Obtaining new resolutions in carnivore tooth pit morphological analyses: A methodological update for digital taphonomy

Using computational learning for non-melanoma skin cancer and actinic keratosis near-infrared hyperspectral signature classification

BACKGROUND

The early detection of Non-Melanoma Skin Cancer (NMSC) is essential to ensure patients receive the most effective treatment. Diagnostic screening tools for NMSC are crucial due to high confusion rates with other types of skin lesions, such as Actinic Keratosis. Nevertheless, current means of diagnosing and screening patients rely on either visual criteria, that are often conditioned by subjectivity and experience, or highly invasive, slow, and costly methods, such as histological diagnoses. From this, the objectives of the present study are to test if classification accuracies improve in the Near-Infrared region of the electromagnetic spectrum, as opposed to previous research in shorter wavelengths.

METHODS

This study utilizes near-infrared hyperspectral imaging, within the range of 900.6 and 1454.8 nm. Images were captured for a total of 125 patients, including 66 patients with Basal Cell Carcinoma, 42 with cutaneous Squamous Cell Carcinoma, and 17 with Actinic Keratosis, to differentiate between healthy and unhealthy skin lesions. A combination of hybrid convolutional neural networks (for feature extraction) and support vector machine algorithms (as a final activation layer) was employed for analysis. In addition, we test whether transfer learning is feasible from networks trained on shorter wavelengths of the electromagnetic spectrum.

RESULTS

The implemented method achieved a general accuracy of over 80 %, with some tasks reaching over 90 %. F1 scores were also found to generally be over the optimal threshold of 0.8. The best results were obtained when detecting Actinic Keratosis, however differentiation between the two types of malignant lesions was often noted to be more difficult. These results demonstrate the potential of near-infrared hyperspectral imaging combined with advanced machine learning techniques in distinguishing NMSC from other skin lesions. Transfer learning was unsuccessful in improving the training of these algorithms.

CONCLUSIONS

We have shown that the Near-Infrared region of the electromagnetic spectrum is highly useful for the identification and study of non-melanoma type skin lesions. While the results are promising, further research is required to develop more robust algorithms that can minimize the impact of noise in these datasets before clinical application is feasible.

Data-driven classification and explainable-AI in the field of lung imaging

Detecting lung diseases in medical images can be quite challenging for radiologists. In some cases, even experienced experts may struggle with accurately diagnosing chest diseases, leading to potential inaccuracies due to complex or unseen biomarkers. This review paper delves into various datasets and machine learning techniques employed in recent research for lung disease classification, focusing on pneumonia analysis using chest X-ray images. We explore conventional machine learning methods, pretrained deep learning models, customized convolutional neural networks (CNNs), and ensemble methods. A comprehensive comparison of different classification approaches is presented, encompassing data acquisition, preprocessing, feature extraction, and classification using machine vision, machine and deep learning, and explainable-AI (XAI). Our analysis highlights the superior performance of transfer learning-based methods using CNNs and ensemble models/features for lung disease classification. In addition, our comprehensive review offers insights for researchers in other medical domains too who utilize radiological images. By providing a thorough overview of various techniques, our work enables the establishment of effective strategies and identification of suitable methods for a wide range of challenges. Currently, beyond traditional evaluation metrics, researchers emphasize the importance of XAI techniques in machine and deep learning models and their applications in classification tasks. This incorporation helps in gaining a deeper understanding of their decision-making processes, leading to improved trust, transparency, and overall clinical decision-making. Our comprehensive review serves as a valuable resource for researchers and practitioners seeking not only to advance the field of lung disease detection using machine learning and XAI but also from other diverse domains.

Near-infrared hyperspectral imaging and robust statistics for in vivo non-melanoma skin cancer and actinic keratosis characterisation

One of the most common forms of cancer in fair skinned populations is Non-Melanoma Skin Cancer (NMSC), which primarily consists of Basal Cell Carcinoma (BCC), and cutaneous Squamous Cell Carcinoma (SCC). Detecting NMSC early can significantly improve treatment outcomes and reduce medical costs. Similarly, Actinic Keratosis (AK) is a common skin condition that, if left untreated, can develop into more serious conditions, such as SCC. Hyperspectral imagery is at the forefront of research to develop non-invasive techniques for the study and characterisation of skin lesions. This study aims to investigate the potential of near-infrared hyperspectral imagery in the study and identification of BCC, SCC and AK samples in comparison with healthy skin. Here we use a pushbroom hyperspectral camera with a spectral range of ≈ 900 to 1600 nm for the study of these lesions. For this purpose, an ad hoc platform was developed to facilitate image acquisition. This study employed robust statistical methods for the identification of an optimal spectral window where the different samples could be differentiated. To examine these datasets, we first tested for the homogeneity of sample distributions. Depending on these results, either traditional or robust descriptive metrics were used. This was then followed by tests concerning the homoscedasticity, and finally multivariate comparisons of sample variance. The analysis revealed that the spectral regions between 900.66-1085.38 nm, 1109.06-1208.53 nm, 1236.95-1322.21 nm, and 1383.79-1454.83 nm showed the highest differences in this regard, with <1% probability of these observations being a Type I statistical error. Our findings demonstrate that hyperspectral imagery in the near-infrared spectrum is a valuable tool for analyzing, diagnosing, and evaluating non-melanoma skin lesions, contributing significantly to skin cancer research.

Using machine learning on new feature sets extracted from three-dimensional models of broken animal bones to classify fragments according to break agent

Distinguishing agents of bone modification at paleoanthropological sites is an important means of understanding early hominin evolution. Fracture pattern analysis is used to help determine site formation processes, including whether hominins were hunting or scavenging for animal food resources. Determination of how these behaviors manifested in ancient human sites has major implications for our biological and behavioral evolution, including social and cognitive abilities, dietary impacts of having access to in-bone nutrients like marrow, and cultural variation in butchering and food processing practices. Nevertheless, previous analyses remain inconclusive, often suffering from lack of replicability, misuse of mathematical methods, and/or failure to overcome equifinality. In this paper, we present a new approach aimed at distinguishing bone fragments resulting from hominin and carnivore breakage. Our analysis is founded on a large collection of scanned three-dimensional models of fragmentary bone broken by known agents, to which we apply state of the art machine learning algorithms. Our classification of fragments achieves an average mean accuracy of 77% across tests, thus demonstrating notable, but not overwhelming, success for distinguishing the agent of breakage. We note that, while previous research applying such algorithms has claimed higher success rates, fundamental errors in the application of machine learning protocols suggest that the reported accuracies are unjustified and unreliable. The systematic, fully documented, and proper application of machine learning algorithms leads to an inherent reproducibility of our study, and therefore our methods hold great potential for deciphering when and where hominins first began exploiting marrow and meat, and clarifying their importance and influence on human evolution.

A 39,600-year-old leather punch board from Canyars, Gavà, Spain

Puncture alignments are found on Palaeolithic carvings, pendants, and other fully shaped osseous artifacts. These marks were interpreted as abstract decorations, system of notations, and features present on human and animal depictions. Here, we create an experimental framework for the analysis and interpretation of human-made punctures and apply it to a highly intriguing, punctured bone fragment found at Canyars, an Early Upper Palaeolithic coastal site from Catalonia, Spain. Changes of tool and variation in the arrangement and orientation of punctures are consistent with the interpretation of this object as the earliest-known leather work punch board recording six episodes of hide pricking, one of which was to produce a linear seam. Our results indicate that Aurignacian hunters-gatherers used this technology to produce leather works and probably tailored clothes well before the introduction of bone eyed needles in Europe 15,000 years later.

A Novel Approach for the Shape Characterisation of Non-Melanoma Skin Lesions Using Elliptic Fourier Analyses and Clinical Images

The early detection of Non-Melanoma Skin Cancer (NMSC) is crucial to achieve the best treatment outcomes. Shape is considered one of the main parameters taken for the detection of some types of skin cancer such as melanoma. For NMSC, the importance of shape as a visual detection parameter is not well-studied. A dataset of 993 standard camera images containing different types of NMSC and benign skin lesions was analysed. For each image, the lesion boundaries were extracted. After an alignment and scaling, Elliptic Fourier Analysis (EFA) coefficients were calculated for the boundary of each lesion. The asymmetry of lesions was also calculated. Then, multivariate statistics were employed for dimensionality reduction and finally computational learning classification was employed to evaluate the separability of the classes. The separation between malignant and benign samples was successful in most cases. The best-performing approach was the combination of EFA coefficients and asymmetry. The combination of EFA and asymmetry resulted in a balanced accuracy of 0.786 and an Area Under Curve of 0.735. The combination of EFA and asymmetry for lesion classification resulted in notable success rates when distinguishing between benign and malignant lesions. In light of these results, skin lesions’ shape should be integrated as a fundamental part of future detection techniques in clinical screening.

3D Insights into the Effects of Captivity on Wolf Mastication and Their Tooth Marks; Implications in Ecological Studies of Both the Past and Present

Human populations have been known to develop complex relationships with large carnivore species throughout time, with evidence of both competition and collaboration to obtain resources throughout the Pleistocene. From this perspective, many archaeological and palaeontological sites present evidence of carnivore modifications to bone. In response to this, specialists in the study of microscopic bone surface modifications have resorted to the use of 3D modeling and data science techniques for the inspection of these elements, reaching novel limits for the discerning of carnivore agencies. The present research analyzes the tooth mark variability produced by multiple Iberian wolf individuals, with the aim of studying how captivity may affect the nature of tooth marks left on bone. In addition to this, four different populations of both wild and captive Iberian wolves are also compared for a more in-depth comparison of intra-species variability. This research statistically shows that large canid tooth pits are the least affected by captivity, while tooth scores appear more superficial when produced by captive wolves. The superficial nature of captive wolf tooth scores is additionally seen to correlate with other metric features, thus influencing overall mark morphologies. In light of this, the present study opens a new dialogue on the reasons behind this, advising caution when using tooth scores for carnivore identification and contemplating how elements such as stress may be affecting the wolves under study.

Hyperspectral imaging and robust statistics in non-melanoma skin cancer analysis

Non-Melanoma skin cancer is one of the most frequent types of cancer. Early detection is encouraged so as to ensure the best treatment, Hyperspectral imaging is a promising technique for non-invasive inspection of skin lesions, however, the optimal wavelengths for these purposes are yet to be conclusively determined. A visible-near infrared hyperspectral camera with an ad-hoc built platform was used for image acquisition in the present study. Robust statistical techniques were used to conclude an optimal range between 573.45 and 779.88 nm to distinguish between healthy and non-healthy skin. Wavelengths between 429.16 and 520.17 nm were additionally found to be optimal for the differentiation between cancer types.

Developments in data science solutions for carnivore tooth pit classification

Competition for resources is a key question in the study of our early human evolution. From the first hominin groups, carnivores have played a fundamental role in the ecosystem. From this perspective, understanding the trophic pressure between hominins and carnivores can provide valuable insights into the context in which humans survived, interacted with their surroundings, and consequently evolved. While numerous techniques already exist for the detection of carnivore activity in archaeological and palaeontological sites, many of these techniques present important limitations. The present study builds on a number of advanced data science techniques to confront these issues, defining methods for the identification of the precise agents involved in carcass consumption and manipulation. For the purpose of this study, a large sample of 620 carnivore tooth pits is presented, including samples from bears, hyenas, jaguars, leopards, lions, wolves, foxes and African wild dogs. Using 3D modelling, geometric morphometrics, robust data modelling, and artificial intelligence algorithms, the present study obtains between 88 and 98% accuracy, with balanced overall evaluation metrics across all datasets. From this perspective, and when combined with other sources of taphonomic evidence, these results show that advanced data science techniques can be considered a valuable addition to the taphonomist’s toolkit for the identification of precise carnivore agents via tooth pit morphology.

How Exactly Did the Nose Get That Long? A Critical Rethinking of the Pinocchio Effect and How Shape Changes Relate to Landmarks

The Pinocchio effect has long been discussed in the literature on geometric morphometrics. It denotes the observation that Procrustes superimposition tends to distribute shape changes over many landmarks, even though a different superimposition may exist for the same landmark configurations that concentrates changes in just one or a few landmarks. This is widely seen as a flaw of Procrustes methods. Visualizations illustrating the Pinocchio effect use a comparison of the same pair of shapes superimposed in two different ways: in a resistant-fit superimposition that concentrates the shape difference in just one or a few landmarks, and in Procrustes superimposition, which distributes differences over most or all landmarks. Because these superimpositions differ only in the non-shape aspects of size, position and orientation, they are equivalent from the perspective of shape analysis. Simulation studies of the Pinocchio effect usually generate data, either single pairs or larger samples of landmark configurations, in a particular superimposition so that differences occur mostly or exclusively at just one or a few landmarks, but no steps are taken to remove variation from size, position and orientation. When these configurations are then compared with Procrustes-superimposed data, differences appear and are attributed to the Pinocchio effect. Overall, it is ironic that all manifestations of the Pinocchio effect in one way or another rely on differences in the non-shape properties of position and orientation. Rigorous thinking about shape variation and careful choice of visualization methods can prevent confusion over this issue.