Integrating Text and Image Analysis: Exploring GPT-4V's Capabilities in Advanced Radiological Applications Across Subspecialties.

This study demonstrates that GPT-4V outperforms GPT-4 across radiology subspecialties in analyzing 207 cases with 1312 images from the Radiological Society of North America Case Collection.

The clinical value of the hepatic venous pressure gradient in patients undergoing hepatic resection for hepatocellular carcinoma with or without liver cirrhosis.

The role of hepatic venous pressure gradient (HVPG) measurement in risk stratification before liver resection is an ongoing area of debate. This study examines the impact of preoperative HVPG levels on overall survival (OS)/time to recurrence (TTR) and postoperative complications after hepatic resection of hepatocellular carcinoma (HCC). Thirty-eight HCC patients undergoing HVPG measurement before liver resection at Cambridge University Hospitals NHS Foundation Trust between January 2014 and April 2022 were retrospectively analysed. Statistical analysis comprised univariable/multivariable Cox/logistic regression to identify risk factors of reduced OS/TTR or 90-day post-resection complications and Kaplan-Meier estimator, log-rank, chi-squared, Fisher's exact, and Mann-Whitney U test, or Student's t-test for survival/subgroup analysis. The median HPVG was 6 (range: 0-14) mmHg. The HVPG was an independent risk factor for poorer TTR in the overall cohort (cut-off: ≥7.5 mmHg (17.18/43.81 months; P = 0.009)). In the subgroup analysis of cirrhotic patients (N = 29 (76%)), HVPG was additionally an independent risk factor for lower OS (cut-off: ≥8.5 mmHg [44.39/76.84 months; P = 0.012]). The HVPG had no impact on OS/TTR in non-cirrhotic patients (N = 9 (24%)), nor was it associated with postoperative complications in any cohort. In conclusion, preoperative HVPG levels are useful predictors for TTR and OS in cirrhotic HCC patients undergoing hepatic resection.

Comparative Analysis of Multimodal Large Language Model Performance on Clinical Vignette Questions.

This study compares 2 large language models and their performance vs that of competing open-source models.

International pharmacy students' perceptions towards artificial intelligence in medicine-A multinational, multicentre cross-sectional study.

AIMS: To explore international undergraduate pharmacy students' views on integrating artificial intelligence (AI) into pharmacy education and practice. METHODS: This cross-sectional institutional review board-approved multinational, multicentre study comprised an anonymous online survey of 14 multiple-choice items to assess pharmacy students' preferences for AI events in the pharmacy curriculum, the current state of AI education, and students' AI knowledge and attitudes towards using AI in the pharmacy profession, supplemented by 8 demographic queries. Subgroup analyses were performed considering sex, study year, tech-savviness, and prior AI knowledge and AI events in the curriculum using the Mann-Whitney U-test. Variances were reported for responses in Likert scale format. RESULTS: The survey gathered 387 pharmacy student opinions across 16 faculties and 12 countries. Students showed predominantly positive attitudes towards AI in medicine (58%, n = 225) and expressed a strong desire for more AI education (72%, n = 276). However, they reported limited general knowledge of AI (63%, n = 242) and felt inadequately prepared to use AI in their future careers (51%, n = 197). Male students showed more positive attitudes towards increasing efficiency through AI (P = .011), while tech-savvy and advanced-year students expressed heightened concerns about potential legal and ethical issues related to AI (P < .001/P = .025, respectively). Students who had AI courses as part of their studies reported better AI knowledge (P < .001) and felt more prepared to apply it professionally (P < .001). CONCLUSIONS: Our findings underline the generally positive attitude of international pharmacy students towards AI application in medicine and highlight the necessity for a greater emphasis on AI education within pharmacy curricula.

Mapping gender and geographic diversity in artificial intelligence research: Editor representation in leading computer science journals.

Background: The growing role of artificial intelligence (AI) in healthcare, particularly radiology, requires its unbiased and fair development and implementation, starting with the constitution of the scientific community. Purpose: To examine the gender and country distribution among academic editors in leading computer science and AI journals. Material and Methods: This cross-sectional study analyzed the gender and country distribution among editors-in-chief, senior, and associate editors in all 75 Q1 computer science and AI journals in the Clarivate Journal Citations Report and SCImago Journal Ranking 2022. Gender was determined using an open-source algorithm (Gender Guesser™), selecting the gender with the highest calibrated probability. Result: Among 4,948 editorial board members, women were underrepresented in all positions (editors-in-chief/senior editors/associate editors: 14%/18%/17%). The proportion of women correlated positively with the SCImago Journal Rank indicator (ρ = 0.329; p = .004). The U.S., the U.K., and China comprised 50% of editors, while Australia, Finland, Estonia, Denmark, the Netherlands, the U.K., Switzerland, and Slovenia had the highest women editor representation per million women population. Conclusion: Our results highlight gender and geographic disparities on leading computer science and AI journal editorial boards, with women being underrepresented in all positions and a disproportional relationship between the Global North and South.

Biomedical Ethical Aspects Towards the Implementation of Artificial Intelligence in Medical Education.

The increasing use of artificial intelligence (AI) in medicine is associated with new ethical challenges and responsibilities. However, special considerations and concerns should be addressed when integrating AI applications into medical education, where healthcare, AI, and education ethics collide. This commentary explores the biomedical ethical responsibilities of medical institutions in incorporating AI applications into medical education by identifying potential concerns and limitations, with the goal of implementing applicable recommendations. The recommendations presented are intended to assist in developing institutional guidelines for the ethical use of AI for medical educators and students.

Dual center validation of deep learning for automated multi-label segmentation of thoracic anatomy in bedside chest radiographs.

BACKGROUND AND OBJECTIVES: Bedside chest radiographs (CXRs) are challenging to interpret but important for monitoring cardiothoracic disease and invasive therapy devices in critical care and emergency medicine. Taking surrounding anatomy into account is likely to improve the diagnostic accuracy of artificial intelligence and bring its performance closer to that of a radiologist. Therefore, we aimed to develop a deep convolutional neural network for efficient automatic anatomy segmentation of bedside CXRs. METHODS: To improve the efficiency of the segmentation process, we introduced a "human-in-the-loop" segmentation workflow with an active learning approach, looking at five major anatomical structures in the chest (heart, lungs, mediastinum, trachea, and clavicles). This allowed us to decrease the time needed for segmentation by 32% and select the most complex cases to utilize human expert annotators efficiently. After annotation of 2,000 CXRs from different Level 1 medical centers at Charité - University Hospital Berlin, there was no relevant improvement in model performance, and the annotation process was stopped. A 5-layer U-ResNet was trained for 150 epochs using a combined soft Dice similarity coefficient (DSC) and cross-entropy as a loss function. DSC, Jaccard index (JI), Hausdorff distance (HD) in mm, and average symmetric surface distance (ASSD) in mm were used to assess model performance. External validation was performed using an independent external test dataset from Aachen University Hospital (n = 20). RESULTS: The final training, validation, and testing dataset consisted of 1900/50/50 segmentation masks for each anatomical structure. Our model achieved a mean DSC/JI/HD/ASSD of 0.93/0.88/32.1/5.8 for the lung, 0.92/0.86/21.65/4.85 for the mediastinum, 0.91/0.84/11.83/1.35 for the clavicles, 0.9/0.85/9.6/2.19 for the trachea, and 0.88/0.8/31.74/8.73 for the heart. Validation using the external dataset showed an overall robust performance of our algorithm. CONCLUSIONS: Using an efficient computer-aided segmentation method with active learning, our anatomy-based model achieves comparable performance to state-of-the-art approaches. Instead of only segmenting the non-overlapping portions of the organs, as previous studies did, a closer approximation to actual anatomy is achieved by segmenting along the natural anatomical borders. This novel anatomy approach could be useful for developing pathology models for accurate and quantifiable diagnosis.

Combined CT-guided high-dose-rate brachytherapy (CT-HDRBT) and transarterial chemoembolization with irinotecan-loaded microspheres improve local tumor control and progression-free survival in patients with unresectable colorectal liver metastases compared with mono-CT-HDRBT.

Purpose: To compare the effectivity and toxicity of monotherapy with computed tomography-guided high-dose-rate brachytherapy (CT-HDRBT) vs. combination therapy of transarterial chemoembolization with irinotecan (irinotecan-TACE) and CT-HDRBT in patients with large unresectable colorectal liver metastases (CRLM) with a diameter of > 3 cm. Material and methods: Forty-four retrospectively matched patients with unresectable CRLM were treated either with mono-CT-HDRBT or with a combination of irinotecan-TACE and CT-HDRBT (n = 22 in each group). Matching parameters included treatment, disease, and baseline characteristics. National Cancer Institute Common Terminology Criteria for Adverse Events (version 5.0) were used to evaluate treatment toxicity and the Society of Interventional Radiology classification was applied to analyze catheter-related adverse events. Statistical analysis involved Cox regression, Kaplan-Meier estimator, log-rank test, receiver operating characteristic curve analysis, Shapiro-Wilk test, Wilcoxon test, paired sample t-test, and McNemar test. P-values < 0.05 were deemed significant. Results: Combination therapy ensued longer median progression-free survival (PFS: 5/2 months, p = 0.002) and significantly lower local (23%/68%, p < 0.001) and intrahepatic (50%/95%, p < 0.001) progress rates compared with mono-CT-HDRBT after a median follow-up time of 10 months. Additionally, tendencies for longer local tumor control (LTC: 17/9 months, p = 0.052) were found in patients undergoing both interventions. After combination therapy, aspartate and alanine aminotransferase toxicity levels increased significantly, while total bilirubin toxicity levels showed significantly higher increases after monotherapy. No catheter-associated major or minor complications were identified in each cohort. Conclusions: Combining irinotecan-TACE with CT-HDRBT can improve LTC rates and PFS compared with mono-CT-HDRBT in patients with unresectable CRLM. The combination of irinotecan-TACE and CT-HDRBT shows satisfying safety profiles.

What Does DALL-E 2 Know About Radiology?

Generative models, such as DALL-E 2 (OpenAI), could represent promising future tools for image generation, augmentation, and manipulation for artificial intelligence research in radiology, provided that these models have sufficient medical domain knowledge. Herein, we show that DALL-E 2 has learned relevant representations of x-ray images, with promising capabilities in terms of zero-shot text-to-image generation of new images, the continuation of an image beyond its original boundaries, and the removal of elements; however, its capabilities for the generation of images with pathological abnormalities (eg, tumors, fractures, and inflammation) or computed tomography, magnetic resonance imaging, or ultrasound images are still limited. The use of generative models for augmenting and generating radiological data thus seems feasible, even if the further fine-tuning and adaptation of these models to their respective domains are required first.

Non-Invasive Imaging Biomarkers to Predict the Hepatopulmonary Shunt Fraction Before Transarterial Radioembolization in Patients with Hepatocellular Carcinoma.

Purpose: To identify disease-specific profiles comprising patient characteristics and imaging biomarkers on contrast-enhanced (CE)-computed tomography (CT) that enable the non-invasive prediction of the hepatopulmonary shunt fraction (HPSF) in patients with hepatocellular carcinoma (HCC) before resin-based transarterial radioembolization (TARE). Patients and Methods: This institutional review board-approved (EA2/071/19) retrospective study included 56 patients with HCC recommended for TARE. All patients received tri-phasic CE-CT within 6 weeks prior to an angiographic TARE evaluation study using technetium-99m macroaggregated albumin. Imaging biomarkers representative of tumor extent, morphology, and perfusion, as well as disease-specific clinical parameters, were used to perform data-driven variable selection with backward elimination to generate multivariable linear regression models predictive of HPSF. Results were used to create clinically applicable risk scores for patients scheduled for TARE. Additionally, Cox regression was used to identify independent risk factors for poor overall survival (OS). Results: Mean HPSF was 13.11% ± 7.6% (range: 2.8- 35.97%). Index tumor diameter (p = 0.014) or volume (p = 0.034) in combination with index tumor non-rim arterial phase enhancement (APHE) (p < 0.001) and washout (p < 0.001) were identified as significant non-invasive predictors of HPSF on CE-CT. Specifically, the prediction models revealed that the HPSF increased with index lesion diameter or volume and showed higher HPSF if non-rim APHE was present. In contrast, index tumor washout was associated with decreased HPSF levels. Independent risk factors of poorer OS were radiogenomic venous invasion and ascites at baseline. Conclusion: The featured prediction models can be used for the initial non-invasive estimation of HPSF in patients with HCC before TARE to assist in clinical treatment evaluation while potentially sparing ineligible patients from the angiographic shunt evaluation study.

Sex Differences in Renal Cell Carcinoma: The Importance of Body Composition.

PURPOSE: To examine sex-specific differences in renal cell carcinoma (RCC) in relation to abdominal fat accumulation, psoas muscle density, tumor size, pathology, and survival, and to evaluate possible associations with RCC characteristics and outcome. METHODS: A total of 470 patients with RCC who underwent nephrectomy between 2006 and 2019 were included in this retrospective study. Specific characteristics of RCC patients were collected, including sex, height, tumor size, grade, and data on patient survival, if available. Abdominal fat measurements and psoas muscle area were determined at the level of L3 (cm2). RESULTS: Women had a higher subcutaneous (p < 0.001) and men had a higher visceral fat area, relative proportion of visceral fat area (p < 0.001), and psoas muscle index (p < 0.001). Logistic regression analysis showed an association between higher psoas muscle index and lower grade tumors [women: odds ratio (OR) 0.94, 95% confidence interval (CI) 0.89-0.99, p = 0.011; men: OR 0.97 (95% CI, 0.95-0.99, p = 0.012]. Univariate regression analysis demonstrated an association between psoas muscle index and overall survival (women: OR 1.41, 95% CI 1.03-1.93, p = 0.033; men: OR 1.62 (95% CI, 1.33-1.97, p < 0.001). In contrast, there were no associations between abdominal fat measurements and tumor size, grade, or survival. Also, there were no sex-specific differences in tumor size or tumor grades. CONCLUSIONS: A higher preoperative psoas muscle index was independently associated with overall survival in RCC patients, with a stronger association in men compared with women. In addition, the psoas muscle index showed an inverse association with tumor grade, whereby this association was slightly more pronounced in women than in men.

Dataset of prostate MRI annotated for anatomical zones and cancer.

In the present work, we present a publicly available, expert-segmented representative dataset of 158 3.0 Tesla biparametric MRIs [1]. There is an increasing number of studies investigating prostate and prostate carcinoma segmentation using deep learning (DL) with 3D architectures [2], [3], [4], [5], [6], [7]. The development of robust and data-driven DL models for prostate segmentation and assessment is currently limited by the availability of openly available expert-annotated datasets [8], [9], [10]. The dataset contains 3.0 Tesla MRI images of the prostate of patients with suspected prostate cancer. Patients over 50 years of age who had a 3.0 Tesla MRI scan of the prostate that met PI-RADS version 2.1 technical standards were included. All patients received a subsequent biopsy or surgery so that the MRI diagnosis could be verified/matched with the histopathologic diagnosis. For patients who had undergone multiple MRIs, the last MRI, which was less than six months before biopsy/surgery, was included. All patients were examined at a German university hospital (Charité Universitätsmedizin Berlin) between 02/2016 and 01/2020. All MRI were acquired with two 3.0 Tesla MRI scanners (Siemens VIDA and Skyra, Siemens Healthineers, Erlangen, Germany). Axial T2W sequences and axial diffusion-weighted sequences (DWI) with apparent diffusion coefficient maps (ADC) were included in the data set. T2W sequences and ADC maps were annotated by two board-certified radiologists with 6 and 8 years of experience, respectively. For T2W sequences, the central gland (central zone and transitional zone) and peripheral zone were segmented. If areas of suspected prostate cancer (PIRADS score of ≥ 4) were identified on examination, they were segmented in both the T2W sequences and ADC maps. Because restricted diffusion is best seen in DWI images with high b-values, only these images were selected and all images with low b-values were discarded. Data were then anonymized and converted to NIfTI (Neuroimaging Informatics Technology Initiative) format.

Blind spots on western blots: Assessment of common problems in western blot figures and methods reporting with recommendations to improve them.

Western blotting is a standard laboratory method used to detect proteins and assess their expression levels. Unfortunately, poor western blot image display practices and a lack of detailed methods reporting can limit a reader's ability to evaluate or reproduce western blot results. While several groups have studied the prevalence of image manipulation or provided recommendations for improving western blotting, data on the prevalence of common publication practices are scarce. We systematically examined 551 articles published in the top 25% of journals in neurosciences (n = 151) and cell biology (n = 400) that contained western blot images, focusing on practices that may omit important information. Our data show that most published western blots are cropped and blot source data are not made available to readers in the supplement. Publishing blots with visible molecular weight markers is rare, and many blots additionally lack molecular weight labels. Western blot methods sections often lack information on the amount of protein loaded on the gel, blocking steps, and antibody labeling protocol. Important antibody identifiers like company or supplier, catalog number, or RRID were omitted frequently for primary antibodies and regularly for secondary antibodies. We present detailed descriptions and visual examples to help scientists, peer reviewers, and editors to publish more informative western blot figures and methods. Additional resources include a toolbox to help scientists produce more reproducible western blot data, teaching slides in English and Spanish, and an antibody reporting template.

Prostate158 - An expert-annotated 3T MRI dataset and algorithm for prostate cancer detection.

BACKGROUND: The development of deep learning (DL) models for prostate segmentation on magnetic resonance imaging (MRI) depends on expert-annotated data and reliable baselines, which are often not publicly available. This limits both reproducibility and comparability. METHODS: Prostate158 consists of 158 expert annotated biparametric 3T prostate MRIs comprising T2w sequences and diffusion-weighted sequences with apparent diffusion coefficient maps. Two U-ResNets trained for segmentation of anatomy (central gland, peripheral zone) and suspicious lesions for prostate cancer (PCa) with a PI-RADS score of ≥4 served as baseline algorithms. Segmentation performance was evaluated using the Dice similarity coefficient (DSC), the Hausdorff distance (HD), and the average surface distance (ASD). The Wilcoxon test with Bonferroni correction was used to evaluate differences in performance. The generalizability of the baseline model was assessed using the open datasets Medical Segmentation Decathlon and PROSTATEx. RESULTS: Compared to Reader 1, the models achieved a DSC/HD/ASD of 0.88/18.3/2.2 for the central gland, 0.75/22.8/1.9 for the peripheral zone, and 0.45/36.7/17.4 for PCa. Compared with Reader 2, the DSC/HD/ASD were 0.88/17.5/2.6 for the central gland, 0.73/33.2/1.9 for the peripheral zone, and 0.4/39.5/19.1 for PCa. Interrater agreement measured in DSC/HD/ASD was 0.87/11.1/1.0 for the central gland, 0.75/15.8/0.74 for the peripheral zone, and 0.6/18.8/5.5 for PCa. Segmentation performances on the Medical Segmentation Decathlon and PROSTATEx were 0.82/22.5/3.4; 0.86/18.6/2.5 for the central gland, and 0.64/29.2/4.7; 0.71/26.3/2.2 for the peripheral zone. CONCLUSIONS: We provide an openly accessible, expert-annotated 3T dataset of prostate MRI and a reproducible benchmark to foster the development of prostate segmentation algorithms.

Gender Segregation, Occupational Sorting, and Growth of Wage Disparities Between Women.

Average female wages in traditionally male occupations have steeply risen over the past couple of decades in Germany. This trend led to a new and substantial pay gap between women working in male-typed occupations and other women. I dissect the emergence of these wage disparities between women, using data from the German Socio-Economic Panel (1992-2015). Compositional change with respect to education is the main driver for growing inequality. Other factors are less influential but still relevant: marginal returns for several wage-related personal characteristics have grown faster in male-typed occupations. Net of individual-level heterogeneity, traditionally male occupations have also become more attractive because of rising returns to task-specific skills. Discrimination of women in typically male lines of work seems to have declined, too, which erased part of the wage penalty these women had previously experienced. In sum, I document changes in the occupational sorting behavior of women as well as shifts in occupation-level reward mechanisms that have had a profound impact on the state of inequality between working women.