressing knowledge about sequences of events that lead to adverse outcomes (AOs) such as toxicity. In this paper we use the building blocks of adverse outcome pathways—namely key events (KEs) and key event relationships—to construct networks which can be used to make predictions of the likelihood of AOs. The networks of KEs are augmented by data from and knowledge about assays as well as by structure activity relationship predictions linking chemical classes to the observation of KEs. These inputs are combined within a reasoning framework to produce an information-rich display of the relevant knowledge and data and predictions of AOs both in the abstract case and for individual chemicals. Illustrative examples are given for skin sensitization, reprotoxicity and non-genotoxic carcinogenicity.

Microfluidic paper-based analytical devices (μPADs) have been widely used in point-of-care testing owing to their simple operation, low volume of the sample required, and the lack of the need for an external force. To obtain accurate semi-quantitative or quantitative results, μPADs need to respond to the challenges posed by differences in reaction conditions. In this paper, multi-layer μPADs are fabricated by the imprinting method for the colorimetric detection of C-reactive protein (CRP). Different lighting conditions and shooting angles of scenes are simulated in image acquisition, and the detection-related performance of μPADs is improved by using a machine learning algorithm. The You Only Look Once (YOLO) model is used to identify the areas of reaction in μPADs. This model can observe an image only once to predict the objects present in it and their locations. The YOLO model trained in this study was able to identify all the reaction areas quickly without incurring any error. These reaction areas were categorized by classification algorithms to determine the risk level of CRP concentration. Multi-layer perceptron, convolutional neural network, and residual network algorithms were used for the classification tasks, where the latter yielded the highest accuracy of 96%. It has a promising application prospect in fast recognition and analysis of μPADs.

Neurotoxicity is one of the main causes of drug withdrawal, and the biological experimental methods of detecting neurotoxic toxicity are time-consuming and laborious. In addition, the existing computational prediction models of neurotoxicity still have some shortcomings. In response to these shortcomings, we collected a large number of data set of neurotoxicity and used PyBioMed molecular descriptors and eight machine learning algorithms to construct regression prediction models of chemical neurotoxicity. Through the cross-validation and test set validation of the models, it was found that the extra-trees regressor model had the best predictive effect on neurotoxicity (${q}_{\mathrm{test}}^2$ = 0.784). In addition, we get the applicability domain of the models by calculating the standard deviation distance and the lever distance of the training set. We also found that some molecular descriptors are closely related to neurotoxicity by calculating the contribution of the molecular descriptors to the models. Considering the accuracy of the regression models, we recommend using the extra-trees regressor model to predict the chemical autonomic neurotoxicity.

We demonstrate the use of a convolutional neural network to perform neutron-gamma pulse shape discrimination, where the only inputs to the network are the raw digitised SiPM signals from a dual scintillator detector element made of 6LiF:ZnS(Ag) scintillator and PVT plastic. A realistic labelled dataset was created to train the network by exposing the detector to an AmBe source, and a data-driven method utilsing a separate PMT was used to assign labels to the recorded signals. This approach is compared to the charge integration and continuous wavelet transform methods and is found to provide superior levels of discrimination, achieving an AUC of 0.995 +/- 0.003. We find that the neural network is capable of extracting interpretable features directly from the raw data. In addition, by visualising the high-dimensional representations of the network with the t-SNE algorithm, we discover that not only is this method robust to minor mislabeling of the training dataset but that it is possible to identify an underlying substructure within the signals that goes beyond the original labelling. This technique could be utilised to explore and cluster complex, raw detector data in a novel way that may reveal more insights than standard analysis methods., 13 pages, 8 figures, submitted to Nucl. Instr. Meth. A

Significance: Diffuse reflectance spectroscopy (DRS) allows discrimination of tissue type. Its application is limited by the inability to mark the scanned tissue and the lack of real-time measurements. Aim: This study aimed to develop a real-time tracking system to enable localization of a DRS probe to aid the classification of tumor and non-tumor tissue. Approach: A green-colored marker attached to the DRS probe was detected using hue-saturation-value (HSV) segmentation. A live, augmented view of tracked optical biopsy sites was recorded in real time. Supervised classifiers were evaluated in terms of sensitivity, specificity, and overall accuracy. A developed software was used for data collection, processing, and statistical analysis. Results: The measured root mean square error (RMSE) of DRS probe tip tracking was 1.18±0.58 mm and 1.05±0.28 mm for the x and y dimensions, respectively. The diagnostic accuracy of the system to classify tumor and non-tumor tissue in real time was 94% for stomach and 96% for the esophagus. Conclusions: We have successfully developed a real-time tracking and classification system for a DRS probe. When used on stomach and esophageal tissue for tumor detection, the accuracy derived demonstrates the strength and clinical value of the technique to aid margin assessment in cancer resection surgery.

In this work, the capability of restricted Boltzmann machines (RBMs) to find solutions for the Kitaev honeycomb model with periodic boundary conditions is investigated. The measured groundstate (GS) energy of the system is compared and, for small lattice sizes (e.g. $3 \times 3$ with $18$ spinors), shown to agree with the analytically derived value of the energy up to a deviation of $0.09\%$. Moreover, the wave-functions we find have $99.89\%$ overlap with the exact ground state wave-functions. Furthermore, the possibility of realizing anyons in the RBM is discussed and an algorithm is given to build these anyonic excitations and braid them for possible future applications in quantum computation. Using the correspondence between topological field theories in (2+1)d and 2d CFTs, we propose an identification between our RBM states with the Moore-Read state and conformal blocks of the $2$d Ising model., Comment: (15+5) pages, 11 figures, 5 tables: Minor journal revisions and additions. + Journal ref

Paper spray ionization has been used as a fast sampling/ionization method for the direct mass spectrometric analysis of biological samples at ambient conditions. Here, we demonstrated that by utilizing paper spray ionization-mass spectrometry (PSI-MS) coupled with field asymmetric waveform ion mobility spectrometry (FAIMS), predictive metabolic and lipidomic profiles of routine breast core needle biopsies could be obtained effectively. By the combination of machine learning algorithms and pathological examination reports, we developed a classification model, which has an overall accuracy of 87.5% for an instantaneous differentiation between cancerous and noncancerous breast tissues utilizing metabolic and lipidomic profiles. Our results suggested that paper spray ionization-ion mobility spectrometry-mass spectrometry (PSI-IMS-MS) is a powerful approach for rapid breast cancer diagnosis based on altered metabolic and lipidomic profiles.

Funder: Royal Society; doi: http://dx.doi.org/10.13039/501100000288, Funder: Trinity College, University of Cambridge; doi: http://dx.doi.org/10.13039/501100000727, Funder: John Fell Fund, University of Oxford; doi: http://dx.doi.org/10.13039/501100004789, We use a deep neural network (NN) to detect and place region-of-interest (ROI) boxes around ultracold atom clouds in absorption and fluorescence images—with the ability to identify and bound multiple clouds within a single image. The NN also outputs segmentation masks that identify the size, shape and orientation of each cloud from which we extract the clouds’ Gaussian parameters. This allows 2D Gaussian fits to be reliably seeded thereby enabling fully automatic image processing. The method developed performs significantly better than a more conventional method based on a standardized image analysis library (Scikit-image) both for identifying ROI and extracting Gaussian parameters.

In the present study, iodide-mediated 3,3′,5,5′-tetramethylbenzidine (TMB)-H2O2 reaction system was applied to a microfluidic paper-based analytical device (μPAD) for non-enzymatic colorimetric determination of H2O2. The proposed system is portable and incorporates a μPAD with a machine learning-based smartphone app. A smartphone app called “Hi-perox Sens” capable of image capture, cropping and processing was developed to make the system simple and user-friendly. Briefly, circular μPADs were designed and tested with varying concentrations of H2O2. Following the color change, the images of the μPADs were taken with four different smartphones under seven different illumination conditions. In order to make the system more robust and adaptive against illumination variation and camera optics, the images were first processed for feature extraction and then used to train machine learning classifiers. According to the results, TMB + KI showed the highest classification accuracy (97.8%) with inter-phone repeatability at t = 30 s under versatile illumination and maintained its accuracy for 10 minutes. In addition, the performance of the system was also comparable to two different commercially available H2O2 kits in real samples.

Significance Prostate cancer is the most common cancer among men. An accurate diagnosis of its severity at detection plays a major role in improving their survival. Recently, machine learning models using biomarkers identified from Raman micro-spectroscopy discriminated intraductal carcinoma of the prostate (IDC-P) from cancer tissue with a ≥85 % detection accuracy and differentiated high-grade prostatic intraepithelial neoplasia (HGPIN) from IDC-P with a ≥97.8 % accuracy. Aim To improve the classification performance of machine learning models identifying different types of prostate cancer tissue using a new dimensional reduction technique. Approach A radial basis function (RBF) kernel support vector machine (SVM) model was trained on Raman spectra of prostate tissue from a 272-patient cohort (Centre hospitalier de l'Universite de Montreal, CHUM) and tested on two independent cohorts of 76 patients [University Health Network (UHN)] and 135 patients (Centre hospitalier universitaire de Quebec-Universite Laval, CHUQc-UL). Two types of engineered features were used. Individual intensity features, i.e., Raman signal intensity measured at particular wavelengths and novel Raman spectra fitted peak features consisting of peak heights and widths. Results Combining engineered features improved classification performance for the three aforementioned classification tasks. The improvements for IDC-P/cancer classification for the UHN and CHUQc-UL testing sets in accuracy, sensitivity, specificity, and area under the curve (AUC) are (numbers in parenthesis are associated with the CHUQc-UL testing set): +4 % (+8 % ), +7 % (+9 % ), +2 % (6%), +9 (+9) with respect to the current best models. Discrimination between HGPIN and IDC-P was also improved in both testing cohorts: +2.2 % (+1.7 % ), +4.5 % (+3.6 % ), +0 % (+0 % ), +2.3 (+0). While no global improvements were obtained for the normal versus cancer classification task [+0 % (-2 % ), +0 % (-3 % ), +2 % (-2 % ), +4 (+3)], the AUC was improved in both testing sets. Conclusions Combining individual intensity features and novel Raman fitted peak features, improved the classification performance on two independent and multicenter testing sets in comparison to using only individual intensity features.

Significance: Early detection of oral cancer is vital for high-risk patients, and machine learning-based automatic classification is ideal for disease screening. However, current datasets collected from high-risk populations are unbalanced and often have detrimental effects on the performance of classification. Aim: To reduce the class bias caused by data imbalance. Approach: We collected 3851 polarized white light cheek mucosa images using our customized oral cancer screening device. We use weight balancing, data augmentation, undersampling, focal loss, and ensemble methods to improve the neural network performance of oral cancer image classification with the imbalanced multi-class datasets captured from high-risk populations during oral cancer screening in low-resource settings. Results: By applying both data-level and algorithm-level approaches to the deep learning training process, the performance of the minority classes, which were difficult to distinguish at the beginning, has been improved. The accuracy of “premalignancy” class is also increased, which is ideal for screening applications. Conclusions: Experimental results show that the class bias induced by imbalanced oral cancer image datasets could be reduced using both data- and algorithm-level methods. Our study may provide an important basis for helping understand the influence of unbalanced datasets on oral cancer deep learning classifiers and how to mitigate.

Significance: Sub-diffuse optical properties may serve as useful cancer biomarkers, and wide-field heatmaps of these properties could aid physicians in identifying cancerous tissue. Sub-diffuse spatial frequency domain imaging (sd-SFDI) can reveal such wide-field maps, but the current time cost of experimentally validated methods for rendering these heatmaps precludes this technology from potential real-time applications. Aim: Our study renders heatmaps of sub-diffuse optical properties from experimental sd-SFDI images in real time and reports these properties for cancerous and normal skin tissue subtypes. Approach: A phase function sampling method was used to simulate sd-SFDI spectra over a wide range of optical properties. A machine learning model trained on these simulations and tested on tissue phantoms was used to render sub-diffuse optical property heatmaps from sd-SFDI images of cancerous and normal skin tissue. Results: The model accurately rendered heatmaps from experimental sd-SFDI images in real time. In addition, heatmaps of a small number of tissue samples are presented to inform hypotheses on sub-diffuse optical property differences across skin tissue subtypes. Conclusion: These results bring the overall process of sd-SFDI a fundamental step closer to real-time speeds and set a foundation for future real-time medical applications of sd-SFDI such as image guided surgery.

Significance: Screening and early detection of oral potentially malignant lesions (OPMLs) are of great significance in reducing the mortality rates associated with head and neck malignancies. Intra-oral multispectral optical imaging of tissues in conjunction with cloud-based machine learning (CBML) can be used to detect oral precancers at the point-of-care (POC) and guide the clinician to the most malignant site for biopsy. Aim: Develop a bimodal multispectral imaging system (BMIS) combining tissue autofluorescence and diffuse reflectance (DR) for mapping changes in oxygenated hemoglobin (HbO2) absorption in the oral mucosa, quantifying tissue abnormalities, and guiding biopsies. Approach: The hand-held widefield BMIS consisting of LEDs emitting at 405, 545, 575, and 610 nm, 5MPx monochrome camera, and proprietary Windows-based software was developed for image capture, processing, and analytics. The DR image ratio (R610/R545) was compared with pathologic classification to develop a CBML algorithm for real-time assessment of tissue status at the POC. Results: Sensitivity of 97.5% and specificity of 92.5% were achieved for discrimination of OPML from patient normal in 40 sites, whereas 82% sensitivity and 96.6% specificity were obtained for discrimination of abnormal (OPML + SCC) in 89 sites. Site-specific algorithms derived for buccal mucosa (27 sites) showed improved sensitivity and specificity of 96.3% for discrimination of OPML from normal. Conclusions: Assessment of oral cancer risk is possible by mapping of HbO2 absorption in tissues, and the BMIS system developed appears to be suitable for biopsy guidance and early detection of oral cancers.

Funder: Trinity College, University of Cambridge; doi: http://dx.doi.org/10.13039/501100000727, Selecting the most relevant features and samples out of a large set of candidates is a task that occurs very often in the context of automated data analysis, where it improves the computational performance and often the transferability of a model. Here we focus on two popular subselection schemes applied to this end: CUR decomposition, derived from a low-rank approximation of the feature matrix, and farthest point sampling (FPS), which relies on the iterative identification of the most diverse samples and discriminating features. We modify these unsupervised approaches, incorporating a supervised component following the same spirit as the principal covariates (PCov) regression method. We show how this results in selections that perform better in supervised tasks, demonstrating with models of increasing complexity, from ridge regression to kernel ridge regression and finally feed-forward neural networks. We also present adjustments to minimise the impact of any subselection when performing unsupervised tasks. We demonstrate the significant improvements associated with PCov-CUR and PCov-FPS selections for applications to chemistry and materials science, typically reducing by a factor of two the number of features and samples required to achieve a given level of regression accuracy.

The orbital angular momentum (OAM) of light has been at the center of several classical and quantum applications for imaging, information processing and communication. However, the complex structure inherent in OAM states makes their detection and classification nontrivial in many circumstances. Most of the current detection schemes are based on models of the OAM states built upon the use of Laguerre–Gauss (LG) modes. However, this may not in general be sufficient to capture full information on the generated states. In this paper, we go beyond the LG assumption, and employ hypergeometric-Gaussian (HyGG) modes as the basis states of a refined model that can be used—in certain scenarios—to better tailor OAM detection techniques. We show that enhanced performances in OAM detection are obtained for holographic projection via spatial light modulators in combination with single-mode fibers (SMFs), and for classification techniques based on a machine learning approach. Furthermore, a three-fold enhancement in the SMF coupling efficiency is obtained for the holographic technique, when using the HyGG model with respect to the LG one. This improvement provides a significant boost in the overall efficiency of OAM-encoded single-photon detection systems. Given that most of the experimental works using OAM states are effectively based on the generation of HyGG modes, our findings thus represent a relevant addition to experimental toolboxes for OAM-based protocols in quantum communication, cryptography and simulation.

The clinical importance of blood group (BG) antigens is related to their ability to induce immune antibodies that can cause hemolysis. Yet, ABO and D (Rh) are still considered to be the key antigens for healthy blood transfusion and secondary antigens are the next priority. Serological typing is the most widely used typing method. Rapid and accurate blood grouping plays an important role in some clinical conditions, rather than conventional techniques. Hence, developing a simple and economical model for rapid blood grouping would facilitate these tests. In recent decades, paper-based microfluidics such as μPADs has gained much interest in wide application areas such as point-of-care diagnostic. In this study, we evaluated μPADs that are performed for blood grouping and its recent progress. A comprehensive literature search was performed using databases including PUBMED, SCOPUS, Web of Science and Google Scholar. Keywords were blood grouping or typing, paper analytical device, rapid test, etc. After investigation of search results, 16 papers from 2010 to 2020 were included. Further information in detail was classified in Table 1. Generally, two principles for blood typing μPADs are introduced. The lateral chromatographic flow method and the vertical flow-through method that detects BG in a visual-based manner. To detect results with acceptable clarity many factors and challenges like paper, blood sample, buffer, Ab and RBC interaction and also μPADs stability need to be considered, which are discussed. In conclusion, the simplicity, stability, cheapness, portability and biocompatibility of μPADs for blood grouping confirming its utility and also they have the capability to robust, universal blood-grouping platform. Table 1 Summary of blood grouping tests using paper-based analytical devices Antigens Type of diagnosis Validation method Sample No Accuracy Action time Paper type Stability Sample dilution Buffer Ref A, B, Rh Forward volunteers records 5 - - Whatman No. 4 - 1/2 PBS* (Khan et al. 2010) A, B, Rh Forward gel assay test and conventional slide test 100 100% 1 min Whatman No. 4 and Kleeenex paper towel 7 Days in 4 °C 1/1 NSS (Al-Tamimi et al. 2012) A, B, Rh Forward gel card assay 99 100% 20 Sec + Washing Kleeenex paper towel - 1/1 NSS (Li et al. 2012) A, B, Rh Forward - - - - Kleeenex paper towel - 45/100 PSS (Li et al. 2013) A, B, Rh Forward gel card assay 98 100% 1.5 min Kleeenex paper towel - 85/100 PBS (Guan et al. 2014b) C, E, c, e, K, Jka, Jkb, M, N, S, P1, and Lea Forward gel card assay 266 100% - Kleeenex paper towel - 1/1 NSS (Li et al. 2014b) A, B, Rh Forward and Reverse conventional slide test 96 ≈ 91% 10 min Whatman No. 1 21 Days in 4 °C 1/2 NSS (Noiphung et al. 2015) C, c, E, e, K, k, Fya, Fyb, Jka, Jkb, M, N, S and s, P1, Lea and Leb Forward - 478 - - Kleeenex paper towel - 1/1 NSS, PBS (Then et al. 2015) A, B Forward and Reverse conventional slide test 76 100% 5-8 min Whatman No. 4 38 Days in 4 °C 1/4, 1/1 NSS (Songjaroen and Laiwattanapaisal 2016) D, K Forward volunteers records 210 - 7.5 min Kleenex paper towel - 1/1 NSS (Yeow et al. 2016) A, B, c, e, D, C, E, M, N, S, s, P1, Jka, Jkb, Lea, Leb, Fya, and Fyb Forward and Reverse gel card assay 3550 ≈100% 30 s Fiber glass and cotton linter 180 Days in 25 °C 45/100, 1/1 PBS (Zhang et al. 2017) A, B Forward conventional slide test 598 100% 3 min Whatman No. 113 14 Day in 4 °C 1/1 NSS (Songjaroen et al. 2018) A, B, Rh Forward conventional slide test - - 30 Sec + Washing Unrefined sisal paper - 1/2 NSS (Casals-Terré et al. 2019) A, B, Rh Forward - - - - Whatman No.1 - 1/1 NSS (Ansari et al. 2020) ABORh Forward and Reverse conventional slide test - 100% Unrefined Eucalyptus papers - 1/2 NSS, PBS (Casals-Terré et al. 2020) A, B, Rh Forward - - - 30 Sec + Washing Whatman No. 4 modified with chitosan ≥ 100 days in 25 °C 1/1 NSS (Parween et al. 2020)

Significance: Oral cancer is among the most common cancers globally, especially in low- and middle-income countries. Early detection is the most effective way to reduce the mortality rate. Deep learning-based cancer image classification models usually need to be hosted on a computing server. However, internet connection is unreliable for screening in low-resource settings. Aim: To develop a mobile-based dual-mode image classification method and customized Android application for point-of-care oral cancer detection. Approach: The dataset used in our study was captured among 5025 patients with our customized dual-modality mobile oral screening devices. We trained an efficient network MobileNet with focal loss and converted the model into TensorFlow Lite format. The finalized lite format model is ∼16.3 MB and ideal for smartphone platform operation. We have developed an Android smartphone application in an easy-to-use format that implements the mobile-based dual-modality image classification approach to distinguish oral potentially malignant and malignant images from normal/benign images. Results: We investigated the accuracy and running speed on a cost-effective smartphone computing platform. It takes ∼300 ms to process one image pair with the Moto G5 Android smartphone. We tested the proposed method on a standalone dataset and achieved 81% accuracy for distinguishing normal/benign lesions from clinically suspicious lesions, using a gold standard of clinical impression based on the review of images by oral specialists. Conclusions: Our study demonstrates the effectiveness of a mobile-based approach for oral cancer screening in low-resource settings.

Thermal papers, commonly used for printed receipts or lottery tickets, are omnipresent in our everyday life. They are regarded as semi-porous substrates, and yet can be critical to analyze when looking for latent fingermarks due to their thermosensibility. The aim of this study was to investigate a development sequence that would better combine the adequate detection techniques in order to maximize the chances to develop latent fingermarks left on these substrates. Different methods of development have been compared on test substrates: black magnetic powder, Lumicyano™, thermal development, ninhydrin and 1,2-indanedione/ZnCl2. Whitening stages and thermal development have been focused on, tested and optimized. The results of these preliminary tests enabled the study of three development sequences. They have subsequently been compared to the one currently used in the Gendarmerie's laboratories and the best results have been provided during pseudo-operational comparative trials by one of these sequences, consisting in 6 stages.

Significance: Acoustically detecting the rich optical absorption contrast in biological tissues, photoacoustic tomography (PAT) seamlessly bridges the functional and molecular sensitivity of optical excitation with the deep penetration and high scalability of ultrasound detection. As a result of continuous technological innovations and commercial development, PAT has been playing an increasingly important role in life sciences and patient care, including functional brain imaging, smart drug delivery, early cancer diagnosis, and interventional therapy guidance. Aim: Built on our 2016 tutorial article that focused on the principles and implementations of PAT, this perspective aims to provide an update on the exciting technical advances in PAT. Approach: This perspective focuses on the recent PAT innovations in volumetric deep-tissue imaging, high-speed wide-field microscopic imaging, high-sensitivity optical ultrasound detection, and machine-learning enhanced image reconstruction and data processing. Representative applications are introduced to demonstrate these enabling technical breakthroughs in biomedical research. Conclusions: We conclude the perspective by discussing the future development of PAT technologies.

Significance: Physiological parameters extracted from diffuse reflectance spectroscopy (DRS) provide clinicians quantitative information about tissue that helps aid in diagnosis. There is a great need for an accurate and cost-effective method for extracting parameters from DRS measurements. Aim: The aim is to explore the accuracy and speed of physiological parameter extraction using machine learning models compared to that of the widely used Monte Carlo lookup table (MCLUT) inverse model. Approach: Diffuse reflectance spectra were simulated using a light transport model based on Monte Carlo simulations and weighted to six wavelengths. Deep learning (DL), random forest (RF), gradient boosting machine (GBM), and generalized linear model (GLM) machine learning models were built using a training set of 10,000 spectra from the simulated data. The MCLUT and machine learning models were used to predict physiological parameters from a separate test set of 30,000 simulated spectra. Mean absolute errors were calculated to evaluate the accuracy and compare it among MCLUT and machine learning models. In addition, the computational time to predict parameters from the test set was recorded to compare the speed among MCLUT and machine learning models. Results: The DL, RF, GBM, and GLM models all had significantly lower errors than the MCLUT inverse method for six wavelengths. The DL model proved to have the lowest errors, with all absolute percent errors under 10%. The DL model had much faster runtimes than the MCLUT. Conclusions: Machine learning is promising for extracting physiological parameters from six-wavelength DRS data, with both lower errors and a faster runtime than the widely used MCLUT model.

Significance: Raman spectroscopy has been developed for surgical guidance applications interrogating live tissue during tumor resection procedures to detect molecular contrast consistent with cancer pathophysiological changes. To date, the vibrational spectroscopy systems developed for medical applications include single-point measurement probes and intraoperative microscopes. There is a need to develop systems with larger fields of view (FOVs) for rapid intraoperative cancer margin detection during surgery. Aim: We design a handheld macroscopic Raman imaging system for in vivo tissue margin characterization and test its performance in a model system. Approach: The system is made of a sterilizable line scanner employing a coherent fiber bundle for relaying excitation light from a 785-nm laser to the tissue. A second coherent fiber bundle is used for hyperspectral detection of the fingerprint Raman signal over an area of 1 cm2. Machine learning classifiers were trained and validated on porcine adipose and muscle tissue. Results: Porcine adipose versus muscle margin detection was validated ex vivo with an accuracy of 99% over the FOV of 95 mm2 in ∼3 min using a support vector machine. Conclusions: This system is the first large FOV Raman imaging system designed to be integrated in the workflow of surgical cancer resection. It will be further improved with the aim of discriminating brain cancer in a clinically acceptable timeframe during glioma surgery.

Purpose: Mesenchymal stem cells (MSCs) have demonstrated clinically relevant therapeutic effects for treatment of trauma and chronic diseases. The proliferative potential, immunomodulatory characteristics, and multipotentiality of MSCs in monolayer culture is reflected by their morphological phenotype. Standard techniques to evaluate culture viability are subjective, destructive, or time-consuming. We present an image analysis approach to objectively determine morphological phenotype of MSCs for prediction of culture efficacy. Approach: The algorithm was trained using phase-contrast micrographs acquired during the early and mid-logarithmic stages of MSC expansion. Cell regions are localized using edge detection, thresholding, and morphological operations, followed by cell marker identification using H-minima transform within each region to differentiate individual cells from cell clusters. Clusters are segmented using marker-controlled watershed to obtain single cells. Morphometric and textural features are extracted to classify cells based on phenotype using machine learning. Results: Algorithm performance was validated using an independent test dataset of 186 MSCs in 36 culture images. Results show 88% sensitivity and 86% precision for overall cell detection and a mean Sorensen–Dice coefficient of 0.849 ± 0.106 for segmentation per image. The algorithm exhibited an area under the curve of 0.816 (CI95 = 0.769 to 0.886) and 0.787 (CI95 = 0.716 to 0.851) for classifying MSCs according to their phenotype at early and mid-logarithmic expansion, respectively. Conclusions: The proposed method shows potential to segment and classify low and moderately dense MSCs based on phenotype with high accuracy and robustness. It enables quantifiable and consistent morphology-based quality assessment for various culture protocols to facilitate cytotherapy development.

Purpose: We investigated the performance of a neural network (NN) material decomposition method under varying pileup conditions. Approach: Experiments were performed at tube current settings that provided count rates incident on the detector through air equal to 9%, 14%, 27%, 40%, and 54% of the maximum detector count rate. An NN was trained for each count-rate level using transmission measurements through known thicknesses of basis materials (PMMA and aluminum). The NN trained for each count-rate level was applied to x-ray transmission measurements through test materials and to CT data of a rod phantom. Material decomposition error was evaluated as the distance in basis material space between the estimated thicknesses and ground truth. Results: There was no clear trend between count-rate level and material decomposition error for all test materials except neoprene. As an example result, Teflon error was 0.33 cm at the 9% count-rate level and 0.12 cm at the 54% count-rate level for the x-ray transmission experiments. Decomposition error increased with count-rate level for the neoprene test case, with 0.65-cm error at 9% count-rate level and 1.14-cm error at the 54% count-rate level. In the CT study, material decomposition error decreased with increasing incident count rate. For example, the material decomposition error for Teflon was 0.089, 0.066, 0.054 at count-rate levels of 14%, 27%, and 40%, respectively. Conclusions: Results demonstrate over a range of incident count-rate levels that an NN trained at a specific count-rate level can learn the relationship between photon-counting spectral measurements and basis material thicknesses.

Significance: Functional near-infrared spectroscopy (fNIRS) has been widely used to probe human brain function during task state and resting state. However, the existing analysis toolboxes mainly focus on task activation analysis, few software packages can assist resting-state fNIRS studies. Aim: We aimed to provide a versatile and easy-to-use toolbox to perform analysis for both resting state and task fNIRS. Approach: We developed a MATLAB toolbox called NIRS-KIT that works for both resting-state analysis and task activation detection. Results: NIRS-KIT implements common and necessary processing steps for performing fNIRS data analysis, including data preparation, quality control, preprocessing, individual-level analysis, group-level statistics with several popular statistical models, and multiple comparison correction methods, and finally results visualization. For resting-state fNIRS analysis, functional connectivity analysis, graph theory-based network analysis, and amplitude of low-frequency fluctuations analysis are provided. Additionally, NIRS-KIT also supports activation analysis for task fNIRS. Conclusions: NIRS-KIT offers an open source tool for researchers to analyze resting-state and/or task fNIRS data in one suite. It contains several key features: (1) good compatibility, supporting multiple fNIRS recording systems, data formats of NIRS-SPM and Homer2, and the shared near-infrared spectroscopy format data format recommended by the fNIRS society; (2) flexibility, supporting customized preprocessing scripts; (3) ease-to-use, allowing processing fNIRS signals in batch manner with user-friendly graphical user interfaces; and (4) feature-packed data viewing and result visualization. We anticipate that this NIRS-KIT will facilitate the development of the fNIRS field.