Pharmacogenet Genomics. 2025 Jan 21. doi: 10.1097/FPC.0000000000000558. Online ahead of print.

ABSTRACT

Ibrutinib treatment is often complicated by cardiovascular side effects (CVSEs). The objective of this retrospective pharmacogenetic study is to replicate a previously reported association of 'high-risk' patients, who are homozygous carriers of at least two of GATA4 rs804280 AA, KCNQ1 rs163182 GG, and KCNQ1 rs2237895 AA, with increased risk of hypertension or atrial fibrillation, and explore associations for other pharmacogenes (e.g. CYP3A4, CYP3A5, CYP2D6, and ABCB1) with ibrutinib CVSEs. Univariate associations with P < 0.05 were adjusted for significant pretreatment cardiovascular conditions. In total 57 patients were included in the analysis. In the primary analysis, 'high-risk' patients were not more likely to experience hypertension or atrial fibrillation (70 vs. 41%, chi-square P value = 0.06). In secondary analyses, 'high-risk' patients were more likely to experience any CVSE during treatment (75 vs. 41%, P = 0.013), develop a cardiac rhythm or function disorder (65 vs. 24%, P = 0.008), and have a treatment modification due to CVSE (45 vs. 8%, P = 0.004). Additionally, high-risk homozygous variant genotypes of KCNQ1 rs163182 GG and rs2237895 AA were each associated with an increased likelihood of treatment modifications due to CVSE (40 vs. 11%, P = 0.021 and 45 vs. 9%, P = 0.004, respectively) and cardiac rhythm or function disorders (60 vs. 27%, P = 0.037 and 60 vs. 27%, P = 0.037). This study found supportive evidence that 'high-risk' genotype was associated with increased ibrutinib CVSEs. Validation of these associations is necessary before prospective trials testing whether personalized ibrutinib treatment approaches improve clinical outcomes.

PMID:39832190 | DOI:10.1097/FPC.0000000000000558

Eur J Clin Pharmacol. 2025 Jan 17. doi: 10.1007/s00228-025-03805-x. Online ahead of print.

ABSTRACT

OBJECTIVE: The study aims to verify the usage of mathematical modeling in predicting patients' medication doses in association with their genotypes versus real-world data.

METHODS: The work relied on collecting, extracting, and using real-world data on dosing and patients' genotypes. Drug metabolizing enzymes, i.e., cytochrome CYP 450, were the focus. A total number of 1914 subjects from 26 studies were considered, and CYP2D6 and CYP2C19 gene polymorphisms were used for the verification.

RESULTS: Results show that the mathematical model was able to predict the reported optimal dosing of the values provided in the considered studies. Predicting patients' optimal doses circumvents trial and error in patients' treatments.

DISCUSSION: The authors discussed the advantages of using a mathematical model in patients' dosing and identified multiple issues that would hinder the usability of raw data in the future, especially in the era of artificial intelligence (AI). The authors recommend that researchers and healthcare professionals use simple descriptive metabolic activity terms for patients and use allele activity scores for drug dosing rather than phenotype/genotype classifications.

CONCLUSION: The authors verified that a mathematical model could assist in providing data for better-informed decision-making in clinical settings and drug research and development.

PMID:39832006 | DOI:10.1007/s00228-025-03805-x

Front Pharmacol. 2025 Jan 3;15:1540478. doi: 10.3389/fphar.2024.1540478. eCollection 2024.

NO ABSTRACT

PMID:39830351 | PMC:PMC11739166 | DOI:10.3389/fphar.2024.1540478

Front Pharmacol. 2025 Jan 3;15:1526101. doi: 10.3389/fphar.2024.1526101. eCollection 2024.

ABSTRACT

INTRODUCTION: The field of pharmacogenetics (PGx) is experiencing significant growth, with increasing evidence to support its application in psychiatric care, suggesting its potential to personalize treatment plans, optimize medication efficacy, and reduce adverse drug reactions. However, the perceived utility and practicability of PGx for psychiatric treatment in youth remains underexplored. This study investigated perceived barriers and attitudes in Australian young adults towards the implementation of PGx testing to guide antidepressant treatment in primary care.

METHODS: Semi-structured focus groups and interviews were conducted with 17 participants aged between 18 and 24 years. These sessions were recorded and transcribed before thematic analysis was used to identify collective themes.

RESULTS: Three key themes were identified, including attitudes towards the medication prescription process, concerns and attitudes towards PGx testing, and perceived barriers to its clinical implementation. Although PGx testing was positively perceived by most participants, all participants shared concerns about PGx testing. Participants voiced concerns about the financial impact of PGx testing, the potential for treatment delays, and the accuracy of PGx testing in guiding antidepressant treatment. Additionally, participants noted that the low awareness and willingness of general practitioners to incorporate PGx testing into routine practice could hinder successful clinical implementation.

DISCUSSION: Prior to the implementation of PGx testing into Australian primary practices, it is essential to acknowledge patient perspectives and ensure that clinical practices remain patient-focused. This study highlights important considerations for integrating PGx testing into antidepressant pharmacotherapy and emphasizes the need for future research to address and mitigate the perceived barriers of young adults.

PMID:39830342 | PMC:PMC11739104 | DOI:10.3389/fphar.2024.1526101

Clin Pharmacol Ther. 2025 Jan 20. doi: 10.1002/cpt.3557. Online ahead of print.

ABSTRACT

Tuberculosis (TB) is a major health burden in Africa. Although TB is treatable, anti-TB drugs are associated with adverse drug reactions (ADRs), which are partly attributed to pharmacogenetic variation. The distribution of star alleles (haplotypes) influencing anti-TB drug metabolism is unknown in many African populations. This presents challenges in implementing genotype-guided therapy in Africa to decrease the occurrence of ADRs and enhance the efficacy of anti-TB drugs. In this study, we used StellarPGx to call variants and star alleles in NAT1, NAT2, GSTM1, GSTT1, GSTP1, and CYP2E1, from 1079 high-depth African whole genomes. We present the distribution of common, rare, and potential novel star alleles across various Sub-Saharan African (SSA) populations, in comparison with other global populations. NAT1*10 (53.6%), GSTT1*0 (65%), GSTM1*0 (48%), and NAT2*5 (17.5%) were among the predominant functionally relevant star alleles. Additionally, we predicted varying phenotype distributions for NAT1 and NAT2 (acetylation) and the glutathione-S-transferase (GST) enzymes (detoxification activity) between SSA and other global populations. Forty-seven potentially novel haplotypes were identified computationally across the genes. This study provides insight into the distribution of key variants and star alleles potentially relevant to anti-TB drug metabolism and other drugs prescribed across various African populations. The high number of potentially novel star alleles exemplifies the need for pharmacogenomics studies in the African context. Overall, our study provides a foundation for functional pharmacogenetic studies and potential implementation of pharmacogenetic testing in Africa to reduce the risk of ADRs related to treatment of TB and other diseases.

PMID:39829327 | DOI:10.1002/cpt.3557

Pharmacogenomics. 2025 Jan 19:1-5. doi: 10.1080/14622416.2025.2454217. Online ahead of print.

ABSTRACT

BACKGROUND: Macrolides are widely used antibiotics, but adverse drug reactions (ADRs), particularly in genetically predisposed individuals, can compromise their safety. This study examines the impact of pharmacogenetic markers on macrolide safety in participants with bacterial complications of influenza.

OBJECTIVE: To evaluate how polymorphisms in genes encoding transporter proteins (ABCB1) and enzymes (CYP3A4, CYP3A5) influence ADR risk during macrolide therapy.

METHODS: A prospective study included 100 participants with lower respiratory tract bacterial complications of influenza treated with azithromycin or erythromycin for five days. Genotyping targeted ABCB1 (3435C>T), CYP3A4 (C>T intron 6), and CYP3A5 (6986A>G) polymorphisms. ADRs were monitored daily and correlated with genetic markers.

RESULTS: The ABCB1 (3435C>T) polymorphism was associated with higher rates of abdominal pain and diarrhea in CT and TT genotypes (OR = 2.12, p = 0.043). The CYP3A4 (C>T intron 6) polymorphism increased ADR risk in erythromycin-treated participants (OR = 24.0, p = 0.0339). No significant effects were observed for CYP3A5 (6986A>G).

CONCLUSION: Genetic polymorphisms in ABCB1 and CYP3A4 genes predict macrolide-related ADRs. Pharmacogenetic screening could improve macrolide safety, particularly for genetically susceptible individuals.

PMID:39829075 | DOI:10.1080/14622416.2025.2454217

J Particip Med. 2025 Jan 20;17:e49941. doi: 10.2196/49941.

ABSTRACT

BACKGROUND: Adolescents and young adults (AYA) with cystic fibrosis (CF) are at risk for deviating from their daily treatment regimen due to significant time burden, complicated daily therapies, and life stressors. Developing patient-centric, effective, engaging, and practical behavioral interventions is vital to help sustain therapeutically meaningful self-management.

OBJECTIVE: This study aimed to devise and refine a patient-centered telecoaching intervention to foster self-management in AYA with CF using a combination of intervention development approaches, including an evidence- and theory-based approach (ie, applying existing theories and research evidence for behavior change) and a target population-centered approach (ie, intervention refinement based on the perspectives and actions of those individuals who will use it).

METHODS: AYA with CF, their caregivers, and health professionals from their CF care teams were recruited to take part in focus groups (or individual qualitative interviews) through a video call interface to (1) obtain perspectives on the overall structure and logistics of the intervention (ie, Step 1) and (2) refine the overall framework of the intervention and obtain feedback on feasibility, content, materials, and coach training (ie, Step 2). Qualitative data were analyzed using a reflexive thematic analysis process. Results were used to create and then modify the intervention structure and content in response to community partner input.

RESULTS: For Step 1, a total of 31 AYA and 20 clinicians took part in focus groups or interviews, resulting in 2 broad themes: (1) video call experience and (2) logistics and content of intervention. For Step 2, a total of 22 AYA, 18 clinicians, and 11 caregivers completed focus groups or interviews, yielding 3 major themes: (1) intervention structure, (2) intervention materials, and (3) session-specific feedback. Our Step 1 qualitative findings helped inform the structure (eg, telecoaching session frequency and duration) and approach of the telecoaching intervention. Step 2 qualitative results generally suggested that community partners perceived the feasibility and practicality of the proposed telecoaching intervention in promoting self-management in the face of complex treatment regimens. Extensive specific feedback was used to refine our telecoaching intervention before its efficacy testing in subsequent research. The diverse community partner input was critical in optimizing and tailoring our telecoaching intervention.

CONCLUSIONS: This study documents the methods and results for engaging key community partners in creating an evidence-based behavioral intervention to promote self-management in AYA with CF. Incorporating the lived experiences and perspectives of community partners is essential when devising tailored and patient-centered interventions.

PMID:39832355 | DOI:10.2196/49941

Cochrane Database Syst Rev. 2025 Jan 20;1:CD009730. doi: 10.1002/14651858.CD009730.pub3.

ABSTRACT

BACKGROUND: Cystic fibrosis is a multisystem disease characterised by the production of thick secretions causing recurrent pulmonary infection, often with unusual bacteria. Intravenous (IV) antibiotics are commonly used in the treatment of acute deteriorations in symptoms (pulmonary exacerbations); however, recently the assumption that exacerbations are due to increases in bacterial burden has been questioned. This is an update of a previously published review.

OBJECTIVES: To establish whether IV antibiotics for the treatment of pulmonary exacerbations in people with cystic fibrosis improve short-term and long-term clinical outcomes.

SEARCH METHODS: We searched the Cochrane Cystic Fibrosis Trials Register, compiled from electronic database searches and handsearching of journals and conference abstract books. We also searched the reference lists of relevant articles and reviews and ongoing trials registers. Date of last search of Cochrane Trials Register: 19 June 2024.

SELECTION CRITERIA: Randomised controlled trials and the first treatment cycle of cross-over studies comparing IV antibiotics (given alone or in an antibiotic combination) with placebo, or inhaled or oral antibiotics for people with cystic fibrosis experiencing a pulmonary exacerbation. Studies comparing different IV antibiotic regimens were also eligible.

DATA COLLECTION AND ANALYSIS: We assessed studies for eligibility and risk of bias, and extracted data. Using GRADE, we assessed the certainty of the evidence for the outcomes lung function % predicted (forced expiratory volume in one second (FEV1) and forced vital capacity (FVC)), time to next exacerbation and quality of life.

MAIN RESULTS: We included 45 studies involving 2810 participants. The included studies were mostly small, and inadequately reported, many of which were quite old. The certainty of the evidence was mostly low. Combined intravenous antibiotics versus placebo Data reported for absolute change in % predicted FEV1 and FVC suggested a possible improvement in favour of IV antibiotics, but the evidence is very uncertain (1 study, 12 participants; very low-certainty evidence). The study did not measure time to next exacerbation or quality of life. Intravenous versus nebulised antibiotics Five studies (122 participants) reported FEV1, with analysable data only from one study (16 participants). We found no difference between groups (moderate-certainty evidence). Three studies (91 participants) reported on FVC, with analysable data from only one study (54 participants). We are very uncertain on the effect of nebulised antibiotics (very low-certainty evidence). In one study, the 16 participants on nebulised plus IV antibiotics had a lower mean number of days to next exacerbation than those on combined IV antibiotics (low-certainty evidence), but we found no difference in quality of life between groups (low-certainty evidence). Intravenous versus oral antibiotics Three studies (172 participants) reported no difference in different measures of lung function. We found no difference in analysable data between IV and oral antibiotic regimens in either FEV1 % predicted or FVC % predicted (1 study, 24 participants; low-certainty evidence) or in the time to the next exacerbation (1 study, 108 participants; very low-certainty evidence). No study measured quality of life. Intravenous antibiotic regimens compared One study (analysed as two data sets) compared the duration of IV antibiotic regimens between two groups (split according to initial antibiotic response). The first part was a non-inferiority study in 214 early treatment responders to establish whether 10 days of IV antibiotic treatment was as effective as 14 days. Second, investigators looked at whether 14 or 21 days of IV antibiotics were more effective in 705 participants who did not respond early to treatment. We found no difference in FEV1 % predicted with any duration of treatment (919 participants; high-certainty evidence) or the time to next exacerbation (information later taken from registry data). Investigators did not report FVC or quality of life. Other comparisons We also found little or no difference in lung function when comparing single IV antibiotic regimens to placebo (2 studies, 70 participants), or in lung function and time to next exacerbation when comparing different single antibiotic regimens (2 studies, 95 participants). There may be a greater improvement in lung function in participants receiving combined IV antibiotics compared to single IV antibiotics (6 studies, 265 participants; low- to very low-certainty evidence), but probably no difference in the time to next exacerbation (1 study, 34 participants; low-certainty evidence). Four studies compared a single IV antibiotic plus placebo to a combined IV antibiotic regimen with high levels of heterogeneity in the results. We are very uncertain if there is any difference between groups in lung function (4 studies, 214 participants) and there may be little or no difference to being re-admitted to hospital for an exacerbation (2 studies, 104 participants). Nine studies (417 participants) compared combined IV antibiotic regimens with a great variation in drugs. We identified no differences in any measure of lung function or the time to next exacerbation between different regimens (low- to very low-certainty evidence). There were mixed results for adverse events across all comparisons; common adverse effects included elevated liver function tests, gastrointestinal events and haematological abnormalities. There were limited data for other secondary outcomes, such as weight, and there was no evidence of treatment effect.

AUTHORS' CONCLUSIONS: The evidence of benefit from administering IV antibiotics for pulmonary exacerbations in cystic fibrosis is often poor, especially in terms of size of studies and risk of bias, particularly in older studies. We are not certain whether there is any difference between specific antibiotic combinations, and neither is there evidence of a difference between the IV route and the inhaled or oral routes. There is limited evidence that shorter antibiotic duration in adults who respond early to treatment is not different to a longer period of treatment. There remain several unanswered questions regarding optimal IV antibiotic treatment regimens.

PMID:39831540 | DOI:10.1002/14651858.CD009730.pub3

World Allergy Organ J. 2024 Dec 27;18(1):101016. doi: 10.1016/j.waojou.2024.101016. eCollection 2025 Jan.

ABSTRACT

BACKGROUND: This study aimed to evaluate the impact of severe asthma (SA) treatments after 12 months in achieving clinical remission (CR) within the context of the Severe Asthma Network in Italy (SANI) using the recent SANI definition of CR on treatment.

METHODS: CR has been defined by SANI as complete, partial, and no CR. Complete CR is defined by the absence of oral corticosteroids (OCS), no symptoms, no exacerbations, and stable lung function, and partial CR requires the absence of OCS and the fulfillment of 2 out of the other 3 criteria. Patients who do not meet the previous criteria do not reach CR.

RESULTS: After 12 months of treatment, 283 patients were selected to evaluate the effectiveness of biologics (225 patients) and inhaled therapy (58 patients) in achieving CR. Among patients treated with biologic agents, 45.8% reached complete CR, 23.1% partial CR, and 31.1% no CR. Differences in CR achievement according to type of biologic agent administered were observed. Interesting results were found when assessing the inhaled therapy (ICS/LABA/LAMA and no biologics) effectiveness: 34.5% patients reached complete CR, 34.5% partial CR, and 31.0% did not reach CR. This finding is noteworthy since it further supports the efficacy of inhaled treatment in certain SA patients and highlights the relevance of using CR as a modern outcome of SA treatments. Chronic rhinosinusitis with nasal polyps (CRSwNP) comorbidity was associated, though not significantly, with CR achievement in patients treated with biologics. Asthma Control Test (ACT) and Asthma Control Questionnaire (ACQ) scores significantly impacted CR (p = 0.003 and p = 0.027, respectively), while biomarkers, namely IgE, blood eosinophils, or fractional exhaled nitric oxide (FeNO), were not associated with CR achievement.

CONCLUSIONS: This study confirmed the effectiveness of biologics in reaching CR and demonstrated also inhaled therapies able to achieve CR. These innovative findings should encourage post hoc analysis of randomized clinical trials or even retrospective analysis of SA patient cohorts to evaluate CR with different inhaled treatments and further define the populations eligible for each treatment.

TRIAL REGISTRATION: ClinicalTrials.gov ID: NCT06625216; Central Ethics Committee: Comitato Etico Area Vasta Nord-Ovest Toscana (study number 1245/2016, protocol number:73714).

PMID:39829953 | PMC:PMC11741032 | DOI:10.1016/j.waojou.2024.101016

Biomed Phys Eng Express. 2025 Jan 20. doi: 10.1088/2057-1976/adabea. Online ahead of print.

ABSTRACT

Deep learning has emerged as a powerful tool in medical imaging, particularly for corneal topographic map classification. However, the scarcity of labeled data poses a significant challenge to achieving robust performance. This study investigates the impact of various data augmentation strategies on enhancing the performance of a customized convolutional neural network model for corneal topographic map classification. We propose a hybrid data augmentation approach that combines traditional transformations, generative adversarial networks, and specific generative models. Experimental results demonstrate that the hybrid data augmentation method, achieves the highest accuracy of 99.54%, significantly outperforming individual data augmentation techniques. This hybrid approach not only improves model accuracy but also mitigates overfitting issues, making it a promising solution for medical image classification tasks with limited data availability.

PMID:39832385 | DOI:10.1088/2057-1976/adabea

Biol Reprod. 2025 Jan 20:ioaf009. doi: 10.1093/biolre/ioaf009. Online ahead of print.

ABSTRACT

Economic losses in cattle farms are frequently associated with failed pregnancies. Some studies found that the transcriptomic profiles of blood and endometrial tissues in cattle with varying pregnancy outcomes display discrepancies even before artificial insemination (AI) or embryo transfer (ET). In the study, 330 samples from seven distinct sources and two tissue types were integrated and divided into two groups based on the ability to establish and maintain pregnancy after AI or ET: P (pregnant) and NP (nonpregnant). By analyzing gene co-variation and employing machine learning algorithms, the objective was to identify genes that could predict pregnancy outcomes in cattle. Initially, within each tissue type, the top 100 differentially co-expressed genes (DCEG) were identified based on the analysis of changes in correlation coefficients and network topological structure. Subsequently, these genes were used in models trained by seven different machine learning algorithms. Overall, models trained on DCEGs exhibited superior predictive accuracy compared to those trained on an equivalent number of differential expression genes (DEGs). Among them, the deep learning models based on differential co-expression genes in blood and endometrial tissue achieved prediction accuracies of 91.7% and 82.6%, respectively. Finally, the importance of DCEGs was ranked using SHapley Additive exPlanations (SHAP) and enrichment analysis, identifying key signaling pathways that influence pregnancy. In summary, this study identified a set of genes potentially affecting pregnancy by analyzing the overall co-variation of gene connections between multiple sources. These key genes facilitated the development of interpretable machine learning models that accurately predict pregnancy outcomes in cattle.

PMID:39832283 | DOI:10.1093/biolre/ioaf009

Dentomaxillofac Radiol. 2025 Jan 20:twaf006. doi: 10.1093/dmfr/twaf006. Online ahead of print.

ABSTRACT

OBJECTIVES: This study aimed to develop an automated method for generating clearer, well-aligned panoramic views by creating an optimized three-dimensional (3D) reconstruction zone centered on the teeth. The approach focused on achieving high contrast and clarity in key dental features, including tooth roots, morphology, and periapical lesions, by applying a 3D U-Net deep learning model to generate an arch surface and align the panoramic view.

METHODS: This retrospective study analyzed anonymized cone-beam CT (CBCT) scans from 312 patients (mean age 40 years; range 10-78; 41.3% male, 58.7% female). A 3D U-Net deep learning model segmented the jaw and dentition, facilitating panoramic view generation. During preprocessing, CBCT scans were binarized, and a cylindrical reconstruction method aligned the arch along a straight coordinate system, reducing data size for efficient processing. The 3D U-Net segmented the jaw and dentition in two steps, after which the panoramic view was reconstructed using 3D spline curves fitted to the arch, defining the optimal 3D reconstruction zone. This ensured the panoramic view captured essential anatomical details with high contrast and clarity. To evaluate performance, we compared contrast between tooth roots and alveolar bone and assessed intersection over union (IoU) values for tooth shapes and periapical lesions (#42, #44, #46) relative to the conventional method, demonstrating enhanced clarity and improved visualization of critical dental structures.

RESULTS: The proposed method outperformed the conventional approach, showing significant improvements in the contrast between tooth roots and alveolar bone, particularly for tooth #42. It also demonstrated higher IoU values in tooth morphology comparisons, indicating superior shape alignment. Additionally, when evaluating periapical lesions, our method achieved higher performance with thinner layers, resulting in several statistically significant outcomes. Specifically, average pixel values within lesions were higher for certain layer thicknesses, demonstrating enhanced visibility of lesion boundaries and better visualization.

CONCLUSIONS: The fully automated AI-based panoramic view generation method successfully created a 3D reconstruction zone centered on the teeth, enabling consistent observation of dental and surrounding tissue structures with high contrast across reconstruction widths. By accurately segmenting the dental arch and defining the optimal reconstruction zone, this method shows significant advantages in detecting pathological changes, potentially reducing clinician fatigue during interpretation while enhancing clinical decision-making accuracy. Future research will focus on further developing and testing this approach to ensure robust performance across diverse patient cases with varied dental and maxillofacial structures, thereby increasing the model's utility in clinical settings.

ADVANCES IN KNOWLEDGE: This study introduces a novel method for achieving clearer, well-aligned panoramic views focused on the dentition, providing significant improvements over conventional methods.

PMID:39832267 | DOI:10.1093/dmfr/twaf006

J Food Sci. 2025 Jan;90(1):e70003. doi: 10.1111/1750-3841.70003.

ABSTRACT

Bruises can affect the appearance and nutritional value of apples and cause economic losses. Therefore, the accurate detection of bruise levels and bruise time of apples is crucial. In this paper, we proposed a method that combines a self-designed multispectral imaging system with deep learning to accurately detect the level and time of bruising on apples. To enhance the accuracy of extracting bruised regions with subtle features and irregular edges, an improved DeepLabV3+ was proposed. More specifically, depthwise separable convolution and efficient channel attention were employed, and the loss function was replaced with a focal loss. With these improvements, DeepLabV3+ achieved the maximum intersection over union of 95.5% and 91.0% for segmenting bruises on two types of apples in the test set, as well as maximum F1-score of 97.5% and 95.2%. In addition, the spectral data of the bruised regions were extracted. After spectral preprocessing, EfficientNetV2, DenseNet121, and ShuffleNetV2 were utilized to identify the bruise levels and times and DenseNet121 exhibited the best performance. To improve the identification accuracy, an improved DenseNet121 was proposed. The learning rate was adjusted using the cosine annealing algorithm, and squeeze-and-excitation attention mechanism and the Gaussian error linear unit activation function were utilized. Test set results demonstrated that the accuracies of the bruising levels were 99.5% and 99.1%, and those of the bruise time were 99.0% and 99.3%, respectively. This provides a new method for detecting bruise levels and bruised time on apples.

PMID:39832229 | DOI:10.1111/1750-3841.70003

Network. 2025 Jan 20:1-21. doi: 10.1080/0954898X.2025.2451388. Online ahead of print.

ABSTRACT

The image retrieval is the process of retrieving the relevant images to the query image with minimal searching time in internet. The problem of the conventional Content-Based Image Retrieval (CBIR) system is that they produce retrieval results for either colour images or grey scale images alone. Moreover, the CBIR system is more complex which consumes more time period for producing the significant retrieval results. These problems are overcome through the proposed methodologies stated in this work. In this paper, the General Image (GI) and Medical Image (MI) are retrieved using deep learning architecture. The proposed system is designed with feature computation module, Retrieval Convolutional Neural Network (RETCNN) module, and Distance computation algorithm. The distance computation algorithm is used to compute the distances between the query image and the images in the datasets and produces the retrieval results. The average precision and recall for the proposed RETCNN-based CBIRS is 98.98% and 99.15% respectively for GI category, and the average precision and recall for the proposed RETCNN-based CBIRS are 99.04% and 98.89% respectively for MI category. The significance of these experimental results is used to produce the higher image retrieval rate of the proposed system.

PMID:39832139 | DOI:10.1080/0954898X.2025.2451388

Oncologist. 2025 Jan 17;30(1):oyae341. doi: 10.1093/oncolo/oyae341.

ABSTRACT

BACKGROUND: Peritoneal metastasis (PM) after the rupture of hepatocellular carcinoma (HCC) is a critical issue that negatively affects patient prognosis. Machine learning models have shown great potential in predicting clinical outcomes; however, the optimal model for this specific problem remains unclear.

METHODS: Clinical data were collected and analyzed from 522 patients with ruptured HCC who underwent surgery at 7 different medical centers. Patients were assigned to the training, validation, and test groups in a random manner, with a distribution ratio of 7:1.5:1.5. Overall, 78 (14.9%) patients experienced postoperative PM. Five different types of models, including logistic regression, support vector machines, classification trees, random forests, and deep learning (DL) models, were trained using these data and evaluated based on their receiver operating characteristic curve and area under the curve (AUC) values and F1 scores.

RESULTS: The DL models achieved the highest AUC values (10-fold training cohort: 0.943, validation set: 0.928, and test set: 0.892) and F1 scores (10-fold training set: 0.917, validation cohort: 0.908, and test set:0.899) The results of the analysis indicate that tumor size, timing of hepatectomy, alpha-fetoprotein levels, and microvascular invasion are the most important predictive factors closely associated with the incidence of postoperative PM.

CONCLUSION: The DL model outperformed all other machine learning models in predicting postoperative PM after the rupture of HCC based on clinical data. This model provides valuable information for clinicians to formulate individualized treatment plans that can improve patient outcomes.

PMID:39832130 | DOI:10.1093/oncolo/oyae341

EJNMMI Phys. 2025 Jan 20;12(1):3. doi: 10.1186/s40658-024-00713-4.

ABSTRACT

BACKGROUND: The topic of the effect of the patient table on attenuation in myocardial perfusion imaging (MPI) SPECT is gaining new relevance due to deep learning methods. Existing studies on this effect are old, rare and only consider phantom measurements, not patient studies. This study investigates the effect of the patient table on attenuation based on the difference between reconstructions of phantom scans and polar maps of patient studies.

METHODS: Jaszczak phantom scans are acquired according to quality control and MPI procedures. An algorithm is developed to automatically remove the patient table from the CT for attenuation correction. The scans are then reconstructed with attenuation correction either with or without the patient table in the CT. The reconstructions are compared qualitatively and on the basis of their percentage difference. In addition, a small retrospective cohort of 15 patients is examined by comparing the resulting polar maps. Polar maps are compared qualitatively and based on the segment perfusion scores.

RESULTS: The phantom reconstructions look qualitatively similar in both the quality control and MPI procedures. The percentage difference is highest in the lower part of the phantom, but it always remains below 17.5%. Polar maps from patient studies also look qualitatively similar. Furthermore, the segment scores are not significantly different (p=0.83).

CONCLUSIONS: The effect of the patient table on attenuation in MPI SPECT is negligible.

PMID:39832088 | DOI:10.1186/s40658-024-00713-4

Int J Comput Assist Radiol Surg. 2025 Jan 20. doi: 10.1007/s11548-025-03323-2. Online ahead of print.

ABSTRACT

PURPOSE: Pulmonary perfusion imaging is a key lung health indicator with clinical utility as a diagnostic and treatment planning tool. However, current nuclear medicine modalities face challenges like low spatial resolution and long acquisition times which limit clinical utility to non-emergency settings and often placing extra financial burden on the patient. This study introduces a novel deep learning approach to predict perfusion imaging from non-contrast inhale and exhale computed tomography scans (IE-CT).

METHODS: We developed a U-Net Transformer architecture modified for Siamese IE-CT inputs, integrating insights from physical models and utilizing a self-supervised learning strategy tailored for lung function prediction. We aggregated 523 IE-CT images from nine different 4DCT imaging datasets for self-supervised training, aiming to learn a low-dimensional IE-CT feature space by reconstructing image volumes from random data augmentations. Supervised training for perfusion prediction used this feature space and transfer learning on a cohort of 44 patients who had both IE-CT and single-photon emission CT (SPECT/CT) perfusion scans.

RESULTS: Testing with random bootstrapping, we estimated the mean and standard deviation of the spatial Spearman correlation between our predictions and the ground truth (SPECT perfusion) to be 0.742 ± 0.037, with a mean median correlation of 0.792 ± 0.036. These results represent a new state-of-the-art accuracy for predicting perfusion imaging from non-contrast CT.

CONCLUSION: Our approach combines low-dimensional feature representations of both inhale and exhale images into a deep learning model, aligning with previous physical modeling methods for characterizing perfusion from IE-CT. This likely contributes to the high spatial correlation with ground truth. With further development, our method could provide faster and more accurate lung function imaging, potentially expanding its clinical applications beyond what is currently possible with nuclear medicine.

PMID:39832070 | DOI:10.1007/s11548-025-03323-2

Radiol Med. 2025 Jan 20. doi: 10.1007/s11547-025-01949-5. Online ahead of print.

ABSTRACT

BACKGROUND: Accurate differentiation between benign and malignant pancreatic lesions is critical for effective patient management. This study aimed to develop and validate a novel deep learning network using baseline computed tomography (CT) images to predict the classification of pancreatic lesions.

METHODS: This retrospective study included 864 patients (422 men, 442 women) with confirmed histopathological results across three medical centers, forming a training cohort, internal testing cohort, and external validation cohort. A novel hybrid model, Multi-Scale Large Kernel Attention with Mobile Vision Transformer (MVIT-MLKA), was developed, integrating CNN and Transformer architectures to classify pancreatic lesions. The model's performance was compared with traditional machine learning methods and advanced deep learning models. We also evaluated the diagnostic accuracy of radiologists with and without the assistance of the optimal model. Model performance was assessed through discrimination, calibration, and clinical applicability.

RESULTS: The MVIT-MLKA model demonstrated superior performance in classifying pancreatic lesions, achieving an AUC of 0.974 (95% CI 0.967-0.980) in the training set, 0.935 (95% CI 0.915-0.954) in the internal testing set, and 0.924 (95% CI 0.902-0.945) in the external validation set, outperforming traditional models and other deep learning models (P < 0.05). Radiologists aided by the MVIT-MLKA model showed significant improvements in diagnostic accuracy and sensitivity compared to those without model assistance (P < 0.05). Grad-CAM visualization enhanced model interpretability by effectively highlighting key lesion areas.

CONCLUSION: The MVIT-MLKA model efficiently differentiates between benign and malignant pancreatic lesions, surpassing traditional methods and significantly improving radiologists' diagnostic performance. The integration of this advanced deep learning model into clinical practice has the potential to reduce diagnostic errors and optimize treatment strategies.

PMID:39832039 | DOI:10.1007/s11547-025-01949-5

Brief Bioinform. 2024 Nov 22;26(1):bbaf009. doi: 10.1093/bib/bbaf009.

ABSTRACT

Single-cell high-throughput chromosome conformation capture (Hi-C) technology enables capturing chromosomal spatial structure information at the cellular level. However, to effectively investigate changes in chromosomal structure across different cell types, there is a requisite for methods that can identify cell types utilizing single-cell Hi-C data. Current frameworks for cell type prediction based on single-cell Hi-C data are limited, often struggling with features interpretability and biological significance, and lacking convincing and robust classification performance validation. In this study, we propose four new feature sets based on the contact matrix with clear interpretability and biological significance. Furthermore, we develop a novel deep learning framework named scHiClassifier based on multi-head self-attention encoder, 1D convolution and feature fusion, which integrates information from these four feature sets to predict cell types accurately. Through comprehensive comparison experiments with benchmark frameworks on six datasets, we demonstrate the superior classification performance and the universality of the scHiClassifier framework. We further assess the robustness of scHiClassifier through data perturbation experiments and data dropout experiments. Moreover, we demonstrate that using all feature sets in the scHiClassifier framework yields optimal performance, supported by comparisons of different feature set combinations. The effectiveness and the superiority of the multiple feature set extraction are proven by comparison with four unsupervised dimensionality reduction methods. Additionally, we analyze the importance of different feature sets and chromosomes using the "SHapley Additive exPlanations" method. Furthermore, the accuracy and reliability of the scHiClassifier framework in cell classification for single-cell Hi-C data are supported through enrichment analysis. The source code of scHiClassifier is freely available at https://github.com/HaoWuLab-Bioinformatics/scHiClassifier.

PMID:39831891 | DOI:10.1093/bib/bbaf009

J Thorac Dis. 2024 Dec 31;16(12):8379-8388. doi: 10.21037/jtd-24-1165. Epub 2024 Dec 11.

ABSTRACT

BACKGROUND: The benefits of pulmonary rehabilitation (PR) for patients with idiopathic pulmonary fibrosis (IPF) have been limited to improving dyspnea, exercise capacity, and quality of life (QoL). This study aimed to assess the current status of PR and its effect on prognosis.

METHODS: The Nationwide Korean Health Insurance Review and Assessment Service (HIRA) database was used in this study. Annual PR implementation rate since 2016 following its coverage in the health insurance was analyzed. IPF cases were defined using the International Classification of Diseases 10th Revision (ICD-10) codes and rare intractable diseases (RID) codes. Risk of acute exacerbation (AE) and mortality of IPF patients with or without PR were analyzed.

RESULTS: Of the 4,228 patients with IPF, only 205 (4.85%) received PR. Patients in the PR group were more frequently treated with pirfenidone and systemic steroids than non-PR group. In patients treated with steroids, mortality risk increased regardless of PR application, with hazard ratio (HR) of 1.63 [95% confidence interval (CI): 1.26-2.10, P<0.001] in the PR group and 1.38 (95% CI: 1.21-1.57, P<0.001) in the non-PR group, compared to those not treated with steroids. Additionally, PR did not significant affect mortality risk in patients not receiving steroids (HR, 1.49, 95% CI: 0.87-2.54, P=0.15). Similar patterns were seen for the risk of AE.

CONCLUSIONS: PR was applied in only a minority of patients with IPF. It did not succeed in reducing the risk of AE or mortality. A prospective study targeting early-stage patients is needed to evaluate the impact of PR considering the progressive nature of IPF disease itself.

PMID:39831231 | PMC:PMC11740027 | DOI:10.21037/jtd-24-1165