Transfer learning with CNNs for efficient prostate cancer and BPH detection in transrectal ultrasound images.

Early detection of prostate cancer (PCa) and benign prostatic hyperplasia (BPH) is crucial for maintaining the health and well-being of aging male populations. This study aims to evaluate the performance of transfer learning with convolutional neural networks (CNNs) for efficient classification of PCa and BPH in transrectal ultrasound (TRUS) images. A retrospective experimental design was employed in this study, with 1380 TRUS images for PCa and 1530 for BPH. Seven state-of-the-art deep learning (DL) methods were employed as classifiers with transfer learning applied to popular CNN architectures. Performance indices, including sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), Kappa value, and Hindex (Youden's index), were used to assess the feasibility and efficacy of the CNN methods. The CNN methods with transfer learning demonstrated a high classification performance for TRUS images, with all accuracy, specificity, sensitivity, PPV, NPV, Kappa, and Hindex values surpassing 0.9400. The optimal accuracy, sensitivity, and specificity reached 0.9987, 0.9980, and 0.9980, respectively, as evaluated using twofold cross-validation. The investigated CNN methods with transfer learning showcased their efficiency and ability for the classification of PCa and BPH in TRUS images. Notably, the EfficientNetV2 with transfer learning displayed a high degree of effectiveness in distinguishing between PCa and BPH, making it a promising tool for future diagnostic applications.

Classification of Color Fundus Photographs Using Fusion Extracted Features and Customized CNN Models.

This study focuses on overcoming challenges in classifying eye diseases using color fundus photographs by leveraging deep learning techniques, aiming to enhance early detection and diagnosis accuracy. We utilized a dataset of 6392 color fundus photographs across eight disease categories, which was later augmented to 17,766 images. Five well-known convolutional neural networks (CNNs)-efficientnetb0, mobilenetv2, shufflenet, resnet50, and resnet101-and a custom-built CNN were integrated and trained on this dataset. Image sizes were standardized, and model performance was evaluated via accuracy, Kappa coefficient, and precision metrics. Shufflenet and efficientnetb0demonstrated strong performances, while our custom 17-layer CNN outperformed all with an accuracy of 0.930 and a Kappa coefficient of 0.920. Furthermore, we found that the fusion of image features with classical machine learning classifiers increased the performance, with Logistic Regression showcasing the best results. Our study highlights the potential of AI and deep learning models in accurately classifying eye diseases and demonstrates the efficacy of custom-built models and the fusion of deep learning and classical methods. Future work should focus on validating these methods across larger datasets and assessing their real-world applicability.

Integrating ECG Monitoring and Classification via IoT and Deep Neural Networks.

Anesthesia assessment is most important during surgery. Anesthesiologists use electrocardiogram (ECG) signals to assess the patient's condition and give appropriate medications. However, it is not easy to interpret the ECG signals. Even physicians with more than 10 years of clinical experience may still misjudge. Therefore, this study uses convolutional neural networks to classify ECG image types to assist in anesthesia assessment. The research uses Internet of Things (IoT) technology to develop ECG signal measurement prototypes. At the same time, it classifies signal types through deep neural networks, divided into QRS widening, sinus rhythm, ST depression, and ST elevation. Three models, ResNet, AlexNet, and SqueezeNet, are developed with 50% of the training set and test set. Finally, the accuracy and kappa statistics of ResNet, AlexNet, and SqueezeNet in ECG waveform classification were (0.97, 0.96), (0.96, 0.95), and (0.75, 0.67), respectively. This research shows that it is feasible to measure ECG in real time through IoT and then distinguish four types through deep neural network models. In the future, more types of ECG images will be added, which can improve the real-time classification practicality of the deep model.

Classification of the Multiple Stages of Parkinson's Disease by a Deep Convolution Neural Network Based on 99mTc-TRODAT-1 SPECT Images.

Single photon emission computed tomography (SPECT) has been employed to detect Parkinson's disease (PD). However, analysis of the SPECT PD images was mostly based on the region of interest (ROI) approach. Due to limited size of the ROI, especially in the multi-stage classification of PD, this study utilizes deep learning methods to establish a multiple stages classification model of PD. In the retrospective study, the 99mTc-TRODAT-1 was used for brain SPECT imaging. A total of 202 cases were collected, and five slices were selected for analysis from each subject. The total number of images was thus 1010. According to the Hoehn and Yahr Scale standards, all the cases were divided into healthy, early, middle, late four stages, and HYS I~V six stages. Deep learning is compared with five convolutional neural networks (CNNs). The input images included grayscale and pseudo color of two types. The training and validation sets were 70% and 30%. The accuracy, recall, precision, F-score, and Kappa values were used to evaluate the models' performance. The best accuracy of the models based on grayscale and color images in four and six stages were 0.83 (AlexNet), 0.85 (VGG), 0.78 (DenseNet) and 0.78 (DenseNet).

First detection of white spot syndrome virus (WSSV) in the mud shrimp Austinogebia edulis in Taiwan.

The white spot syndrome virus (WSSV) causes mass mortalities in the aquaculture of shrimps worldwide. The mud shrimp Austinogebia edulis (Ngoc-Ho & Chan, 1992) is an economically important sea food item occurring along the west coast of Taiwan. While the population of A. edulis began to decrease with some fluctuations in the last decade, the current study aims to discover the causes for such sporadic population decline. This study explores the effects of microbial pathogens and innate immunity on the populations of A. edulis. Here, we report firstly about WSSV infection of A. edulis from the coastal zone of western Taiwan which is one of the possible causes of population decrease of A. edulis in Shengang. However, WSSV infection is not the only reason for its population decrease because a similar infection rate of WSSV was found in Wangong. Population changes may be related to both environmental pollution stress and WSSV. Both factors likely caused a massive reduction of hemocytes and an abnormal increase of phenoloxidase and superoxide dismutase activity, which were spectrophotometrically measured. Since there is no effective way to treat WSSV infection, improving the coastal environment appears the most effective way to increase the population size of feral shrimps.

Seasonal changes in bacterial communities associated with healthy and diseased Porites coral in southern Taiwan.

We compared the bacterial communities associated with healthy scleractinian coral Porites sp. with those associated with coral infected with pink spot syndrome harvested during summer and winter from waters off the coast of southern Taiwan. Members of the bacterial community associated with the coral were characterized by means of denaturing gradient gel electrophoresis (DGGE) of a short region of the 16S rRNA gene and clone library analysis. Of 5 different areas of the 16S rRNA gene, we demonstrated that the V3 hypervariable region is most suited to represent the coral-associated bacterial community. The DNA sequences of 26 distinct bands extracted from DGGE gels and 269 sequences of the 16S rRNA gene from clone libraries were determined. We found that the communities present in diseased coral were more heterogeneous than the bacterial communities of uninfected coral. In addition, bacterial communities associated with coral harvested in the summer were more diverse than those associated with coral collected in winter, regardless of the health status of the coral. Our study suggested that the compositions of coral-associated bacteria communities are complex, and the population of bacteria varies greatly between seasons and in coral of differing health status.

Investigated geometrical characteristics and image density of left ventricle of multi-detector computed tomography in early coronary artery disease patients.

BACKGROUND: Coronary artery disease (CAD) remains the leading cause of death worldwide. Currently, cardiac multi-detector computed tomography (MDCT) is widely used to diagnose CAD. The purpose in this study is to identify informative and useful predictors from left ventricular (LV) in the early CAD patients using cardiac MDCT images. MATERIALS AND METHODS: Study groups comprised 42 subjects who underwent a screening health examination, including laboratory testing and cardiac angiography by 64-slice MDCT angiography. Two geometrical characteristics and one image density were defined as shape, size and stiffness on MDCT image. The t-test, logistic regression, and receiver operating characteristic curve were applied to assess and identify the significant predictors. The Kappa statistics was used to exam the agreements with physician's judgments (i.e., Golden of True, GOT). RESULTS: The proposed three characteristics of LV MDCT images are important predictors and risk factors for the early CAD patients. These predictors present over 80% of AUC and higher odds ratio. The Kappa statistics was 0.68 for the combinations of shape and stiffness into logistic regression. CONCLUSIONS: The shape, size and stiffness of the left ventricular on MDCT can be used to be the effective indicators in the early CAD patients. Besides, the combinations of shape and stiffness into logistic regression could provide substantial agreement with physician's judgments.

Norcembranoidal diterpenes from a Formosan soft coral Sinularia sp.

Two norcembranoidal diterpenes, 5-episinuleptolide acetate (1) and scabrolide D (2), were isolated from a Formosan octocoral identified as Sinularia sp. The structures of norcembranoids 1 and 2 were established by spectroscopic methods and by comparison of the spectral data with those of known analogues and 1 was proven to be a new natural product. Norcembranoid 1 was found to exhibit cytotoxicity toward a panel of tumor cells.

Isolation of marine bacteria with antimicrobial activities from cultured and field-collected soft corals.

Bacteria associated with eight field-collected and five cultured soft corals of Briareum sp., Sinularia sp., Sarcophyton sp., Nephtheidae sp., and Lobophytum sp. were screened for their abilities in producing antimicrobial metabolites. Field-collected coral samples were collected from Nanwan Bay in southern Taiwan. Cultured corals were collected from the cultivating tank at National Museum of Marine Biology and Aquarium. A total of 1,526 and 1,138 culturable, heterotrophic bacteria were isolated from wild and cultured corals, respectively; seawater requirement and antimicrobial activity were then assessed. There is no significant difference between the ratio of seawater-requiring bacteria on the wild and cultured corals. The ratio of antibiotic-producing bacteria within the seawater-requiring bacteria did not differ between the corals. Nineteen bacterial strains that showed high antimicrobial activity were selected for 16S rDNA sequencing. Three strains could be assigned at the family level (Rhodobacteraceae). The remaining 16 strains belong to eight genera: Marinobacterium (2 strains), Pseudoalteromonas (1), Vibrio (5), Enterovibrio (1), Tateyamaria (1), Labrenzia (2), and Pseudovibrio (4). The crude extract from bacteria strains CGH2XX was found to have high cytotoxicity against the cancer cell line HL-60 (IC(50) = 0.94 µg/ml) and CCRF-CEM (IC(50) = 1.19 µg/ml). Our results demonstrate that the marine bacteria from corals have great potential in the discovery of useful medical molecules.

Hormones and reproduction in scleractinian corals.

Most broadcast spawning scleractinian corals synchronously release gametes during a brief annual spawning period. In southern Taiwan, the mass spawning of scleractinians occurs in lunar mid-March. The exact cues triggering this annual phenomenon remain unclear. A scleractinian coral, Euphyllia ancora has been selected as a model for the hormones and reproduction studies. Testosterone (T) and estradiol (E2) in free and glucuronided forms were identified and consistently detected in coral polyps throughout the year. Peak levels of free E2, glucuronided E2 and T were obtained in the coral tissue just prior to spawning. The presence of specific aromatase activity was demonstrated in coral tissue. Higher concentrations of free E2 than glucuronided E2 were detected in the coral tissue throughout the year. In contrast, higher levels of glucuronided E2 than free E2 and glucuronided T were found in seawater during mass coral spawning. Furthermore, immunoreactivity and biological activity of immunoreactive gonadotropin-releasing hormone (irGnRH) was detected and quantified in coral tissue. Coral extracts (irGnRH) and mammalian (m)GnRH agonist had a similar dose-dependent effect on luteinizing hormone (LH) release in black porgy fish pituitary cells (in vitro). Peak levels of irGnRH were detected during the spawning period. In in vivo experiments, mGnRH agonist time- and dose-dependently stimulated aromatase activity, as well as the levels of T and E2 in free and glucuronided forms in coral. In conclusion, our data suggest that irGnRH and glucuronided E2 may play important roles in the control of reproduction and mass spawning in corals.

The presence and ancestral role of gonadotropin-releasing hormone in the reproduction of scleractinian coral, Euphyllia ancora.

The objectives of this study were to investigate the presence of immunoreactive GnRH (irGnRH) in scleractinian coral, Euphyllia ancora, study its seasonal variation, and evaluate its biological activity. irGnRH was detected and quantified in coral polyps. The biological activity of coral irGnRH was tested on pituitary cells from black porgy by evaluating its ability to stimulate LH release. Coral extracts (10(-9)-10(-5) M irGnRH) as well as mammalian (m) GnRH agonist (10(-10)-10(-6) M) had a similar dose-dependent effect on LH release. Furthermore, GnRH receptor antagonist dose-dependently inhibited the stimulation of LH release in response to coral extracts (10(-5) M irGnRH) and mGnRH agonist (10(-6) M). Peak levels of irGnRH (10-fold increase) were observed during the spawning period in a 3-yr investigation. Significantly higher aromatase activity and estradiol (E2) levels were also detected during the period of spawning compared with the nonreproductive season. In in vivo experiments, mGnRH agonist time- and dose-dependently stimulated aromatase activity as well as the concentrations of testosterone and E2 in free and glucuronided forms in coral. In conclusion, our data indicate that irGnRH does exist in coral, with its ability to stimulate LH release in fish. Seasonal variations of coral irGnRH, with a dramatic increase during the spawning period, concomitant to that in aromatase and E2, as well as the ability of mGnRH agonist to stimulate coral aromatase, steroidogenesis, and steroid glucuronization suggest that irGnRH plays an important role in the control of oocyte growth and mass spawning in corals.

Corals have already evolved the vertebrate-type hormone system in the sexual reproduction.

Most broadcast spawning scleractinian corals synchronously release gametes during a brief annual spawning period. In southern Taiwan, the mass spawning of scleractinians occurs in lunar mid-March. Endocrine system has been proposed to play important roles in this annual phenomenon. A scleractinian coral, Euphyllia ancora has been selected as a model for the hormones and reproduction studies. We detected the presence of estradiol (E2), testosterone (T), glucuronided E2, glucuronided T, aromatase, immunoreactive (ir)GnRH in coral polyps E. ancora. Annual profiles of sex steroids, aromatase, and irGnRH have also been characterized. We found the parallel increases in irGnRH concentrations, aromatase activity and free E2 and glucuronided E2 concentrations at the time of coral mass spawning. The stimulation of mammalian (m)GnRH agonist in the increased aromatase activity and sex steroid concentrations was also observed in corals. Coral extracts (irGnRH) and mGnRH agonist had a similar dose-dependent effect on luteinizing hormone release in black porgy fish pituitary cells (in vitro). In conclusion, our data suggest that irGnRH and glucuronided E2 may play important roles in the control of reproduction and mass spawning in corals. Corals already evolved the vertebrate-type hormone system in the sexual reproduction.

Sex steroids in scleractinian coral, Euphyllia ancora: implication in mass spawning.

The objectives of this study were to investigate the presence and annual cycle of sex steroids in scleractinian coral, Euphyllia ancora. The free and conjugated forms of sex steroids in coral and spawning seawater were investigated, and aromatase activity in the coral tissue was identified. Polyps collected from corals and seawater were extracted with diethyl ether, and purified by alumina column and reversed-phase HPLC; testosterone and estradiol-17beta (E2) was measured by a validated RIA. E2 and testosterone in their free and glucuronide forms were consistently detected in coral tissue throughout the year. Peak concentrations of free E2, E2 glucuronide, and testosterone glucuronide were obtained in the coral tissue just prior to spawning. The presence of specific aromatase activity was demonstrated in coral tissue. Free E2 and E2 glucuronide concentrations were higher than androgen (testosterone and testosterone glucuronide) in coral tissue and spawning seawater. Higher concentrations of free E2 than E2 glucuronide were detected in coral tissues throughout the year. In contrast, higher concentrations of E2 glucuronide than free E2 and testosterone glucuronide were found in seawater during mass coral spawning. No steroid sulfate could be detected in the coral tissue and seawater. We suggest that the release of E2 glucuronide may play an important role in coral mass spawning.