المؤلفون: Dorfner, Felix J., Vahldiek, Janis L., Donle, Leonhard, Zhukov, Andrei, Xu, Lina, Häntze, Hartmut, Makowski, Marcus R., Aerts, Hugo J. W. L., Proft, Fabian, Rodriguez, Valeria Rios, Rademacher, Judith, Protopopov, Mikhail, Haibel, Hildrun, Diekhoff, Torsten, Torgutalp, Murat, Adams, Lisa C., Poddubnyy, Denis, Bressem, Keno K.

مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning

الوصف: Purpose: To examine whether incorporating anatomical awareness into a deep learning model can improve generalizability and enable prediction of disease progression. Methods: This retrospective multicenter study included conventional pelvic radiographs of 4 different patient cohorts focusing on axial spondyloarthritis (axSpA) collected at university and community hospitals. The first cohort, which consisted of 1483 radiographs, was split into training (n=1261) and validation (n=222) sets. The other cohorts comprising 436, 340, and 163 patients, respectively, were used as independent test datasets. For the second cohort, follow-up data of 311 patients was used to examine progression prediction capabilities. Two neural networks were trained, one on images cropped to the bounding box of the sacroiliac joints (anatomy-aware) and the other one on full radiographs. The performance of the models was compared using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. Results: On the three test datasets, the standard model achieved AUC scores of 0.853, 0.817, 0.947, with an accuracy of 0.770, 0.724, 0.850. Whereas the anatomy-aware model achieved AUC scores of 0.899, 0.846, 0.957, with an accuracy of 0.821, 0.744, 0.906, respectively. The patients who were identified as high risk by the anatomy aware model had an odds ratio of 2.16 (95% CI: 1.19, 3.86) for having progression of radiographic sacroiliitis within 2 years. Conclusion: Anatomical awareness can improve the generalizability of a deep learning model in detecting radiographic sacroiliitis. The model is published as fully open source alongside this study.

الوصول الحر: http://arxiv.org/abs/2405.07369Test

المؤلفون: Häntze, Hartmut, Xu, Lina, Dorfner, Felix J., Donle, Leonhard, Truhn, Daniel, Aerts, Hugo, Prokop, Mathias, van Ginneken, Bram, Hering, Alessa, Adams, Lisa C., Bressem, Keno K.

مصطلحات موضوعية: Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, J.3

الوصف: Purpose: To introduce a deep learning model capable of multi-organ segmentation in MRI scans, offering a solution to the current limitations in MRI analysis due to challenges in resolution, standardized intensity values, and variability in sequences. Materials and Methods: he model was trained on 1,200 manually annotated MRI scans from the UK Biobank, 221 in-house MRI scans and 1228 CT scans, leveraging cross-modality transfer learning from CT segmentation models. A human-in-the-loop annotation workflow was employed to efficiently create high-quality segmentations. The model's performance was evaluated on NAKO and the AMOS22 dataset containing 600 and 60 MRI examinations. Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD) was used to assess segmentation accuracy. The model will be open sourced. Results: The model showcased high accuracy in segmenting well-defined organs, achieving Dice Similarity Coefficient (DSC) scores of 0.97 for the right and left lungs, and 0.95 for the heart. It also demonstrated robustness in organs like the liver (DSC: 0.96) and kidneys (DSC: 0.95 left, 0.95 right), which present more variability. However, segmentation of smaller and complex structures such as the portal and splenic veins (DSC: 0.54) and adrenal glands (DSC: 0.65 left, 0.61 right) revealed the need for further model optimization. Conclusion: The proposed model is a robust, tool for accurate segmentation of 40 anatomical structures in MRI and CT images. By leveraging cross-modality learning and interactive annotation, the model achieves strong performance and generalizability across diverse datasets, making it a valuable resource for researchers and clinicians. It is open source and can be downloaded from https://github.com/hhaentze/MRSegmentatorTest.
Comment: 13 pages, 6 figures; corrected co-author info

الوصول الحر: http://arxiv.org/abs/2405.06463Test

المؤلفون: Häntze, Hartmut, Xu, Lina, Donle, Leonhard, Dorfner, Felix J., Hering, Alessa, Adams, Lisa C., Bressem, Keno K.

مصطلحات موضوعية: Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, J.3

الوصف: Computed tomography (CT) segmentation models frequently include classes that are not currently supported by magnetic resonance imaging (MRI) segmentation models. In this study, we show that a simple image inversion technique can significantly improve the segmentation quality of CT segmentation models on MRI data, by using the TotalSegmentator model, applied to T1-weighted MRI images, as example. Image inversion is straightforward to implement and does not require dedicated graphics processing units (GPUs), thus providing a quick alternative to complex deep modality-transfer models for generating segmentation masks for MRI data.
Comment: 3 pages, 2 figures

الوصول الحر: http://arxiv.org/abs/2405.03713Test

المؤلفون: Dorfner, Felix J., Jürgensen, Liv, Donle, Leonhard, Mohamad, Fares Al, Bodenmann, Tobias R., Cleveland, Mason C., Busch, Felix, Adams, Lisa C., Sato, James, Schultz, Thomas, Kim, Albert E., Merkow, Jameson, Bressem, Keno K., Bridge, Christopher P.

مصطلحات موضوعية: Computer Science - Computation and Language, Computer Science - Artificial Intelligence

الوصف: Introduction: With the rapid advances in large language models (LLMs), there have been numerous new open source as well as commercial models. While recent publications have explored GPT-4 in its application to extracting information of interest from radiology reports, there has not been a real-world comparison of GPT-4 to different leading open-source models. Materials and Methods: Two different and independent datasets were used. The first dataset consists of 540 chest x-ray reports that were created at the Massachusetts General Hospital between July 2019 and July 2021. The second dataset consists of 500 chest x-ray reports from the ImaGenome dataset. We then compared the commercial models GPT-3.5 Turbo and GPT-4 from OpenAI to the open-source models Mistral-7B, Mixtral-8x7B, Llama2-13B, Llama2-70B, QWEN1.5-72B and CheXbert and CheXpert-labeler in their ability to accurately label the presence of multiple findings in x-ray text reports using different prompting techniques. Results: On the ImaGenome dataset, the best performing open-source model was Llama2-70B with micro F1-scores of 0.972 and 0.970 for zero- and few-shot prompts, respectively. GPT-4 achieved micro F1-scores of 0.975 and 0.984, respectively. On the institutional dataset, the best performing open-source model was QWEN1.5-72B with micro F1-scores of 0.952 and 0.965 for zero- and few-shot prompting, respectively. GPT-4 achieved micro F1-scores of 0.975 and 0.973, respectively. Conclusion: In this paper, we show that while GPT-4 is superior to open-source models in zero-shot report labeling, the implementation of few-shot prompting can bring open-source models on par with GPT-4. This shows that open-source models could be a performant and privacy preserving alternative to GPT-4 for the task of radiology report classification.

الوصول الحر: http://arxiv.org/abs/2402.12298Test

المؤلفون: Han, Tianyu, Adams, Lisa C., Papaioannou, Jens-Michalis, Grundmann, Paul, Oberhauser, Tom, Löser, Alexander, Truhn, Daniel, Bressem, Keno K.

مصطلحات موضوعية: Computer Science - Computation and Language, Computer Science - Artificial Intelligence

الوصف: As large language models (LLMs) like OpenAI's GPT series continue to make strides, we witness the emergence of artificial intelligence applications in an ever-expanding range of fields. In medicine, these LLMs hold considerable promise for improving medical workflows, diagnostics, patient care, and education. Yet, there is an urgent need for open-source models that can be deployed on-premises to safeguard patient privacy. In our work, we present an innovative dataset consisting of over 160,000 entries, specifically crafted to fine-tune LLMs for effective medical applications. We investigate the impact of fine-tuning these datasets on publicly accessible pre-trained LLMs, and subsequently, we juxtapose the performance of pre-trained-only models against the fine-tuned models concerning the examinations that future medical doctors must pass to achieve certification.

الوصول الحر: http://arxiv.org/abs/2304.08247Test

المؤلفون: Bressem, Keno K., Papaioannou, Jens-Michalis, Grundmann, Paul, Borchert, Florian, Adams, Lisa C., Liu, Leonhard, Busch, Felix, Xu, Lina, Loyen, Jan P., Niehues, Stefan M., Augustin, Moritz, Grosser, Lennart, Makowski, Marcus R., Aerts, Hugo JWL., Löser, Alexander

المصدر: Expert Systems with Applications 2024;237(21):121598

مصطلحات موضوعية: Computer Science - Computation and Language, Computer Science - Artificial Intelligence

الوصف: This paper presents medBERTde, a pre-trained German BERT model specifically designed for the German medical domain. The model has been trained on a large corpus of 4.7 Million German medical documents and has been shown to achieve new state-of-the-art performance on eight different medical benchmarks covering a wide range of disciplines and medical document types. In addition to evaluating the overall performance of the model, this paper also conducts a more in-depth analysis of its capabilities. We investigate the impact of data deduplication on the model's performance, as well as the potential benefits of using more efficient tokenization methods. Our results indicate that domain-specific models such as medBERTde are particularly useful for longer texts, and that deduplication of training data does not necessarily lead to improved performance. Furthermore, we found that efficient tokenization plays only a minor role in improving model performance, and attribute most of the improved performance to the large amount of training data. To encourage further research, the pre-trained model weights and new benchmarks based on radiological data are made publicly available for use by the scientific community.
Comment: Keno K. Bressem and Jens-Michalis Papaioannou and Paul Grundmann contributed equally

الوصول الحر: http://arxiv.org/abs/2303.08179Test

المؤلفون: Adams, Lisa C., Busch, Felix, Truhn, Daniel, Makowski, Marcus R., Aerts, Hugo JWL., Bressem, Keno K.

المصدر: J Med Internet Res 2023;25:e43110

مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Electrical Engineering and Systems Science - Image and Video Processing

الوصف: Generative models such as DALL-E 2 could represent a promising future tool for image generation, augmentation, and manipulation for artificial intelligence research in radiology provided that these models have sufficient medical domain knowledge. Here 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, continuation of an image beyond its original boundaries, or removal of elements, while pathology generation or CT, MRI, and ultrasound images are still limited. The use of generative models for augmenting and generating radiological data thus seems feasible, even if further fine-tuning and adaptation of these models to the respective domain is required beforehand.
Comment: 4 Figures

الوصول الحر: http://arxiv.org/abs/2209.13696Test

المؤلفون: Bressem, Keno K., Niehues, Stefan M., Hamm, Bernd, Makowski, Marcus R., Vahldiek, Janis L., Adams, Lisa C.

مصطلحات موضوعية: Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning

الوصف: Segmentation of pulmonary infiltrates can help assess severity of COVID-19, but manual segmentation is labor and time-intensive. Using neural networks to segment pulmonary infiltrates would enable automation of this task. However, training a 3D U-Net from computed tomography (CT) data is time- and resource-intensive. In this work, we therefore developed and tested a solution on how transfer learning can be used to train state-of-the-art segmentation models on limited hardware and in shorter time. We use the recently published RSNA International COVID-19 Open Radiology Database (RICORD) to train a fully three-dimensional U-Net architecture using an 18-layer 3D ResNet, pretrained on the Kinetics-400 dataset as encoder. The generalization of the model was then tested on two openly available datasets of patients with COVID-19, who received chest CTs (Corona Cases and MosMed datasets). Our model performed comparable to previously published 3D U-Net architectures, achieving a mean Dice score of 0.679 on the tuning dataset, 0.648 on the Coronacases dataset and 0.405 on the MosMed dataset. Notably, these results were achieved with shorter training time on a single GPU with less memory available than the GPUs used in previous studies.
Comment: 8 Pages, 2 figures, 3 tables

الوصول الحر: http://arxiv.org/abs/2101.09976Test

المؤلفون: Adams, Lisa C., Busch, Felix, Truhn, Daniel, Makowski, Marcus R., Aerts, Hugo J. W. L., Bressem, Keno K.

المصدر: Adams , L C , Busch , F , Truhn , D , Makowski , M R , Aerts , H J W L & Bressem , K K 2023 , ' What Does DALL-E 2 Know About Radiology? ' , Journal of Medical Internet Research , vol. 25 , no. 1 , e43110 . https://doi.org/10.2196/43110Test

مصطلحات موضوعية: DALL-E, creating images from text, image creation, image generation, transformer language model, machine learning, generative model, radiology, x-ray, artificial intelligence, medical imaging, text-to-image, diagnostic imaging

الوصف: 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.

العلاقة: https://cris.maastrichtuniversity.nl/en/publications/f4e3d721-ba80-4370-b0c6-8852e6a034a7Test

الإتاحة: https://doi.org/10.2196/43110Test
https://cris.maastrichtuniversity.nl/en/publications/f4e3d721-ba80-4370-b0c6-8852e6a034a7Test

المؤلفون: Adams, Lisa C, Busch, Felix, Truhn, Daniel, Makowski, Marcus R, Aerts, Hugo J W L, Bressem, Keno K

مصطلحات موضوعية: DALL-E, creating images from text, image creation, image generation, transformer language model, machine learning, generative model, radiology, x-ray, artificial intelligence, medical imaging, text-to-image, diagnostic imaging, ddc:610

الوصف: 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.

وصف الملف: application/pdf

العلاقة: https://refubium.fu-berlin.de/handle/fub188/40974Test; http://dx.doi.org/10.17169/refubium-40695Test

الإتاحة: https://doi.org/10.17169/refubium-40695Test
https://doi.org/10.2196/43110Test
https://refubium.fu-berlin.de/handle/fub188/40974Test