In-Process Control Assay of Pharmaceutical Microtablets Using Hyperspectral Imaging Coupled with Multivariate Analysis

Copper concentrate dual-band joint classification using reflectance hyperspectral images in the VIS-NIR and SWIR bands

A study on the classification of copper concentrates relevant to the copper refining industry is performed by means of reflectance hyperspectral images in the visible and near infrared (VIS-NIR) bands (400-1000 nm) and in the short-wave infrared (SWIR) (900-1700 nm) band. A total of 82 copper concentrate samples were press compacted into 13-mm-diameter pellets, and their mineralogical composition was characterized via quantitative evaluation of minerals and scanning electron microscopy. The most representative minerals contained in these pellets are bornite, chalcopyrite, covelline, enargite, and pyrite. Three databases (VIS-NIR, SWIR, and VIS-NIR-SWIR) containing a collection of average reflectance spectra computed from 9×9p i x e l neighborhoods in each pellet hyperspectral image are compiled to train the classification models. The classification models tested in this work are a linear discriminant classifier and two non-linear classifiers, a quadratic discriminant classifier, and a fine K-nearest neighbor classifier (FKNNC). The results obtained show that the joint use of VIS-NIR and SWIR bands allows for the accurate classification of similar copper concentrates that contain only minor differences in their mineralogical composition. Specifically, among the three tested classification models, the FKNNC performs the best in terms of overall classification accuracy, achieving 93.4% accuracy in the test set when only VIS-NIR data are used to construct the classification model, up to 80.5% using only SWIR data, and up to 97.6% using both VIS-NIR and SWIR bands together.

Spectrally-shaped illumination for improved optical inspection of lateral III-V-semiconductor oxidation

We report an hyperspectral imaging microscopy system based on a spectrally-shaped illumination and its use to offer an enhanced in-situ inspection of a technological process that is critical in Vertical-Cavity Surface-Emitting Laser (VCSEL) manufacturing, the lateral III-V-semiconductor oxidation (AlOx). The implemented illumination source exploits a digital micromirror device (DMD) to arbitrarily tailor its emission spectrum. When combined to an imager, this source is shown to provide an additional ability to detect minute surface reflectance contrasts on any VCSEL or AlOx-based photonic structure and, in turn, to offer improved in-situ inspection of the oxide aperture shapes and dimensions down to the best-achievable optical resolution. The demonstrated technique is very versatile and could be readily extended to the real-time monitoring of oxidation or other semiconductor technological processes as soon as they rely on a real-time yet accurate measurement of spatio-spectral (reflectance) maps.

Quantitative Mass Spectrometry Imaging Using Multivariate Curve Resolution and Deep Learning: A Case Study

In the present contribution, a novel approach based on multivariate curve resolution and deep learning (DL) is proposed for quantitative mass spectrometry imaging (MSI) as a potent technique for identifying different compounds and creating their distribution maps in biological tissues without need for sample preparation. As a case study, chlordecone as a carcinogenic pesticide was quantitatively determined in mouse liver using matrix-assisted laser desorption ionization-MSI (MALDI-MSI). For this purpose, data from seven standard spots containing 0 to 20 picomoles of chlordecone and four unknown tissues from the mouse livers infected with chlordecone for 1, 5, and 10 days were analyzed using a convolutional neural network (CNN). To solve the lack of sufficient data for CNN model training, each pixel was considered as a sample, the designed CNN models were trained by pixels in training sets, and their corresponding amounts of chlordecone were obtained by multivariate curve resolution-alternating least-squares (MCR-ALS). The trained models were then externally evaluated using calibration pixels in test sets for 1, 5, and 10 days of exposure, respectively. Prediction R² for all three data sets ranged from 0.93 to 0.96, which was superior to support vector machine (SVM) and partial least-squares (PLS). The trained CNN models were finally used to predict the amount of chlordecone in mouse liver tissues, and their results were compared with MALDI-MSI and GC-MS methods, which were comparable. Inspection of the results confirmed the validity of the proposed method.

A Review of Pharmaceutical Robot based on Hyperspectral Technology

The quality and safety of medicinal products are related to patients’ lives and health. Therefore, quality inspection takes a key role in the pharmaceutical industry. Most of the previous solutions are based on machine vision, however, their performance is limited by the RGB sensor. The pharmaceutical visual inspection robot combined with hyperspectral imaging technology is becoming a new trend in the high-end medical quality inspection process since the hyperspectral data can provide spectral information with spatial knowledge. Yet, there is no comprehensive review about hyperspectral imaging-based medicinal products inspection. This paper focuses on the pivotal pharmaceutical applications, including counterfeit drugs detection, active component analysis of tables, and quality testing of herbal medicines and other medical materials. We discuss the technology and hardware of Raman spectroscopy and hyperspectral imaging, firstly. Furthermore, we review these technologies in pharmaceutical scenarios. Finally, the development tendency and prospect of hyperspectral imaging technology-based robots in the field of pharmaceutical quality inspection is summarized.

Spectra Fusion of Mid-Infrared (MIR) and X-ray Fluorescence (XRF) Spectroscopy for Estimation of Selected Soil Fertility Attributes

Previous works indicate that data fusion, compared to single data modelling can improve the assessment of soil attributes using spectroscopy. In this work, two different kinds of proximal soil sensing techniques i.e., mid-infrared (MIR) and X-ray fluorescence (XRF) spectroscopy were evaluated, for assessment of seven fertility attributes. These soil attributes include pH, organic carbon (OC), phosphorous (P), potassium (K), magnesium (Mg), calcium (Ca) and moisture contents (MC). Three kinds of spectra fusion (SF) (spectra concatenation) approaches of MIR and XRF spectra were compared, namely, spectra fusion-Partial least square (SF-PLS), spectra fusion-Sequential Orthogonalized Partial least square (SF-SOPLS) and spectra fusion-Variable Importance Projection-Sequential Orthogonalized Partial least square (SF-VIP-SOPLS). Furthermore, the performance of SF models was compared with the developed single sensor model (based on individual spectra of MIR and XRF). Compared with the results obtained from single sensor model, SF models showed improvement in the prediction performance for all studied attributes, except for OC, Mg, and K prediction. More specifically, the highest improvement was observed with SF-SOPLS model for pH [R2p = 0.90, root mean square error prediction (RMSEP) = 0.15, residual prediction deviation (RPD) = 3.30, and ratio of performance inter-quantile (RPIQ) = 3.59], successively followed by P (R2p = 0.91, RMSEP = 4.45 mg/100 g, RPD = 3.53, and RPIQ = 4.90), Ca (R2p = 0.92, RMSEP = 177.11 mg/100 g, RPD = 3.66, and RPIQ = 3.22) and MC (R2p = 0.80, RMSEP = 1.91%, RPD = 2.31, RPIQ = 2.62). Overall the study concluded that SF approach with SOPLS attained better performance over the traditional model developed with the single sensor spectra, hence, SF is recommended as the best SF method for improving the prediction accuracy of studied soil attributes. Moreover, the multi-sensor spectra fusion approach is not limited for only MIR and XRF data but in general can be extended for complementary information fusion in order to improve the model performance in precision agriculture (PA) applications.

Real-time determination and visualization of two independent quantities during a manufacturing process of pharmaceutical tablets by near-infrared hyperspectral imaging combined with multivariate analysis

During pharmaceutical manufacturing, line-scan hyperspectral imaging enables us to collect several electromagnetic spectra at each pixel in a two-dimensional plane for each tablet. The present study quantitatively determines two independent values of the active pharmaceutical ingredient (API) content in a tablet and the amount of coating on a surface of the same tablet simultaneously; the process is visualized by means of a near-infrared hyperspectral imaging (NIR-HSI) system combined with multivariate data analysis at a typical manufacturing speed of 4,000 tablets per minute. The API content and the amount of coating were controlled to be in the range 80-120% and 0-7 mg, respectively. The results of the cross validation of regression models demonstrated a coefficient of determination (R²) of 0.942, a root-mean-square error of cross validation (RMSECV) of 3.48% for the API content, an R² of 0.939, and an RMSECV of 0.46 mg for the amount of coating. These results demonstrated that the API content in a tablet as well as the amount of coating on the surface of the same tablet can be simultaneously determined with sufficient accuracy. This technique is practically applicable to process analytical technology in pharmaceutical manufacturing.

Hyperspectral near infrared image calibration and regression

Reference materials are used in diffuse reflectance imaging for transforming the digitized camera signal into reflectance and absorbance units for subsequent interpretation. Traditional white and dark reference signals are generally used for calculating reflectance or absorbance, but these can be supplemented with additional reflectance targets to improve the accuracy of reflectance transformations. In this work we provide an overview of hyperspectral image regression and assess the effects of reflectance calibration on image interpretation using partial least squares regression. Linear and quadratic reflectance transformations based on additional reflectance targets decrease average measurement errors and make it easier to estimate model pseudorank during image regression. The lowest measurement and prediction errors were obtained with the column and wavelength specific quadratic transformations which retained the spatial information provided by the line-scanning instrument and reduced errors in the predicted concentration maps.

A novel multivariate curve resolution-alternating least squares (MCR-ALS) methodology for application in hyperspectral Raman imaging analysis

Multivariate curve resolution-alternating least squares (MCR-ALS) applied to hyperspectral Raman imaging is extensively used to spatially and spectrally resolve the individual, pure chemical species within complex, heterogeneous samples. A critical aspect of performing MCR-ALS with hyperspectral Raman imaging is the selection of the number of chemical components within the experimental data. Several methods have previously been proposed to determine the number of chemical components, but it remains a challenging task that if done incorrectly, can lead to the loss of chemical information. In this work, we show that the choice of 'optimal' number of factors in the MCR-ALS model may vary depending on the relative contribution of the targeted species to the overall spectral intensity. In a data set consisting of 27 hyperspectral Raman images of TiO2 polymorphs, it was observed that the more dominant species were best resolved with a parsimonious model. However, species with intensities near the noise level often needed more factors to be resolved than was predicted by standard methods. Based on the observations in this data set, we propose a new method that employs approximate reference spectra for determining optimal model complexity for identifying minor constituents with MCR-ALS.

Convolutional neural network for hyperspectral data analysis and effective wavelengths selection

Fusion of spectral and spatial information has been proved to be an effective approach to improve model performance in near-infrared hyperspectral data analysis. Regardless, most of the existing spectral-spatial classification methods require fairly complex pipelines and exact selection of parameters, which mainly depend on the investigator's experience and the object under test. Convolutional neural network (CNN) is a powerful tool for representing complicated data and usually works with few "hand-engineering", making it an appropriate candidate for developing a general and automatic approach. In this paper, a two-branch convolutional neural network (2B-CNN) was developed for spectral-spatial classification and effective wavelengths (EWs) selection. The proposed network was evaluated by three classification data sets, including herbal medicine, coffee bean and strawberry. The results showed that the 2B-CNN obtained the best classification accuracies (96.72% in average) when compared with support vector machine (92.60% in average), one dimensional CNN (92.58% in average), and grey level co-occurrence matrix based support vector machine (93.83% in average). Furthermore, the learned weights of the two-dimensional branch in 2B-CNN were adopted as the indicator of EWs and compared with the successive projections algorithm. The 2B-CNN models built with wavelengths selected by the weight indicator achieved the best accuracies (96.02% in average) among all the examined EWs models. Different from the conventional EWs selection method, the proposed algorithm works without any additional retraining and has the ability to comprehensively consider the discriminative power in spectral domain and spatial domain.