Effectiveness of Human-Artificial Intelligence Collaboration in Cephalometric Landmark Detection.

Detection of cephalometric landmarks has contributed to the analysis of malocclusion during orthodontic diagnosis. Many recent studies involving deep learning have focused on head-to-head comparisons of accuracy in landmark identification between artificial intelligence (AI) and humans. However, a human-AI collaboration for the identification of cephalometric landmarks has not been evaluated. We selected 1193 cephalograms and used them to train the deep anatomical context feature learning (DACFL) model. The number of target landmarks was 41. To evaluate the effect of human-AI collaboration on landmark detection, 10 images were extracted randomly from 100 test images. The experiment included 20 dental students as beginners in landmark localization. The outcomes were determined by measuring the mean radial error (MRE), successful detection rate (SDR), and successful classification rate (SCR). On the dataset, the DACFL model exhibited an average MRE of 1.87 ± 2.04 mm and an average SDR of 73.17% within a 2 mm threshold. Compared with the beginner group, beginner-AI collaboration improved the SDR by 5.33% within a 2 mm threshold and also improved the SCR by 8.38%. Thus, the beginner-AI collaboration was effective in the detection of cephalometric landmarks. Further studies should be performed to demonstrate the benefits of an orthodontist-AI collaboration.

Diagnosis of schizophrenia with functional connectome data: a graph-based convolutional neural network approach.

Previous deep learning methods have not captured graph or network representations of brain structural or functional connectome data. To address this, we developed the BrainNet-Global Covariance Pooling-Attention Convolutional Neural Network (BrainNet-GA CNN) by incorporating BrainNetCNN and global covariance pooling into the self-attention mechanism. Resting-state functional magnetic resonance imaging data were obtained from 171 patients with schizophrenia spectrum disorders (SSDs) and 161 healthy controls (HCs). We conducted an ablation analysis of the proposed BrainNet-GA CNN and quantitative performance comparisons with competing methods using the nested tenfold cross validation strategy. The performance of our model was compared with competing methods. Discriminative connections were visualized using the gradient-based explanation method and compared with the results obtained using functional connectivity analysis. The BrainNet-GA CNN showed an accuracy of 83.13%, outperforming other competing methods. Among the top 10 discriminative connections, some were associated with the default mode network and auditory network. Interestingly, these regions were also significant in the functional connectivity analysis. Our findings suggest that the proposed BrainNet-GA CNN can classify patients with SSDs and HCs with higher accuracy than other models. Visualization of salient regions provides important clinical information. These results highlight the potential use of the BrainNet-GA CNN in the diagnosis of schizophrenia.

Estimating Cervical Vertebral Maturation with a Lateral Cephalogram Using the Convolutional Neural Network.

Recently, the estimation of bone maturation using deep learning has been actively conducted. However, many studies have considered hand-wrist radiographs, while a few studies have focused on estimating cervical vertebral maturation (CVM) using lateral cephalograms. This study proposes the use of deep learning models for estimating CVM from lateral cephalograms. As the second, third, and fourth cervical vertebral regions (denoted as C2, C3, and C4, respectively) are considerably smaller than the whole image, we propose a stepwise segmentation-based model that focuses on the C2-C4 regions. We propose three convolutional neural network-based classification models: a one-step model with only CVM classification, a two-step model with region of interest (ROI) detection and CVM classification, and a three-step model with ROI detection, cervical segmentation, and CVM classification. Our dataset contains 600 lateral cephalogram images, comprising six classes with 100 images each. The three-step segmentation-based model produced the best accuracy (62.5%) compared to the models that were not segmentation-based.

Deep Anatomical Context Feature Learning for Cephalometric Landmark Detection.

In the past decade, anatomical context features have been widely used for cephalometric landmark detection and significant progress is still being made. However, most existing methods rely on handcrafted graphical models rather than incorporating anatomical context during training, leading to suboptimal performance. In this study, we present a novel framework that allows a Convolutional Neural Network (CNN) to learn richer anatomical context features during training. Our key idea consists of the Local Feature Perturbator (LFP) and the Anatomical Context loss (AC loss). When training the CNN, the LFP perturbs a cephalometric image based on prior anatomical distribution, forcing the CNN to gaze relevant features more globally. Then AC loss helps the CNN to learn the anatomical context based on spatial relationships between the landmarks. The experimental results demonstrate that the proposed framework makes the CNN learn richer anatomical representation, leading to increased performance. In the performance comparisons, the proposed scheme outperforms state-of-the-art methods on the ISBI 2015 Cephalometric X-ray Image Analysis Challenge.

SVM-based waist circumference estimation using Kinect.

BACKGROUND AND OBJECTIVE: Conventional anthropometric studies using Kinect depth sensors have concentrated on estimating the distances between two points such as height. This paper deals with a novel waist measurement method using SVM regression, further widening spectrum of Kinect's potential applications. Waist circumference is a key index for the diagnosis of abdominal obesity, which has been linked to metabolic syndromes and other related diseases. Yet, the existing measuring method, tape measure, requires a trained personnel and is therefore costly and time-consuming. METHODS: A dataset was constructed by recording both 30 frames of Kinect depth image and careful tape measurement of 19 volunteers by a clinical investigator. This paper proposes a new SVM regressor-based approach for estimating waist circumference. A waist curve vector is extracted from a raw depth image using joint information provided by Kinect SDK. To avoid overfitting, a data augmentation technique is devised. The 30 frontal vectors and 30 backside vectors, each sampled for 1 s per person, are combined to form 900 waist curve vectors and a total of 17,100 samples were collected from 19 individuals. On an individual basis, we performed leave-one-out validation using the SVM regressor with the tape measurement-gold standard of waist circumference measurement-values labeled as ground-truth. On an individual basis, we performed leave-one-out validation using the SVM regressor with the tape measurement-gold standard of waist circumference measurement-values labeled as ground-truth. RESULTS: The mean error of the SVM regressor was 4.62 cm, which was smaller than that of the geometric estimation method. Potential uses are discussed. CONCLUSIONS: A possible method for measuring waist circumference using a depth sensor is demonstrated through experimentation. Methods for improving accuracy in the future are presented. Combined with other potential applications of Kinect in healthcare setting, the proposed method will pave the way for patient-centric approach of delivering care without laying burdens on patients.

Author Correction: Classification and Visualization of Alzheimer's Disease using Volumetric Convolutional Neural Network and Transfer Learning.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Classification and Visualization of Alzheimer's Disease using Volumetric Convolutional Neural Network and Transfer Learning.

Recently, deep-learning-based approaches have been proposed for the classification of neuroimaging data related to Alzheimer's disease (AD), and significant progress has been made. However, end-to-end learning that is capable of maximizing the impact of deep learning has yet to receive much attention due to the endemic challenge of neuroimaging caused by the scarcity of data. Thus, this study presents an approach meant to encourage the end-to-end learning of a volumetric convolutional neural network (CNN) model for four binary classification tasks (AD vs. normal control (NC), progressive mild cognitive impairment (pMCI) vs. NC, stable mild cognitive impairment (sMCI) vs. NC and pMCI vs. sMCI) based on magnetic resonance imaging (MRI) and visualizes its outcomes in terms of the decision of the CNNs without any human intervention. In the proposed approach, we use convolutional autoencoder (CAE)-based unsupervised learning for the AD vs. NC classification task, and supervised transfer learning is applied to solve the pMCI vs. sMCI classification task. To detect the most important biomarkers related to AD and pMCI, a gradient-based visualization method that approximates the spatial influence of the CNN model's decision was applied. To validate the contributions of this study, we conducted experiments on the ADNI database, and the results demonstrated that the proposed approach achieved the accuracies of 86.60% and 73.95% for the AD and pMCI classification tasks respectively, outperforming other network models. In the visualization results, the temporal and parietal lobes were identified as key regions for classification.

Classification of schizophrenia and normal controls using 3D convolutional neural network and outcome visualization.

BACKGROUND: The recent deep learning-based studies on the classification of schizophrenia (SCZ) using MRI data rely on manual extraction of feature vector, which destroys the 3D structure of MRI data. In order to both identify SCZ and find relevant biomarkers, preserving the 3D structure in classification pipeline is critical. OBJECTIVES: The present study investigated whether the proposed 3D convolutional neural network (CNN) model produces higher accuracy compared to the support vector machine (SVM) and other 3D-CNN models in distinguishing individuals with SCZ spectrum disorders (SSDs) from healthy controls. We sought to construct saliency map using class saliency visualization (CSV) method. METHODS: Task-based fMRI data were obtained from 103 patients with SSDs and 41 normal controls. To preserve spatial locality, we used 3D activation map as input for the 3D convolutional autoencoder (3D-CAE)-based CNN model. Data on 62 patients with SSDs were used for unsupervised pretraining with 3D-CAE. Data on the remaining 41 patients and 41 normal controls were processed for training and testing with CNN. The performance of our model was analyzed and compared with SVM and other 3D-CNN models. The learned CNN model was visualized using CSV method. RESULTS: Using task-based fMRI data, our model achieved 84.15%∼84.43% classification accuracies, outperforming SVM and other 3D-CNN models. The inferior and middle temporal lobes were identified as key regions for classification. CONCLUSIONS: Our findings suggest that the proposed 3D-CAE-based CNN can classify patients with SSDs and controls with higher accuracy compared to other models. Visualization of salient regions provides important clinical information.

Alteration of Semantic Networks during Swear Words Processing in Schizophrenia.

OBJECTIVE: Positive symptoms, such as delusion and hallucination, commonly include negative emotional content in schizophrenia. We investigated the neural basis implicated during the processing of strong negative emotional words in patients with schizophrenia. METHODS: In our study, 35 patients with schizophrenia and 19 healthy controls were recruited, and the participants were asked to passively view the words that contained swearing and neutral content during functional magnetic resonance imaging. RESULTS: Patients with schizophrenia, compared to healthy controls, showed hypoactivation to the swear and neutral words stimuli in the left inferior frontal gyrus, left middle frontal gyrus, and left angular/supramarginal gyrus. More specifically, patients with remitted schizophrenia were found to have greater activation to the stimuli in the left middle/inferior frontal gyrus than patients with active schizophrenia. Furthermore, in the analysis of regions of interests, the left inferior and middle frontal gyrus activity was related to the severity of positive symptoms, including delusion and suspiciousness. CONCLUSION: Our results suggest that patients with schizophrenia have difficulty in semantic processing and inhibitory control of swear words, and these abnormalities may be connected with the severity of positive symptoms.

Potentiation of natural killer (NK) cell activity by methanol extract of cultured cambial meristematic cells of wild ginseng and its mechanism.

AIMS: As an alternative strategy to obtain large amounts of ginseng extract with high yield of ginsenosides, we have utilized culture of cambial meristematic cells (CMCs) from wild ginseng. The anti-tumor effects of methanol extract of ginseng CMCs (MEGC) and their action mechanisms were investigated. MAIN METHODS: Mice were intraperitoneally administered with MEGC, and we explored NK cell activity, suppression of in vivo growth of tumor cells and relevant molecule expression. KEY FINDINGS: MEGC significantly potentiated NK cell activity and suppressed in vivo growth of B16 melanoma cells. However, we observed no increase in NK cell number and unaltered expression of NK cell-activating (NKG2D) and inhibitory (Ly49, CD94/NKG2A) receptors as well as NK cell activation markers (CD25, CD69, CD119, and CD212) in MEGC-treated group compared to the controls. Instead, MEGC significantly enhanced IL-2 responsiveness in the early effector phase and the constitutive expression of granzyme B. SIGNIFICANCE: Our data indicate that culture of CMCs is an attractive alternative method for sustainable production of ginseng extracts and clinical use. In addition, we have unraveled a novel mechanism underlying the potentiation of NK cell activity and antitumor effect of ginseng extract, in which it upregulates the constitutive expression of cytotoxic mediator(s) and IL-2 responsiveness.

Suppression of lipopolysaccharide-induced expression of inflammatory indicators in RAW 264.7 macrophage cells by extract prepared from Ginkgo biloba cambial meristematic cells.

CONTEXT: Ginkgo biloba L. (Ginkgoaceae) leaves have been used as an herbal medicine that has a complex range of biological activities. However, when we consider that biological activity of plant extracts is highly variable according to the source, location, and harvest season, technology to obtain the natural products with homogeneity is extremely important. OBJECTIVE: We established the technology to obtain the cambial meristematic cells (CMCs) of Ginkgo biloba, which were expanded in vitro with homogeneity through a suspension culture and then determined the anti-inflammatory activity of fractionated samples prepared from the ethanol extract of CMCs. MATERIALS AND METHODS: We determined the anti-inflammatory activity of samples using lipopolysaccharide (LPS)-stimulated RAW 264.7 macrophage cells. Especially, influence of sample treatment on the expression of various indicators, such as nitric oxide (NO), inducible nitric oxide synthase (iNOS), cyclooxygenase (COX)-2, mitogen-activated protein (MAP) kinases, transcription factor, and cytokines, involved in inflammatory activity was assessed. RESULTS: A fractionated sample demonstrated 53.4% inhibition of LPS-induced NO production from the cells. Additionally, when fractionated samples were treated, iNOS and COX-2 expressions were almost completely suppressed. Fractionated samples also inhibited the phosphorylation of LPS-induced extracellular signal-regulated (ERK) and p38 MAP kinases more than 60%. IκB phosphorylation and subsequent nuclear factor (NF)-κB activation were also suppressed by fractionated samples. The expression of pro-inflammatory cytokines, IL-6 and tumor necrosis factor (TNF)-α, was significantly inhibited by the sample treatment. DISCUSSION AND CONCLUSION: Fractionated samples from the ethanol extract of Ginkgo biloba CMCs could potentially be the source of a powerful anti-inflammatory substance.

Secretome analysis reveals an Arabidopsis lipase involved in defense against Alternaria brassicicola.

The Arabidopsis thaliana secretome was analyzed by the proteomic approach, which led to the identification of secreted proteins implicated in many aspects of cell biology. We then investigated the change in the Arabidopsis secretome in response to salicylic acid and identified several proteins involved in pathogen response. One of these, a secreted lipase with a GDSL-like motif designated GDSL LIPASE1 (GLIP1), was further characterized for its function in disease resistance. glip1 plants were markedly more susceptible to infection by the necrotrophic fungus Alternaria brassicicola compared with the parental wild-type plants. The recombinant GLIP1 protein possessed lipase and antimicrobial activities that directly disrupt fungal spore integrity. Furthermore, GLIP1 appeared to trigger systemic resistance signaling in plants when challenged with A. brassicicola, because pretreatment of the glip1 mutant with recombinant GLIP1 protein inhibited A. brassicicola-induced cell death in both peripheral and distal leaves. Moreover, glip1 showed altered expression of defense- and ethylene-related genes. GLIP1 transcription was increased by ethephon, the ethylene releaser, but not by salicylic acid or jasmonic acid. These results suggest that GLIP1, in association with ethylene signaling, may be a critical component in plant resistance to A. brassicicola.

Hybrid genetic algorithms for feature selection.

This paper proposes a novel hybrid genetic algorithm for feature selection. Local search operations are devised and embedded in hybrid GAs to fine-tune the search. The operations are parameterized in terms of their fine-tuning power, and their effectiveness and timing requirements are analyzed and compared. The hybridization technique produces two desirable effects: a significant improvement in the final performance and the acquisition of subset-size control. The hybrid GAs showed better convergence properties compared to the classical GAs. A method of performing rigorous timing analysis was developed, in order to compare the timing requirement of the conventional and the proposed algorithms. Experiments performed with various standard data sets revealed that the proposed hybrid GA is superior to both a simple GA and sequential search algorithms.