Objective: This work addresses two key problems of skin lesion classification. The first problem is the effective use of high-resolution images with pretrained standard architectures for image classification. The second problem is the high class imbalance encountered in real-world multi-class datasets. Methods: To use high-resolution images, we propose a novel patch-based attention architecture that provides global context between small, high-resolution patches. We modify three pretrained architectures and study the performance of patch-based attention. To counter class imbalance problems, we compare oversampling, balanced batch sampling, and class-specific loss weighting. Additionally, we propose a novel diagnosis-guided loss weighting method which takes the method used for groundtruth annotation into account. Results: Our patch-based attention mechanism outperforms previous methods and improves the mean sensitivity by 7 %. Class balancing significantly improves the mean sensitivity and we show that our diagnosis-guided loss weighting method improves the mean sensitivity by 3 % over normal loss balancing. Conclusion: The novel patch-based attention mechanism can be integrated into pretrained architectures and provides global context between local patches while outperforming other patch-based methods. Hence, pretrained architectures can be readily used with high-resolution images without downsampling. The new diagnosis-guided loss weighting method outperforms other methods and allows for effective training when facing class imbalance. Significance: The proposed methods improve automatic skin lesion classification. They can be extended to other clinical applications where high-resolution image data and class imbalance are relevant.

Following a 'bottom-up approach' in understanding many-particle effects and dynamics we provide a systematic ab initio study of the dependence of the breathing dynamics of ultracold bosons in a 1D harmonic trap on the number of bosons ranging from few to many. To this end, we employ (2013)]. The beating behavior for two bosons is found numerically and consequently explained by an analytical approach. Drawing on this, we show how to compute the complete breathing mode spectrum in this case. We examine how the two-mode breathing behavior of two bosons evolves to the single-frequency behavior of the many-particle limit when adding more particles. In the limit of many particles, we numerically study the dependence of the breathing mode frequency on both the interaction strength as well as on the particle number. We provide an estimate for the parameter region where the mean-field description provides a valid approximation.

No abstract

No abstract

Recent developments in artificial intelligence and machine learning have led to novel and promising applications in gastrointestinal endoscopy and beyond. Endoscopic AI has already become a topic of intensive research and marketing, and a recent review in this journal is a timely and thorough guide that defines terminology and outlines best practices for the development and assessment of AI systems. Our commentary highlights selected aspects of AI research and elaborates upon potential roles that the GI scientific community and professional societies may play in ensuring that the preclinical achievements translate into clinical reality. We believe that: Databases of diagnostic AI software need to be made transparent as should the conditions of the testing scenarios. Clinical expertise is required from the early phases of system development and testing. Medicolegal implications need to be clarified as AI gets increasingly involved in medical decision making. Finally, through the establishment of a continuously updated and curated, dedicated database for AI system evaluation ("rolling gold standard"), the GI societies could actively advance and frame this everchanging field.