Explore the vast range of titles available.

A knowledge gap persists between machine learning (ML) developers (e.g., data scientists) and practitioners (e.g., clinicians), hampering the full utilization of ML for clinical data analysis. We investigated the potential of the ChatGPT Advanced Data Analysis (ADA), an extension of GPT-4, to bridge this gap and perform ML analyses efficiently. Real-world clinical datasets and study details from large trials across various medical specialties were presented to ChatGPT ADA without specific guidance. ChatGPT ADA autonomously developed state-of-the-art ML models based on the original study’s training data to predict clinical outcomes such as cancer development, cancer progression, disease complications, or biomarkers such as pathogenic gene sequences. Following the re-implementation and optimization of the published models, the head-to-head comparison of the ChatGPT ADA-crafted ML models and their respective manually crafted counterparts revealed no significant differences in traditional performance metrics ( p  ≥ 0.072). Strikingly, the ChatGPT ADA-crafted ML models often outperformed their counterparts. In conclusion, ChatGPT ADA offers a promising avenue to democratize ML in medicine by simplifying complex data analyses, yet should enhance, not replace, specialized training and resources, to promote broader applications in medical research and practice. A knowledge gap persists between machine learning developers and clinicians. Here, the authors show that the Advanced Data Analysis extension of ChatGPT could bridge this gap and simplify complex data analyses, making them more accessible to clinicians.

Although generative adversarial networks (GANs) can produce large datasets, their limited diversity and fidelity have been recently addressed by denoising diffusion probabilistic models, which have demonstrated superiority in natural image synthesis. In this study, we introduce Medfusion, a conditional latent DDPM designed for medical image generation, and evaluate its performance against GANs, which currently represent the state-of-the-art. Medfusion was trained and compared with StyleGAN-3 using fundoscopy images from the AIROGS dataset, radiographs from the CheXpert dataset, and histopathology images from the CRCDX dataset. Based on previous studies, Progressively Growing GAN (ProGAN) and Conditional GAN (cGAN) were used as additional baselines on the CheXpert and CRCDX datasets, respectively. Medfusion exceeded GANs in terms of diversity (recall), achieving better scores of 0.40 compared to 0.19 in the AIROGS dataset, 0.41 compared to 0.02 (cGAN) and 0.24 (StyleGAN-3) in the CRMDX dataset, and 0.32 compared to 0.17 (ProGAN) and 0.08 (StyleGAN-3) in the CheXpert dataset. Furthermore, Medfusion exhibited equal or higher fidelity (precision) across all three datasets. Our study shows that Medfusion constitutes a promising alternative to GAN-based models for generating high-quality medical images, leading to improved diversity and less artifacts in the generated images.

To my knowledge, this is the first study of MRI screening that used a randomised design. [...]this study not only allows for comparison of respective cancer detection rate and diagnostic accuracy, as did all previous studies2–5 on the screening performance of MRI versus mammography, but also provides important outcome measures useful to evaluate the oncological implications of the respective screening methods. For the time being, the authors report on tumour stage at diagnosis (eg, cancer size and lymph node status) as an established proxy for the effects of screening on breast cancer mortality and the need for adjuvant chemotherapy. To measure the effect of a new screening method on tumour stage at diagnosis, the results of subsequent (incident) screening rounds are more informative than those of the first round. [...]at the incident screening rounds performed by Saadatmand and colleagues, the tumour stage shift between MRI and mammography screening becomes even more apparent, with two node-positive cancers (11%) of 18 invasive cancers in the MRI group compared with five (63%) of eight in the mammography group (p=0·014) and no interval cancers observed.

Identifying image features that are robust with respect to segmentation variability is a tough challenge in radiomics. So far, this problem has mainly been tackled in test–retest analyses. In this work we analyse radiomics feature reproducibility in two phases: first with manual segmentations provided by four expert readers and second with probabilistic automated segmentations using a recently developed neural network (PHiseg). We test feature reproducibility on three publicly available datasets of lung, kidney and liver lesions. We find consistent results both over manual and automated segmentations in all three datasets and show that there are subsets of radiomic features which are robust against segmentation variability and other radiomic features which are prone to poor reproducibility under differing segmentations. By providing a detailed analysis of robustness of the most common radiomics features across several datasets, we envision that more reliable and reproducible radiomic models can be built in the future based on this work.

Recent advances in computer vision have shown promising results in image generation. Diffusion probabilistic models have generated realistic images from textual input, as demonstrated by DALL-E 2, Imagen, and Stable Diffusion. However, their use in medicine, where imaging data typically comprises three-dimensional volumes, has not been systematically evaluated. Synthetic images may play a crucial role in privacy-preserving artificial intelligence and can also be used to augment small datasets. We show that diffusion probabilistic models can synthesize high-quality medical data for magnetic resonance imaging (MRI) and computed tomography (CT). For quantitative evaluation, two radiologists rated the quality of the synthesized images regarding \"realistic image appearance\", \"anatomical correctness\", and \"consistency between slices\". Furthermore, we demonstrate that synthetic images can be used in self-supervised pre-training and improve the performance of breast segmentation models when data is scarce (Dice scores, 0.91 [without synthetic data], 0.95 [with synthetic data]).

Breast density is an independent risk factor for the development of breast cancer and also decreases the sensitivity of mammography for screening. Consequently, women with extremely dense breasts face an increased risk of late diagnosis of breast cancer. These women are, therefore, underserved with current mammographic screening programs. The results of recent studies reporting on contrast-enhanced breast MRI as a screening method in women with extremely dense breasts provide compelling evidence that this approach can enable an important reduction in breast cancer mortality for these women and is cost-effective. Because there is now a valid option to improve breast cancer screening, the European Society of Breast Imaging (EUSOBI) recommends that women should be informed about their breast density. EUSOBI thus calls on all providers of mammography screening to share density information with the women being screened. In light of the available evidence, in women aged 50 to 70 years with extremely dense breasts, the EUSOBI now recommends offering screening breast MRI every 2 to 4 years. The EUSOBI acknowledges that it may currently not be possible to offer breast MRI immediately and everywhere and underscores that quality assurance procedures need to be established, but urges radiological societies and policymakers to act on this now. Since the wishes and values of individual women differ, in screening the principles of shared decision-making should be embraced. In particular, women should be counselled on the benefits and risks of mammography and MRI-based screening, so that they are capable of making an informed choice about their preferred screening method. Key Points • The recommendations in Figure 1 summarize the key points of the manuscript

Unmasking the decision making process of machine learning models is essential for implementing diagnostic support systems in clinical practice. Here, we demonstrate that adversarially trained models can significantly enhance the usability of pathology detection as compared to their standard counterparts. We let six experienced radiologists rate the interpretability of saliency maps in datasets of X-rays, computed tomography, and magnetic resonance imaging scans. Significant improvements are found for our adversarial models, which are further improved by the application of dual-batch normalization. Contrary to previous research on adversarially trained models, we find that accuracy of such models is equal to standard models, when sufficiently large datasets and dual batch norm training are used. To ensure transferability, we additionally validate our results on an external test set of 22,433 X-rays. These findings elucidate that different paths for adversarial and real images are needed during training to achieve state of the art results with superior clinical interpretability. Unmasking the decision making process of machine learning models is essential for implementing diagnostic support systems in clinical practice. Here, the authors demonstrate that adversarially trained models can significantly enhance the usability of pathology detection as compared to their standard counterparts.

This paper summarizes information about breast MRI to be provided to women and referring physicians. After listing contraindications, procedure details are described, stressing the need for correct scheduling and not moving during the examination. The structured report including BI-RADS® categories and further actions after a breast MRI examination are discussed. Breast MRI is a very sensitive modality, significantly improving screening in high-risk women. It also has a role in clinical diagnosis, problem solving, and staging, impacting on patient management. However, it is not a perfect test, and occasionally breast cancers can be missed. Therefore, clinical and other imaging findings (from mammography/ultrasound) should also be considered. Conversely, MRI may detect lesions not visible on other imaging modalities turning out to be benign (false positives). These risks should be discussed with women before a breast MRI is requested/performed. Because breast MRI drawbacks depend upon the indication for the examination, basic information for the most important breast MRI indications is presented. Seventeen notes and five frequently asked questions formulated for use as direct communication to women are provided. The text was reviewed by Europa Donna–The European Breast Cancer Coalition to ensure that it can be easily understood by women undergoing MRI. Key Points • Information on breast MRI concerns advantages/disadvantages and preparation to the examination • Claustrophobia, implantable devices, allergic predisposition, and renal function should be checked • Before menopause, scheduling on day 7–14 of the cycle is preferred • During the examination, it is highly important that the patient keeps still • Availability of prior examinations improves accuracy of breast MRI interpretation

EUSOBI and 30 national breast radiology bodies support mammography for population-based screening, demonstrated to reduce breast cancer (BC) mortality and treatment impact. According to the International Agency for Research on Cancer, the reduction in mortality is 40 % for women aged 50–69 years taking up the invitation while the probability of false-positive needle biopsy is <1 % per round and overdiagnosis is only 1–10 % for a 20-year screening. Mortality reduction was also observed for the age groups 40–49 years and 70–74 years, although with “limited evidence”. Thus, we firstly recommend biennial screening mammography for average-risk women aged 50–69 years; extension up to 73 or 75 years, biennially, is a second priority, from 40–45 to 49 years, annually, a third priority. Screening with thermography or other optical tools as alternatives to mammography is discouraged. Preference should be given to population screening programmes on a territorial basis, with double reading. Adoption of digital mammography (not film-screen or phosphor-plate computer radiography) is a priority, which also improves sensitivity in dense breasts. Radiologists qualified as screening readers should be involved in programmes. Digital breast tomosynthesis is also set to become “routine mammography” in the screening setting in the next future. Dedicated pathways for high-risk women offering breast MRI according to national or international guidelines and recommendations are encouraged. Key points • EUSOBI and 30 national breast radiology bodies support screening mammography . • A first priority is double - reading biennial mammography for women aged 50 – 69 years . • Extension to 73 – 75 and from 40 – 45 to 49 years is also encouraged . • Digital mammography ( not film - screen or computer radiography ) should be used . • DBT is set to become “ routine mammography ” in the screening setting in the next future .

Diagnosing breast cancer in its intraductal stage might be helpful to prevent the development of invasive cancer. Our aim was to investigate the sensitivity with which ductal carcinoma in situ (DCIS) is diagnosed by mammography and by breast MRI. During a 5-year period, 7319 women who were referred to an academic national breast centre received MRI in addition to mammography for diagnostic assessment and screening. Mammograms and breast MRI studies were assessed independently by different radiologists. We investigated the sensitivity of each method of detection and compared the biological profiles of mammography-diagnosed DCIS versus DCIS detected by MRI alone. We also compared the risk profiles of women with mammography-detected DCIS with those of MRI-detected DCIS. 193 women received a final surgical pathology diagnosis of pure DCIS. Of those, 167 had undergone both imaging tests preoperatively. 93 (56%) of these cases were diagnosed by mammography and 153 (92%) by MRI (p<0·0001). Of the 89 high-grade DCIS, 43 (48%) were missed by mammography, but diagnosed by MRI alone; all 43 cases missed by mammography were detected by MRI. By contrast, MRI detected 87 (98%) of these lesions; the two cases missed by MRI were detected by mammography. Age, menopausal status, personal or family history of breast cancer or of benign breast disease, and breast density of women with MRI-only diagnosed DCIS did not differ significantly from those of women with mammography-diagnosed DCIS. MRI could help improve the ability to diagnose DCIS, especially DCIS with high nuclear grade.