82 research outputs found
Correction: Six minute walk distance and reference values in healthy Italian children: A cross-sectional study (PLoS ONE (2018) 13, 10 (e0205792) DOI:10.1371/journal.pone.0205792)
No full textThe affiliation for the fifth author is incorrect. Roberto Codella is not affiliated with #4–8 but with #4 and #8: School of Exercise Sciences, Department of Biomedical Sciences for Health, Università degli Studi di Milano, Milan, Italy and Metabolism Research Center, IRCCS Policlinico San Donato, San Donato Milanese, Italy
ISIC2018_Task1-2_Training_Input.zip
No full text To comply with the attribution requirements of the CC-BY-NC license , the aggregate "ISIC 2018: Training" data must be cited as:
HAM10000 Dataset: (c) by ViDIR Group, Department of Dermatology, Medical University of Vienna; https://doi.org/10.1038/sdata.2018.161
MSK Dataset: (c) Anonymous; https://arxiv.org/abs/1710.05006; https://arxiv.org/abs/1902.03368
When referencing this dataset in your own manuscripts and publications, please use the following full citations:
[1] Noel Codella, Veronica Rotemberg, Philipp Tschandl, M. Emre Celebi, Stephen Dusza, David Gutman, Brian Helba, Aadi Kalloo, Konstantinos Liopyris, Michael Marchetti, Harald Kittler, Allan Halpern: "Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)", 2018; https://arxiv.org/abs/1902.03368
[2] Tschandl, P., Rosendahl, C. & Kittler, H. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci. Data 5, 180161 doi:10.1038/sdata.2018.161 (2018).</blockquote
A reinforcement learning model for AI-based decision support in skin cancer
Get PDF: We investigated whether human preferences hold the potential to improve diagnostic artificial intelligence (AI)-based decision support using skin cancer diagnosis as a use case. We utilized nonuniform rewards and penalties based on expert-generated tables, balancing the benefits and harms of various diagnostic errors, which were applied using reinforcement learning. Compared with supervised learning, the reinforcement learning model improved the sensitivity for melanoma from 61.4% to 79.5% (95% confidence interval (CI): 73.5-85.6%) and for basal cell carcinoma from 79.4% to 87.1% (95% CI: 80.3-93.9%). AI overconfidence was also reduced while simultaneously maintaining accuracy. Reinforcement learning increased the rate of correct diagnoses made by dermatologists by 12.0% (95% CI: 8.8-15.1%) and improved the rate of optimal management decisions from 57.4% to 65.3% (95% CI: 61.7-68.9%). We further demonstrated that the reward-adjusted reinforcement learning model and a threshold-based model outperformed naïve supervised learning in various clinical scenarios. Our findings suggest the potential for incorporating human preferences into image-based diagnostic algorithms
Investigating the generalizability of Economic Evaluations conducted in Italy: a critical review
No full textbstract: Aim. To assess the methodological quality of Italian HEEs and their generalizability or
transferability to different settings.
Methods. A literature search was performed on Pubmed search engine to identify trial-based, non-
experimental prospective studies or model-based full economic evaluations, carried out in Italy from
1995 to 2013. The studies were randomly assigned to four reviewers who applied a detailed checklist
to assess the generalizability and the quality of reporting. The review process followed a three-step
blinded procedure. The reviewers who carried out the data extraction were blind as to the name of the
author(s) of each study. Second, after the first review, articles were re-assigned through a second blind
randomization to a second reviewer. Finally, any disagreement between the first two reviews was
solved by a senior researcher.
Results. One-hundred fifty-one economic evaluations eventually met the inclusion criteria. Over time,
we observed an increasing transparency of methods and a greater generalizability of results, along
with a wider and more representative sample in trials and a larger adoption of transition-Markov
models. On the other hand, often context-specific economic evaluations are carried out and not enough
effort is done to assure the transferability of their results to other contexts. In recent studies, Cost-
Effectiveness Analyses and the use of the Incremental Cost-Effectiveness Ratio were preferred.
Conclusion. Despite a quite positive temporal trend, generalizability of results still appears as an
unsolved question, even if some indication of improvement within Italian studies has been observe
Investigating the Generalizability of Economic Evaluations Conducted in Italy: A Critical Review
No full textObjectives To assess the methodological quality of Italian health economic evaluations and their generalizability or transferability to different settings. Methods A literature search was performed on the PubMed search engine to identify trial-based, nonexperimental prospective studies or model-based full economic evaluations carried out in Italy from 1995 to 2013. The studies were randomly assigned to four reviewers who applied a detailed checklist to assess the generalizability and quality of reporting. The review process followed a three-step blinded procedure. The reviewers who carried out the data extraction were blind as to the name of the author(s) of each study. Second, after the first review, articles were reassigned through a second blind randomization to a second reviewer. Finally, any disagreement between the first two reviewers was solved by a senior researcher. Results One hundred fifty-one economic evaluations eventually met the inclusion criteria. Over time, we observed an increasing transparency in methods and a greater generalizability of results, along with a wider and more representative sample in trials and a larger adoption of transition-Markov models. However, often context-specific economic evaluations are carried out and not enough effort is made to ensure the transferability of their results to other contexts. In recent studies, cost-effectiveness analyses and the use of incremental cost-effectiveness ratio were preferred. Conclusions Despite a quite positive temporal trend, generalizability of results still appears as an unsolved question, even if some indication of improvement within Italian studies has been observed
Learning representations from EEG with deep recurrent-convolutional neural networks
No full textOne of the challenges in modeling cognitive events from electroencephalogram (EEG) data is finding representations that are invariant to inter- and intra-subject differences, as well as to inherent noise associated with EEG data collection. Herein, we propose a novel approach for learning such representations from multichannel EEG time-series, and demonstrate its advantages in the context of mental load classification task. First, we transform EEG activities into a sequence of topology-preserving multi-spectral images, as opposed to standard EEG analysis techniques that ignore such spatial information. Next, we train a deep recurrent-convolutional network inspired by state-of-the-art video classification techniques to learn robust representations from the sequence of images. The proposed approach is designed to preserve the spatial, spectral, and temporal structure of EEG which leads to finding features that are less sensitive to variations and distortions within each dimension. Empirical evaluation on the cognitive load classification task demonstrated significant improvements in classification accuracy over current state-of-the-art approaches in this field
Guest Editorial Skin Lesion Image Analysis for Melanoma Detection
Get PDFMELANOMA is the deadliest form of skin cancer, with roughly 91,000 new cases reported every year in the US and more than 9,000 deaths. Unlike many other cancer types, the incidence rate of melanoma has been steadily increasing in the past several decades. Early diagnosis is crucial since melanoma can be cured with a simple excision, if detected early. In the past, the primary form of diagnosis for melanoma was unaided clinical examination, which has limited and variable accuracy, leading to significant challenges both in the early detection of disease and the minimization of unnecessary biopsies. In recent years, dermoscopy, a high-resolution skin imaging technique that allows visualization of deeper skin structures by reducing surface reflectance, has improved the diagnostic capability of trained specialists. Unfortunately, dermoscopy remains difficult to learn and several studies have demonstrated limitations of dermoscopy when proper training is not administered. In addition, even with sufficient training, visual analysis remains subjective
Human–computer collaboration for skin cancer recognition
Get PDFThe rapid increase in telemedicine coupled with recent advances in diagnostic artificial intelligence (AI) create the imperative to consider the opportunities and risks of inserting AI-based support into new paradigms of care. Here we build on recent achievements in the accuracy of image-based AI for skin cancer diagnosis to address the effects of varied representations of AI-based support across different levels of clinical expertise and multiple clinical workflows. We find that good quality AI-based support of clinical decision-making improves diagnostic accuracy over that of either AI or physicians alone, and that the least experienced clinicians gain the most from AI-based support. We further find that AI-based multiclass probabilities outperformed content-based image retrieval (CBIR) representations of AI in the mobile technology environment, and AI-based support had utility in simulations of second opinions and of telemedicine triage. In addition to demonstrating the potential benefits associated with good quality AI in the hands of non-expert clinicians, we find that faulty AI can mislead the entire spectrum of clinicians, including experts. Lastly, we show that insights derived from AI class-activation maps can inform improvements in human diagnosis. Together, our approach and findings offer a framework for future studies across the spectrum of image-based diagnostics to improve human–computer collaboration in clinical practice
A radial self-calibrated (RASCAL) generalized autocalibrating partially parallel acquisition (GRAPPA) method using weight interpolation
No full text- …
