Employing Raman Spectroscopy and Machine Learning for the Identification of Breast Cancer.

BACKGROUND: Breast cancer poses a significant health risk to women worldwide, with approximately 30% being diagnosed annually in the United States. The identification of cancerous mammary tissues from non-cancerous ones during surgery is crucial for the complete removal of tumors. RESULTS: Our study innovatively utilized machine learning techniques (Random Forest (RF), Support Vector Machine (SVM), and Convolutional Neural Network (CNN)) alongside Raman spectroscopy to streamline and hasten the differentiation of normal and late-stage cancerous mammary tissues in mice. The classification accuracy rates achieved by these models were 94.47% for RF, 96.76% for SVM, and 97.58% for CNN, respectively. To our best knowledge, this study was the first effort in comparing the effectiveness of these three machine-learning techniques in classifying breast cancer tissues based on their Raman spectra. Moreover, we innovatively identified specific spectral peaks that contribute to the molecular characteristics of the murine cancerous and non-cancerous tissues. CONCLUSIONS: Consequently, our integrated approach of machine learning and Raman spectroscopy presents a non-invasive, swift diagnostic tool for breast cancer, offering promising applications in intraoperative settings.

Original and liposome-modified indocyanine green-assisted fluorescence study with animal models.

Medical diagnosis heavily relies on the use of bio-imaging techniques. One such technique is the use of ICG-based biological sensors for fluorescence imaging. In this study, we aimed to improve the fluorescence signals of ICG-based biological sensors by incorporating liposome-modified ICG. The results from dynamic light scattering and transmission electron microscopy showed that MLM-ICG was successfully fabricated with a liposome diameter of 100-300 nm. Fluorescence spectroscopy showed that MLM-ICG had the best properties among the three samples (Blank ICG, LM-ICG, and MLM-ICG), as samples immersed in MLM-ICG solution achieved the highest fluorescence intensity. The NIR camera imaging also showed a similar result. For the rat model, the best period for fluorescence tests was between 10 min and 4 h, where most organs reached their maximum fluorescence intensity except for the liver, which continued to rise. After 24 h, ICG was excreted from the rat's body. The study also analyzed the spectra properties of different rat organs, including peak intensity, peak wavelength, and FWHM. In conclusion, the use of liposome-modified ICG provides a safe and optimized optical agent, which is more stable and efficient than non-modified ICG. Incorporating liposome-modified ICG in fluorescence spectroscopy could be an effective way to develop novel biosensors for disease diagnosis.

Enhanced denitrification performance of granular sludge for the treatment of waste brine from ion exchange resin process.

Ion exchange resin process is a widely used process in wastewater treatment plants, but its waste brine is characterized by high salinity and nitrate concentration, leading to costly treatment. This study innovatively explored the use of an up-flow anaerobic sludge bed (USB) for the treatment of waste brine from ion exchange resin process, following a pilot-scale ion exchange resin process. Specifically, the D890 ion exchange resin was employed for nitrate removal from secondary effluent, with resin regeneration using 4% NaCl solution. The USB was inoculated with anaerobic granular sludge and acclimated under various single-factor conditions, which revealed the optimal pH range of 6.5-9, salt concentration of 2%, hydraulic retention time of 12 h, C/N ratio of 3.3, and up-flow velocity of 1.5 m/h for reactor operation. This study provides a novel approach for the cost-effective treatment of waste brine from ion exchange resin process. The study found that the denitrification efficiency was highest when the NO3--N concentration was around 200 mg/L, with NO3--N and TN removal rates exceeding 95% and 90%, respectively, under optimal operating conditions. Characterization of the granular sludge during different phases of the operation revealed a significant increase in proteobacteria and gradually became the dominant species over time. This study presents a novel, cost-effective approach to treat waste brine from ion exchange resin process, and the long-term stable operation of the reactor offers a reliable option for resin regeneration wastewater treatment.

Paediatric lung injury due to accidental ingestion of meperfluthrin: a case report.

BACKGROUND: It is common for children to accidentally ingest chemical drugs with different degrees of toxicity. Meperfluthrin is a highly effective and easy-to-use pyrethroid pesticide with low toxicity. It is widely used in electric mosquito coils. This type of electric mosquito coil is used in daily life, which increases the chance of exposure among children and, consequently, may lead to accidental ingestion. There are only few reports of meperfluthrin poisoning causing lung injury in children. We report a rare clinical case of lung injury wherein a child ingested meperfluthrin orally. CASE PRESENTATION: We report the case of a 1-year-old boy who accidentally swallowed an electric mosquito coil containing meperfluthrin and developed cough and fever. The patient's parents observed him swallowing the electric mosquito coil (Qiangshou®). Although he was stopped, the child had already swallowed approximately 10 ml of the liquid. According to the instructions, it contained 9 mg/ml of meperfluthrin, thus, it was assumed that he ingested meperfluthrin at a dose of approximately 90 mg. Computed tomography (CT) of his lungs showed uneven brightness in both lungs with multiple spots, scaly shadows, and mesh. Density of the shadows indicated lung parenchymal and interstitial lung disease. Lung tidal function tests indicated obstructive ventilation dysfunction. After evaluation and treatment, his cough drastically reduced, his fever disappeared, and his lung CT findings showed improvement. Therefore, accidental ingestion of meperfluthrin led to acute lung injury in a paediatric patient. Because of prompt treatment, his lung lesions recovered well. CONCLUSIONS: Meperfluthrin causes airway mucosal damage and hypersensitivity. Lung CT and lung tidal function measurements can be used to monitor changes in the condition. Presently, there is a lack of specific detoxification drugs for meperfluthrin poisoning. Thus, the focus of treatment is to protect the airway mucosa and reduce inflammatory reactions.

Heat Waves Alter Macrophyte-Derived Detrital Nutrients Release under Future Climate Warming Scenarios.

In addition to a rise in global air and water mean temperatures, extreme climate events such as heat waves are increasing in frequency, intensity, and duration in many regions of the globe. Developing a mechanistic understanding of the impacts of heat waves on key ecosystem processes and how they differ from just an increase in mean temperatures is therefore of utmost importance for adaptive management against effects of global change. However, little is known about the impact of extreme events on freshwater ecosystem processes, particularly the decomposition of macrophyte detritus. We performed a mesocosm experiment to evaluate the impact of warming and heat waves on macrophyte detrital decomposition, applied as a fixed increment (+4 °C) above ambient and a fluctuating treatment with similar energy input, ranging from 0 to 6 °C above ambient (i.e., simulating heat waves). We showed that both warming and heat waves significantly accelerate dry mass loss of the detritus and carbon (C) release but found no significant differences between the two heated treatments on the effects on detritus dry mass loss and C release amount. This suggests that moderate warming indirectly enhanced macrophyte detritus dry mass loss and C release mainly by the amount of energy input rather than by the way in which warming was provided (i.e., by a fixed increment or in heat waves). However, we found significantly different amounts of nitrogen (N) and phosphorus (P) released between the two warming treatments, and there was an asymmetric response of N and P release patterns to the two warming treatments, possibly due to species-specific responses of decomposers to short-term temperature fluctuations and litter quality. Our results conclude that future climate scenarios can significantly accelerate organic matter decomposition and C, N, and P release from decaying macrophytes, and more importantly, there are asymmetric alterations in macrophyte-derived detrital N and P release dynamic. Therefore, future climate change scenarios could lead to alterations in N/P ratios in the water column via macrophyte decomposition processes and ultimately affect the structure and function of aquatic ecosystems, especially in the plankton community.

Climate warming and heat waves affect reproductive strategies and interactions between submerged macrophytes.

Extreme climatic events, such as heat waves, are predicted to increase in frequency and intensity during the next hundred years, which may accelerate shifts in hydrological regimes and submerged macrophyte composition in freshwater ecosystems. Since macrophytes are profound components of aquatic systems, predicting their response to extreme climatic events is crucial for implementation of climate change adaptation strategies. We therefore performed an experiment in 24 outdoor enclosures (400 L) separating the impact of a 4 °C increase in mean temperature with the same increase, that is the same total amount of energy input, but resembling a climate scenario with extreme variability, oscillating between 0 °C and 8 °C above present conditions. We show that at the moderate nutrient conditions provided in our study, neither an increase in mean temperature nor heat waves lead to a shift from a plant-dominated to an algal-dominated system. Instead, we show that species-specific responses to climate change among submerged macrophytes may critically influence species composition and thereby ecosystem functioning. Our results also imply that more fluctuating temperatures affect the number of flowers produced per plant leading to less sexual reproduction. Our findings therefore suggest that predicted alterations in climate regimes may influence both plant interactions and reproductive strategies, which have the potential to inflict changes in biodiversity, community structure and ecosystem functioning.

Antiparasitic efficacy of Gracillin and Zingibernsis newsaponin from Costus speciosus (Koen ex. Retz) Sm. against Ichthyophthirius multifiliis.

The present study aims to evaluate the antiparasitic activity of active components from Costus speciosus against Ichthyophthirius multifiliis. Bioassay-guided fractionation was employed to identify active compounds from C. speciosus yielding 2 bioactive compounds: Gracillin and Zingibernsis newsaponin. In-vitro assays revealed that Gracillin and Zingibernsis newsaponin could be 100% effective against I. multifiliis at concentrations of 0.8 and 4.5 mg L(-1), with median effective concentration (EC50) values of 0.53 and 3.2 mg L(-1), respectively. All protomonts and encysted tomonts were killed when the concentrations of Gracillin and Zingibernsis newsaponin were 1.0 and 5.0 mg L(-1). In-vivo experiments demonstrated that fish treated with Gracillin and Zingibernsis newsaponin at concentrations of 1.0 and 5.0 mg L(-1) carried significantly fewer parasites than the control (P<0.05). Mortality of fish did not occur in the treatment group (Zingibernsis newsaponin at 5.0 mg L(-1)) during the trial, although 100% of untreated fish died. Acute toxicities (LD50) of Gracillin and Zingibernsis newsaponin for grass carp were 1.64 and 20.7 mg L(-1), respectively. These results provided evidence that the 2 compounds can be selected as lead compounds for the development of new drugs against I. multifiliis.

[3D-TV health assessment system by the multi-modal physiological signals].

In order to meet the requirements of the multi-physiological signal measurement of the 3D-TV health assessment, try to find the suitable biological acquisition chips and design the hardware system which can detect different physiological signals in real time. The systems mainly uses ARM11/S3C6410 microcontroller to control the EEG/EOG acquisition chip RHA2116 and the ECG acquisition chip ADS1298, and then the microcontroller transfer the data collected by the chips to the PC software by the USB port which can display and save the experimental data in real time, then use the Matlab software for further processing of the data, finally make a final health assessment. In the meantime, for the different varieties in the different brain regions of watching 3D-TV, developed the special brain electrode placement and the experimental data processing methods, then effectively disposed the multi-signal data in the multilevel.

Responses of submerged macrophytes to different particle size microplastics and tetracycline co-pollutants at the community and population level.

Microplastics (MPs) and antibiotics are ubiquitous in aquatic ecosystems, and their accumulation and combined effects are considered emerging threats that may affect biodiversity and ecosystem function. The particle size of microplastics plays an important role in their combined effects with antibiotics. Submerged macrophytes are crucial in maintaining the health and stability of freshwater ecosystems. However, little is known about the combined effects of different particle size of MPs and antibiotics on freshwater plants, particularly their effects on submerged macrophyte communities. Thus, there is an urgent need to study their effects on the macrophyte communities to provide essential information for freshwater ecosystem management. In the present study, a mesocosm experiment was conducted to explore the effects of three particle sizes (5 µm, 50 µm, and 500 µm) of polystyrene-microplastics (PSMPs) (75 mg/L), tetracycline (TC) (50 mg/L), and their co-pollutants on interactions between Hydrilla verticillata and Elodea nuttallii. Our results showed that the effects of MPs are size-dependent on macrophytes at the community level rather than at the population level, and that small and medium sized MPs can promote the growth of the two test macrophytes at the community level. In addition, macrophytes at the community level have a stronger resistance to pollutant stress than those at the population level. Combined exposure to MPs and TC co-pollutants induces species-specific responses and antagonistic toxic effects on the physio-biochemical traits of submerged macrophytes. Our study provides evidence that MPs and co-pollutants not only affect the morphology and physiology at the population level but also the interactions between macrophytes. Thus, there are promising indications on the potential consequences of MPs and co-pollutants on macrophyte community structure, which suggests that future studies should focus on the effects of microplastics and their co-pollutants on aquatic macrophytes at the community level rather than only at the population level. This will improve our understanding of the profound effects of co-pollutants in aquatic environments on the structure and behavior of aquatic communities and ecosystems.

The characteristics and environmental significance of BVOCs released by aquatic macrophytes.

Biogenic volatile organic compounds (BVOCs) emitted by plants serve crucial biological functions and potentially impact atmospheric environment and global carbon cycling. Despite their significance, BVOC emissions from aquatic macrophytes have been relatively understudied. In this study, for the first time we identified there were 68 major BVOCs released from 34 common aquatic macrophytes, and these compounds referred to alcohols, aldehydes, alkanes, alkenes, arenes, ethers, furans, ketones, phenol. For type of BVOC emissions from different life form and phylogenetic group of aquatic macrophytes, 34 of the 68 BVOCs from emergent and submerged macrophytes are classified into alkene and alcohol compounds, over 50% BVOCs from dicotyledon and monocotyledon belong to alcohol and arene compounds. Charophyte and pteridophyte emitted significantly fewer BVOCs than dicotyledon and monocotyledon, and each of them only released 12 BVOCs. These BVOCs may be of great importance for the growth and development of macrophytes, because many BVOCs, such as azulene, (E)-ß-farnesene, and dimethyl sulfide are proved to play vital roles in plant growth, defense, and information transmission. Our results confirmed that both life form and phylogenetic group of aquatic macrophytes had significantly affected the BVOC emissions form macrophytes, and suggested that the intricate interplay of internal and external factors that shape BVOC emissions from aquatic macrophytes. Thus, further studies are urgently needed to investigate the influence factors and ecological function of BVOCs released by macrophytes within aquatic ecosystem.

Lower concentration polyethylene microplastics can influence free-floating macrophyte interactions by combined effects of many weak interactions: A nonnegligible ecological impact.

Microplastics (MPs) are ubiquitous in freshwater ecosystems and their accumulation has been considered an emerging threat. Early research on the effects of MPs on macrophytes primarily focused on the toxicological impacts on individual macrophytes, with several studies suggesting that lower concentrations of MPs have little impact on macrophytes. However, the ecological implications of lower MP concentrations on macrophyte communities remain largely unexplored. Here, we experimented to assess the effects of lower concentrations including 25 mg/L, 50 mg/L, 75 mg/L, and 100 mg/L of polyethylene (PE) microplastics on Spirodela polyrhiza and Lemna minor, and their community. Our results also indicated that PE concentrations below 100 mg/L had no significant effect on relative growth rate, specific leaf area, Chlorophyll a, Chlorophyll b, Chlorophyll a + b, carotenoid, malondialdehyde (MDA), catalase, and soluble sugar of monocultural S. polyrhiza. However, a lower concentration of PE significantly decreased the MDA of monocultural L. minor and significantly affected the comprehensive index of S. polyrhiza. These findings suggested that lower concentrations of PE can influence interactions between macrophytes maybe due to the cumulative effects of many weak interactions. Additionally, our study showed that 75 mg/L and 100 mg/L PE additions decreased the competitive balance index value of two macrophytes under mixed-culture condition. This result implied that the ecological influence of lower concentration MPs on macrophytes may manifest at the community level rather than at the population level, due to species-specific responses and varying degrees of sensitivity of macrophytes to PE concentrations. Thus, our study emphasizes the need to closely monitor the ecological consequences of emerging contaminants such as MPs accumulation on macrophyte communities, rather than focusing solely on the morphology and physiology of individual macrophytes.

Human Tooth Crack Image Analysis with Multiple Deep Learning Approaches.

Tooth cracks, one of the most common dental diseases, can result in the tooth falling apart without prompt treatment; dentists also have difficulty locating cracks, even with X-ray imaging. Indocyanine green (ICG) assisted near-infrared fluorescence (NIRF) dental imaging technique can solve this problem due to the deep penetration of NIR light and the excellent fluorescence characteristics of ICG. This study extracted 593 human cracked tooth images and 601 non-cracked tooth images from NIR imaging videos. Multiple imaging analysis methods such as classification, object detection, and super-resolution were applied to the dataset for cracked image analysis. Our results showed that machine learning methods could help analyze tooth crack efficiently: the tooth images with cracks and without cracks could be well classified with the pre-trained residual network and squeezenet1_1 models, with a classification accuracy of 88.2% and 94.25%, respectively; the single shot multi-box detector (SSD) was able to recognize cracks, even if the input image was at a different size from the original cracked image; the super-resolution (SR) model, SR-generative adversarial network demonstrated enhanced resolution of crack images using high-resolution concrete crack images as the training dataset. Overall, deep learning model-assisted human crack analysis improves crack identification; the combination of our NIR dental imaging system and deep learning models has the potential to assist dentists in crack diagnosis.

Standard: human intestine-on-a-chip.

Organs-on-chips are microphysiological systems that allow to replicate the key functions of human organs and accelerate the innovation in life sciences including disease modeling, drug development, and precision medicine. However, due to the lack of standards in their definition, structural design, cell source, model construction, and functional validation, a wide range of translational application of organs-on-chips remains a challenging. "Organs-on-chips: Intestine" is the first group standard on human intestine-on-a-chip in China, jointly agreed and released by the experts from the Chinese Society of Biotechnology on 29th April 2024. This standard specifies the scope, terminology, definitions, technical requirements, detection methods, and quality control in building the human intestinal model on a chip. The publication of this group standard will guide the institutional establishment, acceptance and execution of proper practical protocols and accelerate the international standardization of intestine-on-a-chip for translational applications.

Depletion of PHF14, a novel histone-binding protein gene, causes neonatal lethality in mice due to respiratory failure.

The plant homeodomain (PHD) finger is identified in many chromatin-binding proteins, and functions as a 'reader' that recognizes specific epigenetic marks on histone tails, bridging transcription factors and their associated complexes to chromatin, and regulating gene expression. PHD finger-containing proteins perform many biological functions and are involved in many human diseases including cancer. PHF14 is predicted to code for a protein with multiple PHD fingers. However, its function is unidentified. The aim of this study is to characterize PHF14 and investigate its biological significance by employing multiple approaches including mouse gene-targeting knockout, and molecular cloning and characterization. Three transcripts of PHF14 in human cell lines were identified by reverse transcriptase polymerase chain reaction. Two isoforms of PHF14 (PHF14α and PHF14ß) were cloned in this study. It was found that PHF14 was ubiquitously expressed in mouse tissues and human cell lines. PHF14α, the major isoform of PHF14, was localized in the nucleus and also bound to chromatin during cell division. Interestingly, co-immunoprecipitation results suggested that PHF14α bound to histones via its PHD fingers. Strikingly, gene-targeting knockout of PHF14 in mice resulted in a neonatal lethality due to respiratory failure. Pathological analysis revealed severe disorders of tissue and cell structures in multiple organs, particularly in the lungs. These results indicated that PHF14 might be an epigenetic regulator and play an important role in the development of multiple organs in mouse.

Microplastics and co-pollutant with ciprofloxacin affect interactions between free-floating macrophytes.

Microplastic and antibiotic contamination are considered an increasing environmental problem in aquatic systems, while little is known about the impact of microplastics and co-pollutant with antibiotics on freshwater vascular plants, particularly the effects of interactions between macrophytes. Here, we performed a mesocosm experiment to evaluate the impact of polyethylene-microplastics and their co-pollutants with ciprofloxacin on the growth and physiological characteristics of Spirodela polyrhiza and Lemna minor and the interactions between these two macrophytes. Our results showed that microplastics alone cannot significantly influence fresh weight and specific leaf area of the two test free-floating macrophytes, but the effects on photosynthetic pigments, malondialdehyde, catalase and soluble sugar contents were species-specific. Ciprofloxacin can significant adverse effects on the growth and physiological traits of the two test macrophytes and microplastic mitigated the toxicity of ciprofloxacin on the two free-floating plants to a certain extent. In addition, our studies showed that microplastics and co-pollutants can influence relative yield and competitiveness of S. polyrhiza and L. minor by directly or indirectly influencing their physiology and growth. Therefore our findings suggest that species-specific sensibility to microplastic and its co-pollutant among free-floating macrophytes may influence macrophyte population dynamics and thereby community structure and ecosystem functioning. And microplastics altered other contaminant behaviours and toxicity, and may directly or indirectly influence macrophytes interactions and community structure. The present study is the first experimental study exploring the effects of microplastics alone and with their co-pollutants on interactions between free-floating macrophytes, which can provide basic theoretical guidance for improving the stability of freshwater ecosystems.

Mapping soil available copper content in the mine tailings pond with combined simulated annealing deep neural network and UAV hyperspectral images.

Improper discharge of slag from mining will pollute the surrounding soil, thereby affecting the ecology and becoming an important global problem. The available copper (ACu) content in polluted soil is an important factor affecting plant growth and development. When investigating a large area of soil with ACu, manual sampling by points and inspection are mainly used, due to the heterogeneity of soil, the efficiency and accuracy are lower. The Unmanned aerial vehicle (UAV) equipped with a hyperspectral sensor as a remote sensing technology is widely used in soil indicator monitoring because of its rapid and convenience. Meanwhile, using the relationship between soil organic matter and available copper has the potential to predict available copper. In this study, we selected the study area with tailings area in the Jianghan Plain of China and used a UAV equipped with a hyperspectral sensor to predict ACu and soil organic matter (SOM) in the soil with two datasets. Firstly, 74 soil samples were collected in the study area, and the ACu and SOM of the soil samples were determined. Second, a hyperspectral image of the study area is obtained using a UAV equipped with a hyperspectral sensor. Thirdly, we combine hyperspectral data with competitive adaptive reweighted sampling (CARS) to obtain feature bands and utilize simulated annealing deep neural network (SA-DNN) to generate estimation models. Finally, maps of the distribution of ACu and SOM in the area were generated using the model. In two datasets, the model of ACu with R2 values both are 0.89, and R2 on the model of SOM is 0.89 and 0.88. The results show that the combination of UAV hyperspectral imagery with the SA-DNN model has good performance in the prediction of organic matter and available copper, which is helpful for soil environmental monitoring.

Mouthwash as a non-invasive method of indocyanine green delivery for near-infrared fluorescence dental imaging.

SIGNIFICANCE: X-ray imaging serves as the mainstream imaging in dentistry, but it involves risk of ionizing radiation. AIM: This study presents the feasibility of indocyanine green-assisted near-infrared fluorescence (ICG-NIRF) dental imaging with 785-nm NIR laser in the first (ICG-NIRF-I: 700 to 1000 nm) and second (ICG-NIRF-II: 1000 to 1700 nm) NIR wavelengths. APPROACH: Sprague Dawley rats with different postnatal days were used as animal models. ICG, as a fluorescence agent, was delivered to dental structures by subcutaneous injection (SC) and oral administration (OA). RESULTS: For SC method, erupted and unerupted molars could be observed from ICG-NIRF images at a short imaging time (<1 min). ICG-NIRF-II could achieve a better image contrast in unerupted molars at 24 h after ICG injection. The OA could serve as a non-invasive method for ICG delivery; it could also cause the glow-in-dark effect in unerupted molars. For erupted molars, OA can be considered as mouthwash and exhibits outstanding performance for delivery of ICG dye; erupted molar structures could be observed at a short imaging time (<1 min) and low ICG dose (0.05 mg / kg). CONCLUSIONS: Overall, ICG-NIRF with mouthwash could perform in-vivo dental imaging in two NIR wavelengths at a short time and low ICG dose.

Machine-learning-assisted spontaneous Raman spectroscopy classification and feature extraction for the diagnosis of human laryngeal cancer.

The early detection of laryngeal cancer significantly increases the survival rates, permits more conservative larynx sparing treatments, and reduces healthcare costs. A non-invasive optical form of biopsy for laryngeal carcinoma can increase the early detection rate, allow for more accurate monitoring of its recurrence, and improve intraoperative margin control. In this study, we evaluated a Raman spectroscopy system for the rapid intraoperative detection of human laryngeal carcinoma. The spectral analysis methods included principal component analysis (PCA), random forest (RF), and one-dimensional (1D) convolutional neural network (CNN) methods. We measured the Raman spectra from 207 normal and 500 tumor sites collected from 10 human laryngeal cancer surgical specimens. Random Forest analysis yielded an overall accuracy of 90.5%, sensitivity of 88.2%, and specificity of 92.8% on average over 10 trials. The 1D CNN demonstrated the highest performance with an accuracy of 96.1%, sensitivity of 95.2%, and specificity of 96.9% on average over 50 trials. In predicting the first three principal components (PCs) of normal and tumor data, both RF and CNN demonstrated high performances, except for the tumor PC2. This is the first study in which CNN-assisted Raman spectroscopy was used to identify human laryngeal cancer tissue with extracted feature weights. The proposed Raman spectroscopy feature extraction approach has not been previously applied to human cancer diagnosis. Raman spectroscopy, as assisted by machine learning (ML) methods, has the potential to serve as an intraoperative, non-invasive tool for the rapid diagnosis of laryngeal cancer and margin detection.

Multiple-Inputs Convolutional Neural Network for COVID-19 Classification and Critical Region Screening From Chest X-ray Radiographs: Model Development and Performance Evaluation.

Background: The COVID-19 pandemic is becoming one of the largest, unprecedented health crises, and chest X-ray radiography (CXR) plays a vital role in diagnosing COVID-19. However, extracting and finding useful image features from CXRs demand a heavy workload for radiologists. Objective: The aim of this study was to design a novel multiple-inputs (MI) convolutional neural network (CNN) for the classification of COVID-19 and extraction of critical regions from CXRs. We also investigated the effect of the number of inputs on the performance of our new MI-CNN model. Methods: A total of 6205 CXR images (including 3021 COVID-19 CXRs and 3184 normal CXRs) were used to test our MI-CNN models. CXRs could be evenly segmented into different numbers (2, 4, and 16) of individual regions. Each region could individually serve as one of the MI-CNN inputs. The CNN features of these MI-CNN inputs would then be fused for COVID-19 classification. More importantly, the contributions of each CXR region could be evaluated through assessing the number of images that were accurately classified by their corresponding regions in the testing data sets. Results: In both the whole-image and left- and right-lung region of interest (LR-ROI) data sets, MI-CNNs demonstrated good efficiency for COVID-19 classification. In particular, MI-CNNs with more inputs (2-, 4-, and 16-input MI-CNNs) had better efficiency in recognizing COVID-19 CXRs than the 1-input CNN. Compared to the whole-image data sets, the efficiency of LR-ROI data sets showed approximately 4% lower accuracy, sensitivity, specificity, and precision (over 91%). In considering the contributions of each region, one of the possible reasons for this reduced performance was that nonlung regions (eg, region 16) provided false-positive contributions to COVID-19 classification. The MI-CNN with the LR-ROI data set could provide a more accurate evaluation of the contribution of each region and COVID-19 classification. Additionally, the right-lung regions had higher contributions to the classification of COVID-19 CXRs, whereas the left-lung regions had higher contributions to identifying normal CXRs. Conclusions: Overall, MI-CNNs could achieve higher accuracy with an increasing number of inputs (eg, 16-input MI-CNN). This approach could assist radiologists in identifying COVID-19 CXRs and in screening the critical regions related to COVID-19 classifications.

Isotopic turnover of a submersed macrophyte following transplant: the roles of growth and metabolism in eutrophic conditions.

Stable isotopic turnover with isotopic change due to growth and metabolic tissue replacement associated with a change in environmental conditions is a critical aspect of the use of stable isotope analyses as time-integrating tracers of resource-consumer interactions. However, stable isotopic turnover in plants remains poorly understood compared with those of animals, and here we used continuous flow elemental analyzer-isotopic ratio mass spectrometry (EA-IRMS) to analyse the turnover of stable carbon and nitrogen isotopes in a submersed macrophyte (Vallisneria natans) after transplantation to hypereutrophic and mesoeutrophic treatments in a field mesocosm experiment. The direction and magnitude of the isotopic shifts of V. natans were suggested to be determined by the inorganic nutrient availability and its isotopic content in the different treatments. Based on the modelling results of turnover, the contribution of growth to the isotopic turnover was as high as those observed in various aquatic ectotherms. However, the contribution of metabolism was also considerable, especially for nitrogen in the hypereutrophic treatment, which was argued to be a response, co-occurring with growth inhabitation and biochemical disorder of V. natans, to the stress induced by the eutrophication. Our results indicated that isotope turnover in a macrophyte is a feasible technique for estimating its ecophysiological conditions in the natural environment, and that it may facilitate understanding of isotopic data in field studies of food web and habitat restoration under eutrophic conditions.