A deep-learning-based workflow to assess taxonomic affinity of hominid teeth with a test on discriminating Pongo and Homo upper molars

OBJECTIVES

Convolutional neural network (CNN) is a state-of-art deep learning (DL) method with superior performance in image classification. Here, a CNN-based workflow is proposed to discriminate hominid teeth. Our hope is that this method could help confirm otherwise questionable records of Homo from Pleistocene deposits where there is a standing risk of mis-attributing molars of Pongo to Homo.

METHODS AND MATERIALS

A two-step workflow was designed. The first step is converting the enamel-dentine junction (EDJ) into EDJ card, that is, a two-dimensional image conversion of the three-dimensional EDJ surface. In this step, researchers must carefully orient the teeth according to the cervical plane. The second step is training the CNN learner with labeled EDJ cards. A sample consisting of 53 fossil Pongo and 53 Homo (modern human and Neanderthal) was adopted to generate EDJ cards, which were then separated into training set (n = 84) and validation set (n = 22). To assess the feasibility of this workflow, a Pongo-Homo classifier was trained from the aforementioned EDJ card set, and then the classifier was used to predict the taxonomic affinities of six samples (test set) from von Koenigswald's Chinese Apothecary collection.

RESULTS

Results show that EDJ cards in validation set are classified accurately by the CNN learner. More importantly, taxonomic predictions for six specimens in test set match well with the diagnosis results deduced from multiple lines of evidence, implying the great potential of CNN method.

DISCUSSION

This workflow paves a way for future studies using CNN to address taxonomic complexity (e.g., distinguishing Pongo and Homo teeth from the Pleistocene of Asia). Further improvements include visual interpretation and extending the applicability to moderately worn teeth.

Species specificity and sexual dimorphism in tooth shape among the three sympatric haplochromine species in Lake Kivu cichlids

Tooth shape is used to differentiate between morphologically similar species of vertebrates, including fish. This study aimed to quantify tooth shape of three sympatric species: Haplochromis kamiranzovu, H. insidiae, and H. astatodon endemic to Lake Kivu, whose existing identification criteria are currently only qualitative. A quantitative tooth shape analysis was performed based on digitized tooth outline data with a subsequent elliptic Fourier analysis to test for differences among the three species. We looked at crown shape and size differences within H. kamiranzovu and H. insidiae at geographical, habitat, and gender levels. No comparison at habitat level was done for H. astatodon because it is found only in littoral zone. The analysis revealed significant tooth shape differences among the three species. Haplochromis astatodon had a significantly longer major cusp height and a longer and larger minor cusp than that of H. insidiae. It had also a longer major cusp height and a longer and larger minor cusp than that of H. kamiranzovu. Tooth shape differences of H. kamiranzovu and H. insidiae species were not significantly different between littoral and pelagic fish (p > .05) while differences were significant between southern and northern Lake Kivu populations (p < .05). Tooth sizes in H. kamiranzovu and H. insidiae were significantly different, both in height and width as well as in their ratios, and this was true at sex and geographic levels (p < .05), but not at habitat level (p > .05). Tooth shape was also significantly different with sharp teeth for males compared with females of southern populations versus northern ones. These shape- and size-related differences between sexes suggest differences in the foraging strategies toward available food resources in the lake habitat. Further research should explain the genetic basis of the observed pattern.