Leukemia diagnosis primarily relies on manual microscopic analysis of bone marrow morphology supported by additional laboratory parameters, making it complex and time consuming. While artificial intelligence (AI) solutions have been proposed, most utilize private datasets and only cover parts of the diagnostic pipeline. Therefore, we present a large, high-quality, publicly available leukemia bone marrow dataset spanning the entire diagnostic process, from cell detection to diagnosis. Using this dataset, we further propose methods for cell detection, cell classification, and diagnosis prediction. The dataset comprises 246 pediatric patients with diagnostic, clinical and laboratory information, over 40 000 cells with bounding box annotations and more than 28 000 of these with high-quality class labels, making it the most comprehensive dataset publicly available. Evaluation of the AI models yielded an average precision of 0.96 for the cell detection, an area under the curve of 0.98, and an F1-score of 0.61 for the 33-class cell classification, and a mean F1-score of 0.90 for the diagnosis prediction using predicted cell counts. While the proposed Höfener et al. - Bone Marrow Dataset & Methods for Childhood Leukemia Page 3 approaches demonstrate their usefulness for AI-assisted diagnostics, the dataset will foster further research and development in the field, ultimately contributing to more precise diagnoses and improved patient outcomes.

In hematology, computational models offer significant potential to improve diagnostic accuracy, streamline workflows, and reduce the tedious work of analyzing single cells in peripheral blood or bone marrow smears. However, clinical adoption of computational models has been hampered by the lack of generalization due to large batch effects, small dataset sizes, and poor performance in transfer learning from natural images. To address these challenges, we introduce DinoBloom, the first foundation model for single cell images in hematology, utilizing a tailored DINOv2 pipeline. Our model is built upon an extensive collection of 13 diverse, publicly available datasets of peripheral blood and bone marrow smears, the most substantial open-source cohort in hematology so far, comprising over 380,000 white blood cell images. To assess its generalization capability, we evaluate it on an external dataset with a challenging domain shift. We show that our model outperforms existing medical and non-medical vision models in (i) linear probing and k-nearest neighbor evaluations for cell-type classification on blood and bone marrow smears and (ii) weakly supervised multiple instance learning for acute myeloid leukemia subtyping by a large margin. A family of four DinoBloom models (small, base, large, and giant) can be adapted for a wide range of downstream applications, be a strong baseline for classification problems, and facilitate the assessment of batch effects in new datasets. All models are available at github.com/marrlab/DinoBloom.

Sparsely activated neural networks with conditional computation learn to route their inputs through different "expert" subnetworks, providing a form of modularity that densely activated models lack. Despite their possible benefits, models with learned routing often underperform their parameter-matched densely activated counterparts as well as models that use non-learned heuristic routing strategies. In this paper, we hypothesize that these shortcomings stem from the gradient estimation techniques used to train sparsely activated models that use non-differentiable discrete routing decisions. To address this issue, we introduce Soft Merging of Experts with Adaptive Routing (SMEAR), which avoids discrete routing by using a single "merged" expert constructed via a weighted average of all of the experts' parameters. By routing activations through a single merged expert, SMEAR does not incur a significant increase in computational costs and enables standard gradient-based training. We empirically validate that models using SMEAR outperform models that route based on metadata or learn sparse routing through gradient estimation. Furthermore, we provide qualitative analysis demonstrating that the experts learned via SMEAR exhibit a significant amount of specialization. All of the code used in our experiments is publicly available.

Subscribe now to get Fox News First in your email. And here's what you need to know to start your day ... 'DANGEROUS RACE' - Elon Musk, futurists call for major action as AI technology grows stronger, smarter. Continue reading … 'HORRENDOUS' COVERAGE - Nashville massacre coverage marked by media's'subtle smears' against Christianity. RED ALERT - China makes serious threats over meeting between Speaker McCarthy, Taiwan's leader. 'PROTECTED HER CHILDREN' - Head of school praised for going'straight for the shooter' during school massacre.

On a beautiful day in May 2015, I drove the 13 hours from my home in Portland, Oregon, to Harris Ranch, California, halfway between San Francisco and Los Angeles. At the time, Tesla was touting a battery-swap station that could send Tesla drivers on their way in a fully powered vehicle in less than the time it takes to fill up a car with gas. Overtaken by curiosity, I had decided to spend a long Memorial Day weekend in California's Central Valley to see if Elon Musk's latest bit of dream weaving could stand up to reality. There, amid the pervasive stench of cow droppings from a nearby feedlot, I discovered that Tesla's battery swap station was not in fact being made available to owners who regularly drove between California's two largest cities. Instead, the company was running diesel generators to power additional Superchargers (the kind that take 30 to 60 minutes to recharge a battery) to handle the holiday rush, their exhaust mingling with the unmistakable smell of bullshit.

A proof-of-concept study suggests that artificial intelligence (AI) may classify images captured during rapid onsite examination of endobronchial ultrasound guided transbronchial need aspiration (EBUS-TBNA) with high accuracy. The results of this study were published in the European Respiratory Journal. The use of AI in medicine has become more common in areas such as cervical cancer screening, which has led experts to question its potential in other fields of medicine. No data have been published on the application of AI during rapid on-site examination of EBUS-TBNA. A team of investigators "evaluated the performance of an AI model, consisting of an open-sounded convolutional neural network using transfer learning, for its ability to accurately classify images of [rapid onsite examination] of EBUS-TBNA smears in the bronchoscopy suite."

There aren't many computer chips that you have to build a life support system for. You actually need to supply everything they would normally get in a fully biological body. As Hon Weng Chong, the CEO of Australia's Cortical Labs explains, it's all about creating computer systems that learn -- and that learn faster with less training data. That requires a different approach than standard Intel, Nvidia, or AMD chips, he says. "What we've actually built is a hybrid chip that is comprised of a CMOS sensor, so it's a silicon chip with a very fine mesh of electrodes. They're about 17 microns in pitch and there are about 22,000 of them," Chong told me on The AI Show recently.

Engineers at Duke University have developed a microscope that adapts its lighting angles, colors and patterns while teaching itself the optimal settings needed to complete a given diagnostic task. In the initial proof-of-concept study, the microscope simultaneously developed a lighting pattern and classification system that allowed it to quickly identify red blood cells infected by the malaria parasite more accurately than trained physicians and other machine learning approaches. The results appear online on November 19 in the journal Biomedical Optics Express. "A standard microscope illuminates a sample with the same amount of light coming from all directions, and that lighting has been optimized for human eyes over hundreds of years," said Roarke Horstmeyer, assistant professor of biomedical engineering at Duke. "But computers can see things humans can't," Hortmeyer said. "So not only have we redesigned the hardware to provide a diverse range of lighting options, we've allowed the microscope to optimize the illumination for itself."

Deep learning, a powerful form of artificial intelligence (AI), has wide spanning uses in a number of fields. Many people worry the technology could prove devastating for humanity, but recently, a group of researchers has shown how it could drastically benefit people, particularly those living in underdeveloped parts of the world. The team, coming from UCLA Samueli School of Engineering, Los Angeles, leveraged deep learning to take standard smartphone camera capabilities up to the level of a lab-grade microscope. This means the images will be taken from a phone, but their quality will be as detailed and precise as from a high-tech laboratory microscope. This could ultimately be used to conduct inexpensive lab-grade analysis in poor parts of the world, where technologies for high-quality diagnostics are unavailable.

Instead they have commonly assigned structure to a domain using statistical techniques such as Bayes' Theorem