Frontiers in Medicine

BackgroundTo evaluate the effect of infliximab (IFX), in comparison with cyclophosphamide (CP) on refractory uveitis of BD. MethodsSubjects with uveitis and retinal vasculitis (RV) resistant to conventional treatment were included. Ten patients were divided in the IFX and CP groups. Patients in the IFX group received four courses of 3 mg/kg of IFX, intravenously. Patients in the CP group received four courses of pulse CP of 1000 mg, by the monthly interval. All patients received weekly 25 mg of methotrexate, (or 5 mg/kg of cyclosporine daily), and 3 mg/kg and 1 mg/kg of daily azathioprine and prednisolone, respectively. To evaluate the treatment effects, visual acuity (VA), anterior uveitis (AU), posterior uveitis (PU), and RV were assessed, at the baseline and four months after treatment. ResultsIn ten patients included in this study there were no significant differences in the treatment effects of IFX, compared to the CP regarding VA, PU, AU and RV. RV became inactive after four months of treatment in all five patients in the IFX group versus four patients in the CP group. ConclusionIFX and CP have the same efficacy in the short-term treatment of uveitis in BD. In future investigations, multi-center studies with larger sample sizes are required to investigate the cost-effectiveness of IFX in the treatment of uveitis of BD. HighlightsO_LIA new anti-TNF biologic agent, infliximab and cyclophosphamide have the same efficacy in the treatment of uveitis in BD, and since it has less toxicity, it is a superior treatment option. C_LIO_LIIn areas where access to the contemporary treatment is limited and expensive, the use of traditional medication results in an increased quality-adjusted life year (QALY). C_LIO_LIMulti-center studies with larger sample sizes are required to investigate the cost-effectiveness of infliximab in the treatment of uveitis of BD. C_LI

BackgroundOptical Coherence Tomography Angiography (OCTA) provides high-resolution visualization of retinal microvasculature, with vascular density (VD) serving as a one of the key quantitative metrics. However, VD measurements are highly sensitive to image binarization step, and no standardized approach exists. MethodsWe analyzed 51 OCTA scans (human and porcine) using 29 binarization algorithms, including global and local thresholding techniques from ImageJ and DoxaPy, as well as Random Walker segmentation. VD was calculated for each binarization algorithm and compared against Optovue-generated values (ground truth). Results were evaluated using hierarchical clustering and agreement between them was determined by Bland-Altman analysis. ResultsWolf algorithm was found to exhibit least deviation from mean Optovue VD values for human SCP layer (46.5 {+/-} 1.2% vs. 48.3 {+/-} 1.4%; p = 3.62 x 10-5); however, there is not significant difference between VDs from Optovue and Wolf algorithms from porcine SCP layer (46.2 {+/-} 1.8 % vs 46.3 {+/-} 1.4% ; p=0.74). For DCP layer, Phansalkar algorithm exhibited least VD variability (50.7 {+/-} 2.0% vs. 51.9 {+/-} 1.7%; p=2.53 x 10-4) in the human cohort. Whereas Percentile algorithm exhibited least, non-significant variations in the porcine DCP layer VD (50.0 {+/-} 1.4 % vs. 50.3 {+/-} 1.4%; p=0.75). DiscussionEach binarization technique evaluated in this study impacts OCTA-derived VD measurements differently. Local adaptive algorithms collectively outperform global methods, particularly for SCP analysis. Standardization of image processing pipelines and layer-specific optimization are essential to improve reproducibility and clinical consistency.

Introductiondiabetic retinopathy remains the mainly cause of blindness worldwide and its diagnoses and assessment is poorer as the countryside the patient is. To minimize de boundaries of health care and improve the accuracy how the treatment is stablished, the artificial intelligence (AI) techniques have been studied years ago using fundus phothographies for instance. This scoping review aims to study these AI techniques applied in Opctical Coherence Tomography (OCT) images. MethodsThis scoping review will follow the methodology framework defined in "Scoping studies: advancing the methodology". In this methodological framework, six stages are proposed for scoping review Studiesidentifying the research question; identifying relevant studies; study selection; charting the data; collating, summarizing, and reporting the results; and consultation. The research questions aim to investigate what are the methods, and techniques used in artificial intelligence due to perfmorm a clinical diagnostic using OCT scanners. The team will focus on the Scopus Document Search e PubMed (Medline). The search query is a combination of terms related to Diabetic Retinopathy AND Artificial Intelligence. Ethics and DisseminationThis is a scoping review study and there is no requirement for ethical approval, as primary data will not be collected. The results from this scoping review will be published in a peer reviewed journal and reported at scientific meetings. We intend to share the results with the Ophthalmologists. ARTICLE SUMMARYO_ST_ABSStrengths and Limitations of this studyC_ST_ABSThis protocol uses a comprehensive approach, relating one research question, that will enable the identification of the main gaps and opportunities in the area; O_LIDue to the comprehensiveness of this review protocol, it can serve as the basis for future works, with more specific scope, and the proposal of standards; C_LIO_LIThe investigation of who are the mainly artificial intelligence skills will allow other researchs in this area; C_LIO_LIThe inclusion of aspects of data governance in the protocol will serve as the basis for establishing an assessment model of artificial intelligence and diabetic macular thickness; C_LIO_LIOne weakness of this review protocol was the number of the studies including glaucoma in their criterias. C_LI

BackgroundNon-invasive imaging modalities offer a great deal of clinically significant information that aid in the diagnosis of various medical conditions. Coupled with the never-before-seen capabilities of Artificial Intelligence (AI), uncharted territories that offer novel innovative diagnostics are reached. This systematic review compiled all studies that utilized AI in Nailfold Capillaroscopy as a future diagnostic tool. Methods and FindingsFive databases for medical publications were searched using the keywords artificial intelligence, machine learning, deep learning and nailfold capillaroscopy to return 105 studies. After applying the eligibility criteria, 10 studies were selected for the final analysis. Data was extracted into tables that addressed population characteristics, AI model development and nature and results of their respective performance. We found supervised deep learning approaches to be the most commonly used (n = 8). Systemic Sclerosis was the most commonly studied disease (n = 6). Sample size ranged from 17,126 images obtained from 289 participants to 50 images from 50 participants. Ground truth was determined either by experts labelling (n = 6) or known clinical status (n = 4). Significant variation was noticed in model training, testing and feature extraction, and therefore the reporting of model performance. Recall, precision and Area Under the Curve were the most used metrics to report model performance. Execution times ranged from 0.064 to 120 seconds per image. Only two models offered future predictions besides the diagnostic output. ConclusionsAI has demonstrated a truly remarkable potential in the interpretation of Nailfold Capillaroscopy by providing physicians with an intelligent decision-supportive tool for improved diagnostics and prediction. With more validation studies, this potential can be translated to daily clinical practice.

ObjectivesTo explore factors affected untimely receiving intravitreal anti-Vascular endothelial growth factor (VEGF) injection based on the Capability, Opportunity and Motivation-Behavior (COM-B) model in patients with Diabetic Macular Edema (DME) and regard these factors as main targets for interventions. DesignAn exploratory qualitative study was conducted using semi-structured interviews with patients with DME. The COM-B model was used to guide data collection and analysis. SettingThe study was carried out in outpatient department of ophthalmology in China. Participants24 patients with DME who experienced anti-VEGF treatment at least one injection within one year were recruited using convenience and purposed sampling. ResultsThe themes and subthemes were identified. Physical capability included (1) lack of knowledge, (2) high treatment expenditure, and psychological capability included prioritized glycemic control rather than anti-VEGF. Social opportunity included (1) no anti-VEGF available, (2) Recommended eyedrops, laser and oral drug but not mentioned intravitreal anti-VEGF injection, (3) As an optional therapy, selected more convenient treatment rather than anti-VEGF agents, and physical opportunity included (1) no confidence in treatment from doctor, (2) communication between doctors and patients. Reflective motivation included (1) outcome expectancies, and automatic motivation included (1) fear of injection, (2) fear of blindness. ConclusionWe should attach importance to these eleven factors, especially to effective interaction between doctors and patients, and doctors authoritative treatment advice, which interventions were based on in the future. Strengths and limitations of this study{Rightarrow} The qualitative design was used to understand factors affecting timely intravitreal anti-VEGF injections in patients with DME and to explore the potential measures to change them. {Rightarrow}The study highlighted the importance of efficient communication between clinicians and patients. {Rightarrow}The study didnt consider other clinical variables, such as the severity and duration of diabetes, which should be included in the future studies.

Intravitreal bevacizumab(IVB) injection, is a humanized monoclonal antibody that has been in use for the treatment of retinal diseases, very cheaply, especially for developing countries like Nepal. This is a retrospective study designed to evaluate the indications and outcomes of IVB at Hetauda Community Eye Hospital from 2019 to 2022. In this study, among 247 patients including 260 eyes with a follow-up rate of 221 patients involving 234 eyes, the mean patient age was 64.4 years, with male predominance of 56.1%. Thus, IVB was used principally in the treatment of diabetic retinopathy, neovascular age-related macular degeneration, and branch retinal vein occlusion. The results indicated significant improvements in central macular thickness and visual acuity with respect to diabetic retinopathy, nAMD, and BRVO. The study thus puts forth the effectiveness of IVB in improving visual outcomes and reducing CMT in a resource-constrained setting; hence, its use should be implemented as a viable treatment option within such an environment.

Diabetes foot ulcer (DFU) is one of the main complications of diabetes mellitus (DM) and one of the main causes of death worldwide from non-communicable diseases (NCDs). The development of an instrument tool for the early diagnosis of diabetic foot is crucial since the findings can be used to prioritize clinical examinations for patients who are at risk. This literature review aimed to examine the philosophical viewpoint on transculturalizing instrument instruments to detect DFU from a variety of study reports published in both domestic and foreign journals. The original research publications published between January 2018 and December 2023 were the focus of the literature search. This study used secondary data, which came from 17 credible journal publications obtained from Science Direct, CINAHL, Pubmed, and SCOPUS databases. The PICOS framework was utilized to assess the papers suitability after they were selected. Articles meeting the inclusion requirements would be chosen: the studies should show the outcome of DFU detection or intervention for the outcome, and the population should consist of DM patients with or without DFU, with early DFU detection or intervention for Intervention. The studies could use any kind of research design, including descriptive, cross-sectional, observational, quasi-experimental, randomized controlled trials, and mixed methods, and should be written in English. The result of this literature review showed all the newly developed instrument tools to detect DFU have tested the validity and reliability of content, particularly translation to the local language to meet cultural appropriateness. It is important for researchers working on new DFU detection risk tools to consider including transcultural theory in their assessment instruments for DFU early detection.

Extensive Macular Atrophy with Pseudodrusen (EMAP) is a rare and rapidly progressive retinal disease marked by central vision loss, chorioretinal atrophy, and pseudodrusen, primarily affecting middle-aged individuals. Recent studies have identified a statistically significant association between long-term use of benzathine penicillin (BP) and the onset of EMAP. However, the molecular mechanisms underlying this relationship remain unclear. In this study, we performed an integrative in silico analysis to explore the genes modulated by BP that are expressed in ocular tissues and involved in retinal metabolic pathways. Using public databases (PubChem, GTEx, HPA, EYEDB), we identified 52 BP-responsive genes, with six (CD4, CRP, IL6, IL1R1, TAC1, TNF) directly modulated by BP and expressed in the retina. These genes are implicated in inflammation, immune response, and retinal homeostasis. Expression data show strong presence in eye and brain tissues, and several are associated with age-related macular degeneration (AMD). Network analysis revealed gene-gene and protein-protein interactions, highlighting a shared pathophysiological axis. Notably, IL6 and TNF are involved in oxidative stress, endoplasmic reticulum stress, and chronic inflammation--hallmarks of both EMAP and atrophic AMD. Our findings suggest that BP may induce EMAP by dysregulating retinal genes involved in neurodegeneration, providing new insights into drug safety and retinal disease mechanisms.

Bladder cancer is 10th most common malignancy and carries the highest treatment cost among all cancers. The high cost of bladder cancer treatment stems from its high recurrence rate, which necessitates frequent surveillance. White light cystoscopy (WLC), the standard of care surveillance tool to examine the bladder for lesions, has limited sensitivity for early-stage bladder cancer. Blue light cystoscopy (BLC) utilizes a fluorescent dye to induce contrast in cancerous regions, improving the sensitivity of detection by 43%. Nevertheless, the added cost and lengthy administration time of the dye limits the availability of BLC for surveillance. Here, we report the first demonstration of digital staining on clinical endoscopy videos collected with standard-of-care clinical equipment to convert WLC images to accurate BLC-like images. We introduce key pre-processing steps to circumvent color and brightness variations in clinical datasets needed for successful model performance; the results show excellent qualitative and quantitative agreement of the digitally stained WLC (dsWLC) images with ground truth BLC images as measured through staining accuracy analysis and color consistency assessment. In short, dsWLC can provide the fluorescent contrast needed to improve the detection sensitivity of bladder cancer, thereby increasing the accessibility of BLC contrast for bladder cancer surveillance use without the cost and time burden associated with the dye and specialized equipment.

BackgroundSerum lipids were reported to be significant predictive factors in various tumors. In order to develop and validate a nomogram for predicting castration-resistant prostate cancer (CRPC) free survival in advanced hormone-sensitive prostate cancer (HSPC) patients, the goal of this study was to assess the prognostic impact of the lipid profiles. Material and MethodsThe follow-up information of 146 CRPC patients who received androgen deprivation therapy as the first and only therapy before progression were retrospectively examined. To evaluate prognostic variables, univariate and multivariate Cox regression analyses were used. The concordance index (C-index), calibration curves, receiver operating characteristic (ROC) curves, and decision curve analyses (DCA) were used to design and evaluate a novel nomogram model. ResultsTotal cholesterol (TC), low-density lipoprotein cholesterol (LDL-C), apolipoprotein B (apoB), N stage and Gleason sum were determined to be independent prognostic markers and were combined to create a nomogram. This nomogram performed well in the customized prediction of CRPC development at 6th, 12th, 18th and 24th month. The C-indexes in training and validation sets were 0.740 and 0.755, respectively. ROC curves, calibration plots, and DCA all suggested favorable discrimination and predictive ability. Besides, the nomogram also performed better predictive ability than N stage and Gleason sum. The Nomogram-related risk score divided the patient population into two groups with significant progression disparities. ConclusionsThe established nomogram could aid in identifying the patients at high risk for rapid progression of advanced HSPC, so as to formulate individualized therapeutic regimens and follow-up strategies in time.

The prevalence of fundus lesion-related diseases is increasing, which ophthalmic anti-VEGF drugs have become the drugs of choice for the treatment of fundus lesions diseases. To evaluate the clinical value of three ophthalmic anti-VEGF drugs in the treatment of fundus lesions diseases, to guide the rational use of the clinic. Inpatients with fundus lesions who had intravitreal injections of Aflibercept, Conbercept and Leizumab during 2020 were studied and six indicators were selected for a comprehensive evaluation. In terms of safety, Aflibercept, Conbercept, and Leizumab experienced adverse effects of elevated Intraocular Pressure (IOP). In terms of effectiveness, Leizumab was strong, that of Aflibercept was stronger and that of Conbercept was weaker. In terms of economic, there was no significant difference in the cost of Aflibercept, Conbercept and Leizumab and a significant difference in the total treatment cost and the cost of surgery. In terms of appropriateness, Aflibercept was more suitable than Conbercept, and there was no significant difference between Leizumab and Aflibercept. In terms of accessibility, Aflibercept, Conbercept and Leizumab were all accessible to urban residents in Henan Province. For rural people, these are unreachable. In terms of innovation, Aflibercep was the most innovative, followed by Leizumab and finally Conbercept. In terms of effectiveness and accessibility, Leizumab performed best compared to Aflibercept and Conbercept. In terms of accessibility and innovation, Aflibercept performed best compared to Conbercept and Leizumab. In terms of safety and economic, Aflibercept, Conbercept and Leizumab performed comparably.

Coronavirus disease 2019 (COVID-19) is a newly emerged infection of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) and has been pandemic all over the world. This study described acute kidney injury (AKI) at early stage of COVID-19 and its clinical significance. Three-hundred and fifty-five COVID-19 patients with were recruited and clinical data were collected from electronic medical records. Patients prognosis was tracked and risk factors of AKI was analyzed. Of 355 COVID-19 patients, common, severe and critical ill cases accounted for 63.1%, 16.9% and 20.0%, respectively. On admission, 56 (15.8%) patients were with AKI. Although AKI was more common in critical ill patients with COVID-19, there was no significant association between oxygenation index and renal functional indices among COVID-19 patients with AKI. By multivariate logistic regression, male, older age and comorbidity with diabetes were three important independent risk factors predicting AKI among COVID-19 patients. Among 56 COVID-19 patients with AKI, 33.9% were died on mean 10.9 day after hospitalization. Fatality rate was obviously higher among COVID-+19 patients with AKI than those without AKI (RR=7.08, P<0.001). In conclusion, male elderly COVID-19 patients with diabetes are more susceptible to AKI. AKI at early stage may be a negative prognostic indicator for COVID-19.

BackgroundArtificial Intelligence (AI) has demonstrated a high image processing capacity and improved diagnostic accuracy in dermatology. In this context, Computer-Aided Diagnosis (CAD) systems have shown a diagnostic performance comparable to that of specialists in classifying skin lesions, particularly pigmented lesions. The present study aims to validate Legit.Health is a reliable tool for diagnosing and assessing the severity of patients with skin lesions suspicious of malignancy. ObjectiveTo validate that the Legit.Health medical device optimises clinical workflow by enhancing diagnostic accuracy and determining the malignancy or severity of patients with skin lesions suspicious of malignancy. MethodsAn observational, prospective study was conducted, incorporating both longitudinal and retrospective cases. A total of 76 retrospective patients with 88 lesions and 32 prospective patients with 42 lesions attending Instituto de Dermatologia Integral Madrid, Spain, were recruited. The diagnostic performance of Legit.Health was compared with that of dermatologists in the retrospective images against a gold standard (biopsy results). In the prospective phase of the study, the performance of the current Legit.Health medical device was evaluated alongside dermatologists assisted by the device and the latest version of the device (Legit.Health Plus). Analyses were performed to calculate the AUC (area under the curve), accuracy, sensitivity, and specificity. ResultsIn the retrospective analysis, the device demonstrated an AUC of 0.76 compared to 0.79 for dermatologists in detecting malignant lesions. For these images, the device achieved the following accuracy scores: top-1 = 0.23, top-3 = 0.38, and top-5 = 0.47, whereas dermatologists achieved top-1 = 0.33 and top-3 = 0.45 (providing only three possible diagnoses). When the specific histologic subtype of naevus was not considered in the diagnosis, Legit.Health achieved an accuracy of top-1 = 0.50, top-3 = 0.71, and top-5 = 0.78, compared to dermatologists top-1 = 0.50 and top-3 = 0.70. In the prospective analysis, we examined the performance of dermatologists using the Legit.Health medical device, the device alone, and the latest version of the device. In the malignancy analysis, they achieved an AUC of 0.94, 0.95, and 0.97, respectively. Regarding diagnostic accuracy, dermatologists assisted by the medical device achieved a top-1 accuracy of 0.30, while both the medical device alone and its latest version achieved top-1 accuracies of 0.22 and 0.26, respectively, which increased to 0.44 and 0.52 when expanding to top-5. When the specific histologic subtype of naevus was not considered in the diagnosis, accuracies increased to 0.85, 0.74, and 0.81, respectively, further improving as top-K was increased to top-5, reaching 0.89 and 0.93, respectively. ConclusionsThe devices diagnostic capability in distinguishing malignant conditions is on par with that of expert dermatologists. This confirms its reliability as a tool for detecting skin malignant categories in ICD-11, assisting in prioritising patients based on urgency and directing them to the appropriate specialist or consultation.

BackgroundProstate cancer is one of the most common malignant tumors and poses a substantial threat to human health. PSA or enhanced MRI is widely used in prostate cancer screening or diagnosis. However, false-positive results of PSA or enhanced MRI will lead to unnecessary puncture biopsy, and patients will have to bear the adverse consequences of mental pain, expensive examination costs, and examination injuries; whereas false-negative results of PSA or enhanced MRI will lead to delayed treatment, and patients will have to bear the adverse consequences of poor prognosis, expensive treatment costs, poor quality of life, and short survival period. There is an urgent need to find convenient, economical and non-invasive diagnostic methods to reduce the PSA or enhanced MRI false-negative and false-positive rates. The aim of this study was to evaluate the diagnostic value of YiDiXie-SS and YiDiXie-HS in prostate cancer. Patients and methodsThe study finally included 464 subjects with positive PSA test (prostate cancer group, n=292; BPH group, n=172). Remaining serum samples from the subjects were collected and tested with YiDiXie all-cancer detection kit. The sensitivity and specificity of YiDiXie-SS and YiDiXie-HS were evaluated respectively. ResultsThe sensitivity of YiDiXie-SS was 100% (95% CI: 98.7% - 100%; 292/292) and its specificity was 60.5% (95% CI: 53.0% - 67.5%; 104/172). As shown in Table 3, the sensitivity of YiDiXie-HS was 93.8% (95% CI: 90.5% - 96.1%; 274/292) and its specificity was 86.0% (95% CI: 80.1% - 90.4%; 148/172). The sensitivity of YiDiXie-SS in PSA-positive patients was 100% (95% CI: 98.6% - 100%; 279/279), and the specificity was 58.0% (95% CI: 49.8% - 65.2%; 90/ 156). This means that the application of YiDiXie-SS reduces the PSA false-positive rate by 58.0% (95% CI: 49.8% - 65.2%; 90/156) with essentially no increase in malignancy leakage. The sensitivity of YiDiXie-HS in PSA-negative patients was 92.3% (95% CI: 66.7% - 99.6%; 12/13), and the specificity was 81.3% (95% CI: 57.0% - 93.4%; 13/ 16). This means that the application of YiDiXie-HS reduced the PSA false negative rate by 92.3% (95% CI: 66.7% - 99.6%; 12/13). YiDiXie-SS had a sensitivity of 100% (95% CI: 97.6% - 100%; 159/159) and a specificity of 59.6% (95% CI: 49.5% - 68.9%; 56/94) in enhanced MRI-positive patients. This means that the application of YiDiXie-SS reduces the false-positive rate of enhanced MRI by 59.6% (95% CI: 49.5% - 68.9%; 56/94) with essentially no increase in malignancy leakage. the sensitivity of YiDiXie-HS in enhanced MRI-negative patients was 90.2% (95% CI: 79.0% - 95.7%; 46/51), and the specificity was 83.3% (95% CI: 55.2% - 97.0%; 10/12). This means that the application of YiDiXie-HS reduced the false negative rate of enhanced MRI by 90.2% (95% CI: 79.0% - 95.7%; 46/51). O_TBL View this table: org.highwire.dtl.DTLVardef@11a3a26org.highwire.dtl.DTLVardef@dfb213org.highwire.dtl.DTLVardef@24332forg.highwire.dtl.DTLVardef@9c6e6eorg.highwire.dtl.DTLVardef@15f918_HPS_FORMAT_FIGEXP M_TBL O_FLOATNOTable 3.C_FLOATNO O_TABLECAPTIONThe performance of YiDiXie-HS C_TABLECAPTION C_TBL ConclusionYiDiXie-SS significantly reduces the false-positive rate of PSA or enhanced MRI-positive patients without increasing the number of under-diagnosed malignant tumors. YiDiXie-HS significantly reduces the false-negative rate of PSA or enhanced MRI-negative patients. YiDiXie-SS and YiDiXie-HS can play an important role in prostate cancer, and are expected to solve the problem of "high false-positive rate of PSA or enhanced MRI" and "high false-negative rate of PSA or enhanced MRI". Clinical trial numberChiCTR2200066840.

PURPOSETo investigate the effect of abstinence duration on image quality of prostate with high-field magnetic resonance imaging(MRI); MATERIALS AND METHODSThis study included males who underwent prostate MRI in Xian No.3 Hospital from November 2021 to November 2022.And these males were divided into two groups according to whether they had ejaculation before MRI examination within 3 days. Two radiologists blinded evaluated the boundary sharpness of the peripheral zone (PZ) and central gland (CG) of prostate using a three-point Likert-scale. The region of interests (ROIs) of the PZ and CG at both sides on the sagittal T2W image were drawn and the signal intensity (SI) of ROIs was measured, then the SI ratio (SIR) was calculated. The Wilcoxons test and the independent-samples T test was utilized to compare the differences of the two groups; RESULTSA total of fifty young males were included in the study. There were twenty males abstinence more than 3-days, and thirty males were abstinence within 3-days. The qualitative analysis showed that the different structure of prostate in abstinence group was easier to identify than in ejaculation group(P[&le;]0.05). The quantitative analysis showed that the SIR of PZ and CG in the ejaculation group were lower than in the abstinence group (all P[&le;]0.05), and the peripheral zone was significantly lower; CONCLUSIONIn order to make the results more accurate, we suggested that the abstinence should more than 3 days prior to the examination.

Breast cancer, which is among the top causes of cancer-related deaths in women worldwide, demonstrates the importance of effective and rapid diagnostic tools, especially in early diagnosis, to enhance the survival level. Although machine learning (ML) advances have had an increasing number of medical imaging applications, limitations of diversity and applicability of datasets, the interpretation and efficiency of models remain a challenge to clinical use. The paper assesses eight of the most popular ML models, such as Convolutional Neural Network (CNN), Kolmogorov-Arnold Network (KAN), k-Nearest Neighbors, Support Vector Machine, XGBoost, Random Forest, Naive Bayes, and a Hybrid model based on the Mammogram Mastery dataset of Iraq-Sulaymaniyah, which consists of 745 original and 9,685 augmented mammogram images. The hybrid model has the best accuracy (0.9667) and F1 Score (0.9444), and the KAN model has the best ROC AUC (0.9760) and Log Loss (0.1421), meaning they are best in terms of discriminative power and proper calibration. Random Forest, which has the lowest false negatives (3) when compared with Fast Multinomial and Fast Text, became most secure in clinical screening since it struck a balance between sensitivity and computing efficiency. The two practical challenges, though, are the slow inference time of the KAN model (0.323 seconds) and the expensive training cost (1009.10 seconds) of the Hybrid model. These insights explain that the Hybrid and KAN models are promising means of improving the accuracy of the diagnostics, and Random Forest can serve as a practically representative tool for reducing the number of missed diagnoses. The context of future research needs to address multi-dataset validation from multiple institutions, speed optimization of inference, multi-classification, and improved interpretability that will be used in clinically integrative settings. By addressing these gaps, ML-based diagnostics have the potential to increase the rate of breast cancer diagnosis, minimizing diagnostic errors and improving patient outcomes in various clinical contexts, which can facilitate the scaling of screening services available across the world.

The segmentation of anterior Lamina Cribrosa surface from the OCT image is an essential task for analysis of glaucomatous damage. A Bayesian method is used to segment LC surface whereas prior knowledge about shape and position of LC layer is obtained by the non local Markov Random field and K-means segmentation. The Metropolis-Hastings (MH) algorithm provides autocorrelation graph and distribution of samples from a probability distribution. By using this technique acceptance probability is calculated. Finally, the LC layer is analysed whether it is normal or abnormal. This technique provides an accuracy of 96.7%

BackgroundMalignant skin melanoma (MSM), a highly aggressive skin cancer from melanocytes, has a higher mortality rate than other skin cancers due to its metastatic nature. Despite advancements in diagnostics and treatment, melanoma remains a significant health concern in China. MethodsData from the Global Burden of Disease (GBD) 2021 database was utilized to analyze MSM trends in China from 1990 to 2021. Statistical analyses, including Joinpoint regression and decomposition analysis, were employed to examine changes in incidence and mortality. The ARIMA model was used to project age-standardized incidence and mortality rates through 2036. ResultsIn 2021, China reported approximately 13,437 new cases of MSM, with a total patient population of 81,219 and 5,373 MSM-related deaths. Between 1990 and 2021, the incidence and prevalence rates of MSM significantly increased, while mortality rates showed a slight decline. The highest incidence rate was observed in the 55-59 age group, with males facing notably higher risks than females. Joinpoint regression analysis indicated rapid Age-Standardized Incidence Rate (ASIR) growth from 2004 to 2012, and decomposition analysis identified population aging as the primary driving factor. ARIMA forecasts suggest that by 2036, ASIR will reach 0.88 for males and 0.71 for females, while Age-Standardized Death Rate (ASDR) will stabilize or decline. ConclusionThe MSM burden in China has intensified, with increasing incidence and prevalence rates over time. Although mortality rates have declined slightly, the impact of melanoma on public health remains significant.

Colour vision deficiency (CVD) affects up to 8% of males and 0.5% of females and currently lacks effective treatments. Individuals with CVD require visually accessible environments to flourish, the absence of which can cause unacceptable disparities in academic achievement and career progression. For current and aspiring clinician-scientists with CVD, inaccessible colour figures in scientific publications can hinder understanding of key information and potentially cause patient harm. Therefore, our work characterises the accessibility of major medical journal figures for individuals with CVD using established guidelines and provides recommendations for improving figure accessibility. We observed that among 138 journal figures evaluated from nine leading medical journals, 107 (80%) failed to conform with colour contrast and labelling requirements from the Web Content Accessibility Guidelines (WCAG), indicating that readers with CVD may be unable to perceive displayed information. 215 of 395 (55%) sub-figures within the aforementioned figures were judged to be completely inaccessible to individuals with protan or deutan deficiencies, the commonest CVD subtypes. Despite universal publisher declarations of compliance with WCAG directives, no journals figures were fully compliant with these guidelines. Our findings demonstrate the need for urgent action by authors and publishers to augment the colour contrast of journal figures and add secondary labels to enable their comprehension by audiences with CVD. We believe that these design changes will, too, improve the clarity of figures for general audiences.

IntroductionThe existing techniques to creat working space for retroperitoneal laparoscopic surgery are often accompanied by air leakage or poor visibility due to blood and fat tissues smudging during dissection.This single-center experience describes a modified dissection technique to create a retroperitoneal working space during laparoscopic surgery. Materials and MethodsFrom May 2021 to December 2022, we performed a modified dissection technique to create a retroperitoneal working space prior retroperitoneal laparoscopic surgery in 47 patients. During the procedure, laparoscopic dissection is successively performed. The retroperitoneum is initially accessed by puncturing the trocar through a 10-mm transverse skin incision in the midaxillary line. Under endoscopic monitoring, the tip of the trocar is adjusted to a relative avascular layer between the transversus abdominis muscle and the pararenal fat. Laparoscopic dissection is performed to develop until the working space is fully established. All data referring to patient demographics, surgery, dilation-related complication, and perioperative outcomes were collected retrospectively. ResultsIn all cases, a satisfactory retroperitoneal space was created for surgery. The median time of creating retroperitoneal working space was 6 (IQR:5,7) minutes. No dissection-related complications were noted within a median follow-up period of 9 (IQR:7,15) months. ConclusionModified retroperitoneal dissection with laparoscopy is a safe, simple, effective, and minimally invasive technique. It provides an adequate working space and an excellent view without obvious bleeding.