Arch Dermatol Res. 2025 Jan 28;317(1):311. doi: 10.1007/s00403-024-03785-5.

ABSTRACT

The area of wound healing presents a promising field of interest for clinicians as well as the scientific community. A major concern for physicians is the rising number of elderly people suffering from diabetes, leprosy, tuberculosis and the associated chronic wounds. While traditional therapies target basic wound care, innovative strategies that accelerate wound healing are needed. V-RAF murine sarcoma viral oncogene homolog B1 (BRAF) inhibitors are anti-cancer drugs used primarily for melanoma. They also exhibit paradoxical activity, a phenomenon characterized by unintended activation of the Mitogen-Activated Protein Kinase (MAPK) signalling pathway leading to skin hyperproliferation. Studies have demonstrated that BRAF inhibitors can be repurposed to accelerate the healing of acute and chronic wounds by exploiting their paradoxical activity. This review evaluates studies on BRAF inhibitors by employing a systematic search strategy using databases such as PubMed, Scopus, Google Scholar, and Web of Science. Articles were screened based on relevance to the paradoxical activity of BRAF inhibitors, their mechanisms, and applications in wound healing. Evidence from in vitro, in vivo, and clinical studies demonstrates that BRAF inhibitors can enhance processes such as epithelialization and angiogenesis, essential for wound repair. This review summarizes the reports on the paradoxical activity of BRAF inhibitors, the predicted mechanisms behind the paradoxical activity, and their potential use in wound healing.

PMID:39873776 | DOI:10.1007/s00403-024-03785-5

J Chem Inf Model. 2025 Jan 27. doi: 10.1021/acs.jcim.4c02019. Online ahead of print.

ABSTRACT

The drug discovery process can be significantly accelerated by using deep learning methods to suggest molecules with druglike features and, more importantly, that are good candidates to bind specific proteins of interest. We present a novel deep learning generative model, Prot2Drug, that learns to generate ligands binding specific targets leveraging (i) the information carried by a pretrained protein language model and (ii) the ability of transformers to capitalize the knowledge gathered from thousands of protein-ligand interactions. The embedding unveils the receipt to follow for designing molecules binding a given protein, and Prot2Drug translates such instructions by using the syntax of the molecular language generating novel compounds which are predicted to have favorable physicochemical properties and high affinity toward specific targets. Moreover, Prot2Drug reproduced numerous known interactions between compounds and proteins used for generating them and suggested novel protein targets for known compounds, indicating potential drug repurposing strategies. Remarkably, Prot2Drug facilitates the design of promising ligands even for protein targets with limited or no information about their ligands or 3D structure.

PMID:39871540 | DOI:10.1021/acs.jcim.4c02019

Echocardiography. 2025 Jan;42(1):e70084. doi: 10.1111/echo.70084.

ABSTRACT

This manuscript presents a rare case of a complex pulmonary venous malposition with an intact atrial septum and ventricular septum. The study demonstrates the diagnostic utility of echocardiography and computed tomography in the evaluation of complex congenital heart disease.

PMID:39873326 | DOI:10.1111/echo.70084

Front Genet. 2025 Jan 13;15:1484651. doi: 10.3389/fgene.2024.1484651. eCollection 2024.

ABSTRACT

INTRODUCTION: PIK3CA related disorders (PRD, OMIM: *171834) are genetic disorders resulting from pathogenic somatic mosaic variants in the PIK3CA gene, which encodes a protein crucial for regulating cell growth and division. PRD typically manifest during the post-zygotic phase, leading to a broad spectrum of overgrowth and vascular malformations affecting various body regions.

METHODS: Conventional diagnostic methods struggle to detect and confirm pathogenic PIK3CA gene variants due to the mosaic nature of these disorders and the limited accessibility of affected tissues. In this study, we conducted comprehensive genomic profiling on a cohort of individuals with PRD to address these diagnostic challenges.

RESULTS: Our analysis revealed significant diagnostic challenges posed by somatic mosaicism in PRD. The comprehensive genomic profiling allowed for the meticulous evaluation of potentially pathogenic gene variants in affected individuals and their corresponding tissues.

DISCUSSION: Our findings advocate for the adoption of comprehensive genomic profiling in clinical practice to improve the detection and management of PRD. This approach can enhance patient care by providing a more accurate diagnosis and better understanding of the genetic underpinnings of PRD.

PMID:39872006 | PMC:PMC11769973 | DOI:10.3389/fgene.2024.1484651

Asian Pac J Cancer Prev. 2025 Jan 1;26(1):5-15. doi: 10.31557/APJCP.2025.26.1.5.

ABSTRACT

Doxorubicin, a widely used anthracycline antibiotic, has been a cornerstone in cancer chemotherapy since the 1960s. In addition to doxorubicin, anthracycline chemotherapy medications include daunorubicin, idarubicin, and epirubicin. For many years, doxorubicin has been the chemotherapy drug of choice for treating a broad variety of cancers. Despite its efficacy, doxorubicin therapy is hindered by serious side effects, primarily cardiotoxicity, and the challenges of drug resistance. Recent research has focused on optimizing doxorubicin's therapeutic index by developing cardioprotective strategies, such as dexrazoxane, and utilizing non-invasive monitoring techniques to reduce cardiac risk. To counteract drug resistance, innovative formulations like nanoparticle-based delivery systems, enhance targeted drug delivery and overcome cellular resistance mechanisms. Furthermore, using combination approaches involving immunotherapy, photodynamic therapy, and genetic modulation, offer promising synergies to maximize tumor eradication. Personalized approaches, supported by pharmacogenomics and predictive biomarkers, are enhancing individualized treatment regimens, aiming to increase effectiveness and minimize toxicity. Future research on doxorubicin focuses on developing advanced drug delivery systems, such as nanoparticle and liposomal formulations, to enhance targeted delivery, minimize systemic toxicity, and improve therapeutic precision. Efforts are also underway to design combination therapies that integrate doxorubicin with immunotherapies, photodynamic approaches, and gene-based treatments, aiming to overcome resistance and increase tumor-specific effects. These advancements signify a transition toward more personalized and effective doxorubicin-based cancer therapies, prioritizing reduced side effects and improved patient outcomes. This article focusses on the ongoing innovations aimed at maximizing the therapeutic potential of doxorubicin while addressing its limitations.

PMID:39873980 | DOI:10.31557/APJCP.2025.26.1.5

Eur Clin Respir J. 2025 Jan 24;12(1):2458341. doi: 10.1080/20018525.2025.2458341. eCollection 2025.

ABSTRACT

Therapeutic drug monitoring (TDM) of elexacaftor/tezacaftor/ivacaftor (ETI) remains challenging due to a lack of clarity around the parameters that govern ETI plasma concentrations, whilst the use of concomitant CYP3A inducers rifabutin and rifampicin is not recommended. We present the complexities of TDM for ETI performed in a person with cystic fibrosis and refractory Mycobacterium abscessus pulmonary disease. Utilising National Association of Testing Authorities (NATA) accredited assays and target considerations published by the Therapeutic Goods Administration (TGA), Australia, ETI plasma concentration variability was monitored over the course of an acute admission with added complexity from an antibiotic regimen including rifabutin, a moderate cytochrome P450 3A (CYP3A) inducer, and clofazimine, a mild CYP3A inhibitor. This case highlights the challenges surrounding ETI TDM in the context of acute severe illness, malnutrition, chronic infection, and drug-to-drug interactions. The marked clinical improvement seen, alongside sustained ETI plasma concentrations and suppressed sweat chloride levels on serial testing, provided reassurance of the use of ETI and rifabutin concomitantly in this case, and highlights the potential utility of TDM in helping guide clinical practice. Though a current barrier to the application of TDM includes ETI only being available as a fixed dose combination.

PMID:39872799 | PMC:PMC11770854 | DOI:10.1080/20018525.2025.2458341

ERJ Open Res. 2025 Jan 27;11(1):00793-2024. doi: 10.1183/23120541.00793-2024. eCollection 2025 Jan.

ABSTRACT

Identifying mucous plugs by chest CT should be considered carefully because it is potentially a treatable trait https://bit.ly/4gyJHFW.

PMID:39872389 | PMC:PMC11770761 | DOI:10.1183/23120541.00793-2024

ERJ Open Res. 2025 Jan 27;11(1):00386-2024. doi: 10.1183/23120541.00386-2024. eCollection 2025 Jan.

ABSTRACT

pwCF carrying the Q359K/T360K variant may have significant clinical benefit from treatment with ETI that may exceed improvements observed with TI treatment. These data support routine clinical use of ETI in this rare patient group. https://bit.ly/45DjFw9.

PMID:39872382 | PMC:PMC11770694 | DOI:10.1183/23120541.00386-2024

J Mater Chem B. 2025 Jan 28. doi: 10.1039/d4tb02675f. Online ahead of print.

ABSTRACT

The reason why certain bacteria, e.g., Pseudomonas aeruginosa (PA), produce acetylated alginate (Alg) in their biofilms remains one of the most intriguing facts in microbiology. Being the main structural component of the secreted biofilm, like the one formed in the lungs of cystic fibrosis (CF) patients, Alg plays a crucial role in protecting the bacteria from environmental stress and potential threats. Nonetheless, to investigate the PA biofilm environment and its lack of susceptibility to antibiotic treatment, the currently developed in vitro biofilm models use native seaweed Alg, which is a non-acetylated Alg. The role of the acetyl side group on the backbone of bacterial Alg has never been elucidated, and the transposition of experimental results obtained from such systems to clinical conditions (e.g., to treat CF-infection) may be hazardous. We systematically investigated the influence of acetylation on the physico-chemical and mechanical properties of Alg in solution and Ca2+-crosslinked hydrogels. Furthermore, we assessed how the acetylation influenced the interaction of Alg with tobramycin, a common aminoglycoside antibiotic for PA. Our study revealed that the degree of acetylation directly impacts the viscosity and Young's Modulus of Alg in a pH-dependent manner. Acetylation increased the mesh size in biofilm-like Alg hydrogels, directly influencing antibiotic penetration. Our results provide essential insights to create more clinically relevant in vitro infection models to test the efficacy of new drugs or to better understand the 3D microenvironment of PA biofilms.

PMID:39871625 | DOI:10.1039/d4tb02675f

Gut Pathog. 2025 Jan 27;17(1):6. doi: 10.1186/s13099-024-00674-0.

ABSTRACT

BACKGROUND: Asymptomatic carriers significantly influence the transmission dynamics of C. difficile. This study aimed to assess the prevalence of toxigenic C. difficile asymptomatic colonization (tCDAC) and investigate its heterogeneity across different populations. We searched MEDLINE, Web of Science, and Scopus for articles published between 2000 and 2023 on tCDAC. Studies including asymptomatic adults with laboratory-confirmed tCDAC were eligible. We performed a random-effects meta-analysis to estimate the pooled prevalence by clinical characteristics, settings, and geographic areas. In addition, we used outlier analyses and meta-regression to explore sources of prevalence variability.

RESULTS: Fifty-one studies involving 39,447 patients were included. The tCDAC prevalence ranged from 0.5 to 51.5%. Among pooled estimates, a high prevalence was observed in patients with cystic fibrosis, outbreak settings, and cancer patients, whereas the lowest rates were found in healthy individuals and healthcare workers. Similar colonization rates were observed between admitted and hospitalized patients. Our meta-regression analysis revealed lower rates in healthy individuals and higher rates in cystic fibrosis patients and studies from North America. Additionally, compared with that among healthy individuals, the prevalence significantly increased by 15-47% among different populations and settings.

CONCLUSION: Our study revealed that tCDAC is a common phenomenon. We found high prevalence estimates that showed significant variability across populations. This heterogeneity could be partially explained by population characteristics and settings, supporting their role in the pathogenesis and burden of this disease. This highlights the need to identify high-risk groups to improve infection control strategies, decrease transmission dynamics, and better understand the natural history of this disease.

PMID:39871276 | DOI:10.1186/s13099-024-00674-0

J Magn Reson Imaging. 2025 Jan 28. doi: 10.1002/jmri.29719. Online ahead of print.

ABSTRACT

BACKGROUND: Multifrequency MR elastography (mMRE) enables noninvasive quantification of renal stiffness in patients with chronic kidney disease (CKD). Manual segmentation of the kidneys on mMRE is time-consuming and prone to increased interobserver variability.

PURPOSE: To evaluate the performance of mMRE combined with automatic segmentation in assessing CKD severity.

STUDY TYPE: Prospective.

PARTICIPANTS: A total of 179 participants consisting of 95 healthy volunteers and 84 participants with CKD.

FIELD STRENGTH/SEQUENCE: 3 T, single shot spin echo planar imaging sequence.

ASSESSMENT: Participants were randomly assigned into training (n = 58), validation (n = 15), and test (n = 106) sets. Test set included 47 healthy volunteers and 58 CKD participants with different stages (21 stage 1-2, 22 stage 3, and 16 stage 4-5) based on estimated glomerular filtration rate (eGFR). Shear wave speed (SWS) values from mMRE was measured using automatic segmentation constructed through the nnU-Net deep-learning network. Standard manual segmentation was created by a radiologist. In the test set, the automatically segmented renal SWS were compared between healthy volunteers and CKD subgroups, with age as a covariate. The association between SWS and eGFR was investigated in participants with CKD.

STATISTICAL TESTS: Dice similarity coefficient (DSC), analysis of covariance, Pearson and Spearman correlation analyses. P < 0.05 was considered statistically significant.

RESULTS: Mean DSCs between standard manual and automatic segmentation were 0.943, 0.901, and 0.970 for the renal cortex, medulla, and parenchyma, respectively. The automatically quantified cortical, medullary, and parenchymal SWS were significantly correlated with eGFR (r = 0.620, 0.605, and 0.640, respectively). Participants with CKD stage 1-2 exhibited significantly lower cortical SWS values compared to healthy volunteers (2.44 ± 0.16 m/second vs. 2.56 ± 0.17 m/second), after adjusting age.

CONCLUSION: mMRE combined with automatic segmentation revealed abnormal renal stiffness in patients with CKD, even with mild renal impairment.

PLAIN LANGUAGE SUMMARY: The renal stiffness of patients with chronic kidney disease varies according to the function and structure of the kidney. This study integrates multifrequency magnetic resonance elastography with automated segmentation technique to assess renal stiffness in patients with chronic kidney disease. The findings indicate that this method is capable of distinguishing between patients with chronic kidney disease, including those with mild renal impairment, while simultaneously reducing the subjectivity and time required for radiologists to analyze images. This research enhances the efficiency of image processing for radiologists and assists nephrologists in detecting early-stage damage in patients with chronic kidney disease.

LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY: Stage 2.

PMID:39874058 | DOI:10.1002/jmri.29719

Interdiscip Sci. 2025 Jan 28. doi: 10.1007/s12539-024-00684-1. Online ahead of print.

ABSTRACT

Combination therapy, which synergistically enhances treatment efficacy and inhibits disease progression through the combined effects of multiple drugs, has emerged as a mainstream approach for treating complex diseases and alleviating symptoms. However, drug-drug interactions (DDIs) can sometimes lead to adverse reactions, potentially endangering lives. Therefore, developing efficient and accurate DDI prediction methods is crucial for elucidating drug mechanisms and preventing side effects. Current prediction methods often focus solely on the presence of interactions between drugs when constructing DDI graphs, neglecting the specific types of DDIs. This oversight can result in a decline in predictive performance. To address this issue, we propose an Adaptive Multi-Kernel Graph Neural Network (AMKGNN) for DDI prediction. AMKGNN differentiates DDIs into increase-type and decrease-type interactions, constructing separate increased DDI and decreased DDI graphs as convolutional kernels. AMKGNN employs a graph kernel learning mechanism that adaptively determines the optimal threshold between high-frequency and low-frequency signals in the network to capture node embeddings. Initially, AMKGNN learns drug embedding representations based on these two graph convolutional kernels and various drug features. These representations are then concatenated and input into a deep neural network to predict potential DDIs. The results show that our model achieved AUC and AUPR values above 90% across three sub-tasks on two datasets, significantly outperforming the other five comparison models. Furthermore, ablation experiments and case studies validate the superiority of AMKGNN.

PMID:39873945 | DOI:10.1007/s12539-024-00684-1

Brain Topogr. 2025 Jan 28;38(2):25. doi: 10.1007/s10548-025-01100-7.

ABSTRACT

EEG involves recording electrical activity generated by the brain through electrodes placed on the scalp. Imagined speech classification has emerged as an essential area of research in brain-computer interfaces (BCIs). Despite significant advances, accurately classifying imagined speech signals remains challenging due to their complex and non-stationary nature. Existing approaches often struggle with low signal-to-noise ratios and high inter-subject variability. A proposed method named imagined speech functional connectivity graph (ISFCG) is implemented to deal with these issues. The functional connectivity graphs capture the complex relationships between brain regions during imagined speech tasks. These graphs are then used to extract features that serve as inputs to various machine-learning models. The ISFCG provides an alternative representation of imagined speech signals, focusing on brain connectivity features to enhance the analysis and classification process. Also, a convolutional neural network (CNN) is proposed to learn features from these complex graphs, leading to improved classification accuracy. Experimental results on a benchmark dataset demonstrate the effectiveness of our method.

PMID:39873797 | DOI:10.1007/s10548-025-01100-7

Radiology. 2025 Jan;314(1):e241249. doi: 10.1148/radiol.241249.

ABSTRACT

Background Deep learning (DL) methods can improve accelerated MRI but require validation against an independent reference standard to ensure robustness and accuracy. Purpose To validate the diagnostic performance of twofold-simultaneous-multislice (SMSx2) twofold-parallel-imaging (PIx2)-accelerated DL superresolution MRI in the knee against conventional SMSx2-PIx2-accelerated MRI using arthroscopy as the reference standard. Materials and Methods Adults with painful knee conditions were prospectively enrolled from December 2021 to October 2022. Participants underwent fourfold SMSx2-PIx2-accelerated standard-of-care and investigational DL superresolution MRI at 3 T. Seven radiologists independently evaluated the MRI examinations for overall image quality (using Likert scale scores: 1, very bad, to 5, very good) and the presence or absence of meniscus and ligament tears. Articular cartilage was categorized as intact, or partial or full-thickness defects. Statistical analyses included interreader agreements (Cohen κ and Gwet AC2) and diagnostic performance testing used area under the receiver operating characteristic curve (AUC) values. Results A total of 116 adults (mean age, 45 years ± 15 [SD]; 74 men) who underwent arthroscopic surgery within 38 days ± 22 were evaluated. Overall image quality was better for DL superresolution MRI (median Likert score, 5; range, 3-5) than conventional MRI (median Likert score, 4; range, 3-5) (P < .001). Diagnostic performances of conventional versus DL superresolution MRI were similar for medial meniscus tears (AUC, 0.94 [95% CI: 0.89, 0.97] vs 0.94 [95% CI: 0.90, 0.98], respectively; P > .99), lateral meniscus tears (AUC, 0.85 [95% CI: 0.78, 0.91] vs 0.87 [95% CI: 0.81, 0.94], respectively; P = .96), and anterior cruciate ligament tears (AUC, 0.98 [95% CI: 0.93, >0.99] vs 0.98 [95% CI: 0.93, >0.99], respectively; P > .99). DL superresolution MRI (AUC, 0.78; 95% CI: 0.75, 0.81) had higher diagnostic performance than conventional MRI (AUC, 0.71; 95% CI: 0.67, 0.74; P = .002) for articular cartilage lesions. DL superresolution MRI did not introduce hallucinations or erroneously omit abnormalities. Conclusion Compared with conventional SMSx2-PIx2-accelerated MRI, fourfold SMSx2-PIx2-accelerated DL superresolution MRI in the knee provided better image quality, similar performance for detecting meniscus and ligament tears, and improved performance for depicting articular cartilage lesions. © RSNA, 2025 Supplemental material is available for this article. See also the editorial by Nevalainen in this issue.

PMID:39873603 | DOI:10.1148/radiol.241249

Radiology. 2025 Jan;314(1):e242952. doi: 10.1148/radiol.242952.

NO ABSTRACT

PMID:39873600 | DOI:10.1148/radiol.242952

J Opt Soc Am A Opt Image Sci Vis. 2024 Aug 1;41(8):1585-1593. doi: 10.1364/JOSAA.527500.

ABSTRACT

Compressed ultrafast photography (CUP) is a high-speed imaging technique with a frame rate of up to ten trillion frames per second (fps) and a sequence depth of hundreds of frames. This technique is a powerful tool for investigating ultrafast processes. However, since the reconstruction process is an ill-posed problem, the image reconstruction will be more difficult with the increase of the number of reconstruction frames and the number of pixels of each reconstruction frame. Recently, various deep-learning-based regularization terms have been used to improve the reconstruction quality of CUP, but most of them require extensive training and are not generalizable. In this paper, we propose a reconstruction algorithm for CUP based on the manifold learning and the alternating direction method of multipliers framework (ML-ADMM), which is an unsupervised learning algorithm. This algorithm improves the reconstruction stability and quality by initializing the iterative process with manifold modeling in embedded space (MMES) and processing the image obtained from each ADMM iterative with a nonlinear modeling based on manifold learning. The numerical simulation and experiment results indicate that most of the spatial details can be recovered and local noise can be eliminated. In addition, a high-spatiotemporal-resolution video sequence can be acquired. Therefore, this method can be applied for CUP with ultrafast imaging applications in the future.

PMID:39873585 | DOI:10.1364/JOSAA.527500

Nutr Hosp. 2025 Jan 9. doi: 10.20960/nh.05672. Online ahead of print.

ABSTRACT

BACKGROUND: disease-related malnutrition (DRM) affects 30-50 % of hospitalized patients and is often underdiagnosed, increasing risks of complications and healthcare costs. Traditional DRM detection has relied on manual methods that lack accuracy and efficiency.

OBJECTIVE: this narrative review explores how artificial intelligence (AI), specifically machine learning (ML) and deep learning (DL), can transform the prediction and management of DRM in clinical settings.

METHODS: we examine widely used ML and DL models, assessing their clinical applicability, advantages, and limitations. The integration of these models into electronic health record systems allows for automated risk detection and optimizes real-time patient management.

RESULTS: ML and DL models show significant potential for accurate assessment of nutritional status and prediction of complications in patients with DRM. These models facilitate improved clinical decision-making and more efficient resource management, although their implementation faces challenges related to the need for large volumes of standardized data and integration with existing systems.

CONCLUSION: AI offers promising prospects for proactive DRM management, highlighting the need for interdisciplinary collaboration to overcome existing barriers and maximize its positive impact on patient care.

PMID:39873467 | DOI:10.20960/nh.05672

Biomed Tech (Berl). 2025 Jan 29. doi: 10.1515/bmt-2024-0282. Online ahead of print.

ABSTRACT

OBJECTIVES: In recent years, significant progress has been made in the research of gesture recognition using surface electromyography (sEMG) signals based on machine learning and deep learning techniques. The main motivation for sEMG gesture recognition research is to provide more natural, convenient, and personalized human-computer interaction, which makes research in this field have considerable application prospects in rehabilitation technology. However, the existing gesture recognition algorithms still need to be further improved in terms of global feature capture, model computational complexity, and generalizability.

METHODS: This paper proposes a fusion model of Squeeze-and-Excitation Networks (SE) and DenseNet, inserting attention mechanism between DenseBlock and Transition to focus on the most important information, improving feature representation ability, and effectively solving the problem of gradient vanishing.

RESULTS: This proposed method was tested on the electromyographic gesture datasets NinaPro DB2 and DB4, achieving accuracies of 85.93 and 82.39 % respectively. Through ablation experiments, it was found that the method based on DenseNet-101 as the backbone model produced the best results.

CONCLUSIONS: Compared with existing models, this proposed method has better robustness and generalizability in gesture recognition, providing new ideas for the development of sEMG signal gesture recognition applications in the future.

PMID:39873377 | DOI:10.1515/bmt-2024-0282

IET Syst Biol. 2025 Jan-Dec;19(1):e70001. doi: 10.1049/syb2.70001.

ABSTRACT

Metal ions are significant ligands that bind to proteins and play crucial roles in cell metabolism, material transport, and signal transduction. Predicting the protein-metal ion ligand binding residues (PMILBRs) accurately is a challenging task in theoretical calculations. In this study, the authors employed fused amino acids and their derived information as feature parameters to predict PMILBRs using three classical machine learning algorithms, yielding favourable prediction results. Subsequently, deep learning algorithm was incorporated in the prediction, resulting in improved results for the sets of Ca2+ and Mg2+ compared to previous studies. The validation matrix provided the optimal prediction model for each ionic ligand binding residue, exhibiting the capability of effectively predicting the binding sites of metal ion ligands for real protein chains.

PMID:39873344 | DOI:10.1049/syb2.70001

J Biophotonics. 2025 Jan 28:e202400557. doi: 10.1002/jbio.202400557. Online ahead of print.

ABSTRACT

Liver malignancies, particularly hepatocellular carcinoma (HCC), pose a formidable global health challenge. Conventional diagnostic techniques frequently fall short in precision, especially at advanced HCC stages. In response, we have developed a novel diagnostic strategy that integrates hyperspectral imaging with deep learning. This innovative approach captures detailed spectral data from tissue samples, pinpointing subtle cellular differences that elude traditional methods. A sophisticated deep convolutional neural network processes this data, effectively distinguishing high-grade liver cancer from cirrhosis with an accuracy of 89.45%, a sensitivity of 90.29%, and a specificity of 88.64%. For HCC differentiation specifically, it achieves an impressive accuracy of 93.73%, sensitivity of 92.53%, and specificity of 90.07%. Our results underscore the potential of this technique as a precise, rapid, and non-invasive diagnostic tool that surpasses existing clinical methods in staging liver cancer and differentiating cirrhosis.

PMID:39873135 | DOI:10.1002/jbio.202400557