Search Results (221)

Background/Objectives: Historically, echocardiographic imaging of the right heart has been challenging because its abnormal geometry is not conducive to reproducible anatomical and functional assessment. With the development of advanced echocardiographic techniques, it is now possible to complete an integrated assessment of the right heart that has fewer assumptions, resulting in increased accuracy and precision. Echocardiography continues to be the first-line imaging modality for diagnostic analysis and the management of acute and chronic right heart failure because of its portability, versatility, and affordability compared to cardiac computed tomography, magnetic resonance imaging, nuclear scintigraphy, and positron emission tomography. Virtually all echocardiographic parameters have been well-validated and have demonstrated prognostic significance. The goal of this narrative review of the echocardiographic parameters of the right heart chambers and hemodynamic alterations associated with right ventricular dysfunction is to present information that must be acquired during each examination to deliver a comprehensive assessment of the right heart and to discuss their clinical significance in right heart failure. Methods: Using a literature search in the PubMed database from 1985 to 2025 and the Cochrane database, which included but was not limited to terminology that are descriptive of right heart anatomy and function, disease states involving acute and chronic right heart failure and pulmonary hypertension, and the application of conventional and advanced echocardiographic modalities that strive to elucidate the pathophysiology of right heart failure, we reviewed randomized control trials, observational retrospective and prospective cohort studies, societal guidelines, and systematic review articles. Conclusions: In addition to the conventional 2-dimensional echocardiography and color, spectral, and tissue Doppler measurements, a contemporary echocardiographic assessment of a patient with suspected or proven right heart failure must include 3-dimensional echocardiographic-derived measurements, speckle-tracking echocardiography strain analysis, and hemodynamics parameters to not only characterize the right heart anatomy but to also determine the underlying pathophysiology of right heart failure. Complete and point-of-care echocardiography is available in virtually all clinical settings for routine care, but this imaging tool is particularly indispensable in the emergency department, intensive care units, and operating room, where it can provide an immediate assessment of right ventricular function and associated hemodynamic changes to assist with real-time management decisions. Full article

Timely and accurate diagnosis of gastrointestinal diseases (GIDs) remains a critical bottleneck in clinical endoscopy, particularly due to the limited contrast and sensitivity of conventional white light imaging (WLI) in detecting early-stage mucosal abnormalities. To overcome this, this research presents Spectrum Aided Vision Enhancer (SAVE), an innovative, software-driven framework that transforms standard WLI into high-fidelity hyperspectral imaging (HSI) and simulated narrow-band imaging (NBI) without any hardware modification. SAVE leverages advanced spectral reconstruction techniques, including Macbeth Color Checker-based calibration, principal component analysis (PCA), and multivariate polynomial regression, achieving a root mean square error (RMSE) of 0.056 and structural similarity index (SSIM) exceeding 90%. Trained and validated on the Kvasir v2 dataset (n = 6490) using deep learning models like ResNet-50, ResNet-101, EfficientNet-B2, both EfficientNet-B5 and EfficientNetV2-B0 were used to assess diagnostic performance across six key GI conditions. Results demonstrated that SAVE enhanced imagery and consistently outperformed raw WLI across precision, recall, and F1-score metrics, with EfficientNet-B2 and EfficientNetV2-B0 achieving the highest classification accuracy. Notably, this performance gain was achieved without the need for specialized imaging hardware. These findings highlight SAVE as a transformative solution for augmenting GI diagnostics, with the potential to significantly improve early detection, streamline clinical workflows, and broaden access to advanced imaging especially in resource constrained settings. Full article

Background/Objectives: Global warming and rising CO₂ concentrations pose significant challenges to plant systems. Amid these pressures, this study contributes to understanding how tropical species respond by simultaneously evaluating reproductive and genetic traits. It specifically investigates the effects of maternal exposure to warming and elevated CO₂ on progeny physiology, genetic diversity, and population structure in Stylosanthes capitata, a resilient forage legume native to Brazil. Methods: Maternal plants were cultivated under controlled treatments, including ambient conditions (control), elevated CO₂ at 600 ppm (eCO₂), elevated temperature at +2 °C (eTE), and their combined exposure (eTEeCO₂), within a Trop-T-FACE field facility (Temperature Free-Air Controlled Enhancement and Free-Air Carbon Dioxide Enrichment). Seed traits (seeds per inflorescence, hundred-seed mass, abortion, non-viable seeds, coat color, germination at 32, 40, 71 weeks) and abnormal seedling rates were quantified. Genetic diversity metrics included the average (A) and effective (Ae) number of alleles, observed (Ho) and expected (He) heterozygosity, and inbreeding coefficient (Fis). Population structure was assessed using Principal Coordinates Analysis (PCoA), Analysis of Molecular Variance (AMOVA), number of migrants per generation (Nm), and genetic differentiation index (Fst). Two- and three-way Analysis of Variance (ANOVA) were used to evaluate factor effects. Results: Compared to control conditions, warming increased seeds per inflorescence (+46%), reduced abortion (−42.9%), non-viable seeds (−57%), and altered coat color. The germination speed index (GSI +23.5%) and germination rate (Gr +11%) improved with warming; combined treatments decreased germination time (GT −9.6%). Storage preserved germination traits, with warming enhancing performance over time and reducing abnormal seedlings (−54.5%). Conversely, elevated CO₂ shortened GSI in late stages, impairing germination efficiency. Warming reduced Ae (−35%), He (−20%), and raised Fis (maternal 0.50, progeny 0.58), consistent with the species’ mixed mating system; A and Ho were unaffected. Allele frequency shifts suggested selective pressure under eTE. Warming induced slight structure in PCoA, and AMOVA detected 1% (maternal) and 9% (progeny) variation. Fst = 0.06 and Nm = 3.8 imply environmental influence without isolation. Conclusions: Warming significantly shapes seed quality, reproductive success, and genetic diversity in S. capitata. Improved reproduction and germination suggest adaptive advantages, but higher inbreeding and reduced diversity may constrain long-term resilience. The findings underscore the need for genetic monitoring and broader genetic bases in cultivars confronting environmental stressors. Full article

Background. Medulloblastoma (MB) prognosis and response to therapy depend largely on genetic changes in tumor cells. Many genes and chromosomal abnormalities have been identified as prognostic factors, including amplification of MYC oncogenes, gains in 1q and 17q, deletions in 10q and 21p, or isochromosomes 17 (i(17)(q10)). The frequency of these abnormalities varies greatly between ethnic populations, but the frequency of specific abnormalities, such as MYCC and MYCN amplification, 17q gain, and deletions, in the Russian population is unknown. Objective: The aim is to study the frequency of MYCC and MYCN amplifications, 17q gain, and 17p deletion and determine their prognostic value in Russian patients with MB. Methods. This study was performed on MB cells obtained from 18 patients (12 boys and 6 girls, aged between 3 months and 17 years, with a median age of 6.5 years). Determination of cytogenetic aberrations was carried out using FISH assays with MYCC-SO, MYCN-SO, and MYCN-SG/cen2 probes, as well as cen7/p53 dual color probes and PML/RARα dual color probes (Abbott Molecular, USA). One-way ANOVA and Fisher’s F-test were used to compare the two groups. The differences were considered significant when p < 0.05. Results. In 77.7% of patients (14/18), the classical type of MB was present; in 16.7% (3/18), desmoplastic type; and in 5.6% (1/18), nodular desmoplasic types of neoplasms. Amplification of MYC genes was detected in 22.2% of Russian patients (n = 4 out of 18). Patients with MYC amplification had the worst overall survival (OS: 0% vs. 68%, p = 0.0004). Changes on the 17th chromosome were found in 58.3% of patients. Deletion of 17p occurred in 23.1%, and gain of 17q occurred in 46.2%. There were no significant differences in OS, clinical signs, or the presence of additional 17q material or 17p deletion among patients with MB. Conclusions: Amplification of the MYC gene is a predictor of poor overall survival to therapy and a high risk of metastatic relapse. This allows us to more accurately stratify patients into risk groups in order to determine the intensity and duration of therapy. Full article

The color of flowers in Osmanthus fragrans is regulated by carotenoid metabolism. The orange-red variety, Dangui, is believed to have evolved from the yellow variety, Jingui, through a natural bud mutation. This study uses the Jingui cultivar ‘Jinqiu Gui’ (JQG) and its bud mutation cultivar ‘Huolian Jindan’ (HLJD) as materials, combining genome resequencing, ultrastructural observation, targeted metabolomics, and transcriptomic analysis to elucidate the molecular and cellular mechanisms underlying flower color variation. Phylogenetic analysis confirms that HLJD is a natural bud mutation of JQG. Ultrastructural observations reveal that during petal development, chromoplasts are transformed from proplastids. In HLJD petals, starch granules degrade more slowly and exhibit abnormal morphology, resulting in chromoplasts displaying crystalline, tubular, and fibrous composite structures, in contrast to the typical spherical plastoglobuli found in JQG. Targeted metabolomics identified 34 carotenoids, showing significant increases in the levels of ε-carotene, γ-carotene, α-carotene, and β-carotene in HLJD petals compared to JQG, with these levels continuing to accumulate throughout the flowering process, while the levels of the cleavage products α-ionone and β-ionone decrease. Transcriptomic analysis indicates that carotenoid metabolic pathway genes do not correlate directly with the phenotype; however, 49 candidate genes significantly associated with pigment accumulation were identified. Among these, the expression of genes such as glycoside hydrolases (LYG036752, etc.), sucrose synthase (LYG010191), and glucose-1-phosphate adenylyltransferase (LYG003610) are downregulated in HLJD. This study proposes for the first time the pathway of “starch degradation delay → chromoplast structural abnormalities → carotenoid cleavage inhibition” for deepening flower color, providing a new theoretical model for the metabolic regulation of carotenoids in non-photosynthetic tissues of plants. This research not only identifies key target genes (such as glycoside hydrolases) for the color breeding of O. fragrans but also establishes a theoretical foundation for the color enhancement of other ornamental plants. Full article

Biosensors play a central role in the early detection of abnormal glucose levels in individuals with diabetes; therefore, the development of less invasive systems is essential. Herein, a 3D-printed colorimetric biosensor combining microneedles and chitosan nanoparticles was developed for glucose detection in sweat using machine learning. Briefly, hollow 3D-printed polylactic acid microneedles were constructed and loaded with chitosan nanoparticles encapsulating glucose oxidase, horseradish peroxidase, and the chromogenic substrate 2,2′-azino-bis(3-ethylbenzothiazoline-6-sulfonic acid), resulting in the formation of the chitosan nanoparticle−microneedle patches. Glucose detection was performed colorimetrically by first incubating the chitosan nanoparticle−microneedle patches with glucose samples of varying concentrations and then by using photographs of the top side of each microneedle and a color recognition application on a smartphone. The Random Sample Consensus algorithm was used to train a simple linear regression model to predict glucose concentrations in unknown samples. The developed biosensor system exhibited a good linear response range toward glucose (0.025−0.375 mM), a low limit of detection (0.023 mM), a limit of quantification (0.078 mM), high specificity, and recovery rates ranging between 86–112%. Lastly, the biosensor was applied to glucose detection in spiked artificial sweat samples, confirming the potential of the proposed methodology for glucose detection in real samples. Full article

The eye is one of our five sense organs, where optical and neural structures are integrated. It works in synchrony with the brain, enabling the formation of meaningful images. However, lack of function, complete absence or structural abnormalities of cone cells in the cone cells in the retina causes the emergence of types of Color Vision Deficiency (CVD). This deficiency is characterized by the lack of clear vision in the use of colors in the same region of the spectrum, and greatly affects the quality of life of the patient. Therefore, it is important to develop filters that enable colors to be combined successfully. In this study, an original filter design was improved, built on a five-stage systematic structure that complements and supports itself. But optimization regarding performance value needs to be tested with objective methods independent of human decision. Therefore, in order to provide performance analyses based on objective evaluation criteria, original and enhanced images simulated by patients with seven different Color Vision Deficiency (CVD) types were classified with the MobileNet transfer learning model. The classification results show that the developed final filter greatly improves the differences in color perception levels in both eyes. Thus, color stimulation between the two eyes is more balanced, and perceptual symmetry is created. With perceptual symmetry, environmental colors are perceived more consistently and distinguishably, and the visual difficulties encountered by color blind individuals in daily life are reduced. Full article

Artificial intelligence (AI) is revolutionizing the field of medical imaging, offering unprecedented capabilities in data analysis, image interpretation, and decision support. Transcranial Doppler (TCD) and Transcranial Color-Coded Doppler (TCCD) are widely used, non-invasive modalities for evaluating cerebral hemodynamics in acute and chronic conditions. Yet, their reliance on operator expertise and subjective interpretation limits their full potential. AI, particularly machine learning and deep learning algorithms, has emerged as a transformative tool to address these challenges by automating image acquisition, optimizing signal quality, and enhancing diagnostic accuracy. Key applications reviewed include the automated identification of cerebrovascular abnormalities such as vasospasm and embolus detection in TCD, AI-guided workflow optimization, and real-time feedback in general ultrasound imaging. Despite promising advances, significant challenges remain, including data standardization, algorithm interpretability, and the integration of these tools into clinical practice. Developing robust, generalizable AI models and integrating multimodal imaging data promise to enhance diagnostic and prognostic capabilities in TCD and ultrasound. By bridging the gap between technological innovation and clinical utility, AI has the potential to reshape the landscape of neurovascular and diagnostic imaging, driving advancements in personalized medicine and improving patient outcomes. This review highlights the critical role of interdisciplinary collaboration in achieving these goals, exploring the current applications and future directions of AI in TCD and TCCD imaging. This review included 41 studies on the application of artificial intelligence (AI) in neurosonology in the diagnosis and monitoring of vascular and parenchymal brain pathologies. Machine learning, deep learning, and convolutional neural network algorithms have been effectively utilized in the analysis of TCD and TCCD data for several conditions. Conversely, the application of artificial intelligence techniques in transcranial sonography for the assessment of parenchymal brain disorders, such as dementia and space-occupying lesions, remains largely unexplored. Nonetheless, this area holds significant potential for future research and clinical innovation. Full article

Recent archaeological sites dating to the late 19th and early 20th centuries have rarely been studied to date. Among the 500 “glassy” beads excavated from Dohouan (Côte d’Ivoire), elemental analyses reveal that fewer than half contain abnormally high alumina contents, associated with a soda–potash–lime flux (three compositional groups). The remaining beads are typical lead-based glass. The Raman spectra of the alumina-rich beads are quite complex due to their glass–ceramic nature, combining features similar to the vitreous phase of porcelain glaze with the presence of various crystalline phases (quartz, wollastonite, calcium phosphate, calcite). Organic residues are also observed. Colors are primarily produced by transition metal ions, although some specific pigments have also been identified. These characteristics suggest that the alumina-rich beads were manufactured by pressing followed by sintering, as described in patents by Richard Prosser (1840, UK) and Jean Félix Bapterosse (1844, France). A comparison is made with beads from scrap piles at the site of the former Bapterosse factory in Briare, France. This process represents one of the earliest examples of replacing traditional glassmaking with a ceramic process to enhance productivity and reduce costs. Full article

Aim: The aim of this study was to evaluate the specificity, sensitivity and accuracy of the Indicator Plaster Neuropad in detecting established Diabetic Autonomic Neuropathy (DAN). Methods: We studied 180 patients with Diabetes Mellitus (DM, mean age 49.5 ± 16 years, 82 with DM type 1). All patients underwent the following Cardiovascular Reflex Tests (CARTs): R-R variation during deep breathing (Mean Circular Resultant (MCR) and standard deviation (SD)), Valsalva maneuver, R-R variability after a rapid change from lying to standing position and postural hypotension. The presence of DAN was established if ≥2 CARTs were abnormal. According to the result the patients were divided into two groups, one with DAN and one without DAN. Assessment with Neuropad was performed also in all patients. Results: Abnormal perspiration with Neuropad (uncompleted or no change in color) was detected in 94 patients. Established DAN was detected in 85 patients. The sensitivity, specificity and accuracy of Neuropad for the diagnosis of established DAN were 87.1%, 78.9% and 82.8%, respectively and area under the curve was 0.846 and 95% CI (0.787, 0.905). Conclusions: Neuropad has high sensitivity, specificity, and accuracy in detecting established DAN, as defined by ≥2 abnormal CARTs. Full article

Beekeeping is facing a serious crisis due to climate change and diseases such as bee mites (Varroa destructor), which have led to declining populations, collapsing colonies, and reduced beekeeping productivity. Bee mites are small, reddish-brown in color, and difficult to distinguish from bees. Rapid bee mite detection techniques are essential for overcoming this crisis. This study developed a technology for recognizing bee mites and beekeeping objects in beecombs using the You Only Look Once (YOLO) object detection algorithm. The dataset was constructed by acquiring RGB images of beecombs containing mites. Regions of interest with a size of 640 × 640 pixels centered on the bee mites were extracted and labeled as seven classes: bee mites, bees, mite-infected bees, larvae, abnormal larvae, and cells. Image processing, data augmentation, and stratified data distribution methods were applied to enhance the object recognition performance. Four datasets were constructed using different augmentation and distribution strategies, including random and stratified sampling. The datasets were partitioned into training, testing, and validation sets in a 7:2:1 ratio, respectively. A YOLO-based model for the detection of bee mites and seven beekeeping-related objects was developed for each dataset. The F1 scores for the detection of bee mites and seven beekeeping-related objectives using the YOLO model based on original datasets were 94.1% and 91.9%, respectively. The model applied data augmentation, and stratified sampling achieved the highest performance, with F1 scores of 97.4% and 96.4% for the detection of bee mites and seven beekeeping-related objects, respectively. The results underscore the efficacy of using the YOLO architecture on RGB images of beecombs for simultaneously detecting bee mites and various beekeeping-related objects. This advanced mite detection method is expected to contribute significantly to the early identification of pests and disease outbreaks, offering a valuable tool for enhancing beekeeping practices. Full article

Musk, a dried secretion from the sac gland near the urethral foramen of adult male forest musk deer (Moschus berezovskii), has significant economic value and is extensively utilized as a valuable component in traditional Chinese medicine. In the practice of forest musk deer breeding, musk with different colors and varying moisture contents is observed during the season when the musk reaches maturity. For many years, researchers have focused mainly on musk composition and symbiotic bacteria. However, the influence of fecal fungi on the production and quality of musk is unknown. In this study, internal transcribed spacer (ITS) analysis was employed to explore the relationships between the fungal composition of musk deer fecal and the quality and production of musk produced by each individual. The results indicate that fungal genera known to cause diseases, such as Colletotrichum and Apiotrichum, are prevalent in the feces of musk deer that produce abnormal musk. Furthermore, the fecal microbiota health index (GMHI) is lower and the intestinal microbiota dysbiosis index (MDI) is greater in musk deer producing white musk than in normal individuals. Additionally, by correlating musk production with fecal fungi, we also found that Dolichousnea and Scolecoleotia were significantly positively correlated with musk production. Moreover, Metschnikowia, Ganodermataceae_gen_Incertae_sedis, Hypoxylon, Neovaginatispora, Didymella, Dothidea, and Trichoderma were negatively correlated with musk production. This study is the first to investigate gut fungi in relation to musk production/quality, establish gut health and fungal dysbiosis links, and identify candidate fungi tightly associated with musk traits. This exploratory approach is critical for exploring uncharted territories like gut fungi in musk deer and musk traits. Full article

In the past, only Oguchi disease was reported as a hereditary retinal disease from Japan. Dr. Chuuta Oguch was a Professor of Nagoya University in Japan. During the past 40 years, four new clinical entities in hereditary retinal disorders have been detected by the Miyake group from Nagoya, Japan. All disorders show essentially normal fundi, and the diagnosis was made mainly by the analysis of an electroretinogram (ERG). Gene mutations are detected in three of them. Bipolar cell (BP) dysfunction syndrome: Congenital stationary night blindness (CSNB) with negative ERG (a-wave is larger than b-wave) was named as the Schubert–Bornschein type in 1952 and considered to be an independent clinical entity. In 1986, Miyake group classified ninety patients with the Schubert–Bornschein type into two types (complete and incomplete type). The complete type of CSNB (CSNB1) showed no rod function, but the incomplete type CSNB (CSNB2) showed remaining rod function in both subjective dark adaptation and rod ERG. In order to investigate the pathogenesis, these two types of CSNB were analyzed by comparing the monkey ERGs using different glutamate analogs to the retina. The ERG analysis demonstrated that CSNB1 has a complete functional defect in the ON type BP, while CSNB2 has incomplete functional defects in the ON and OFF type BP in both rod and cone visual pathways. Evidence of several different genetic heterogeneities was reported in both diseases, indicating CSNB1 and CSNB2 are independent clinical entities. Another entity, showing total complete defect of both ON and OFF BP, was detected in 1974 and was reported by Miyake group in a brother and younger sister, showing severe photophobia, nystagmus, extremely low visual acuity, and disappearance of color vision (total color blindness). This disorder is a congenital stational condition, and subjective visual functions were severely deteriorated from birth but remained unchanged through life. This disease was termed “Total complete bipolar cell dysfunction syndrome (CSNB3)”. The relationship between BP and subjective visual function was unknown. These three kinds of BP diseases can provide information on how BP relates to subjective visual functions. Occult macular dystrophy (OMD): Occult macular dystrophy (OMD) was discovered by Miyake group in 1989. This disease shows an unusual, inherited macular dystrophy characterized by progressive decrease visual acuity due to macular dysfunction, but the fundus and fluorescein angiography are essentially normal. The full-field rod and cone ERG do not show any abnormality, but the focal macular ERG (FERG) or multifocal ERG is abnormal and the only method for diagnosis. Many pedigrees of this disorder suggest autosomal dominant heredity, showing a genetic mutation of RP1L1. This disease was termed “occult macular dystrophy”. “Occult” means “hidden from sight”. Recently, it has been called “Miyake disease”. Full article

Background: Ultrasonography is essential for diagnosing endometrial pathologies, such as hyperplasia, polyps, and endometrial cancer. The International Endometrial Tumor Analysis (IETA) group provides guidelines for using ultrasound to assess endometrial thickness, texture, and irregularities, aiding in the diagnosis of these conditions. The aim of this study was to evaluate the utility of various endometrial morphological features, as assessed by gray-scale ultrasound, and endometrial vascular features, as assessed by power Doppler ultrasound, in differentiating benign and malignant endometrial pathologies. A secondary objective was to compare the effectiveness of these ultrasound techniques in assessing myometrial invasion. Methods: A total of 162 women, both pre- and postmenopausal, with or without abnormal vaginal bleeding were enrolled in a prospective study. All participants underwent transvaginal gray-scale and color Doppler ultrasound examinations, conducted by examiners with over 15 years of experience in gynecological ultrasonography. Endometrial morphology and vascularity characteristics were evaluated based on the IETA group criteria, which include parameters such as endometrial uniformity, echogenicity, the three-layer pattern, regularity of the endometrial–myometrial border, Doppler color score, and vascular pattern (single dominant vessel with or without branching, multiple vessels with focal or multifocal origin, scattered vessels, color splashes, and circular flow). Sonographic findings were compared with histopathological results for comprehensive assessment. Results: The mean age of the study population was 56.46 ± 10.84 years, with a range from 36 to 88 years. Approximately 53.08% of the subjects were postmenopausal. The mean endometrial thickness, as measured by transvaginal ultrasonography, was 18.02 ± 10.94 mm with a range of 5 to 64 mm (p = 0.028), and it was found to be a significant predictor of endometrial malignancy. The AUC for the ROC analysis was 0.682 (95% CI: 0.452–0.912), with a cut-off threshold of 26 mm, yielding a sensitivity of 62.5% and a specificity of 89%. Vascularization was absent in 68.4% of patients with polyps. Among the cases with submucosal myomas, 80% exhibited a circular flow pattern. Malignant lesions were identified in 22.84% of the cases. Subjective ultrasound assessment of myometrial invasion, categorized as <50% or ≥50%, corresponded in all cases with the histopathological evaluation, demonstrating the effectiveness of ultrasound in evaluating myometrial invasion in endometrial cancer. Conclusions: In this study, cystic atrophic endometrium was identified as the most prevalent cause of postmenopausal bleeding. The most significant ultrasound parameters for predicting malignancy included heterogeneous endometrial echogenicity, increased endometrial thickness, and the presence of multiple vessels with multifocal origins or scattered vascular patterns. Additionally, color Doppler blood flow mapping was demonstrated to be an effective diagnostic tool for the differential diagnosis of benign intrauterine focal lesions. Full article

Infrared imaging is based on thermal radiation and does not rely on visible light, allowing for it to operate normally at night and in low-light conditions. This characteristic is beneficial for regulatory authorities to monitor ships. Existing infrared image segmentation methods face challenges such as the absence of color information, blurred edges, weak high-frequency details, and low contrast due to the imaging principles. Consequently, the segmentation accuracy for small-sized ship targets and edges is low, influenced by the indistinct features of infrared images and the weak difference between the background and targets. To address these issues, this paper proposes an infrared image ship segmentation algorithm called the Infrared Image Edge-Enhanced Segmentation Network (IERNet) to extract ship temperature information. By using pseudo-color infrared images, the sensitivity to edges is enhanced, improving the edge features of ships in infrared images. The Sobel operator is used to obtain edge feature maps, and the Convolutional Block Attention Module (CBAM) extracts key feature information. In the Fusion Unit, edge features guide the extraction of infrared ship features in the backbone network, resulting in feature maps rich in edge information. Finally, a specialized loss function with edge weights supervises the fusion features. An eXtreme Gradient Boosting (XGBoost) machine learning model is then established to predict the ship image brightness temperature threshold, using engine brightness threshold, water area brightness threshold, boundary brightness threshold, and temperature gradient as predictive elements. In terms of image segmentation, our algorithm achieves a segmentation performance of 89.17% mIoU. Regarding the XGBoost model’s performance, it achieves high goodness of fit and small error values on both the training and testing sets, demonstrating its good performance in predicting ship temperature. The model achieves over 70% goodness of fit, and the RMSE values for both models are 3.472, indicating minimal errors. Statistical analysis reveals that the proportion of ship temperature differences predicted by the XGBoost model exceeding 2 is less than 0.020%. The proposed temperature detection method offers higher accuracy and versatility, contributing to more efficient detection of abnormal ship temperatures at night. Full article