Handloomed fabrics recognition with deep learning

Every nation treasures its handloom heritage, and in India, the handloom industry safeguards cultural traditions, sustains millions of artisans, and preserves ancient weaving techniques. To protect this legacy, a critical need arises to distinguish genuine handloom products, exemplified by the renowned "gamucha" from India's northeast, from counterfeit powerloom imitations. Our study's objective is to create an AI tool for effortless detection of authentic handloom items amidst a sea of fakes. Six deep learning architectures-VGG16, VGG19, ResNet50, InceptionV3, InceptionResNetV2, and DenseNet201-were trained on annotated image repositories of handloom and powerloom towels (17,484 images in total, with 14,020 for training and 3464 for validation). A novel deep learning model was also proposed. Despite respectable training accuracies, the pre-trained models exhibited lower performance on the validation dataset compared to our novel model. The proposed model outperformed pre-trained models, demonstrating superior validation accuracy, lower validation loss, computational efficiency, and adaptability to the specific classification problem. Notably, the existing models showed challenges in generalizing to unseen data and raised concerns about practical deployment due to computational expenses. This study pioneers a computer-assisted approach for automated differentiation between authentic handwoven "gamucha"s and counterfeit powerloom imitations-a groundbreaking recognition method. The methodology presented not only holds scalability potential and opportunities for accuracy improvement but also suggests broader applications across diverse fabric products.

A double sliding-window method for baseline correction and noise estimation for Raman spectra of microplastics

When measuring microplastics of environmental samples, additives and attachment of biological materials may result in strong fluorescence in Raman spectra, which increases difficulty for imaging, identification, and quantification. Although there are several baseline correction methods available, user intervention is usually needed, which is not feasible for automated processes. In current study, a double sliding-window (DSW) method was proposed to estimate the baseline and standard deviation of noise. Simulated spectra and experimental spectra were used to evaluate the performance in comparison with two popular and widely used methods. Validation with simulated spectra and spectra of environmental samples showed that DSW method can accurately estimate the standard deviation of spectral noise. DSW method also showed better performance than compared methods when handling spectra of low signal-to-noise ratio (SNR) and elevated baselines. Therefore, DSW method is a useful approach for preprocessing Raman spectra of environmental samples and automated processes.

Drug-related causes attributed to acute kidney injury and their documentation in intensive care patients

PURPOSE

To investigate drug-related causes attributed to acute kidney injury (DAKI) and their documentation in patients admitted to the Intensive Care Unit (ICU).

METHODS

This study was conducted in an academic hospital in the Netherlands by reusing electronic health record (EHR) data of adult ICU admissions between November 2015 to January 2020. First, ICU admissions with acute kidney injury (AKI) stage 2 or 3 were identified. Subsequently, three modes of DAKI documentation in EHR were examined: diagnosis codes (structured data), allergy module (semi-structured data), and clinical notes (unstructured data).

RESULTS

n total 8124 ICU admissions were included, with 542 (6.7%) ICU admissions experiencing AKI stage 2 or 3. The ICU physicians deemed 102 of these AKI cases (18.8%) to be drug-related. These DAKI cases were all documented in the clinical notes (100%), one in allergy module (1%) and none via diagnosis codes. The clinical notes required the highest time investment to analyze.

CONCLUSIONS

Drug-related causes comprise a substantial part of AKI in the ICU patients. However, current unstructured DAKI documentation practice via clinical notes hampers our ability to gain better insights about DAKI occurrence. Therefore, both automating DAKI identification from the clinical notes and increasing structured DAKI documentation should be encouraged.

A deep learning approach to identify blepharoptosis by convolutional neural networks

PURPOSE

Blepharoptosis is a known cause of reversible vision loss. Accurate assessment can be difficult, especially amongst non-specialists. Existing automated techniques disrupt clinical workflow by requiring user input, or placement of reference markers. Neural networks are known to be effective in image classification tasks. We aim to develop an algorithm that can accurately identify blepharoptosis from a clinical photo.

METHODS

A total of 500 clinical photographs from patients with and without blepharoptosis were sourced from a tertiary ophthalmic center in Taiwan. Images were labeled by two oculoplastic surgeons, with an independent third oculoplastic surgeon to adjudicate disagreements. These images were used to train a series of convolutional neural networks (CNNs) to ascertain the best CNN architecture for this particular task.

RESULTS

Of the models that trained on the dataset, most were able to identify ptosis images with reasonable accuracy. We found the best performing model to use the DenseNet121 architecture without pre-training which achieved a sensitivity of 90.1 % with a specificity of 82.4 %, compared to the worst performing model which was used a Resnet34 architecture with pre-training, achieving a sensitivity of 74.1 %, and specificity of 63.6 %. Models with and without pre-training performed similarly (mean accuracy 82.6 % vs. 85.8 % respectively, p = 0.06), though models with pre-training took less time to train (1-minute vs. 16 min, p < 0.01).

CONCLUSIONS

We report the use of AI to accurately diagnose blepharoptosis from a clinical photograph with no external reference markers or user input requirement. Most current-generation CNN architectures performed reasonably on this task, with the DenseNet121, and Resnet18 architectures without pre-training performing best in our dataset.

Machine-learning strategies for testing patterns of morphological variation in small samples: sexual dimorphism in gray wolf (Canis lupus) crania

BACKGROUND

Studies of mammalian sexual dimorphism have traditionally involved the measurement of selected dimensions of particular skeletal elements and use of single data-analysis procedures. Consequently, such studies have been limited by a variety of both practical and conceptual constraints. To compare and contrast what might be gained from a more exploratory, multifactorial approach to the quantitative assessment of form-variation, images of a small sample of modern Israeli gray wolf (Canis lupus) crania were analyzed via elliptical Fourier analysis of cranial outlines, a Naïve Bayes machine-learning approach to the analysis of these same outline data, and a deep-learning analysis of whole images in which all aspects of these cranial morphologies were represented. The statistical significance and stability of each discriminant result were tested using bootstrap and jackknife procedures.

RESULTS

Our results reveal no evidence for statistically significant sexual size dimorphism, but significant sex-mediated shape dimorphism. These are consistent with the findings of prior wolf sexual dimorphism studies and extend these studies by identifying new aspects of dimorphic variation. Additionally, our results suggest that shape-based sexual dimorphism in the C. lupus cranial complex may be more widespread morphologically than had been appreciated by previous researchers.

CONCLUSION

Our results suggest that size and shape dimorphism can be detected in small samples and may be dissociated in mammalian morphologies. This result is particularly noteworthy in that it implies there may be a need to refine allometric hypothesis tests that seek to account for phenotypic sexual dimorphism. The methods we employed in this investigation are fully generalizable and can be applied to a wide range of biological materials and could facilitate the rapid evaluation of a diverse array of morphological/phenomic hypotheses.

Automated identification of cephalometric landmarks: Part 2- Might it be better than human?

OBJECTIVES

To compare detection patterns of 80 cephalometric landmarks identified by an automated identification system (AI) based on a recently proposed deep-learning method, the You-Only-Look-Once version 3 (YOLOv3), with those identified by human examiners.

MATERIALS AND METHODS

The YOLOv3 algorithm was implemented with custom modifications and trained on 1028 cephalograms. A total of 80 landmarks comprising two vertical reference points and 46 hard tissue and 32 soft tissue landmarks were identified. On the 283 test images, the same 80 landmarks were identified by AI and human examiners twice. Statistical analyses were conducted to detect whether any significant differences between AI and human examiners existed. Influence of image factors on those differences was also investigated.

RESULTS

Upon repeated trials, AI always detected identical positions on each landmark, while the human intraexaminer variability of repeated manual detections demonstrated a detection error of 0.97 ± 1.03 mm. The mean detection error between AI and human was 1.46 ± 2.97 mm. The mean difference between human examiners was 1.50 ± 1.48 mm. In general, comparisons in the detection errors between AI and human examiners were less than 0.9 mm, which did not seem to be clinically significant.

CONCLUSIONS

AI showed as accurate an identification of cephalometric landmarks as did human examiners. AI might be a viable option for repeatedly identifying multiple cephalometric landmarks.

Automated identification of cephalometric landmarks: Part 1-Comparisons between the latest deep-learning methods YOLOV3 and SSD

OBJECTIVE

To compare the accuracy and computational efficiency of two of the latest deep-learning algorithms for automatic identification of cephalometric landmarks.

MATERIALS AND METHODS

A total of 1028 cephalometric radiographic images were selected as learning data that trained You-Only-Look-Once version 3 (YOLOv3) and Single Shot Multibox Detector (SSD) methods. The number of target labeling was 80 landmarks. After the deep-learning process, the algorithms were tested using a new test data set composed of 283 images. Accuracy was determined by measuring the point-to-point error and success detection rate and was visualized by drawing scattergrams. The computational time of both algorithms was also recorded.

RESULTS

The YOLOv3 algorithm outperformed SSD in accuracy for 38 of 80 landmarks. The other 42 of 80 landmarks did not show a statistically significant difference between YOLOv3 and SSD. Error plots of YOLOv3 showed not only a smaller error range but also a more isotropic tendency. The mean computational time spent per image was 0.05 seconds and 2.89 seconds for YOLOv3 and SSD, respectively. YOLOv3 showed approximately 5% higher accuracy compared with the top benchmarks in the literature.

CONCLUSIONS

Between the two latest deep-learning methods applied, YOLOv3 seemed to be more promising as a fully automated cephalometric landmark identification system for use in clinical practice.

Diatom identification including life cycle stages through morphological and texture descriptors

Diatoms are unicellular algae present almost wherever there is water. Diatom identification has many applications in different fields of study, such as ecology, forensic science, etc. In environmental studies, algae can be used as a natural water quality indicator. The diatom life cycle consists of the set of stages that pass through the successive generations of each species from the initial to the senescent cells. Life cycle modeling is a complex process since in general the distribution of the parameter vectors that represent the variations that occur in this process is non-linear and of high dimensionality. In this paper, we propose to characterize the diatom life cycle by the main features that change during the algae life cycle, mainly the contour shape and the texture. Elliptical Fourier Descriptors (EFD) are used to describe the diatom contour while phase congruency and Gabor filters describe the inner ornamentation of the algae. The proposed method has been tested with a small algae dataset (eight different classes and more than 50 samples per type) using supervised and non-supervised classification techniques obtaining accuracy results up to 99% and 98% respectively.

Disentangling diatom species complexes: does morphometry suffice?

Accurate taxonomic resolution in light microscopy analyses of microalgae is essential to achieve high quality, comparable results in both floristic analyses and biomonitoring studies. A number of closely related diatom taxa have been detected to date co-occurring within benthic diatom assemblages, sharing many morphological, morphometrical and ecological characteristics. In this contribution, we analysed the hypothesis that, where a large sample size (number of individuals) is available, common morphometrical parameters (valve length, width and stria density) are sufficient to achieve a correct identification to the species level. We focused on some common diatom taxa belonging to the genus Gomphonema. More than 400 valves and frustules were photographed in valve view and measured using Fiji software. Several statistical tools (mixture and discriminant analysis, k-means clustering, classification trees, etc.) were explored to test whether mere morphometry, independently of other valve features, leads to correct identifications, when compared to identifications made by experts. In view of the results obtained, morphometry-based determination in diatom taxonomy is discouraged.

Computer vision applied to herbarium specimens of German trees: testing the future utility of the millions of herbarium specimen images for automated identification

BACKGROUND

Global Plants, a collaborative between JSTOR and some 300 herbaria, now contains about 2.48 million high-resolution images of plant specimens, a number that continues to grow, and collections that are digitizing their specimens at high resolution are allocating considerable recourses to the maintenance of computer hardware (e.g., servers) and to acquiring digital storage space. We here apply machine learning, specifically the training of a Support-Vector-Machine, to classify specimen images into categories, ideally at the species level, using the 26 most common tree species in Germany as a test case.

RESULTS

We designed an analysis pipeline and classification system consisting of segmentation, normalization, feature extraction, and classification steps and evaluated the system in two test sets, one with 26 species, the other with 17, in each case using 10 images per species of plants collected between 1820 and 1995, which simulates the empirical situation that most named species are represented in herbaria and databases, such as JSTOR, by few specimens. We achieved 73.21% accuracy of species assignments in the larger test set, and 84.88% in the smaller test set.

CONCLUSIONS

The results of this first application of a computer vision algorithm trained on images of herbarium specimens shows that despite the problem of overlapping leaves, leaf-architectural features can be used to categorize specimens to species with good accuracy. Computer vision is poised to play a significant role in future rapid identification at least for frequently collected genera or species in the European flora.

Characterization of intact N- and O-linked glycopeptides using higher energy collisional dissociation

Simultaneous elucidation of the glycan structure and the glycosylation site are needed to reveal the biological function of protein glycosylation. In this study, we employed a recent type of fragmentation termed higher energy collisional dissociation (HCD) to examine fragmentation patterns of intact glycopeptides generated from a mixture of standard glycosylated proteins. The normalized collisional energy (NCE) value for HCD was varied from 30 to 60% to evaluate the optimal conditions for the fragmentation of peptide backbones and glycoconjugates. Our results indicated that HCD with lower NCE values preferentially fragmented the sugar chains attached to the peptides to generate a ladder of neutral loss of monosaccharides, thereby enabling the putative glycan structure characterization. In addition, detection of the oxonium ions enabled unambiguous differentiation of glycopeptides from non-glycopeptides. In contrast, HCD with higher NCE values preferentially fragmented the peptide backbone and, thus, provided information needed for confident peptide identification. We evaluated the HCD approach with alternating NCE parameters for confident characterization of intact N- and O-linked glycopeptides in a single liquid chromatography-tandem mass spectrometry (LC-MS/MS) analysis. In addition, we applied a novel data analysis pipeline, so-called GlycoFinder, to form a basis for automated data analysis. Overall, 38 unique intact glycopeptides corresponding to eight glycosylation sites (six N-linked and two O-linked sites) were confidently identified from a standard protein mixture. This approach provided concurrent characterization of both the peptide and the glycan, thereby enabling comprehensive structural characterization of glycoproteins in a single LC-MS/MS analysis.