Diagnosis Of Cancer Research Articles

Advancing cancer diagnosis and prognostication through deep learning mastery in breast, colon, and lung histopathology with ResoMergeNet

Cancer, a global health threat, demands effective diagnostic solutions to combat its impact on public health, particularly for breast, colon, and lung cancers. Early and accurate diagnosis is essential for successful treatment, prompting the rise of Computer-Aided Diagnosis Systems as reliable and cost-effective tools. Histopathology, renowned for its precision in cancer imaging, has become pivotal in the diagnostic landscape of breast, colon, and lung cancers. However, while deep learning models have been widely explored in this domain, they often face challenges in generalizing to diverse clinical settings and in efficiently capturing both local and global feature representations, particularly for multi-class tasks. This underscores the need for models that can reduce biases, improve diagnostic accuracy, and minimize error susceptibility in cancer classification tasks. To this end, we introduce ResoMergeNet (RMN), an advanced deep-learning model designed for both multi-class and binary cancer classification using histopathological images of breast, colon, and lung. ResoMergeNet integrates the Resboost mechanism which enhances feature representation, and the ConvmergeNet mechanism which optimizes feature extraction, leading to improved diagnostic accuracy. Comparative evaluations against state-of-the-art models show ResoMergeNet’s superior performance. Validated on the LC-25000 and BreakHis (400× and 40× magnifications) datasets, ResoMergeNet demonstrates outstanding performance, achieving perfect scores of 100 % in accuracy, sensitivity, precision, and F1 score for binary classification. For multi-class classification with five classes from the LC25000 dataset, it maintains an impressive 99.96 % across all performance metrics. When applied to the BreakHis dataset, ResoMergeNet achieved 99.87 % accuracy, 99.75 % sensitivity, 99.78 % precision, and 99.77 % F1 score at 400× magnification. At 40× magnification, it still delivered robust results with 98.85 % accuracy, sensitivity, precision, and F1 score. These results emphasize the efficacy of ResoMergeNet, marking a substantial advancement in diagnostic and prognostic systems for breast, colon, and lung cancers. ResoMergeNet’s superior diagnostic accuracy can significantly reduce diagnostic errors, minimize human biases, and expedite clinical workflows, making it a valuable tool for enhancing cancer diagnosis and treatment outcomes.

Interfacial cfDNA Enrichment and Amplification with On-Chip Thermoplasmonics for Highly Sensitive Cancerous Liquid Biopsy.

Tumor-derived cell-free DNA (cfDNA) has been exploited as an effective liquid biopsy biomarker for early cancer diagnosis. However, the fragmented and low-abundance nature in circulating blood pose challenges for highly sensitive cfDNA quantification. Herein, a multifunctional plasmonic biosensor termed Interfacial cfDNA Enrichment, Amplification and Sensing with on-chip Thermoplasmonics (INEAST) is developed for cfDNA-based liquid biopsy and lung cancer diagnosis. The INEAST biosensor achieved in situ thermoregulation and label-free cfDNA biosensing by simultaneously harnessing interfacial thermoplasmonics and localized surface plasmon resonance. Typical cfDNA biomarkers, including epidermal growth factor receptor (EGFR), tumor protein 53 (TP53), phosphatase and tensin homologue deleted on chromosome 10 (PTEN), and cyclin-dependent kinase inhibitor (CDKN2A), are quantified with detection limits down to femtomolar-level. Through further validation using blood samples from lung cancer patients, the proposed INEAST bioassays demonstrated superior reliability for lung cancer screening, particularly when combined with clinically available tumor-protein metrics. This study demonstrated that the INEAST biosensor enables rapid and sensitive cfDNA quantification, yielding a promising and compatible liquid biopsy for early-stage lung cancer diagnosis.

A Novel Approach to Diagnosis: Using Convolutional Neural Networks to Classify Non-Small Cell Lung Cancers on CT Scans

Background: Lung cancer is the leading cause of cancer-related deaths around the world, making early detection vital to treatment and survival. However, lung cancer has variable clinical presentations, so diagnosis, even by trained medical professionals, is challenging and time- consuming. Deep Learning (DL) has proven effective in training big data to generate accurate diagnoses through classification in a timely manner. Aim and Objective: This study uses data augmentation and hyperparameter optimization methods on convolutional neural networks (CNN) to understand the benefits of various architectures in addition to creating an accurate transfer-based tool for lung cancer diagnosis on CT scans. Materials and Methods: We found a dataset composed of chest CT images of patients with non-small cell lung cancers (NSCLC) categorized into adenocarcinoma, large cell carcinoma, and squamous cell carcinoma and a control group of normal chest CT scans. We tested the CNN architectures VGG16, InceptionV3, ResNet50, and EfficientNetB0 for feature extraction and observed each model on a variety of different metrics such as validation accuracy, statistical errors, and learning rate. Each model was trained on the prechosen data set 2 times at 6 and 12 epochs and several evaluation metrics were recorded. Observation and Results: EfficientNetB0, ResNet50, VGG16, InceptionV3 achieved test accuracies of 98.92%, 91.40%, 77.42%, 70.97% respectively when implemented with hyperparameter tuning and dropout layers. EfficientNetB0 also exceeded the other architectures in metrics such as precision, recall, and F1-score. Conclusion: Convolutional neural networks using EfficientNetB0 yielded a higher accuracy in diagnosis of non-small cell cancer on CT scan which encourages further research in developing robust diagnostic tools using DL to expedite diagnosis, especially in locations with inadequate healthcare resources.

Consensus statement on chronic pain treatment in cancer survivors.

In September 2023, the Japanese Society for Palliative Medicine (JSPM) issued this consensus statement on chronic pain treatment in cancer survivors. With recent advances in the early diagnosis and treatment of cancer, its prognosis has improved, so prolonged pain in cancer survivors is considered to represent chronic pain and should be addressed. In this statement, we emphasize that not all cancer survivor pain is cancer pain. Pain that is not cancer pain should be managed with analgesics other than opioids and nerve blocks, and pain that persists despite this approach should be treated as non-cancer chronic pain so as to prevent opioid overuse. In addition, cancer survivors at any stage of disease have a potentially life-threatening condition and constantly carry the fear of cancer recurrence. Therefore, even non-cancer pain should not be treated in the same way as general chronic pain, but should be managed with consideration of emotional distress. In the future, we plan to create educational tools for healthcare professionals and to conduct online seminars, both with the goal of providing cancer survivors with appropriate assessment and treatment of chronic pain.

A Pilot Study of PSMA PET/CT and MRI Fusion for Prostate Cancer: Software to Replace PET/MRI Hardware.

Introduction: Prostate-specific membrane antigen positron emission tomography/computed tomography (PSMA PET/CT), in combination with magnetic resonance imaging (MRI), may enhance the diagnosis and staging of prostate cancer. Image fusion of separately acquired PET/CT and MRI images serve to facilitate clinical integration and treatment planning. This study aimed to investigate different PSMA PET/CT and MRI image fusion workflows for prostate cancer visualisation. Methods: Eighteen patients with prostate cancer who underwent PSMA PET/CT and MRI prior to radical prostatectomy were retrospectively selected. Alignment of the prostate was performed between PET/CT and MRI via three techniques: semi-automatic rigid, automatic rigid, and automatic non-rigid. Image fusion accuracy was evaluated through boundary and volume agreement, quantified by the Dice Similarity Coefficient (DSC), 95% Hausdorff Distance (HD), and Mean Surface Distance (MSD), with comparison against reconstructed histopathology slices. Results: Image fusion using all techniques resulted in clear lesion visualisation from PSMA PET/CT overlay and anatomical detail afforded by the MRI base and was consistent with histopathology tumour location. Image fusion accuracy was within the recommended range based on a DSC of 0.8-0.9. The automatic non-rigid registration method had the highest volume agreement (DSC: 0.96 ± <0.01) and boundary agreement (HD: 1.17 ± 0.35 mm) when compared to automatic rigid (DSC 0.88 ± 0.02, HD 3.18 ± 0.29 mm) and semi-automatic rigid (DSC 0.80 ± 0.06, HD 5.25 ± 1.68 mm). Conclusions: Image fusion of clinically obtained PET/CT and MRI is feasible and clinically acceptable for use in prostate cancer diagnosis and surgical management. While the best accuracy was observed with the automatic non-rigid technique, which requires further validation, image fusion with clinically accessible methods (semi-automatic rigid) may currently aid patient education, pre-operative planning, and intra-operative guidance.

Machine learning techniques for breast cancer diagnosis

In the last few years, machine learning techniques have been attracting even greater attention in the field of diagnostics, particularly when detecting breast cancer. Relevant studies dedicated to machine learning techniques in breast cancer diagnosis were analyzed in three areas: solving secondary problems that occur in modern-day breast cancer diagnostics, role in an intelligent assessment of the patient’s condition for preliminary diagnostic decisions, and capability to detect breast cancer risk factors. The results revealed that machine learning techniques applied in breast cancer diagnosis have great potential for improving diagnostic accuracy and efficiency and solving secondary problems. The medical literature analysis has determined the parameters that are used as input data in machine learning techniques. Furthermore, the collected information will be applied to create a parameter system for breast cancer diagnosis using machine learning techniques.

Deep learning-driven multi-omics sequential diagnosis with Hybrid-OmniSeq: Unraveling breast cancer complexity

Breast cancer results from an uncontrolled growth of breast tissue. Many methods of diagnosis are using multi-omics data to better understand the complexity of breast cancer. The new strategy laid out in this work, called “Hybrid-OmniSeq,” is a deep learning-based multi-omics data analysis technology that uses molecular subtypes of breast cancer gene to increase the precision and effectiveness of breast cancer diagnosis. For preprocessing, the BC-VM procedure is utilized, and for molecular subtype analysis, the BC-MSA procedure is utilized. The implementation of Deep Neural Network (DNN) technology in conjunction with Sequential Forward Floating Selection (SFFS) and Truncated Singular Value Decomposition (TSVD) entropy enable adaptive learning from multi-omics gene data. Five machine learning classifiers are used for classification purpose. Hybrid-OmniSeq uses a variety of machine learning classifiers in a thorough analytical process to achieve remarkable diagnostic accuracy. Deep Learning-based multi-omics sequential approach was evaluated using METABRIC RNA-seq data sets of intrinsic subtypes of breast cancer. According to test results, Logistic Regression (LR) had ER (Estrogen Receptor) status values of 94.51%, ER status values of 96.33%, and HER2 (Human Epidermal growth factor Receptor) status values of 92.3%; Random Forest (RF) had ER status values of 93.77%, ER status values of 95.23%, and HER2 status values of 93.4%. LR and RF increase the cancer detection accuracy for all subtypes when compared to alternative machine learning classifiers or the majority voting method, providing a comprehensive understanding of the underlying causes of breast cancer.

Copper- and Iron-Based Nanoflowers in Cancer Theranostics

In recent years, nanoscience and nanotechnology have gained prominence within materials science, offering new opportunities for cancer diagnosis and treatment. Advances in nanotechnology have allowed for the manipulation and size control of nanomaterials, leading to the development of a wide range of materials. The use of nanomaterials as chemical biology tools in cancer theranostics has been widely investigated, owing to their enhanced stability, biocompatibility, and improved cell permeability. These properties enable precise targeting while addressing the limitations of conventional cancer treatments. Nanoflowers, a specific class of nanomaterials, have recently attracted significant interest due to their promising properties for several biomedical applications. However, despite the growing attention toward nanoflowers, detailed reviews on the subject have been limited. This work focuses on two primary types of hybrid nanoflowers: iron- and copper-based ones. Within this article an overview of recent applications in cancer theranostics are thoroughly reviewed, while the synthesis processes for controlling morphology and size, underlying functions, and their characteristics and uses are also extensively explored, aiming to provide a guide for future developments in the field.

Fundamentals of dual-energy computed tomography and its emerging applications in bladder cancer

Nowadays, computed tomography urography and multiparametric magnetic resonance are the most often used imaging techniques in patients with bladder cancer; however, dual-energy computed tomography is making its way into the oncological field. This narrative review article aimed to show the fundamentals of dual-energy computed tomography by outlining its physical principles, techniques, protocols, and postprocessing images to help those who used this cutting-edge technology as the first approach to fully understand its emerging applications in the evaluation of bladder cancer, a field yet to be explored. In particular, we discuss the usefulness of dual-energy computed tomography by focusing on the main images obtained, such as the iodine map, comparing them to the images obtained with conventional computed tomography scans. Dual-energy computed tomography applications may be beneficial for bladder cancer diagnosis, staging, and treatment planning. Nevertheless, its application is limited to its availability in healthcare structures and the training of healthcare personnel who can perform and interpret the scans correctly.

Role CT imaging for Cancer Diagnosis by Determining Sensitivity and Specificity: 144 Cancer Cases in Tobruk, Libya

Role CT imaging for Cancer Diagnosis by Determining Sensitivity and Specificity: 144 Cancer Cases in Tobruk, Libya

Automated derivation of diagnostic criteria for lung cancer using natural language processing on electronic health records: a pilot study

BackgroundThe digitisation of healthcare records has generated vast amounts of unstructured data, presenting opportunities for improvements in disease diagnosis when clinical coding falls short, such as in the recording of patient symptoms. This study presents an approach using natural language processing to extract clinical concepts from free-text which are used to automatically form diagnostic criteria for lung cancer from unstructured secondary-care data.MethodsPatients aged 40 and above who underwent a chest x-ray (CXR) between 2016 and 2022 were included. ICD-10 and unstructured data were pulled from their electronic health records (EHRs) over the preceding 12 months to the CXR. The unstructured data were processed using named entity recognition to extract symptoms, which were mapped to SNOMED-CT codes. Subsumption of features up the SNOMED-CT hierarchy was used to mitigate against sparse features and a frequency-based criteria, combined with univariate logarithmic probabilities, was applied to select candidate features to take forward to the model development phase. A genetic algorithm was employed to identify the most discriminating features to form the diagnostic criteria.Results75002 patients were included, with 1012 lung cancer diagnoses made within 12 months of the CXR. The best-performing model achieved an AUROC of 0.72. Results showed that an existing ‘disorder of the lung’, such as pneumonia, and a ‘cough’ increased the probability of a lung cancer diagnosis. ‘Anomalies of great vessel’, ‘disorder of the retroperitoneal compartment’ and ‘context-dependent findings’, such as pain, statistically reduced the risk of lung cancer, making other diagnoses more likely. The performance of the developed model was compared to the existing cancer risk scores, demonstrating superior performance.ConclusionsThe proposed methods demonstrated success in leveraging unstructured secondary-care data to derive diagnostic criteria for lung cancer, outperforming existing risk tools. These advancements show potential for enhancing patient care and results. However, it is essential to tackle specific limitations by integrating primary care data to ensure a more thorough and unbiased development of diagnostic criteria. Moreover, the study highlights the importance of contextualising SNOMED-CT concepts into meaningful terminology that resonates with clinicians, facilitating a clearer and more tangible understanding of the criteria applied.

DIAGNOSIS OF PROSTATE CANCER WITH ENHANCED EFFICIENCY USING FINE-TUNED CNN AND TRANSFER LEARNING

Cancer is one of the high-risk diseases for humans. Prostate cases are the second most common disease in men after lung cancer, and early diagnosis is vital. Artificial intelligence technologies have begun to be used in the diagnosis of prostate cancer, and more effective and sensitive results have been obtained, preventing potential errors in human-centered methods. In this study, in order to increase the classification performance in the diagnosis of prostate cancer, transfer learning methods and fine-tuning processes, which have higher success and learning ability with less training data, unlike machine learning methods, were applied. The two-class data set consisting of prostate cancer MR images, ‘significant’ and ‘not-significant’, was classified with Alexnet, Densenet201, Googlenet, and Vgg16 models with the feature extraction approach, and 71.40%, 72.05%, 65%, and 80.13% accuracy results were obtained respectively. To increase these rates, pre-trained transfer learning models were used and accuracy results of 89.74%, 94.32%, 85.59%, and 91.05% were achieved, respectively. A 98.10% validation result was obtained using the cross-validation method in the Densenet201 model. DenseNet201 model achieved the highest accuracy result of 98.63% in transfer learning with the combination of the RMSProp optimization method. The proposed transfer learning model provided an improvement of approximately 26% compared to the feature extraction method.

Associations of Financial Toxicity with Employment Concerns and Cancer-Related Distress: A Cross-Sectional Survey among Korean Working-Age Cancer Survivors.

Although South Korea's health insurance has a co-payment-decreasing policy for cancer survivors, information on the extent of financial toxicity and its related factors is limited. We assessed the level of financial toxicity and the association of high levels of financial toxicity with employment concerns after diagnosis and cancer-related distress in working-age cancer survivors. A cross-sectional study was conducted. Study participants were recruited from the National Cancer Survivorship Center between November and December 2022. Financial burden was assessed using the Korean version of the Comprehensive Score for Financial Toxicity, and cancer-related distress was measured using the NCCN Distress Thermometer. Multivariate logistic regression analyses were used to explore the associations between high financial toxicity, cancer-related distress, and changes in employment status after cancer diagnosis. Of 1,403 working-age cancer survivors, approximately 62% reported high levels of financial distress. Survivors reporting early retirement and taking time off work with the intent to return were more likely to report high financial toxicity (adjusted OR 1.69, 95% CI 1.14-2.5; and adjusted OR 2.82, 95% CI 1.24-6.43, respectively) than those with a full-time or part-time job. Moreover, cancer survivors with high distress levels were more likely to report high financial toxicity than those with low distress levels (adjusted OR 4.36, 95% CI 3.17-5.99). High financial toxicity is associated with adverse employment concerns and cancer-related distress among working-age cancer survivors. Therefore, developing cancer survivorship interventions within the healthcare system is necessary to ensure improvements in financial well-being.

C-reactive protein, genetic susceptibility, and the long-term risk of venous thromboembolism in patients with past cancer.

Several studies indicated that C-reactive protein (CRP) is associated with the risk of venous thromboembolism (VTE) in general population. But CRP appears to be unrelated to VTE events in newly diagnosed cancer patients. However, as the survival time of cancer patients increases, the effect of CRP on the long-term risk of VTE may change. We aimed to investigate the association between CRP and VTE in cancer survivors, and further assess the modification effect of genetic susceptibility. Cox proportional hazards model was used to evaluate the association between serum CRP levels and VTE risk, as well as to investigate the joint effect of CRP and genetic susceptibility. The Kaplan-Meier curve and the restricted cubic spline were used to visualize the relationship between CRP and VTE. This study included 30,145 participants with cancer diagnosis at baseline in the UK Biobank. Over a follow-up period of 344,636 person-years, a total of 1,151 VTE events were recorded. Participants were divided into four groups based on the quartiles of CRP levels. The adjusted hazard ratios (95% CIs) of Q1, Q2, Q3, and Q4 were 1.00, 1.20 (0.99-1.44), 1.25 (1.04-1.50), and 1.51 (1.25-1.82), respectively. For those with high genetic risk of VTE, high CRP had an additional increased risk for VTE. CRP can be used as a predictive biomarker for VTE risk in cancer survivors, especially for those with high genetic risk. Future research can explore whether prevention and treatment strategies for VTE can be developed based on CRP for cancer survivors.

A common metric for questionnaires on health anxiety in cancer patients.

After a cancer diagnosis, life is accompanied by worries, concerns and fears that the disease will recur or worsen. These can be normal and useful reactions but may also become so severe that they interfere with everyday functioning. A challenge for patient care is that the theoretical similarity of these reactions, is not consistently conceptualized in practice, hence the empirical comparability of their measures is unclear. Here we intend to show that the theoretical similarity is also empirically justified, and we present a common metric in graphical form that allows direct comparisons between different questionnaires. A total of 1,733 cancer patients completed the Fear of Progression Questionnaire Short Form, Questionnaire on Stress in Cancer Patients-revised version, Concerns About Recurrence Questionnaire, the subscales Health Distress and Negative Health Outlook of the EORTC QLQ-SURV100, and the Whiteley Index. Using a model based on item response theory, we linked the score values of the individual questionnaires. The main outcome of this study is a diagram that can be used to convert the respective values of eight questionnaires on health anxiety to another. All instruments showed a reliability above 0.75 near the mean health anxiety level. The common metric can be used to compare measurements with these questionnaires in terms of the level of health anxiety. Additionally, the reliability of the instruments can be judged at different levels of anxiety. This allows for a better comparability of test results and facilitates communication about the results among experts and with patients.

BD-StableNet: a deep stable learning model with an automatic lesion area detection function for predicting malignancy in BI-RADS category 3–4A lesions

The latest developments combining deep learning technology and medical image data have attracted wide attention and provide efficient noninvasive methods for the early diagnosis of breast cancer. The success of this task often depends on a large amount of data annotated by medical experts, which is time-consuming and may not always be feasible in the biomedical field. The lack of interpretability has greatly hindered the application of deep learning in the medical field. Currently, deep stable learning, including causal inference, make deep learning models more predictive and interpretable. In this study, to distinguish malignant tumors in Breast Imaging-Reporting and Data System (BI-RADS) category 3-4A breast lesions, we propose BD-StableNet, a deep stable learning model for the automatic detection of lesion areas. In this retrospective study, we collected 3103 breast ultrasound images (1418 benign and 1685 malignant lesions) from 493 patients (361 benign and 132 malignant lesion patients) for model training and testing. Compared with other mainstream deep learning models, BD-StableNet has better prediction performance (accuracy = 0.952, area under the curve = 0.982, precision = 0.970, recall = 0.941,F1-score = 0.955 and specificity = 0.965). The lesion area prediction and class activation map results both verify that our proposed model is highly interpretable. The results indicate that BD-StableNet significantly enhances diagnostic accuracy and interpretability, offering a promising noninvasive approach for the diagnosis of BI-RADS category 3-4A breast lesions. Clinically, the use of BD-StableNet could reduce unnecessary biopsies, improve diagnostic efficiency, and ultimately enhance patient outcomes by providing more precise and reliable assessments of breast lesions.

Synthesis and Evaluation of 99mTc-Labeled l-Aspartic Acid as a EuK Polymer Linker for Targeting PSMA to a Novel SPECT Tumor Tracer.

The development of novel tracers targeting prostate-specific membrane antigen (PSMA) has great potential for improving the diagnosis and treatment of prostate cancer (PCa). This study aimed to improve the absolute tumor uptake and tumor-to-background ratios (TBRs) of this novel PSMA tracer by increasing the number of pharmacophores, Glu-urea-Lys (EuK), that specifically bind to PSMA. We successfully synthesized four radioligands and prepared a total of 12 stable radiotracers by coordinating 99mTc with various coligands. [99mTc]Tc-EUKD-EDDA showed the best pharmacokinetic properties both in vitro and in vivo. It effectively increased the absolute uptake in tumors and resulted in good tumor retention. Rapid clearance in nontarget organs resulted in high TBRs. High-contrast SPECT/CT images were obtained within 2-6 h after injection, suggesting that [99mTc]Tc-EUKD-EDDA has great application potential in time-lapse imaging of PCa, which is important for improving the diagnostic accuracy of PCa in clinical practice.

The Role of Resilience and Defense Styles in Caregiver Burden Among the Mothers of Children with Cancer: A Descriptive-Correlational Study

Background: The diagnosis of childhood cancer can be considered a multidimensional crisis for parents, particularly mothers. Objectives: This study aimed to determine the predictive role of defense styles and resilience in the caregiver burden experienced by mothers of children with cancer. Methods: This descriptive-analytical study focuses on mothers of children with cancer who were hospitalized in the pediatric wards of Seyed al-Shohada Hospital in Isfahan, Iran. A total of 136 participants were selected using convenience sampling. The study utilized the Defense Styles Questionnaire (DSQ-40), the Zarit Burden Scale (ZBS), and the Connor-Davidson Resilience Scale (CD-RISC) to collect data. The data were analyzed using STATA16. Results: On average, mothers had a caregiver burden score of 38.65 and a resilience score of 93.51. The majority of mothers (62.5%) exhibited neurotic defensive styles. The regression test results indicated a significant inverse relationship between caregiver burden and resilience (P = 0.002), as well as a significant relationship between the child’s sex and caregiver burden (P &lt; 0.05). Conclusions: Based on the study's findings, it is recommended that counseling and psycho-cognitive programs be designed, developed, implemented, and evaluated to enhance the resilience of mothers of children with cancer and thereby reduce their caregiver burden.

Prevalence of mental disorders and their associations with age at diagnosis and time since diagnosis of nasopharyngeal cancer.

Despite advancements in cancer treatment, understanding the long-term mental health implications for nasopharyngeal carcinoma (NPC) survivors remains an underexplored area. This study aims to examine the prevalence of mental disorders and their correlations with age at diagnosis and time since diagnosis among NPC survivors. A total of 1872 NPC patients were surveyed from September 2020 to June 2021 in this cross-sectional survey. Logistic regression models were used to analyze the associations of age at diagnosis and time since NPC diagnosis with the risk of mental disorders. Additionally, the potential nonlinear trend between these factors was examined using restricted cubic splines. Analyses were conducted both overall and stratified by gender. Gender interaction was also examined. The prevalences of depression, anxiety, and sleep disorders were 32.4, 33.2, and 61.5%, respectively. Age at NPC diagnosis was significantly associated with an elevated risk of depression (adjusted OR (aOR): 1.75 for 30-39 years old; 2.33 for 50-59 years old; 2.59 for ≥60 years old) and sleep disorders (aOR: 2.41 for 40-49 years old; 1.95 for 50-59 years old; 2.26, for ≥60 years old), compared to patients diagnosed with NPC at age < 30 years. Conversely, the risk of depression, anxiety, and sleep disorders exhibited negative associations with the time since diagnosis, compared to patients <3 months. Notably, significant nonlinear associations were observed between time since diagnosis and the risk of depression, anxiety, and sleep disorders, which showed an initial increase, with the highest risk occurring at approximately 3.0 (ORmax: 2.7), 1.5 (ORmax: 2.1), and 4.0 (ORmax: 1.9) months since NPC diagnosis, followed by a gradual recovery to a lower risk level at around 12 months. No gender interactions were observed. The prevalence of mental disorders is notable among NPC survivors, showing a positive correlation with age at diagnosis while displaying a negative correlation with time since diagnosis, thus indicating the need for psychological support, especially within the initial several months following NPC diagnosis.

The Transformative Power of Digital Breast Tomosynthesis and Artificial Intelligence in Breast Cancer Diagnosis.

The integration of Digital Breast Tomosynthesis (DBT) and Artificial Intelligence (AI) represents a significant advance in breast cancer screening. This combination aims to address several challenges inherent in traditional screening while promising an improvement in healthcare delivery across multiple dimensions. For patients, this technological synergy has the potential to lower the number of unnecessary recalls and associated procedures such as biopsies, thereby reducing patient anxiety and improving overall experience without compromising diagnostic accuracy. For radiologists, the use of combined AI and DBT could significantly decrease workload and reduce fatigue by effectively highlighting breast imaging abnormalities, which is especially beneficial in high-volume clinical settings. Health systems stand to gain from streamlined workflows and the facilitated deployment of DBT, which is particularly valuable in areas with a scarcity of specialized breast radiologists. However, despite these potential benefits, substantial challenges remain. Bridging the gap between the development of complex AI algorithms and implementation into clinical practice requires ongoing research and development. This is essential to optimize the reliability of these systems and ensure they are accessible to healthcare providers and patients, who are the ultimate beneficiaries of this technological advancement. This article reviews the benefits of combined AI-DBT imaging, particularly the ability of AI to enhance the benefits of DBT and reduce its existing limitations.