Search

The potato (Solanum tuberosum L.) is the world’s fifth most important staple food with high socioeconomic relevance. Several potato cultivars obtained by selection and crossbreeding are currently on the market. This diversity causes tubers to exhibit different behaviors depending on the processing to which they are subjected. Therefore, it is interesting to identify cultivars with specific characteristics that best suit consumer preferences. In this work, we present a method to classify potatoes according to their cooking or frying as crisps aptitude using NIR hyperspectral imaging (HIS) combined with a Partial Least Squares Discriminant Analysis (PLS-DA). Two classification approaches were used in this study. First, a classification model using the mean spectra of a dataset composed of 80 tubers belonging to 10 different cultivars. Then, a pixel-wise classification using all the pixels of each sample of a small subset of samples comprised of 30 tubers. Hyperspectral images were acquired using fresh-cut potato slices as sample material placed on a mobile platform of a hyperspectral system in the NIR range from 900 to 1,700 nm. After image processing, PLS-DA models were built using different pre-processing combinations. Excellent accuracy rates were obtained for the models developed using the mean spectra of all samples with 90% of tubers correctly classified in the external dataset. Pixel-wise classification models achieved lower accuracy rates between 66.62 and 71.97% in the external validation datasets. Moreover, a forward interval PLS (iPLS) method was used to build pixel-wise PLS-DA models reaching accuracies above 80 and 71% in cross-validation and external validation datasets, respectively. Best classification result was obtained using a subset of 100 wavelengths (20 intervals) with 71.86% of pixels correctly classified in the validation dataset. Classification maps were generated showing that false negative pixels were mainly located at the edges of the fresh-cut slices while false positive were principally distributed at the central pith, which has singular characteristics.

Neurodegenerative diseases are a group of largely incurable disorders characterised by the progressive loss of neurons and for which often the molecular mechanisms are poorly understood. To bridge this gap, researchers employ a range of techniques. A very prominent and useful technique adopted across many different fields is imaging and the analysis of histopathological and fluorescent label tissue samples. Although image acquisition has been efficiently automated recently, automated analysis still presents a bottleneck. Although various methods have been developed to automate this task, they tend to make use of single-purpose machine learning models that require extensive training, imposing a significant workload on the experts and introducing variability in the analysis. Moreover, these methods are impractical to audit and adapt, as their internal parameters are difficult to interpret and change. Here, we present a novel unsupervised automated schema for object segmentation of images, exemplified on a dataset of tissue images. Our schema does not require training data, can be fully audited and is based on a series of understandable biological decisions. In order to evaluate and validate our schema, we compared it with a state-of-the-art automated segmentation method for post-mortem tissues of ALS patients.

Powdery mildew is a worldwide major fungal disease for grapevine, which adversely affects both crop yield and produce quality. Disease identification is based on visible signs of a pathogen once the plant has already been infected; therefore, techniques that allow objective diagnosis of the disease are currently needed. In this study, the potential of hyperspectral imaging (HSI) technology to assess the presence of powdery mildew in grapevine bunches was evaluated. Thirty Carignan Noir grape bunches, 15 healthy and 15 infected, were analyzed using a lab-scale HSI system (900−1700 nm spectral range). Image processing was performed to extract spectral and spatial image features and then, classification models by means of Partial Least Squares Discriminant Analysis (PLS-DA) were carried out for healthy and infected pixels distinction within grape bunches. The best discrimination was achieved for the PLS-DA model with smoothing (SM), Standard Normal Variate (SNV) and mean centering (MC) pre-processing combination, reaching an accuracy of 85.33% in the cross-validation model and a satisfactory classification and spatial location of either healthy or infected pixels in the external validation. The obtained results suggested that HSI technology combined with chemometrics could be used for the detection of powdery mildew in black grapevine bunches.

IntroductionThe MDS-PSP criteria have shown high sensitivity for the PSP diagnosis, but do not discriminate the phenotype diversity. Our purpose was to search for anatomopathological differences among PSP phenotypes resulting from the application of the MDS-PSP criteria comparing with the previous ones.MethodsThirty-four PSP cases from a single brain bank were retrospectively classified according to the criteria used by Respondek et al. in 2014 and the PSP-MDS criteria at 3 years (MDS-3y), 6 years (MDS-6y) and at the last clinical evaluation before death (MDS-last). Semiquantitative measurement of total, cortical and subcortical tau load was compared. For comparative analysis, PSP-Richardson syndrome and PSP postural instability were grouped (PSP-RS/PI) as well as the PSP atypical cortical phenotypes (PSP-Cx).ResultsApplying the Respondek's criteria, PSP phenotypes were distributed as follow: 55.9% PSP-RS/PI, 26.5% PSP-Cx, 11.8% PSP-Parkinsonism (PSP-P), and 5.9% PSP-Cerebellum. PSP-RS/PI and PSP-Cx had a higher total tau load than PSP-P; PSP-Cx showed a higher cortical tau load than PSP-RS/PI and PSP-P; and PSP-RS/PI had a higher subcortical tau load than PSP-P. Applying the MDS-3y, MDS-6y and MDS-last criteria; the PSP-RS/PI group increased (67.6, 70.6 and 70.6% respectively) whereas the PSP-Cx group decreased (8.8, and 8.8 and 11.8%). Then, only differences in total and subcortical tau burden between PSP-RS/PI and PSP-P were observed.InterpretationAfter the retrospective application of the new MDS-PSP criteria, total and subcortical tau load is higher in PSP-RS/PI than in PSP-P whereas no other differences in tau load between phenotypes were found, as a consequence of the loss of phenotypic diversity.

The discrimination power of a hyperspectral imaging system for image segmentation or object detection is determined by the illumination, the camera spatial–spectral resolution, and both the pre-processing and analysis methods used for image processing. In this study, we methodically reviewed the alternatives for each of those factors for a case study from the food industry to provide guidance in the construction and configuration of hyperspectral imaging systems in the visible near infrared range for food quality inspection. We investigated both halogen- and LED-based illuminations and considered cameras with different spatial–spectral resolution trade-offs. At the level of the data analysis, we evaluated the impact of binning, median filtering and bilateral filtering as pre- or post-processing and compared pixel-based classifiers with convolutional neural networks for a challenging application in the food industry, namely ingredient identification in a flour–seed mix. Starting from a basic configuration and by modifying the combination of system aspects we were able to increase the mean accuracy by at least 25 %. In addition, different trade-offs in performance-complexity were identified for different combinations of system parameters, allowing adaptation to diverse application requirements.