Low muscle mass in patients with stroke on admission reduces walking ability at discharge.

BACKGROUND & AIMS: Reduced skeletal muscle mass may negatively influence postural retention and walking function. This study aimed to examine the influence of the skeletal muscle mass index on walking function in patients with stroke. METHODS: This study included patients with cerebral infarction aged ≥65 years. The Asian Working Group for Sarcopenia's skeletal muscle mass index criteria were used to classify the participants into the low and high skeletal muscle mass index groups. The patient characteristics of the two groups were compared. The primary and secondary outcome measures were independent walking and walking speed, respectively. RESULTS: In total, 174 participants were included. There were no significant differences in the length of hospital stay, rehabilitation volume, or functional independence measure score at discharge between the males and females. Multivariate logistic regression analysis revealed that independent walking was independently associated with the skeletal muscle mass index on admission. The SMI, as an explanatory variable, was independently associated with the comfortable and fastest walking speeds. Faster walking was associated with higher skeletal muscle mass indexes on admission for both males and females. CONCLUSIONS: A low skeletal muscle mass index negatively influences walking function improvement in patients with stroke. A strategy aimed at increasing skeletal muscle mass can have beneficial effects on walking function in patients with stroke.

Mismatch between Augmented Reality Navigation Images and Actual Location of a Cauda Equina Tumor:A Case Report.

BACKGROUND: Augmented reality navigation is the one of the navigation technologies that allows computer-generated virtual images to be projected onto a real-world environment. Augmented reality navigation can be used in spinal tumor surgery. However, it is unknown if there are any pitfalls when using this technique. CASE PRESENTATION: The patient in this report underwent complete resection of a cauda equina tumor at the L2-L3 level using microscope-based augmented reality navigation. Although the registration error of navigation was <1 mm, we found a discrepancy between the augmented reality navigation images and the actual location of the tumor, which we have called "navigation mismatch". This mismatch, which was caused by the mobility of the spinal tumor in the dura mater, seems to be one of the pitfalls of augmented reality navigation for spinal tumors. CONCLUSIONS: Combined use of intraoperative ultrasound and augmented reality navigation seems advisable in such cases. J. Med. Invest. 71 : 174-176, February, 2024.

A Novel Frame-Selection Metric for Video Inpainting to Enhance Urban Feature Extraction.

In our digitally driven society, advances in software and hardware to capture video data allow extensive gathering and analysis of large datasets. This has stimulated interest in extracting information from video data, such as buildings and urban streets, to enhance understanding of the environment. Urban buildings and streets, as essential parts of cities, carry valuable information relevant to daily life. Extracting features from these elements and integrating them with technologies such as VR and AR can contribute to more intelligent and personalized urban public services. Despite its potential benefits, collecting videos of urban environments introduces challenges because of the presence of dynamic objects. The varying shape of the target building in each frame necessitates careful selection to ensure the extraction of quality features. To address this problem, we propose a novel evaluation metric that considers the video-inpainting-restoration quality and the relevance of the target object, considering minimizing areas with cars, maximizing areas with the target building, and minimizing overlapping areas. This metric extends existing video-inpainting-evaluation metrics by considering the relevance of the target object and interconnectivity between objects. We conducted experiment to validate the proposed metrics using real-world datasets from Japanese cities Sapporo and Yokohama. The experiment results demonstrate feasibility of selecting video frames conducive to building feature extraction.

Expert-Novice Level Classification Using Graph Convolutional Network Introducing Confidence-Aware Node-Level Attention Mechanism.

In this study, we propose a classification method of expert-novice levels using a graph convolutional network (GCN) with a confidence-aware node-level attention mechanism. In classification using an attention mechanism, highlighted features may not be significant for accurate classification, thereby degrading classification performance. To address this issue, the proposed method introduces a confidence-aware node-level attention mechanism into a spatiotemporal attention GCN (STA-GCN) for the classification of expert-novice levels. Consequently, our method can contrast the attention value of each node on the basis of the confidence measure of the classification, which solves the problem of classification approaches using attention mechanisms and realizes accurate classification. Furthermore, because the expert-novice levels have ordinalities, using a classification model that considers ordinalities improves the classification performance. The proposed method involves a model that minimizes a loss function that considers the ordinalities of classes to be classified. By implementing the above approaches, the expert-novice level classification performance is improved.

Analysis of Continual Learning Techniques for Image Generative Models with Learned Class Information Management.

The advancements in deep learning have significantly enhanced the capability of image generation models to produce images aligned with human intentions. However, training and adapting these models to new data and tasks remain challenging because of their complexity and the risk of catastrophic forgetting. This study proposes a method for addressing these challenges involving the application of class-replacement techniques within a continual learning framework. This method utilizes selective amnesia (SA) to efficiently replace existing classes with new ones while retaining crucial information. This approach improves the model's adaptability to evolving data environments while preventing the loss of past information. We conducted a detailed evaluation of class-replacement techniques, examining their impact on the "class incremental learning" performance of models and exploring their applicability in various scenarios. The experimental results demonstrated that our proposed method could enhance the learning efficiency and long-term performance of image generation models. This study broadens the application scope of image generation technology and supports the continual improvement and adaptability of corresponding models.

Achieving Complete Human Gingival Fibroblast Collagen Coverage on Implant Abutments through Vacuum Ultraviolet (VUV) Photofunctionalization.

PURPOSE: The formation of a biological seal between implant abutments and the surrounding soft tissue is a preventive strategy against peri-implantitis. The aim of this study is to test the hypothesis that surfaces of prosthetic implant abutments treated with vacuum ultraviolet (VUV) light enhance the growth and function of human gingival fibroblasts. MATERIALS AND METHODS: Implant abutments were treated with 172 nm VUV light for one minute. Untreated abutments were subjected as controls. Their surface properties were characterized using SEM, contact angle measurements, and chemical composition analysis. Human gingival fibroblasts were cultured on both untreated and VUV-treated abutments to evaluate cell attachment, proliferation, distribution, and collagen production. Cell detachment assays were also performed under various mechanical and chemical stimuli. RESULTS: After VUV treatment, implant abutments demonstrated a notable transition from hydrophobic to hydrophilic wettability. Surface element analysis revealed a considerable reduction in surface carbon and increases in oxygen and titanium elements on the VUV-treated surfaces. On day 1 of culture, 3.9 times more fibroblasts attached on VUV-treated abutments than on untreated control abutments. Fibroblastic proliferation increased 1.9-3.1 times on VUV-treated abutments, along with a significant improvement in the distribution of populating cells. Collagen production on VUV-treated abutments increased by 1.5-1.7 times. While untreated abutment surfaces showed voids and limited spread of collagen deposition, dense and full coverage of collagen was observed on VUV-treated abutments, with a great contrast in the challenging axial surface zone. Cell retention against mechanical and chemical detaching stimuli was increased 11.3 and 4.3 times, respectively, by VUV treatment. CONCLUSION: Treatment of implant abutments with VUV light for one minute resulted in a reduction of surface carbon and a transformation of the surface from hydrophobic to hydrophilic. This led to enhanced attachment, proliferation, and retention of human gingival fibroblasts, along with nearly complete collagen coverage on implant abutments. These in vitro results indicate the promising potential of utilizing VUV photofunctionalized implant abutments to enhance soft tissue reaction and sealing mechanisms.

Calculation of trunk muscle mass and trunk muscle quality indices for walking independence in asian patients with hip fractures.

BACKGROUND & AIMS: This study aimed to investigate the association between trunk muscle mass and muscle quality, as evaluated by bioelectrical impedance analysis (BIA), and the ability to walk independently in patients with hip fractures. Cutoff values for quantitative and qualitative indicators of the trunk muscles were also calculated. METHODS: This study included 181 patients with hip fractures who were admitted to a convalescent rehabilitation ward. Trunk muscle mass and phase angle of the participants were evaluated on admission. The phase angle in this study was defined as the trunk muscle quality index (TMQI). Patients were classified into the independent (functional independence measure [FIM]-walk score ≥6; n = 101) and non-independent (FIM-walk score ≤5; n = 80) walking groups according to the FIM mobility scores at discharge. RESULTS: The independent group had a higher FIM gain than the non-independent group (37.0 ± 13.6 vs. 27.1 ± 13.5, p < 0.001). Logistic regression analysis showed that the trunk muscle mass index (TMI) and TMQI were associated with the ability to walk independently. Furthermore, cutoff values of TMI and TMQI for male and female to estimate the ability to walk independently were 6.5 kg/m2 and 5.7 kg/m2, and 4.5° and 3.4°, respectively. CONCLUSION: TMI and TMQI are related to the ability to walk independently in patients with hip fractures. These results suggest the importance of improving trunk muscle mass and muscle quality during rehabilitation of patients with hip fractures.

Machine learning-based gait analysis to predict clinical frailty scale in elderly patients with heart failure.

Aims: Although frailty assessment is recommended for guiding treatment strategies and outcome prediction in elderly patients with heart failure (HF), most frailty scales are subjective, and the scores vary among raters. We sought to develop a machine learning-based automatic rating method/system/model of the clinical frailty scale (CFS) for patients with HF. Methods and results: We prospectively examined 417 elderly (≥75 years) with symptomatic chronic HF patients from 7 centres between January 2019 and October 2023. The patients were divided into derivation (n = 194) and validation (n = 223) cohorts. We obtained body-tracking motion data using a deep learning-based pose estimation library, on a smartphone camera. Predicted CFS was calculated from 128 key features, including gait parameters, using the light gradient boosting machine (LightGBM) model. To evaluate the performance of this model, we calculated Cohen's weighted kappa (CWK) and intraclass correlation coefficient (ICC) between the predicted and actual CFSs. In the derivation and validation datasets, the LightGBM models showed excellent agreements between the actual and predicted CFSs [CWK 0.866, 95% confidence interval (CI) 0.807-0.911; ICC 0.866, 95% CI 0.827-0.898; CWK 0.812, 95% CI 0.752-0.868; ICC 0.813, 95% CI 0.761-0.854, respectively]. During a median follow-up period of 391 (inter-quartile range 273-617) days, the higher predicted CFS was independently associated with a higher risk of all-cause death (hazard ratio 1.60, 95% CI 1.02-2.50) after adjusting for significant prognostic covariates. Conclusion: Machine learning-based algorithms of automatically CFS rating are feasible, and the predicted CFS is associated with the risk of all-cause death in elderly patients with HF.

Impact of increased trunk muscle mass on trunk function and activities of daily living in older individuals with cerebral infarction.

BACKGROUND & AIMS: The association between trunk muscle mass or trunk function or trunk muscle strength and activities of daily living (ADLs) has been reported, but no studies have examined the impact of increased trunk muscle mass on trunk function or ADL. This study aimed to determine whether increased trunk muscle mass is associated with trunk function and ADL in older individuals with cerebral infarction during rehabilitation. METHODS: This retrospective observational study enrolled 158 patients with cerebral infarction aged ≥65 years who were admitted for post-stroke rehabilitation. The trunk muscle mass index (TMI) was calculated at admission and discharge using bioelectrical impedance analysis. Patients were divided into two groups: one with increased TMI (64 participants; 41 %) and the other without TMI increase (94 participants; 59 %). Multiple linear regression analysis was performed with functional assessment for control of trunk (FACT) or functional independence measure (FIM)-motor gain as the objective variable and increased TMI group as the explanatory variable. RESULTS: We analyzed a total of 158 patients (79.5 ± 7.8 years of age, 51.9 % men). TMI increase was independently associated with FACT gain (coefficient = 1.413, 95 % confidence interval = 0.34-2.49, P = 0.010), but not with FIM-motor gain. CONCLUSIONS: The results suggest that increased TMI is independently associated with recovery of trunk function. Further prospective studies are needed to elucidate the relationship between increased TMI and ADL.

Human Gingival Fibroblast Growth and Function in Response to Laser-Induced Meso-and Microscale Hybrid Topography on Dental Implant Healing Abutments.

PURPOSE: Laser-created titanium surface topographies enhance soft tissue attachment and implant stability. However, knowledge about the underlying mechanisms governing the tissue-level reaction is lacking. The objective of this study was to examine the behavior and function of human gingival fibroblasts growing on healing abutments with or without laser-textured topography. MATERIALS AND METHODS: Human primary gingival connective tissue fibroblasts were cultured on healing abutments with machined or laser-textured (Laser-Lok, BioHorizons) surfaces. Cellular and molecular responses were evaluated by cell density assay (WST-1), fluorescence microscopy, qRT-PCR, and detachment test. RESULTS: The machined surface showed mono-directional traces and scratches from milling, whereas the laser-textured surface showed a distinct morphology consisting of mono-directional meso-scale channels (15 µm pitch) and woven, oblique micro-ridges formed within the channel. There were no differences in initial fibroblast attachment, subsequent fibroblast proliferation, nor collagen production between the machined and laser-textured surfaces. Fibroblasts growing on laser-textured surface spread mono-directionally along the meso-channels, while cells growing on machined surfaces spread randomly. Fibroblasts on laser-textured surfaces were 1.8-times more resistant to detachment than those on machined surfaces. An adhesive glycoprotein (fibronectin) and trans-membrane adhesion linker gene (integrin beta-1) were upregulated on laser-textured surfaces. CONCLUSIONS: The increased fibroblast retention, uniform growth, increased transcription of cell adhesion proteins compellingly explain the enhanced tissue-level response to laser-created, hybrid textured titanium surfaces. These results provide a cellular and molecular rationale for the tissue reaction to this unique surface and support its extended use from implant fixtures and healing abutments to diverse prosthetic components where enhanced soft tissue responses would be desirable.

Cold stress-induced ferroptosis in liver sinusoidal endothelial cells determines liver transplant injury and outcomes.

Although cold preservation remains the gold standard in organ transplantation, cold stress-induced cellular injury is a significant problem in clinical orthotopic liver transplantation (OLT). Because a recent study showed that cold stress activates ferroptosis, a form of regulated cell death, we investigated whether and how ferroptosis determines OLT outcomes in mice and humans. Treatment with ferroptosis inhibitor (ferrostatin-1) during cold preservation reduced lipid peroxidation (malondialdehyde; MDA), primarily in liver sinusoidal endothelial cells (LSECs), and alleviated ischemia/reperfusion injury in mouse OLT. Similarly, ferrostatin-1 reduced cell death in cold-stressed LSEC cultures. LSECs deficient in nuclear factor erythroid 2-related factor 2 (NRF2), a critical regulator of ferroptosis, were susceptible to cold stress-induced cell death, concomitant with enhanced endoplasmic reticulum (ER) stress and expression of mitochondrial Ca2+ uptake regulator (MICU1). Indeed, supplementing MICU1 inhibitor reduced ER stress, MDA expression, and cell death in NRF2-deficient but not WT LSECs, suggesting NRF2 is a critical regulator of MICU1-mediated ferroptosis. Consistent with murine data, enhanced liver NRF2 expression reduced MDA levels, hepatocellular damage, and incidence of early allograft dysfunction in human OLT recipients. This translational study provides a clinically applicable strategy in which inhibition of ferroptosis during liver cold preservation mitigates OLT injury by protecting LSECs from peritransplant stress via an NRF2-regulatory mechanism.

Importance-aware adaptive dataset distillation.

Herein, we propose a novel dataset distillation method for constructing small informative datasets that preserve the information of the large original datasets. The development of deep learning models is enabled by the availability of large-scale datasets. Despite unprecedented success, large-scale datasets considerably increase the storage and transmission costs, resulting in a cumbersome model training process. Moreover, using raw data for training raises privacy and copyright concerns. To address these issues, a new task named dataset distillation has been introduced, aiming to synthesize a compact dataset that retains the essential information from the large original dataset. State-of-the-art (SOTA) dataset distillation methods have been proposed by matching gradients or network parameters obtained during training on real and synthetic datasets. The contribution of different network parameters to the distillation process varies, and uniformly treating them leads to degraded distillation performance. Based on this observation, we propose an importance-aware adaptive dataset distillation (IADD) method that can improve distillation performance by automatically assigning importance weights to different network parameters during distillation, thereby synthesizing more robust distilled datasets. IADD demonstrates superior performance over other SOTA dataset distillation methods based on parameter matching on multiple benchmark datasets and outperforms them in terms of cross-architecture generalization. In addition, the analysis of self-adaptive weights demonstrates the effectiveness of IADD. Furthermore, the effectiveness of IADD is validated in a real-world medical application such as COVID-19 detection.

Text-Guided Image Editing Based on Post Score for Gaining Attention on Social Media.

Text-guided image editing has been highlighted in the fields of computer vision and natural language processing in recent years. The approach takes an image and text prompt as input and aims to edit the image in accordance with the text prompt while preserving text-unrelated regions. The results of text-guided image editing differ depending on the way the text prompt is represented, even if it has the same meaning. It is up to the user to decide which result best matches the intended use of the edited image. This paper assumes a situation in which edited images are posted to social media and proposes a novel text-guided image editing method to help the edited images gain attention from a greater audience. In the proposed method, we apply the pre-trained text-guided image editing method and obtain multiple edited images from the multiple text prompts generated from a large language model. The proposed method leverages the novel model that predicts post scores representing engagement rates and selects one image that will gain the most attention from the audience on social media among these edited images. Subject experiments on a dataset of real Instagram posts demonstrate that the edited images of the proposed method accurately reflect the content of the text prompts and provide a positive impression to the audience on social media compared to those of previous text-guided image editing methods.

Reduced Cross-Sectional Area of the Gluteus Medius Muscle is Associated With Decreased Activities of Daily Living in Older Adult Patients With Hip Fractures.

We investigated the association between the cross-sectional area (CSA) of the gluteus medius muscle (GMM) and activities of daily living in patients with hip fractures. This retrospective cohort study comprised 111 patients aged ≥65 years who underwent hip fracture rehabilitation. The CSA of the GMM was measured using computed tomography scans in the early stages of hospitalization. The group with decreased CSA of the GMM had a median GMI ≤17 cm2/m2 for male patients and ≤16 cm2/m2 for female patients. Patients in the group with decreased CSA of the GMM had lower functional independence measure gains than those in the control group. After adjusting for confounders, we found that decreased CSA of the GMM was significantly associated with lower functional independence measure gains (ß: -0.432, p < .001). In patients with hip fractures, decreased CSA of the GMM was associated with decreased activities of daily living.

Correlation between trunk function improvement and recovery of activities of daily living after stroke in older adult patients.

OBJECTIVES: To examine the impact of improved trunk function on activities of daily living in stroke patients using the Functional Independence Measure (FIM). METHODS: This retrospective observational study was conducted on patients aged ≥ 65 years who had cerebral infarction. Patients were divided into a group with improved trunk function and a group without trunk function improvement based on the difference between the calculated Functional Assessment for Control of Trunk (FACT) gain at discharge and admission. RESULTS: Of the 218 patients (mean age, 79.5 ± 7.9 years; 56.9% were men) included, 110 patients had improved FACT scores. Multiple linear regression analysis revealed that the group with improved FACT scores had higher FIM gain (coefficient = 7.562, 95% confidence interval = 3.870-11.253, P < 0.001). Multivariate logistic regression showed that the factors associated with FACT score improvement were the Mini Nutritional Assessment Short-Form score at admission, National Institutes of Health Stroke Scale score at admission, FACT score at admission, length of hospital stay, and period of rehabilitation. DISCUSSIONS: Improvement in trunk function suggests a positive correlation with the recovery of activities of daily living in patients with cerebral infarction. This relationship should be further validated through prospective observational studies.

Variations in predictors for urinary continence recovery at different time periods following robot-assisted radical prostatectomy.

INTRODUCTION: Urinary dysfunctions are common sequelae following prostatectomy. This study aimed to discover factors that can predict urinary continence recovery at various time periods after robot-assisted laparoscopic radical prostatectomy (RARP). METHODS: This was a retrospective analysis of data of 419 consecutive patients. Only patients followed up for ≥1 year were enrolled. An answer of "zero pad per day" in the Expanded Prostate Cancer Index Composite urinary assessment (question 5) denoted continence. Possible predictors of urinary continence recovery were evaluated at 3, 3-6, and 6-12 months after the operation. RESULTS: Continence rates at 3, 6, and 12 months after RARP were 12.9%, 21.2%, and 40.2%, respectively. The proportions of patients using 0-1 pad were 54.2%, 75.7%, and 83.1% at 3, 6, and 12 months after RARP, respectively. Multivariable regression analysis revealed that a membranous urethral length (MUL) ≥11 mm was significantly associated with urinary continence recovery both within 3 months (odds ratio: 0.367, P = .003) and 3-6 months (odds ratio: 0.354, P = .001) after RARP. The analysis also revealed that, in patients with urinary continence at 6 months, a large prostate volume (odds ratio: 1.973, P = .044) and a high body mass index (odds ratio: 2.874, P = .027) were negative predictors of urinary continence recovery within 6-12 months. CONCLUSION: A longer MUL was linked to urinary continence recovery within 6 months following RARP, whereas a large prostate volume and a high body mass index were adverse predictors of urinary continence recovery beyond 6 months.

Zero-Shot Traffic Sign Recognition Based on Midlevel Feature Matching.

Traffic sign recognition is a complex and challenging yet popular problem that can assist drivers on the road and reduce traffic accidents. Most existing methods for traffic sign recognition use convolutional neural networks (CNNs) and can achieve high recognition accuracy. However, these methods first require a large number of carefully crafted traffic sign datasets for the training process. Moreover, since traffic signs differ in each country and there is a variety of traffic signs, these methods need to be fine-tuned when recognizing new traffic sign categories. To address these issues, we propose a traffic sign matching method for zero-shot recognition. Our proposed method can perform traffic sign recognition without training data by directly matching the similarity of target and template traffic sign images. Our method uses the midlevel features of CNNs to obtain robust feature representations of traffic signs without additional training or fine-tuning. We discovered that midlevel features improve the accuracy of zero-shot traffic sign recognition. The proposed method achieves promising recognition results on the German Traffic Sign Recognition Benchmark open dataset and a real-world dataset taken from Sapporo City, Japan.

Synergistic Enhancement of Protein Recruitment and Retention via Implant Surface Microtopography and Superhydrophilicity in a Computational Fluid Dynamics Model.

The exact mechanisms by which implant surface properties govern osseointegration are incompletely understood. To gain insights into this process, we examined alterations in protein and blood recruitment around screw implants with different surface topographies and wettability using a computational fluid dynamics (CFD) model. Compared with a smooth surface, a microrough implant surface reduced protein infiltration from the outer zone to the implant thread and interface zones by over two-fold. However, the microrough implant surface slowed blood flow in the interface zone by four-fold. As a result, compared with the smooth surface, the microrough surface doubled the protein recruitment/retention index, defined as the mass of proteins present in the area per unit time. Converting implant surfaces from hydrophobic to superhydrophilic increased the mass of protein infiltration 2-3 times and slowed down blood flow by up to two-fold in the implant vicinity for both smooth and microrough surfaces. The protein recruitment/retention index was highest at the implant interface when the implant surface was superhydrophilic and microrough. Thus, this study demonstrates distinct control of the mass and speed of protein and blood flow through implant surface topography, wettability, and their combination, significantly altering the efficiency of protein recruitment. Although microrough surfaces showed both positive and negative impacts on protein recruitment over smooth surfaces, superhydrophilicity was consistently positive regardless of surface topography.

Vacuum Ultraviolet (VUV) Light Photofunctionalization to Induce Human Oral Fibroblast Transmigration on Zirconia.

Soft tissue adhesion and sealing around dental and maxillofacial implants, related prosthetic components, and crowns are a clinical imperative to prevent adverse outcomes of periodontitis and periimplantitis. Zirconia is often used to fabricate implant components and crowns. Here, we hypothesized that UV treatment of zirconia would induce unique behaviors in fibroblasts that favor the establishment of a soft tissue seal. Human oral fibroblasts were cultured on zirconia specimens to confluency before placing a second zirconia specimen (either untreated or treated with one minute of 172 nm vacuum UV (VUV) light) next to the first specimen separated by a gap of 150 µm. After seven days of culture, fibroblasts only transmigrated onto VUV-treated zirconia, forming a 2.36 mm volume zone and 5.30 mm leading edge. Cells migrating on VUV-treated zirconia were enlarged, with robust formation of multidirectional cytoplastic projections, even on day seven. Fibroblasts were also cultured on horizontally placed and 45° and 60° tilted zirconia specimens, with the latter configurations compromising initial attachment and proliferation. However, VUV treatment of zirconia mitigated the negative impact of tilting, with higher tilt angles increasing the difference in cellular behavior between control and VUV-treated specimens. Fibroblast size, perimeter, and diameter on day seven were greater than on day one exclusively on VUV-treated zirconia. VUV treatment reduced surface elemental carbon and induced superhydrophilicity, confirming the removal of the hydrocarbon pellicle. Similar effects of VUV treatment were observed on glazed zirconia specimens with silica surfaces. One-minute VUV photofunctionalization of zirconia and silica therefore promotes human oral fibroblast attachment and proliferation, especially under challenging culture conditions, and induces specimen-to-specimen transmigration and sustainable photofunctionalization for at least seven days.

Manipulation Direction: Evaluating Text-Guided Image Manipulation Based on Similarity between Changes in Image and Text Modalities.

At present, text-guided image manipulation is a notable subject of study in the vision and language field. Given an image and text as inputs, these methods aim to manipulate the image according to the text, while preserving text-irrelevant regions. Although there has been extensive research to improve the versatility and performance of text-guided image manipulation, research on its performance evaluation is inadequate. This study proposes Manipulation Direction (MD), a logical and robust metric, which evaluates the performance of text-guided image manipulation by focusing on changes between image and text modalities. Specifically, we define MD as the consistency of changes between images and texts occurring before and after manipulation. By using MD to evaluate the performance of text-guided image manipulation, we can comprehensively evaluate how an image has changed before and after the image manipulation and whether this change agrees with the text. Extensive experiments on Multi-Modal-CelebA-HQ and Caltech-UCSD Birds confirmed that there was an impressive correlation between our calculated MD scores and subjective scores for the manipulated images compared to the existing metrics.