PCTC-Net: A Crack Segmentation Network with Parallel Dual Encoder Network Fusing Pre-Conv-Based Transformers and Convolutional Neural Networks.

Cracks are common defects that occur on the surfaces of objects and structures. Crack detection is a critical maintenance task that traditionally requires manual labor. Large-scale manual inspections are expensive. Research has been conducted to replace expensive human labor with cheaper computing resources. Recently, crack segmentation based on convolutional neural networks (CNNs) and transformers has been actively investigated for local and global information. However, the transformer is data-intensive owing to its weak inductive bias. Existing labeled datasets for crack segmentation are relatively small. Additionally, a limited amount of fine-grained crack data is available. To address this data-intensive problem, we propose a parallel dual encoder network fusing Pre-Conv-based Transformers and convolutional neural networks (PCTC-Net). The Pre-Conv module automatically optimizes each color channel with a small spatial kernel before the input of the transformer. The proposed model, PCTC-Net, was tested with the DeepCrack, Crack500, and Crackseg9k datasets. The experimental results showed that our model achieved higher generalization performance, stability, and F1 scores than the SOTA model DTrC-Net.

Personal exposure of PM2.5 and metabolic syndrome markers of pregnant women in South Korea: APPO study.

We examined the association between exposure to PM2.5, focused on individual exposure level, and metabolic dysfunction during pregnancy. APPO study (Air Pollution on Pregnancy Outcome) was a prospective, multicenter, observational cohort study conducted from January 2021 to March 2023. Individual PM2.5 concentrations were calculated using a time-weighted average model. Metabolic dysfunction during pregnancy was assessed based on a modified definition of metabolic syndrome and its components, accounting for pregnancy-specific criteria. Exposure to PM2.5 during pregnancy was associated with worsened metabolic parameters especially glucose metabolism. In comparison to participants exposed to the low PM2.5 group, those exposed to high PM2.5 levels exhibited increased odds of gestational diabetes mellitus (GDM) after adjusting for confounding variables in different adjusted models. Specifically, in model 1, the adjusted odds ratio (aOR) was 3.117 with a 95% confidence interval (CI) of 1.234-7.870; in model 2, the aOR was 3.855 with a 95% CI of 1.255-11.844; in model 3, the aOR was 3.404 with a 95% CI of 1.206-9.607; and in model 4, the aOR was 2.741 with a 95% CI of 0.712-10.547. Exposure to higher levels of PM2.5 during pregnancy was associated with a tendency to worsen metabolic dysfunction markers specifically in glucose homeostasis. Further research is needed to investigate the mechanisms underlying the effects of ambient PM2.5 on metabolic dysfunction during pregnancy.

WRA-Net: Wide Receptive Field Attention Network for Motion Deblurring in Crop and Weed Image.

Automatically segmenting crops and weeds in the image input from cameras accurately is essential in various agricultural technology fields, such as herbicide spraying by farming robots based on crop and weed segmentation information. However, crop and weed images taken with a camera have motion blur due to various causes (e.g., vibration or shaking of a camera on farming robots, shaking of crops and weeds), which reduces the accuracy of crop and weed segmentation. Therefore, robust crop and weed segmentation for motion-blurred images is essential. However, previous crop and weed segmentation studies were performed without considering motion-blurred images. To solve this problem, this study proposed a new motion-blur image restoration method based on a wide receptive field attention network (WRA-Net), based on which we investigated improving crop and weed segmentation accuracy in motion-blurred images. WRA-Net comprises a main block called a lite wide receptive field attention residual block, which comprises modified depthwise separable convolutional blocks, an attention gate, and a learnable skip connection. We conducted experiments using the proposed method with 3 open databases: BoniRob, crop/weed field image, and rice seedling and weed datasets. According to the results, the crop and weed segmentation accuracy based on mean intersection over union was 0.7444, 0.7741, and 0.7149, respectively, demonstrating that this method outperformed the state-of-the-art methods.

The introduction to air pollution on pregnancy outcome (APPO) study: a multicenter cohort study.

OBJECTIVE: The air pollution on pregnancy outcome (APPO) study is a prospective hospital-based cohort study designed to investigate the maternal and fetal effects of a particulate matter with an aerodynamic below 10 µm (PM10) and PM2.5 (below 2.5 µm) exposure. This study aims to analyze a relationship between particulate matter and adverse pregnancy outcomes and to find related biomarkers and develop management guidelines. METHODS: About 1,200 pregnant women are recruited for 3 years (from January 2021 to December 2023) from seven university hospitals to investigate the effects of particulate matter on pregnancy complications and adverse pregnancy outcomes. We collect biological samples by 5 mL of maternal venous blood and 15 mL of urine in each trimester of pregnancy, and 5 mL of umbilical cord blood and 2×2×2 cm of placental tissue are collected after delivery. In addition, by applying PM10 and PM2.5 concentration values and time-activity patterns from the time weighted average model, the individual predicted exposure of air pollution for the pregnant women are obtained. RESULTS: The average exposure of PM10 and PM2.5 of the participants in the entire period of pregnancy, was exceeded the World Health Organization air quality guidelines (an annual level, PM10 >15 µg/m3, PM2.5 >5 µg/m3). Moreover, it was revealed that the PM concentration was increasing toward the 3rd trimester of pregnancy. CONCLUSION: The APPO study will be able to identify the degree of exposure to air pollution in pregnant women and use it as basic data for estimating individual exposure to particulate matter. And the results of the APPO study will facilitate in the development of health management for pregnant women against air pollution.

Human Blastocyst Components Detection Using Multiscale Aggregation Semantic Segmentation Network for Embryonic Analysis.

Infertility is one of the most important health concerns worldwide. It is characterized by not being successful of pregnancy after some periods of periodic unprotected sexual intercourse. In vitro fertilization (IVF) is an assisted reproduction technique that efficiently addresses infertility. IVF replaces the actual mode of reproduction through a manual procedure wherein embryos are cultivated in a controlled laboratory environment until they reach the blastocyst stage. The standard IVF procedure includes the transfer of one or two blastocysts from several blastocysts that are grown in a controlled environment. The morphometric properties of blastocysts with their compartments such as trophectoderm (TE), zona pellucida (ZP), inner cell mass (ICM), and blastocoel (BL), are analyzed through manual microscopic analysis to predict viability. Deep learning has been extensively used for medical diagnosis and analysis and can be a powerful tool to automate the morphological analysis of human blastocysts. However, the existing approaches are inaccurate and require extensive preprocessing and expensive architectures. Thus, to cope with the automatic detection of blastocyst components, this study proposed a novel multiscale aggregation semantic segmentation network (MASS-Net) that combined four different scales via depth-wise concatenation. The extensive use of depthwise separable convolutions resulted in a decrease in the number of trainable parameters. Further, the innovative multiscale design provided rich spatial information of different resolutions, thereby achieving good segmentation performance without a very deep architecture. MASS-Net utilized 2.06 million trainable parameters and accurately detects TE, ZP, ICM, and BL without using preprocessing stages. Moreover, it can provide a separate binary mask for each blastocyst component simultaneously, and these masks provide the structure of each component for embryonic analysis. Further, the proposed MASS-Net was evaluated using publicly available human blastocyst (microscopic) imaging data. The experimental results revealed that it can effectively detect TE, ZP, ICM, and BL with mean Jaccard indices of 79.08, 84.69, 85.88%, and 89.28%, respectively, for embryological analysis, which was higher than those of the state-of-the-art methods.

Comprehensive Computer-Aided Decision Support Framework to Diagnose Tuberculosis From Chest X-Ray Images: Data Mining Study.

BACKGROUND: Tuberculosis (TB) is one of the most infectious diseases that can be fatal. Its early diagnosis and treatment can significantly reduce the mortality rate. In the literature, several computer-aided diagnosis (CAD) tools have been proposed for the efficient diagnosis of TB from chest radiograph (CXR) images. However, the majority of previous studies adopted conventional handcrafted feature-based algorithms. In addition, some recent CAD tools utilized the strength of deep learning methods to further enhance diagnostic performance. Nevertheless, all these existing methods can only classify a given CXR image into binary class (either TB positive or TB negative) without providing further descriptive information. OBJECTIVE: The main objective of this study is to propose a comprehensive CAD framework for the effective diagnosis of TB by providing visual as well as descriptive information from the previous patients' database. METHODS: To accomplish our objective, first we propose a fusion-based deep classification network for the CAD decision that exhibits promising performance over the various state-of-the-art methods. Furthermore, a multilevel similarity measure algorithm is devised based on multiscale information fusion to retrieve the best-matched cases from the previous database. RESULTS: The performance of the framework was evaluated based on 2 well-known CXR data sets made available by the US National Library of Medicine and the National Institutes of Health. Our classification model exhibited the best diagnostic performance (0.929, 0.937, 0.921, 0.928, and 0.965 for F1 score, average precision, average recall, accuracy, and area under the curve, respectively) and outperforms the performance of various state-of-the-art methods. CONCLUSIONS: This paper presents a comprehensive CAD framework to diagnose TB from CXR images by retrieving the relevant cases and their clinical observations from the previous patients' database. These retrieval results assist the radiologist in making an effective diagnostic decision related to the current medical condition of a patient. Moreover, the retrieval results can facilitate the radiologists in subjectively validating the CAD decision.

The effect of salinomycin on ovarian cancer stem-like cells.

OBJECTIVE: The identification of cancer stem-like cells is a recent development in ovarian cancer. Compared to other cancer cells, cancer stem-like cells present more chemo-resistance and more aggressive characteristics. They play an important role in the recurrence and drug resistance of cancer. Therefore, the target therapy of cancer stem-like cell may become a promising and effective approach for ovarian cancer treatment. It may also help to provide novel diagnostic and therapeutic strategies. METHODS: The OVCAR3 cell line was cultured under serum-free conditions to produce floating spheres. The CD44(+)CD117(+) cell line was isolated from the human ovarian cancer cell line OVCAR3 by using immune magnetic-activated cell sorting system. The expression of stemness genes such as OCT3/4, NANOG and SOX2 mRNA were determined by reverse transcription polymerase chain reaction. OVCAR3 parental and OVCAR3 CD44(+)CD117(+) cells were grown in different doses of paclitaxel and salinomycin to evaluate the effect of salinomycin. And growth inhibition of OVCAR3 CD44(+)CD117(+) cells by paclitaxel combined with salinomycin was determined by the 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyl-2H-tetrazolium bromide (MTT) assay. RESULTS: Tumor spheroids generated from the OVCAR3 cell line are shown to have highly enriched CD44 and CD117 expression. Treatment with a combination of paclitaxel and salinomycin demonstrated growth inhibition of OVCAR3 CD44(+)CD117(+) cells. CONCLUSION: The present study is a detailed investigation on the expression of CD44 and CD117 in cancer stem cells and evaluates their specific tumorigenic characteristics in ovarian cancer. This study also demonstrates significant growth inhibition of cancer stem-like cells by paclitaxel combined with salinomycin. Identification of these cancer stem-like cell markers and growth inhibition effect of salinomycin may be the next step to the development of novel target therapy in ovarian cancer.

Stereopsis in drug naïve Parkinson's disease patients.

BACKGROUND: Motor deficits associated with Parkinson's disease (PD) have been well described, yet little attention has been paid to non-motor symptoms, especially cortical visual dysfunction. We investigated stereopsis, as well as the relationship between stereopsis and other cognitive function, in a sample of PD patients. METHODS: We used Titmus stereotest plates for assessing stereopsis. Fifty-nine subjects (29 PD patients and 30 normal controls) were included in this study. The included patients underwent a neurological examination, clinical rating scale and neuropsychological tests. RESULTS: Drug naïve PD patients showed decreased stereopsis on the Titmus fly stereopsis test (Pearson χ2=23.80, p<0.001) compared to PD patients with normal stereopsis. The Hoehn-Yahr stages and Unified Parkinson's Disease Rating Scale motor scores were significantly higher in patients with PD with abnormal stereopsis than in patients with PD with normal stereopsis (p=0.026; p=0.046). The frequency of abnormal visual perception/constructive function was greater in patients with PD with abnormal stereopsis compared to patients with PD with normal stereopsis (Pearson χ2=5.11, p=0.024). CONCLUSION: These findings suggest that stereopsis deficits and visual perception/constructive dysfunction are common in de novo PD patients.

Aminocyclopentadienyl ruthenium complexes as racemization catalysts for dynamic kinetic resolution of secondary alcohols at ambient temperature.

Aminocyclopentadienyl ruthenium complexes, which can be used as room-temperature racemization catalysts with lipases in the dynamic kinetic resolution (DKR) of secondary alcohols, were synthesized from cyclopenta-2,4-dienimines, Ru(3)(CO)(12), and CHCl(3): [2,3,4,5-Ph(4)(eta(5)-C(4)CNHR)]Ru(CO)(2)Cl (4: R = i-Pr; 5: R = n-Pr; 6: R = t-Bu), [2,5-Me(2)-3,4-Ph(2)(eta(5)-C(4)CNHR)]Ru(CO)(2)Cl (7: R = i-Pr; 8: R = Ph), and [2,3,4,5-Ph(4)(eta(5)-C(4)CNHAr)]Ru(CO)(2)Cl (9: Ar = p-NO(2)C(6)H(4); 10: Ar = p-ClC(6)H(4); 11: Ar = Ph; 12: Ar = p-OMeC(6)H(4); 13: Ar = p-NMe(2)C(6)H(4)). The tests in the racemization of (S)-4-phenyl-2-butanol showed that 7 is the most active catalyst, although the difference decreased in the DKR. Complex 4 was used in the DKR of various alcohols; at room temperature, not only simple alcohols but also functionalized ones such as allylic alcohols, alkynyl alcohols, diols, hydroxyl esters, and chlorohydrins were successfully transformed to chiral acetates. In mechanistic studies for the catalytic racemization, ruthenium hydride 14 appeared to be a key species. It was the major organometallic species in the racemization of (S)-1-phenylethanol with 4 and potassium tert-butoxide. In a separate experiment, (S)-1-phenylethanol was racemized catalytically by 14 in the presence of acetophenone.