Data System Research Articles

Leveraging Serial Low-Dose CT Scans in Radiomics-based Reinforcement Learning to Improve Early Diagnosis of Lung Cancer at Baseline Screening.

Purpose To evaluate the feasibility of leveraging serial low-dose CT (LDCT) scans to develop a radiomics-based reinforcement learning (RRL) model for improving early diagnosis of lung cancer at baseline screening. Materials and Methods In this retrospective study, 1951 participants (female patients, 822; median age, 61 years [range, 55-74 years]) (male patients, 1129; median age, 62 years [range, 55-74 years]) were randomly selected from the National Lung Screening Trial between August 2002 and April 2004. An RRL model using serial LDCT scans (S-RRL) was trained and validated using data from 1404 participants (372 with lung cancer) containing 2525 available serial LDCT scans up to 3 years. A baseline RRL (B-RRL) model was trained with only LDCT scans acquired at baseline screening for comparison. The 547 held-out individuals (150 with lung cancer) were used as an independent test set for performance evaluation. The area under the receiver operating characteristic curve (AUC) and the net reclassification index (NRI) were used to assess the performances of the models in the classification of screen-detected nodules. Results Deployment to the held-out baseline scans showed that the S-RRL model achieved a significantly higher test AUC (0.88 [95% CI: 0.85, 0.91]) than both the Brock model (AUC, 0.84 [95% CI: 0.81, 0.88]; P = .02) and the B-RRL model (AUC, 0.86 [95% CI: 0.83, 0.90]; P = .02). Lung cancer risk stratification was significantly improved by the S-RRL model as compared with Lung CT Screening Reporting and Data System (NRI, 0.29; P < .001) and the Brock model (NRI, 0.12; P = .008). Conclusion The S-RRL model demonstrated the potential to improve early diagnosis and risk stratification for lung cancer at baseline screening as compared with the B-RRL model and clinical models. Keywords: Radiomics-based Reinforcement Learning, Lung Cancer Screening, Low-Dose CT, Machine Learning © RSNA, 2024 Supplemental material is available for this article.

The machine learning-based model for lateral lymph node metastasis of thyroid medullary carcinoma improved the prediction ability of occult metastasis.

For medullary thyroid carcinoma (MTC) with no positive findings in the lateral neck before surgery, whether prophylactic lateral neck dissection (LND) is needed remains controversial. A better way to predict occult metastasis in the lateral neck is needed. From January 2010 to January 2022, patients who were diagnosed with MTC and underwent primary surgery at our hospital were retrospectively reviewed. We collected the patients' baseline characteristics, surgical procedure, and rescored the ultrasound images of the primary lesions using American College of Radiology (ACR) Thyroid Imaging, Reporting and Data System (TI-RADS). Regularized logistic regression, 5-fold cross-validation and decision curve analysis was applied for lateral lymph node metastasis (LLNM) model's development and validation. Then, we tested the predictive ability of the LLNM model for occult LLNM in cN0-1a patients. A total of 218 patients were enrolled. Five baseline characteristics and two TI-RADS features were identified as high-risk factors for LLNM: gender, baseline calcitonin (Ctn), tumor size, multifocality, and central lymph node (CLN) status, as well as TI-RADS margin and level. A LLNM model was developed and showed a good discrimination with 5-fold cross-validation mean area under curve (AUC) = 0.92 ± 0.03 in the test dataset. Among cN0-1a patients, our LLNM model achieved an AUC of 0.91 (95% CI, 0.88-0.94) for predicting occult LLNM, which was significantly higher than the AUCs of baseline Ctn (0.83) and CLN status (0.64). We developed a LLNM prediction model for MTC using machine learning based on clinical baseline characteristics and TI-RADS. Our model can predict occult LLNM for cN0-1a patients more accurately, then benefit the decision of prophylactic LND.

A Novel Free-Air Diesel and Ozone Enrichment (FADOE) Research Platform

Air pollution is an escalating concern in the modern world, posing substantial threats to ecosystems processes. While the importance of comprehending the impact of pollutants on natural environments is evident, conducting rigorous field-based experiments presents formidable challenges. Elevating pollutant concentrations within open air environments in a controlled manner is complex. Nonetheless, such real-world experiments are invaluable for revealing the genuine influence of air pollutants on ecosystems and their functioning. Field-scale measurements have emerged as a pivotal avenue for advancing our understanding of the interactions between air pollutants and the natural world, providing unique insights into ecosystem dynamics, including critical processes like pollination and natural pest regulation. In atmospheric and ecological research, free-air exposure systems have proven effective in elevating carbon dioxide (CO2) and ozone (O3) concentrations, facilitating the exploration of their ecological consequences. Yet, nitrogen oxides (NOx), a class of pollutants with significant ecological and atmospheric relevance, have largely eluded field-based ecological investigations. This paper introduces the recently developed FADOE (Free-Air Diesel and Ozone Enrichment) platform, which allows the elevation of O3 and diesel exhaust (including NOx) within a field-scale context. Comprehensive information on the system's design, construction, and performance data from the 2023 summer season is presented.• Air pollution and ecosystem functioning• Elevated ozone and nitrogen oxides (NOx)• Free-air exposure systems for field scale measurements.

Trends in clinical outcomes of older hemodialysis patients: data from the 2023 Korean Renal Data System (KORDS)

With an increasing aging population, the mean age of patients with end-stage kidney disease (ESKD) is globally increasing. However, the current clinical status of elderly patients undergoing hemodialysis (HD) is rarely reported in Korea. The current study analyzed the clinical features and trends of older patients undergoing HD from the Korean Renal Data System (KORDS) database. The patients were divided into three groups according to age: &lt;65 years (the young group), n = 50,591 (35.9%); 65–74 years (the younger-old group), n = 37,525 (26.6%); and ≥75 years (the older-old group), n = 52,856 (37.5%). The proportion of older-old group undergoing HD significantly increased in incidence and decreased in prevalence from 2013 to 2022. The median levels of hemoglobin, serum creatinine, albumin, calcium, phosphorus, and intact parathyroid hormone significantly decreased in the older-old group. The proportions of arteriovenous fistula creation and left forearm placement showed decreased trends with age. Although the utilization of low surface area dialyzers increased with age, the dialysis adequacy, including urea reduction ratio and Kt/V was within acceptable range in the older-old group on HD. Over the past 20 years, the mortality rate in the older-old group has increased, with cardiovascular diseases decreasing and infectious diseases increasing. The incidence of elderly patients undergoing HD has increased over time, but the high mortality of the older-old group needs to be solved. Therefore, it is imperative to develop holistic strategies based on age and individual needs for patients with ESKD.

Performance of LI-RADS category 5 vs combined categories 4 and 5: a systemic review and meta-analysis.

Computed tomography (CT)/magnetic resonance imaging (MRI) Liver Imaging Reporting and Data System (LI-RADS, LR) category 5 has high specificity and modest sensitivity for diagnosis of hepatocellular carcinoma (HCC). The purpose of this study was to compare the diagnostic performance of LR-5 vs combined LR-4 and LR-5 (LR-4/5) for HCC diagnosis. MEDLINE and EMBASE databases through January 03, 2023 were searched for studies reporting the performance of LR-5 and combined LR-4/5 for HCC diagnosis, using CT/MRI LI-RADS version 2014, 2017, or 2018. A bivariate random-effects model was used to calculate the pooled per-observation diagnostic performance. Subgroup analysis was performed based on imaging modalities and type of MRI contrast material. Sixty-nine studies (15,108 observations, 9928 (65.7%) HCCs) were included. Compared to LR-5, combined LR-4/5 showed significantly higher pooled sensitivity (83.0% (95% CI [80.3-85.8%]) vs 65.7% (95% CI [62.4-69.1%]); p < 0.001), lower pooled specificity (75.0% (95% CI [70.5-79.6%]) vs 91.7% (95% CI [90.2-93.1%]); p < 0.001), lower pooled positive likelihood ratio (3.60 (95% CI [3.06-4.23]) vs 6.18 (95% CI [5.35-7.14]); p < 0.001), and lower pooled negative likelihood ratio (0.22 (95% CI [0.19-0.25]) vs 0.38 (95% CI [0.35-0.41]) vs; p < 0.001). Similar results were seen in all subgroups. Our meta-analysis showed that combining LR-4 and LR-5 would increase sensitivity but decrease specificity, positive likelihood ratio, and negative likelihood ratio. These findings may inform management guidelines and individualized management. This meta-analysis estimated the magnitude of changes in the sensitivity and specificity of imaging criteria when LI-RADS categories 4 and 5 were combined; these findings can inform management guidelines and individualized management. There is no single worldwide reporting system for liver imaging, partly due to regional needs. Combining LI-RADS categories 4 and 5 increased sensitivity and decreased specificity and positive and negative likelihood ratios. Changes in the sensitivity and specificity of imaging criteria can inform management guidelines and individualized management.

Gestational Diabetes Prevalence Estimates from Three Data Sources, 2018.

We investigated 2018 gestational diabetes mellitus (GDM) prevalence estimates in three surveillance systems (National Vital Statistics System, State Inpatient Database, and Pregnancy Risk Assessment Monitoring Survey). We calculated GDM prevalence for jurisdictions represented in each system; a subset of data was analyzed for people 18-39 years old in 22 jurisdictions present in all three systems to observe dataset-specific demographics and GDM prevalence using comparable categories. GDM prevalence estimates varied widely by data system and within the data subset despite comparable demographics. Understanding the differences between GDM surveillance data systems can help researchers better identify people and places at higher risk of GDM.

Detection and diagnosis of automated breast ultrasound in patients with BI-RADS category 4 microcalcifications: a retrospective study

BackgroundAutomated Breast Ultrasound (AB US) has shown good application value and prospects in breast disease screening and diagnosis. The aim of the study was to explore the ability of AB US to detect and diagnose mammographically Breast Imaging Reporting and Data System (BI-RADS) category 4 microcalcifications.Methods575 pathologically confirmed mammographically BI-RADS category 4 microcalcifications from January 2017 to June 2021 were included. All patients also completed AB US examinations. Based on the final pathological results, analyzed and summarized the AB US image features, and compared the evaluation results with mammography, to explore the detection and diagnostic ability of AB US for these suspicious microcalcifications.Results250 were finally confirmed as malignant and 325 were benign. Mammographic findings including microcalcifications morphology (61/80 with amorphous, coarse heterogeneous and fine pleomorphic, 13/14 with fine-linear or branching), calcification distribution (189/346 with grouped, 40/67 with linear and segmental), associated features (70/96 with asymmetric shadow), higher BI-RADS category with 4B (88/120) and 4 C (73/38) showed higher incidence in malignant lesions, and were the independent factors associated with malignant microcalcifications. 477 (477/575, 83.0%) microcalcifications were detected by AB US, including 223 malignant and 254 benign, with a significantly higher detection rate for malignant lesions (x2 = 12.20, P < 0.001). Logistic regression analysis showed microcalcifications with architectural distortion (odds ratio [OR] = 0.30, P = 0.014), with amorphous, coarse heterogeneous and fine pleomorphic morphology (OR = 3.15, P = 0.037), grouped (OR = 1.90, P = 0.017), liner and segmental distribution (OR = 8.93, P = 0.004) were the independent factors which could affect the detectability of AB US for microcalcifications. In AB US, malignant calcification was more frequent in a mass (104/154) or intraductal (20/32), and with ductal changes (30/41) or architectural distortion (58/68), especially with the both (12/12). BI-RADS category results also showed that AB US had higher sensitivity to malignant calcification than mammography (64.8% vs. 46.8%).ConclusionsAB US has good detectability for mammographically BI-RADS category 4 microcalcifications, especially for malignant lesions. Malignant calcification is more common in a mass and intraductal in AB US, and tend to associated with architectural distortion or duct changes. Also, AB US has higher sensitivity than mammography to malignant microcalcification, which is expected to become an effective supplementary examination method for breast microcalcifications, especially in dense breasts.

Sonographic risk stratification of FDG-avid thyroid nodules using the Thyroid Imaging Reporting and Data System.

The increasing usage of positron emission tomography/computed tomography (PET/CT) for detection and monitoring of malignancy has led to an increase in incidental detection of thyroid nodules. Nodules that demonstrate increased avidity for 2-[18F]-fluoro-2-deoxy-d-glucose (FDG) have been shown to carry a high incidence of malignancy and warrant further investigation. At present, there has been limited research on the risk stratification of FDG-avid thyroid incidentalomas. Thus, this study aims to evaluate the efficacy of the ACR TIRADS classification in the risk stratification of such nodules. Data were collected retrospectively for FDG-avid thyroid incidentalomas over a 10-year period. Nodules were characterised using the TIRADS classification and, subsequently, underwent fine-needle aspirate cytology. Cytological findings were classified using the Bethesda reporting system. Non-diagnostic samples (Bethesda class I) were excluded. The remaining samples were divided into two groups: benign (Bethesda class II) or suspicious for malignancy/malignant (Bethesda class III or above). Thirty-six percent of low-risk nodules and 45% of high-risk nodules were malignant, respectively (P = 0.516). The sensitivity and specificity of TIRADS for detection of malignant nodules were 56% and 54%, respectively. There were no malignant TIRADS 1 or 2 nodules. The absence of any suspicious sonographic features had a 1.0 negative predictive value. FDG-avid nodules classified as TIRADS 1 or 2 or have no suspicious ultrasound features have a 0% incidence of malignancy and thus may not require further assessment with fine-needle aspirate cytology (FNA) when detected incidentally. FDG-avid nodules that are TIRADS 3 or above should undergo FNA regardless of size due to the high risk of malignancy and poor sensitivity of the TIRADS classification system.

Risk factor analysis and optimal cutoff value selection of PSAD for diagnosing clinically significant prostate cancer in patients with negative mpMRI: results from a high-volume center in Southeast China

BackgroundMulti-parametric magnetic resonance imaging (mpMRI) is a diagnostic tool used for screening, localizing, and staging prostate cancer. Patients with Prostate Imaging Reporting and Data System (PI-RADS) score of 1 and 2 are considered negative mpMRI, with a lower likelihood of detecting clinically significant prostate cancer (csPCa). However, relying solely on mpMRI is insufficient to completely exclude csPCa, necessitating further stratification of csPCa patients using biomarkers.MethodsA retrospective study was conducted on mpMRI-negative patients who underwent prostate biopsy at the First Affiliated Hospital of Zhejiang University from January 2022 to June 2023. A total of 607 patients were included based on inclusion and exclusion criteria. Univariate and multivariate logistic regression analysis were performed to identify risk factors for diagnosing csPCa in patients with negative mpMRI. Receiver Operating Characteristic (ROC) curves were plotted to compare the discriminatory ability of different Prostate-Specific Antigen Density (PSAD) cutoff values for csPCa.ResultsAmong the 607 patients with negative mpMRI, 73 patients were diagnosed with csPCa. In univariate logistic regression analysis, age, PSA, f/tPSA, prostate volume, and PSAD were all associated with diagnosing csPCa in patients with negative mpMRI (P < 0.05), with PSAD being the most accurate predictor. In multivariate logistic regression analysis, f/tPSA, age, and PSAD were independent predictors of csPCa (P < 0.05). PSAD cutoff value of 0.20 ng/ml/ml has better discriminatory ability for predicting csPCa and is a significant risk factor for csPCa in multivariate analysis.ConclusionAge, f/tPSA, and PSAD are independent predictors of diagnosing csPCa in patients with negative mpMRI. It is suggested that patients with negative mpMRI and PSAD less than 0.20 ng/ml/ml could avoid prostate biopsy, as a PSAD cutoff value of 0.20 ng/ml/ml has better diagnostic performance than the traditional cutoff value of 0.15 ng/ml/ml.

Enhancing Accuracy in Breast Density Assessment Using Deep Learning: A Multicentric, Multi-Reader Study

The evaluation of mammographic breast density, a critical indicator of breast cancer risk, is traditionally performed by radiologists via visual inspection of mammography images, utilizing the Breast Imaging-Reporting and Data System (BI-RADS) breast density categories. However, this method is subject to substantial interobserver variability, leading to inconsistencies and potential inaccuracies in density assessment and subsequent risk estimations. To address this, we present a deep learning-based automatic detection algorithm (DLAD) designed for the automated evaluation of breast density. Our multicentric, multi-reader study leverages a diverse dataset of 122 full-field digital mammography studies (488 images in CC and MLO projections) sourced from three institutions. We invited two experienced radiologists to conduct a retrospective analysis, establishing a ground truth for 72 mammography studies (BI-RADS class A: 18, BI-RADS class B: 43, BI-RADS class C: 7, BI-RADS class D: 4). The efficacy of the DLAD was then compared to the performance of five independent radiologists with varying levels of experience. The DLAD showed robust performance, achieving an accuracy of 0.819 (95% CI: 0.736–0.903), along with an F1 score of 0.798 (0.594–0.905), precision of 0.806 (0.596–0.896), recall of 0.830 (0.650–0.946), and a Cohen’s Kappa (κ) of 0.708 (0.562–0.841). The algorithm achieved robust performance that matches and in four cases exceeds that of individual radiologists. The statistical analysis did not reveal a significant difference in accuracy between DLAD and the radiologists, underscoring the model’s competitive diagnostic alignment with professional radiologist assessments. These results demonstrate that the deep learning-based automatic detection algorithm can enhance the accuracy and consistency of breast density assessments, offering a reliable tool for improving breast cancer screening outcomes.

Unveiling South African insect diversity: DNA barcoding’s contribution to biodiversity data

Insects are one of the most species-rich groups on Earth. They comprise much of animal diversity and play vital roles in ecosystems, including pollination, pest control, and decomposition. However, only a fraction of this diversity has been formally described. South Africa is recognised as one of the most biologically diverse countries globally, with an estimated 44 000 insect species. Many crops rely on insect pollinators, including canola, apples, oranges, and sunflowers. A shortage of wild pollinators currently threatens crop yields, yet our knowledge of insect diversity within South Africa is sparse. There are few taxonomic specialists relative to South Africa’s biodiversity, and the methods used for insect identification can be time-consuming and expensive. DNA barcoding provides an important research tool to accelerate insect biodiversity research. In this review, we queried the public DNA barcoding BOLD (Barcode of Life Data System) database for records of “Insecta” within South Africa, and 416 211 published records assigned to 28 239 unique BINs (Barcode Index Numbers) were returned. We identified five taxonomic orders with more BINs than known species in southern Africa (Hymenoptera, Diptera, Thysanoptera, Plecoptera, and Strepsiptera). Most of the barcoded records were derived from Malaise trap sampling in Gauteng, Mpumalanga and Limpopo, while the rest of South Africa remains poorly sampled. We suggest that there is a need for a comprehensive national sampling effort alongside increased investment in taxonomic expertise to generate critical baseline data on insect biodiversity before species are lost to extinction.

Miniaturized high signal-to-noise ratio optical air data system using a compact multi-axis parallel transceiver for airborne application

We have developed a miniaturized multi-channel parallel optical air data system with high signal-to-noise ratio for airborne application. In the system, we designed a fiber amplifier with multi-channel high-energy output that was respectively used as the transmitting signals and a compact multi-axis transceiver with an entrance pupil diameter of 70 mm that was used to receive multi-channel signals simultaneously. We demonstrated the performance of our system both on ground and on board. On ground, the measured line-of-sight speed had an average error of 0.02 m/s and a standard deviation of 0.15 m/s. On board, the standard deviation between the true air speed, angle of attack, and angle of sideslip measured by our system and a commercial Swiss air data system was 1 kt, 0.68°, and 0.54°, respectively, and those standard deviation between our system and a system with the same design but employing multiple single-axis telescopes with entrance pupil diameter of 30 mm was 0.34 kt, 0.36°, and 0.28°, respectively. The signal-to-noise ratio of our system was 4.5 times higher than that of the system with small single-axis telescopes. Our system is very promising for airborne applications because of its small volume, high signal-to-noise ratio, and high data rate.

CalScope: methodology and lessons learned for conducting a remote statewide SARS-CoV-2 seroprevalence study in California using an at-home dried blood spot collection kit and online survey.

To describe the methodology for conducting the CalScope study, a remote, population-based survey launched by the California Department of Public Health (CDPH) to estimate SARS-CoV-2 seroprevalence and understand COVID-19 disease burden in California. Between April 2021 and August 2022, 666,857 randomly selected households were invited by mail to complete an online survey and at-home test kit for up to one adult and one child. A gift card was given for each completed survey and test kit. Multiple customized REDCap databases were used to create a data system which provided task automation and scalable data management through API integrations. Support infrastructure was developed to manage follow-up for participant questions and a communications plan was used for outreach through local partners. Across 3 waves, 32,671 out of 666,857 (4.9%) households registered, 6.3% by phone using an interactive voice response (IVR) system and 95.7% in English. Overall, 25,488 (78.0%) households completed surveys, while 23,396 (71.6%) households returned blood samples for testing. Support requests (n = 5,807) received through the web-based form (36.3%), by email (34.1%), and voicemail (29.7%) were mostly concerned with the test kit (31.6%), test result (26.8%), and gift card (21.3%). Ensuring a well-integrated and scalable data system, responsive support infrastructure for participant follow-up, and appropriate academic and local health department partnerships for study management and communication allowed for successful rollout of a large population-based survey. Remote data collection utilizing online surveys and at-home test kits can complement routine surveillance data for a state health department.

Clinical and histopathological parameters in transrectal ultrasound-guided biopsies associated with tumor upgrading after radical prostatectomy: A comparative analysis of risk groups.

Thanks to technological advances, prostate cancer (PCa) can be diagnosed at a younger age. It is known that most of these patients are in the low-intermediate risk group, and the histological grade of the tumor increases in half of those undergoing radical prostatectomy (Rp) compared to their diagnostic biopsies. This is especially important in terms of active surveillance (AS) and/or the timely evaluation of curative treatment options in patients diagnosed at an early age. Our aim was to investigate clinical and histopathological parameters that may be associated with an increase in the histological grade of the tumor in patients with acinar adenocarcinoma who were diagnosed by transrectal ultrasound-guided biopsy (TRUS-Bx) and underwent Rp. A total of 205 patients with classical acinar adenocarcinoma diagnosed by TRUS-Bx without metastasis and who underwent Rp were grouped according to the D'Amico risk classification. Age at diagnosis, serum prostate-specific antigen (PSA), PSA density, prostate volume, Prostate Imaging Reporting and Data System (PI-RADS) score, clinical stage, Gleason Grade Group (GGG), high-grade intraepithelial neoplasia in tumor-free cores (HGPIN) (single and ≥2 cores), perineural invasion (PNI), and lymphovascular invasion (LVI) was obtained. Additionally, GGG, pathological stage, lymph node metastasis, surgical margin positivity, and tumor volume obtained from Rp were evaluated. Comparisons were made between the case groups in which the tumor grade increased and remained the same, in terms of age, serum PSA, PSA density, HGPIN in tumor-free cores (single and ≥2 cores), PNI, and LVI in all biopsies (with or without tumors), as well as risk groups. In addition, the relationships of HGPIN in tumor-free cores (single and ≥2 cores), PNI, and LVI on TRUS-Bx with age, serum PSA and PSA density, tumor volume, surgical margin positivity, pathological stage, lymph node metastasis, and risk groups were examined separately. Of the patients, 72 (35.1%) were in the low-risk group, 95 (46.3%) in the intermediate-risk group, and 38 (18.5%) in the high-risk group. Most of the patients with an increased histological grade (n = 38, 48.1%) were in the low-risk group (p < 0.05) and had an advanced median age. HGPIN in single and ≥2 tumor-free cores and PNI were more common in these patients (p < 0.01, p < 0.001, and p < 0.05, respectively). According to the multivariable analysis, advanced age (odds ratio [OR]: 1.087, 95% confidence interval [CI]: 1.029-1.148, p < 0.05), high serum PSA (OR: 1.047, 95% CI: 1.006-1.090, p < 0.05), HGPIN in ≥2 tumor-free cores (OR: 6.346, 95% CI: 3.136-12.912, p < 0.001), and PNI (OR: 3.138, 95% CI: 1.179-8.356, p < 0.05) were independent risk factors for a tumor upgrade. Furthermore, being in the low-risk group was an independent risk factor when compared to the intermediate- and high-risk groups (OR: 0.187, 95% CI: 0.080-0.437, p < 0.001 and OR: 0.054, 95% CI: 0.013-0.230, p < 0.001, respectively). The HGPIN diagnosis was more common in the low- and intermediate-risk groups. Advanced age at diagnosis, high serum PSA and PSA density values were associated with PNI on TRUS-Bx. High serum PSA and PSA density values were associated with LVI on TRUS-Bx. Surgical margin positivity was higher in cases with PNI and LVI detected by TRUS-Bx. HGPIN in ≥2 tumor-free cores, PNI, and LVI on TRUS-Bx were associated with a higher rate of lymph node metastases. In patients diagnosed with acinar adenocarcinoma, the presence of HGPIN even in a single tumor-free core on TRUS-Bx was found to be significant in terms of showing an increase in the histological tumor grade in Rp. The diagnosis of HGPIN in ≥2 tumor-free cores on TRUS-Bx was determined as an independent risk factor for an increased Gleason score after Rp. Furthermore, an advanced age, a high serum PSA value, being in the low-risk group, and the presence of PNI were associated with a tumor upgrade. HGPIN in ≥2 tumor-free cores, PNI, and LVI were also associated with lymph node metastasis. Therefore, the diagnosis of HGPIN should be signed out on pathological reports.

Designing interactive visualizations for analyzing chronic lung diseases in a user-centered approach.

Medical practitioners analyze numerous types of data, often using archaic representations that do not meet their needs. Pneumologists who analyze lung function exams must often consult multiple exam records manually, making comparisons cumbersome. Such shortcomings can be addressed with interactive visualizations, but these must be designed carefully with practitioners' needs in mind. A workshop with experts was conducted to gather user requirements and common tasks. Based on the workshop results, we iteratively designed a web-based prototype, continuously consulting experts along the way. The resulting application was evaluated in a formative study via expert interviews with 3 medical practitioners. Participants in our study were able to solve all tasks in accordance with experts' expectations and generally viewed our system positively, though there were some usability and utility issues in the initial prototype. An improved version of our system solves these issues and includes additional customization functionalities. The study results showed that participants were able to use our system effectively to solve domain-relevant tasks, even though some shortcomings could be observed. Using a different framework with more fine-grained control over interactions and visual elements, we implemented design changes in an improved version of our prototype that needs to be evaluated in future work. Employing a user-centered design approach, we developed a visual analytics system for lung function data that allows medical practitioners to more easily analyze the progression of several key parameters over time.

Sign language Detection and Recognization using Deep Learning

In our modern society, effective communication is crucial for social interaction, personal growth, and professional success. Yet, individuals with hearing and speech impairments often encounter significant obstacles in expressing themselves and understanding others, leading to communication barriers and social isolation. Sign language serves as a vital means of communication for the deaf and dumb community, allowing them to convey thoughts, ideas, and emotions through gestures and expressions. This research paper introduces a groundbreaking "Sign Language Detection and Recognition using Deep Learning" system to address these challenges. Utilizing Convolutional Neural Networks (CNN) and image processing techniques like Histogram of Oriented Gradients , our system accurately detects and interprets sign language gestures in real-time. Additionally, it features a two-way communication interface that facilitates seamless interaction between individuals with different communication modalities, enabling inclusive communication among deaf, dumb, and normal individuals. Through a comprehensive methodology encompassing data collection, preprocessing, model training, and system integration, our research aims to advance technology-driven solutions that promote inclusivity, equality, and dignity for individuals with hearing and speech impairments. By empowering effective communication and full participation in social, educational, and professional contexts, our research endeavors to create a more inclusive and accessible world for all members of society.

Diagnostic Accuracy of American College of Radiology Thyroid Imaging Reporting Data System : A Single-Center Cross-sectional Study

Diagnostic Accuracy of American College of Radiology Thyroid Imaging Reporting Data System : A Single-Center Cross-sectional Study

Does abdominal protrusion in pregnant women affect abdominal injury severity in motor vehicle collisions? A nationwide database study.

Some pregnant women avoid vehicle driving owing to the risk of contact between their protruding abdomen and steering wheel. This study was performed to determine whether abdominal protrusion in late-term pregnant car users affects the occurrence and severity of abdominal injuries in motor vehicle collisions using a national crash database. The National Automotive Sampling System/Crashworthiness Data System was used to analyse maternal background, collision characteristics, outcome and Abbreviated Injury Scale (AIS) scores for the body regions of all persons involved in the collision. Comparison of pregnant and non-pregnant women in the driver's seat showed no significant differences in the rate of AIS scores of ≥2 (2+) for abdominal injuries and female outcomes. Comparison of use of the driver's seat and front passenger's seat by pregnant women showed no significant difference in rate of AIS 2+ injuries or in maternal and fetal outcomes. Comparison of pregnant women with a gestational age of ≤27 and >27 weeks in the driver's seat showed no significant differences in rate of AIS 2+ injuries or in maternal and fetal outcomes. Based on the data from relatively low-speed frontal collisions, obstetrician/gynaecologists should advise pregnant women that they do not need to change their preferred car seat from the driver's seat to another seat because of fear of contact between their protruding abdomen and the vehicle interior.

Deep learning of mammogram images to reduce unnecessary breast biopsies: a preliminary study

BackgroundPatients with a Breast Imaging Reporting and Data System (BI-RADS) 4 mammogram are currently recommended for biopsy. However, 70–80% of the biopsies are negative/benign. In this study, we developed a deep learning classification algorithm on mammogram images to classify BI-RADS 4 suspicious lesions aiming to reduce unnecessary breast biopsies.Materials and methodsThis retrospective study included 847 patients with a BI-RADS 4 breast lesion that underwent biopsy at a single institution and included 200 invasive breast cancers, 200 ductal carcinoma in-situ (DCIS), 198 pure atypias, 194 benign, and 55 atypias upstaged to malignancy after excisional biopsy. We employed convolutional neural networks to perform 4 binary classification tasks: (I) benign vs. all atypia + invasive + DCIS, aiming to identify the benign cases for whom biopsy may be avoided; (II) benign + pure atypia vs. atypia-upstaged + invasive + DCIS, aiming to reduce excision of atypia that is not upgraded to cancer at surgery; (III) benign vs. each of the other 3 classes individually (atypia, DCIS, invasive), aiming for a precise diagnosis; and (IV) pure atypia vs. atypia-upstaged, aiming to reduce unnecessary excisional biopsies on atypia patients.ResultsA 95% sensitivity for the “higher stage disease” class was ensured for all tasks. The specificity value was 33% in Task I, and 25% in Task II, respectively. In Task III, the respective specificity value was 30% (vs. atypia), 30% (vs. DCIS), and 46% (vs. invasive tumor). In Task IV, the specificity was 35%. The AUC values for the 4 tasks were 0.72, 0.67, 0.70/0.73/0.72, and 0.67, respectively.ConclusionDeep learning of digital mammograms containing BI-RADS 4 findings can identify lesions that may not need breast biopsy, leading to potential reduction of unnecessary procedures and the attendant costs and stress.

The Impact of Newly Diagnosed Early Breast Cancer on Psychological Resilience, Distress Levels, and the Perception of Health

Confronting a breast cancer diagnosis, along with complex and challenging treatment procedures, is an extremely stressful experience. Psychological resilience is the ability to maintain or restore normal functioning while facing adversity. We aimed to explore the impact of an early breast cancer diagnosis on psychological resilience, distress, and perception of health. A cross-sectional study was conducted, including 50 patients newly diagnosed with early breast cancer and 67 healthy women with screening mammograms graded 1 or 2 using a Breast Imaging Reporting and Data System. The levels of distress, perception of health, and psychological resilience were assessed using the depression, anxiety, and stress scale, the SF 36-Item Health Survey 1.0, and the Connor–Davidson RISC-25 scale. Differences between variables were examined using the t-test and chi-square test for interval and categorial variables. The surveys were conducted within four weeks of a breast cancer diagnosis. Patients with breast cancer reported a deterioration of their health relative to the previous year and significantly higher levels of psychological resilience, while there was no significant difference between the groups in levels of stress, anxiety, or depression. The process of diagnosis with early breast cancer may activate psychological dynamic processes which are involved in the effective adaptation to acute stress, leading to higher resilience levels in breast cancer patients compared to healthy controls.