RESUMO
Cataracts are a leading cause of blindness worldwide, making accurate diagnosis and effective surgical planning critical. However, grading the severity of the lens nucleus is challenging because deep learning (DL) models pretrained using ImageNet perform poorly when applied directly to medical data due to the limited availability of labeled medical images and high interclass similarity. Self-supervised pretraining offers a solution by circumventing the need for cost-intensive data annotations and bridging domain disparities. In this study, to address the challenges of intelligent grading, we proposed a hybrid model called nuclear cataract mask encoder network (NCME-Net), which utilizes self-supervised pretraining for the four-class analysis of nuclear cataract severity. A total of 792 images of nuclear cataracts were categorized into the training set (533 images), the validation set (139 images), and the test set (100 images). NCME-Net achieved a diagnostic accuracy of 91.0 % on the test set, a 5.0 % improvement over the best-performing DL model (ResNet50). Experimental results demonstrate NCME-Net's ability to distinguish between cataract severities, particularly in scenarios with limited samples, making it a valuable tool for intelligently diagnosing cataracts. In addition, the effect of different self-supervised tasks on the model's ability to capture the intrinsic structure of the data was studied. Findings indicate that image restoration tasks significantly enhance semantic information extraction.
RESUMO
In medical image segmentation, it is often necessary to collect opinions from multiple experts to make the final decision. This clinical routine helps to mitigate individual bias. However, when data is annotated by multiple experts, standard deep learning models are often not applicable. In this paper, we propose a novel neural network framework called Multi-rater Prism (MrPrism) to learn medical image segmentation from multiple labels. Inspired by iterative half-quadratic optimization, MrPrism combines the task of assigning multi-rater confidences and calibrated segmentation in a recurrent manner. During this process, MrPrism learns inter-observer variability while taking into account the image's semantic properties and finally converges to a self-calibrated segmentation result reflecting inter-observer agreement. Specifically, we propose Converging Prism (ConP) and Diverging Prism (DivP) to iteratively process the two tasks. ConP learns calibrated segmentation based on multi-rater confidence maps estimated by DivP, and DivP generates multi-rater confidence maps based on segmentation masks estimated by ConP. Experimental results show that the two tasks can mutually improve each other through this recurrent process. The final converged segmentation result of MrPrism outperforms state-of-the-art (SOTA) methods for a wide range of medical image segmentation tasks. The code is available at https://github.com/WuJunde/MrPrism.
RESUMO
AIM: To address the challenges of data labeling difficulties, data privacy, and necessary large amount of labeled data for deep learning methods in diabetic retinopathy (DR) identification, the aim of this study is to develop a source-free domain adaptation (SFDA) method for efficient and effective DR identification from unlabeled data. METHODS: A multi-SFDA method was proposed for DR identification. This method integrates multiple source models, which are trained from the same source domain, to generate synthetic pseudo labels for the unlabeled target domain. Besides, a softmax-consistence minimization term is utilized to minimize the intra-class distances between the source and target domains and maximize the inter-class distances. Validation is performed using three color fundus photograph datasets (APTOS2019, DDR, and EyePACS). RESULTS: The proposed model was evaluated and provided promising results with respectively 0.8917 and 0.9795 F1-scores on referable and normal/abnormal DR identification tasks. It demonstrated effective DR identification through minimizing intra-class distances and maximizing inter-class distances between source and target domains. CONCLUSION: The multi-SFDA method provides an effective approach to overcome the challenges in DR identification. The method not only addresses difficulties in data labeling and privacy issues, but also reduces the need for large amounts of labeled data required by deep learning methods, making it a practical tool for early detection and preservation of vision in diabetic patients.
RESUMO
BACKGROUND: Virtual reality (VR), widely used in the medical field, may affect future medical training and treatment. Therefore, this study examined VR's potential uses and research directions in medicine. METHODS: Citation data were downloaded from the Web of Science Core Collection database (WoSCC) to evaluate VR in medicine in articles published between 1 January 2012 and 31 December 2023. These data were analyzed using CiteSpace 6.2. R2 software. Present limitations and future opportunities were summarized based on the data. RESULTS: A total of 2143 related publications from 86 countries and regions were analyzed. The country with the highest number of publications is the USA, with 461 articles. The University of London has the most publications among institutions, with 43 articles. The burst keywords represent the research frontier from 2020 to 2023, such as "task analysis", "deep learning", and "machine learning". CONCLUSION: The number of publications on VR applications in the medical field has been steadily increasing year by year. The USA is the leading country in this area, while the University of London stands out as the most published, and most influential institution. Currently, there is a strong focus on integrating VR and AI to address complex issues such as medical education and training, rehabilitation, and surgical navigation. Looking ahead, the future trend involves integrating VR, augmented reality (AR), and mixed reality (MR) with the Internet of Things (IoT), wireless sensor networks (WSNs), big data analysis (BDA), and cloud computing (CC) technologies to develop intelligent healthcare systems within hospitals or medical centers.
RESUMO
Background: Despite reports suggesting a link between obesity and keratoconus, the causal relationship is not fully understood. Methods: We used genome-wide association study (GWAS) data from public databases for a two-sample Mendelian randomization analysis to investigate the causal link between body mass index (BMI) and keratoconus. The primary method was inverse variance weighted (IVW), complemented by different analytical techniques and sensitivity analyses to ensure result robustness. A meta-analysis was also performed to bolster the findings' reliability. Results: Our study identified a significant causal relationship between BMI and keratoconus. Out of 20 Mendelian randomization (MR) analyses conducted, 9 showed heterogeneity or pleiotropy. Among the 11 analyses that met all three MR assumptions, 4 demonstrated a significant causal difference between BMI and keratoconus, while the remaining 7 showed a positive trend but were not statistically significant. Meta-analysis confirmed a significant causal relationship between BMI and keratoconus. Conclusion: There is a significant causal relationship between BMI and keratoconus, suggesting that obesity may be a risk factor for keratoconus.
RESUMO
The clinical efficacy of adrenergic ß-receptor (ß-AR) blockers in significantly stabilizing atherosclerotic plaques has been extensively supported by evidence-based medical research; however, the underlying mechanism remains unclear. Recent findings have highlighted the impact of lipid-induced aberrant polarization of macrophages during normal inflammatory-repair and regenerative processes on atherosclerosis formation and progression. In this review, we explore the relationship between macrophage polarization and atherosclerosis, as well as the influence of ß-AR blockers on macrophage polarization. Based on the robust evidence supporting the use of ß-AR blockers for treating atherosclerosis, we propose that their main mechanism involves inhibiting monocyte-derived macrophage differentiation towards an M2-like phenotype.
RESUMO
We conducted a proof-of-concept, phase 2 trial to assess neoadjuvant SHR-1701 with or without chemotherapy, followed by surgery or radiotherapy, and then consolidation SHR-1701 in unresectable stage III non-small-cell lung cancer (NSCLC). In the primary cohort of patients receiving neoadjuvant combination therapy (n = 97), both primary endpoints were met, with a post-induction objective response rate of 58% (95% confidence interval [CI] 47-68) and an 18-month event-free survival (EFS) rate of 56.6% (95% CI 45.2-66.5). Overall, 27 (25%) patients underwent surgery; all achieved R0 resection. Among them, 12 (44%) major pathological responses and seven (26%) pathological complete responses were recorded. The 18-month EFS rate was 74.1% (95% CI 53.2-86.7) in surgical patients and 57.3% (43.0-69.3) in radiotherapy-treated patients. Neoadjuvant SHR-1701 with chemotherapy, followed by surgery or radiotherapy, showed promising efficacy with a tolerable safety profile in unresectable stage III NSCLC. Surgical conversion was feasible in a notable proportion of patients and associated with better survival outcomes.
Assuntos
Carcinoma Pulmonar de Células não Pequenas , Neoplasias Pulmonares , Terapia Neoadjuvante , Estadiamento de Neoplasias , Estudo de Prova de Conceito , Humanos , Carcinoma Pulmonar de Células não Pequenas/tratamento farmacológico , Carcinoma Pulmonar de Células não Pequenas/patologia , Carcinoma Pulmonar de Células não Pequenas/mortalidade , Carcinoma Pulmonar de Células não Pequenas/terapia , Neoplasias Pulmonares/patologia , Neoplasias Pulmonares/tratamento farmacológico , Neoplasias Pulmonares/terapia , Neoplasias Pulmonares/mortalidade , Feminino , Terapia Neoadjuvante/métodos , Pessoa de Meia-Idade , Masculino , Idoso , Adulto , Protocolos de Quimioterapia Combinada Antineoplásica/uso terapêutico , Anticorpos Monoclonais , Proteínas Recombinantes de FusãoRESUMO
Background: Ophthalmopathy occurring in childhood can easily lead to irreversible visual impairment, and therefore a great deal of clinical and fundamental researches have been conducted in pediatric ophthalmopathy. However, a few studies have been performed to analyze such large amounts of research using bibliometric methods. This study intended to apply bibliometric methods to analyze the research hotspots and trends in pediatric ophthalmopathy, providing a basis for clinical practice and scientific research to improve children's eye health. Methods: Publications related to pediatric ophthalmopathy were searched and identified in the Web of Science Core Collection (WoSCC) database. Bibliometric and visualized analysis was performed using the WoSCC analysis system and CiteSpace.6.2.6 software, and high-impact publications were analyzed. Results: This study included a total of 7,177 publications from 162 countries and regions. Of these, 2,269 from the United States and 1,298 from China. The centrality and H-index were highest in the United States at 0.27 and 66, respectively. The University of London and Harvard University had the highest H-index at 37. Freedman,Sharon F published 55 publications, with the highest H-index at 19. The emerging burst keyword in 2020-2023 was "eye tracking," and the burst keywords in 2021-2023 were "choroidal thickness," "pediatric ophthalmology," "impact" and "childhood glaucoma." Retinopathy of prematurity, myopia, retinoblastoma and uveitis in juvenile idiopathic arthritis were the main topics in the high-impact publications, with clinical studies in the majority, especially in retinopathy of prematurity. Conclusion: Eye health in children is a research hotspot, with the United States publishing the largest number of papers and having the greatest influence in research on pediatric ophthalmopathy, and China coming in second. The University of London and Stanford University had the greatest influence. Freedman, Sharon F was the most influential author. Furthermore, "choroidal thickness," "pediatric ophthalmology," "impact," "childhood glaucoma" and "eye tracking"are the latest hotspots in the field of pediatric ophthalmopathy. These hotspots represent hot diseases, hot technologies and holistic concepts, which are exactly the research trends in the field of pediatric ophthalmopathy, providing guidance and grounds for clinical practice and scientific research on children's eye health.
RESUMO
AIM: To figure out whether various atropine dosages may slow the progression of myopia in Chinese kids and teenagers and to determine the optimal atropine concentration for effectively slowing the progression of myopia. METHODS: A systematic search was conducted across the Cochrane Library, PubMed, Web of Science, EMBASE, CNKI, CBM, VIP, and Wanfang database, encompassing literature on slowing progression of myopia with varying atropine concentrations from database inception to January 17, 2024. Data extraction and quality assessment were performed, and a network Meta-analysis was executed using Stata version 14.0 Software. Results were visually represented through graphs. RESULTS: Fourteen papers comprising 2475 cases were included; five different concentrations of atropine solution were used. The network Meta-analysis, along with the surface under the cumulative ranking curve (SUCRA), showed that 1% atropine (100%)>0.05% atropine (74.9%) >0.025% atropine (51.6%)>0.02% atropine (47.9%)>0.01% atropine (25.6%)>control in refraction change and 1% atropine (98.7%)>0.05% atropine (70.4%)>0.02% atropine (61.4%)>0.025% atropine (42%)>0.01% atropine (27.4%)>control in axial length (AL) change. CONCLUSION: In Chinese children and teenagers, the five various concentrations of atropine can reduce the progression of myopia. Although the network Meta-analysis showed that 1% atropine is the best one for controlling refraction and AL change, there is a high incidence of adverse effects with the use of 1% atropine. Therefore, we suggest that 0.05% atropine is optimal for Chinese children to slow myopia progression.
RESUMO
The chemical and physical properties of nanomaterials ultimately rely on their crystal structures, chemical compositions and distributions. In this paper, a series of AuCu bimetallic nanoparticles with well-defined architectures and variable compositions has been addressed to explore their thermal stability and thermally driven behavior by molecular dynamics simulations. By combination of energy and Lindemann criteria, the solid-liquid transition and its critical temperature were accurately identified. Meanwhile, atomic diffusion, bond order, and particle morphology were examined to shed light on thermodynamic evolution of the particles. Our results reveal that composition-dependent melting point of AuCu nanoparticles significantly departs from the Vegard's law prediction. Especially, chemically disordered (ordered) alloy nanoparticles exhibited markedly low (high) melting points in comparison with their unary counterparts, which should be attributed to enhancing (decreasing) atomic diffusivity in alloys. Furthermore, core-shell structures and heterostructures demonstrated a mode transition between the ordinary melting and the two-stage melting with varying Au content. AuCu alloyed nanoparticles presented the evolution tendency of chemical ordering from disorder to order before melting and then to disorder during melting. Additionally, as the temperature increases, the shape transformation was observed in AuCu nanoparticles with heterostructure or L10 structure owing to the difference in thermal expansion coefficients of elements and/or of crystalline orientations. Our findings advance the fundamental understanding on thermodynamic behavior and stability of metallic nanoparticles, offering theoretical insights for design and application of nanosized particles with tunable properties.
RESUMO
AIM: To gain insights into the global research hotspots and trends of myopia. METHODS: Articles were downloaded from January 1, 2013 to December 31, 2022 from the Science Core Database website and were mainly statistically analyzed by bibliometrics software. RESULTS: A total of 444 institutions in 87 countries published 4124 articles. Between 2013 and 2022, China had the highest number of publications (n=1865) and the highest H-index (61). Sun Yat-sen University had the highest number of publications (n=229) and the highest H-index (33). Ophthalmology is the main category in related journals. Citations from 2020 to 2022 highlight keywords of options and reference, child health (pediatrics), myopic traction mechanism, public health, and machine learning, which represent research frontiers. CONCLUSION: Myopia has become a hot research field. China and Chinese institutions have the strongest academic influence in the field from 2013 to 2022. The main driver of myopic research is still medical or ophthalmologists. This study highlights the importance of public health in addressing the global rise in myopia, especially its impact on children's health. At present, a unified theoretical system is still needed. Accurate surgical and therapeutic solutions must be proposed for people with different characteristics to manage and intervene refractive errors. In addition, the benefits of artificial intelligence (AI) models are also reflected in disease monitoring and prediction.
RESUMO
Thyroid-associated ophthalmopathy (TAO), also referred to as Graves' ophthalmopathy, is a medical condition wherein ocular complications arise due to autoimmune thyroid illness. The diagnosis of TAO, reliant on imaging, typical ocular symptoms, and abnormalities in thyroid function or thyroid-associated antibodies, is generally graded and staged. In recent years, Artificial intelligence(AI), particularly deep learning(DL) technology, has gained widespread use in the diagnosis and treatment of ophthalmic diseases. This paper presents a discussion on specific studies involving AI, specifically DL, in the context of TAO, highlighting their applications in TAO diagnosis, staging, grading, and treatment decisions. Additionally, it addresses certain limitations in AI research on TAO and potential future directions for the field.
Assuntos
Inteligência Artificial , Oftalmopatia de Graves , Humanos , Oftalmopatia de Graves/diagnóstico , Oftalmopatia de Graves/terapia , Aprendizado ProfundoRESUMO
Aim: Conventional approaches to diagnosing common eye diseases using B-mode ultrasonography are labor-intensive and time-consuming, must requiring expert intervention for accuracy. This study aims to address these challenges by proposing an intelligence-assisted analysis five-classification model for diagnosing common eye diseases using B-mode ultrasound images. Methods: This research utilizes 2064 B-mode ultrasound images of the eye to train a novel model integrating artificial intelligence technology. Results: The ConvNeXt-L model achieved outstanding performance with an accuracy rate of 84.3% and a Kappa value of 80.3%. Across five classifications (no obvious abnormality, vitreous opacity, posterior vitreous detachment, retinal detachment, and choroidal detachment), the model demonstrated sensitivity values of 93.2%, 67.6%, 86.1%, 89.4%, and 81.4%, respectively, and specificity values ranging from 94.6% to 98.1%. F1 scores ranged from 71% to 92%, while AUC values ranged from 89.7% to 97.8%. Conclusion: Among various models compared, the ConvNeXt-L model exhibited superior performance. It effectively categorizes and visualizes pathological changes, providing essential assisted information for ophthalmologists and enhancing diagnostic accuracy and efficiency.
RESUMO
This study aimed to investigate altered static and dynamic functional network connectivity (FNC) and its correlation with clinical symptoms in patients with knee osteoarthritis (KOA). One hundred and fifty-nine patients with KOA and 73 age- and gender-matched healthy subjects (HS) underwent resting-state functional magnetic resonance imaging (rs-fMRI) and clinical evaluations. Group independent component analysis (GICA) was applied, and seven resting-state networks were identified. Patients with KOA had decreased static FNC within the default mode network (DM), visual network (VS), and cerebellar network (CB) and increased static FNC between the subcortical network (SC) and VS (p < 0.05, FDR corrected). Four reoccurring FNC states were identified using k-means clustering analysis. Although abnormalities in dynamic FNCs of KOA patients have been found using the common window size (22 TR, 44 s), but the results of the clustering analysis were inconsistent when using different window sizes, suggesting dynamic FNCs might be an unstable method to compare brain function between KOA patients and HS. These recent findings illustrate that patients with KOA have a wide range of abnormalities in the static and dynamic FNCs, which provided a reference for the identification of potential central nervous therapeutic targets for KOA treatment and might shed light on the other musculoskeletal pain neuroimaging studies.
Assuntos
Encéfalo , Imageamento por Ressonância Magnética , Rede Nervosa , Osteoartrite do Joelho , Humanos , Imageamento por Ressonância Magnética/métodos , Feminino , Masculino , Osteoartrite do Joelho/diagnóstico por imagem , Osteoartrite do Joelho/fisiopatologia , Pessoa de Meia-Idade , Rede Nervosa/diagnóstico por imagem , Rede Nervosa/fisiopatologia , Idoso , Encéfalo/diagnóstico por imagem , Encéfalo/fisiopatologia , Adulto , Conectoma/métodos , Descanso , Mapeamento Encefálico/métodosRESUMO
Many of the tissues/lesions in the medical images may be ambiguous. Therefore, medical segmentation is typically annotated by a group of clinical experts to mitigate personal bias. A common solution to fuse different annotations is the majority vote, e.g., taking the average of multiple labels. However, such a strategy ignores the difference between the grader expertness. Inspired by the observation that medical image segmentation is usually used to assist the disease diagnosis in clinical practice, we propose the diagnosis-first principle, which is to take disease diagnosis as the criterion to calibrate the inter-observer segmentation uncertainty. Following this idea, a framework named Diagnosis-First segmentation Framework (DiFF) is proposed. Specifically, DiFF will first learn to fuse the multi-rater segmentation labels to a single ground-truth which could maximize the disease diagnosis performance. We dubbed the fused ground-truth as Diagnosis-First Ground-truth (DF-GT). Then, the Take and Give Model (T&G Model) to segment DF-GT from the raw image is proposed. With the T&G Model, DiFF can learn the segmentation with the calibrated uncertainty that facilitate the disease diagnosis. We verify the effectiveness of DiFF on three different medical segmentation tasks: optic-disc/optic-cup (OD/OC) segmentation on fundus images, thyroid nodule segmentation on ultrasound images, and skin lesion segmentation on dermoscopic images. Experimental results show that the proposed DiFF can effectively calibrate the segmentation uncertainty, and thus significantly facilitate the corresponding disease diagnosis, which outperforms previous state-of-the-art multi-rater learning methods.
RESUMO
Background: Thyroid-associated ophthalmopathy (TAO) is the most prevalent autoimmune orbital condition, significantly impacting patients' appearance and quality of life. Early and accurate identification of active TAO along with timely treatment can enhance prognosis and reduce the occurrence of severe cases. Although the Clinical Activity Score (CAS) serves as an effective assessment system for TAO, it is susceptible to assessor experience bias. This study aimed to develop an ensemble deep learning system that combines anterior segment slit-lamp photographs of patients with facial images to simulate expert assessment of TAO. Method: The study included 156 patients with TAO who underwent detailed diagnosis and treatment at Shanxi Eye Hospital Affiliated to Shanxi Medical University from May 2020 to September 2023. Anterior segment slit-lamp photographs and facial images were used as different modalities and analyzed from multiple perspectives. Two ophthalmologists with more than 10 years of clinical experience independently determined the reference CAS for each image. An ensemble deep learning model based on the residual network was constructed under supervised learning to predict five key inflammatory signs (redness of the eyelids and conjunctiva, and swelling of the eyelids, conjunctiva, and caruncle or plica) associated with TAO, and to integrate these objective signs with two subjective symptoms (spontaneous retrobulbar pain and pain on attempted upward or downward gaze) in order to assess TAO activity. Results: The proposed model achieved 0.906 accuracy, 0.833 specificity, 0.906 precision, 0.906 recall, and 0.906 F1-score in active TAO diagnosis, demonstrating advanced performance in predicting CAS and TAO activity signs compared to conventional single-view unimodal approaches. The integration of multiple views and modalities, encompassing both anterior segment slit-lamp photographs and facial images, significantly improved the prediction accuracy of the model for TAO activity and CAS. Conclusion: The ensemble multi-view multimodal deep learning system developed in this study can more accurately assess the clinical activity of TAO than traditional methods that solely rely on facial images. This innovative approach is intended to enhance the efficiency of TAO activity assessment, providing a novel means for its comprehensive, early, and precise evaluation.
Assuntos
Aprendizado Profundo , Oftalmopatia de Graves , Humanos , Oftalmopatia de Graves/diagnóstico por imagem , Qualidade de Vida , Órbita , DorRESUMO
Retinal blood vessels are the only directly observed blood vessels in the body; changes in them can help effective assess the occurrence and development of ocular and systemic diseases. The specificity and efficiency of retinal vessel quantification technology has improved with the advancement of retinal imaging technologies and artificial intelligence (AI) algorithms; it has garnered attention in clinical research and applications for the diagnosis and treatment of common eye and related systemic diseases. A few articles have reviewed this topic; however, a summary of recent research progress in the field is still needed. This article aimed to provide a comprehensive review of the research and applications of retinal vessel quantification technology in ocular and systemic diseases, which could update clinicians and researchers on the recent progress in this field.
RESUMO
BACKGROUND AND OBJECTIVE: The prevalence of myopia and high myopia is increasing globally, underscoring the growing importance of diagnosing high myopia-related pathologies. While existing image segmentation models, such as U-Net, UNet++, ResU-Net, and TransUNet, have achieved significant success in medical image segmentation, they still face challenges when dealing with ultra-widefield (UWF) fundus images. This study introduces a novel automatic segmentation algorithm for the optic disc and peripapillary atrophy (PPA) based on UWF fundus images, aimed at assisting ophthalmologists in more accurately diagnosing high myopia-related diseases. METHODS: In this study, we developed a segmentation model leveraging a Transformer-based network structure, complemented by atrous convolution and selective boundary aggregation modules, to elevate the accuracy of segmenting the optic disc and PPA in UWF photography. The atrous convolution module adeptly manages multi-scale features, catering to the variances in target sizes and expanding the deep network's receptive field. Concurrently, the incorporation of the selective boundary aggregation module in the skip connections of the model significantly improves the differentiation of boundary information between segmentation targets. Moreover, the comparison of our proposed algorithm with classical segmentation models like U-Net, UNet++, ResU-Net, and TransUNet highlights its considerable advantages in processing UWF photographs. RESULTS: The experimental results show that, compared to the other four models, our algorithm demonstrates substantial improvements in segmenting the optic disc and PPA in UWF photographs. In PPA segmentation, our algorithm improves by 0.8% in Dice, 1.8% in sensitivity, and 1.3% in intersection over union (IOU). In optic disc segmentation, our algorithm improves by 0.3% in Dice, 0.6% in precision, and 0.4% in IOU. CONCLUSION: Our proposed method improves the segmentation accuracy of PPA and optic disks based on UWF photographs, which is valuable for diagnosing high myopia-related diseases in ophthalmology clinics.
Assuntos
Miopia , Disco Óptico , Humanos , Disco Óptico/diagnóstico por imagem , Disco Óptico/patologia , Fundo de Olho , Algoritmos , Miopia/diagnóstico , Miopia/patologia , Atrofia/patologia , Processamento de Imagem Assistida por ComputadorRESUMO
Objective: This study aimed to evaluate the value of 18F-FDG PET/CT radiomics in predicting EGFR gene mutations in non-small cell lung cancer by meta-analysis. Methods: The PubMed, Embase, Cochrane Library, Web of Science, and CNKI databases were searched from the earliest available date to June 30, 2023. The meta-analysis was performed using the Stata 15.0 software. The methodological quality and risk of bias of included studies were assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 and Radiomics Quality Score criteria. The possible causes of heterogeneity were analyzed by meta-regression. Results: A total of 17 studies involving 3763 non-small cell lung cancer patients were finally included. We analyzed 17 training cohorts and 10 validation cohorts independently. Within the training cohort, the application of 18F-FDG PET/CT radiomics in predicting EGFR mutations in NSCLC demonstrated a sensitivity of 0.76 (95% CI: 0.70-0.81) and a specificity of 0.78 (95% CI: 0.74-0.82), accompanied by a positive likelihood ratio of 3.5 (95% CI:3.0-4.2), a negative likelihood ratio of 0.31 (95% CI: 0.24-0.39), a diagnostic odds ratio of 11.0 (95% CI: 8.0-16.0), and an area under the curve (AUC) of 0.84 (95% CI: 0.80-0.87). In the validation cohort, the values included a sensitivity of 0.76 (95% CI: 0.67-0.83), a specificity of 0.75 (95% CI: 0.68-0.80), a positive likelihood ratio of 3.0 (95% CI:2.4-3.8), a negative likelihood ratio of 0.32 (95% CI: 0.24-0.44), a diagnostic odds ratio of 9 (95% CI: 6-15), and an AUC of 0.82 (95% CI: 0.78-0.85). The average Radiomics Quality Score (RQS) across studies was 10.47 ± 4.72. Meta-regression analysis identifies the application of deep learning and regions as sources of heterogeneity. Conclusion: 18F-FDG PET/CT radiomics may be useful in predicting mutation status of the EGFR gene in non-small cell lung cancer. Systematic review registration: https://www.crd.york.ac.uk/PROSPERO, identifier CRD42022385364.
RESUMO
INTRODUCTION: Iruplinalkib (WX-0593) is a new-generation, potent ALK tyrosine kinase inhibitor (TKI) that has been found to have systemic and central nervous system (CNS) efficacy in ALK-positive NSCLC. We compared the efficacy and safety of iruplinalkib with crizotinib in patients with ALK TKI-naive, locally advanced or metastatic ALK-positive NSCLC. METHODS: In this open-label, randomized, multicenter, phase 3 study, patients with ALK-positive NSCLC were randomly assigned to receive iruplinalkib 180 mg once daily (7-d run-in at 60 mg once daily) or crizotinib 250 mg twice daily. The primary end point was progression-free survival (PFS) assessed by Independent Review Committee (IRC) per Response Evaluation Criteria in Solid Tumors version 1.1. Secondary end points included PFS by investigator, objective response rate (ORR), time to response, duration of response, intracranial ORR and time to CNS progression by IRC and investigator, overall survival, and safety. An interim analysis was planned after approximately 70% (134 events) of all 192 expected PFS events assessed by IRC were observed. Efficacy was analyzed in the intention-to-treat population. Safety was assessed in the safety population, which included all randomized patients who received at least one dose of the study drugs. This study is registered with Center for Drug Evaluation of China National Medical Products Administration (CTR20191231) and Clinicaltrials.gov (NCT04632758). RESULTS: From September 4, 2019, to December 2, 2020, a total of 292 patients were randomized and treated; 143 with iruplinalkib and 149 with crizotinib. At this interim analysis (145 events), the median follow-up time was 26.7 months (range: 3.7-37.7) in the iruplinalkib group and 25.9 months (range: 0.5-35.9) in the crizotinib group. The PFS assessed by IRC was significantly longer among patients in the iruplinalkib group (median PFS, 27.7 mo [95% confidence interval (CI): 26.3-not estimable] versus 14.6 mo [95% CI: 11.1-16.5] in the crizotinib group; hazard ratio, 0.34 [98.02% CI: 0.23-0.52], p < 0.0001). The ORR assessed by IRC was 93.0% (95% CI: 87.5-96.6) in the iruplinalkib group and 89.3% (95% CI: 83.1-93.7) in the crizotinib group. The intracranial ORR was 90.9% (10 of 11, 95% CI: 58.7-99.8) in the iruplinalkib group and 60.0% (nine of 15, 95% CI: 32.3-83.7) in the crizotinib group for patients with measurable baseline CNS metastases. Incidence of grade 3 or 4 treatment-related adverse events was 51.7% in the iruplinalkib group and 49.7% in the crizotinib group. CONCLUSIONS: Iruplinalkib was found to have significantly improved PFS and improved intracranial antitumor activity versus crizotinib. Iruplinalkib may be a new treatment option for patients with advanced ALK-positive and ALK TKI-naive NSCLC. FUNDING: This study was funded by Qilu Pharmaceutical Co., Ltd., Jinan, People's Republic of China, and partly supported by the National Science and Technology Major Project for Key New Drug Development (2017ZX09304015).