Recently, large language models (LLMs) have taken the spotlight in natural language processing. Further, integrating LLMs with vision enables the users to explore emergent abilities with multimodal data. Visual language models (VLMs), such as LLaVA, Flamingo, or CLIP, have demonstrated impressive performance on various visio-linguistic tasks. Consequently, there are enormous applications of large models that could be potentially used in the biomedical imaging field. Along that direction, there is a lack of related work to show the ability of large models to diagnose the diseases. In this work, we study the zero-shot and few-shot robustness of VLMs on the medical imaging analysis tasks. Our comprehensive experiments demonstrate the effectiveness of VLMs in analyzing biomedical images such as brain MRIs, microscopic images of blood cells, and chest X-rays.

In medical imaging analysis, deep learning has shown promising results. We frequently rely on volumetric data to segment medical images, necessitating the use of 3D architectures, which are commended for their capacity to capture interslice context. However, because of the 3D convolutions, max pooling, up-convolutions, and other operations utilized in these networks, these architectures are often more inefficient in terms of time and computation than their 2D equivalents. Furthermore, there are few 3D pretrained model weights, and pretraining is often difficult. We present a simple yet effective 2D method to handle 3D data while efficiently embedding the 3D knowledge during training. We propose transforming volumetric data into 2D super images and segmenting with 2D networks to solve these challenges. Our method generates a super-resolution image by stitching slices side by side in the 3D image. We expect deep neural networks to capture and learn these properties spatially despite losing depth information. This work aims to present a novel perspective when dealing with volumetric data, and we test the hypothesis using CNN and ViT networks as well as self-supervised pretraining. While attaining equal, if not superior, results to 3D networks utilizing only 2D counterparts, the model complexity is reduced by around threefold. Because volumetric data is relatively scarce, we anticipate that our approach will entice more studies, particularly in medical imaging analysis.

The scarcity of high-quality annotated medical imaging datasets is a major problem that collides with machine learning applications in the field of medical imaging analysis and impedes its advancement. Self-supervised learning is a recent training paradigm that enables learning robust representations without the need for human annotation which can be considered an effective solution for the scarcity of annotated medical data. This article reviews the state-of-the-art research directions in self-supervised learning approaches for image data with a concentration on their applications in the field of medical imaging analysis. The article covers a set of the most recent self-supervised learning methods from the computer vision field as they are applicable to the medical imaging analysis and categorize them as predictive, generative, and contrastive approaches. Moreover, the article covers 40 of the most recent research papers in the field of self-supervised learning in medical imaging analysis aiming at shedding the light on the recent innovation in the field. Finally, the article concludes with possible future research directions in the field.

The scarcity of high-quality annotated medical imaging datasets is a major problem that collides with machine learning applications in the field of medical imaging analysis and impedes its advancement. Self-supervised learning is a recent training paradigm that enables learning robust representations without the need for human annotation which can be considered an effective solution for the scarcity of annotated medical data. This article reviews the state-of-the-art research directions in self-supervised learning approaches for image data with a concentration on their applications in the field of medical imaging analysis. The article covers a set of the most recent self-supervised learning methods from the computer vision field as they are applicable to the medical imaging analysis and categorize them as predictive, generative, and contrastive approaches. Moreover, the article covers 40 of the most recent research papers in the field of self-supervised learning in medical imaging analysis aiming at shedding the light on the recent innovation in the field. Finally, the article concludes with possible future research directions in the field.

AI is no longer just science fiction! And thankfully it is bringing life-changing transformation in the healthcare industry. AI can collect data over time, access data stored in other systems. And it can go over data written on the online books, internet. Gathering all the information together, it can research notes in a matter of seconds! And finally, it can make an educated decision based on all the data it has been over.

I truly believe that artificial intelligence (AI) will shape our future and will bring tremendous impact and applications in industries such as health and agriculture. One of the things that I aim to achieve with dair.ai is to discuss interesting open-source AI technologies that help to address important problems such as medical diagnosis and personalized learning. One of the tools that have caught my attention this week is MedicalTorch (developed by Christian S. Perone), which is an open-source medical imaging analysis tool built on top of PyTorch. It contains a set of loaders, pre-processors and utility functions to efficiently and easily analyze medical images such as those acquired from magnetic resonance imaging (MRI) scans. In this post, I will summarize some of the functionalities offered by the medicaltorch library and how it can be used to conduct medical imaging analysis. Specifically, this will be a tutorial on how to perform spinal cord gray matter segmentation using a technique based on convolutional neural networks (CNNs).

In today's post-EHR health environment, the amount of data generated by digitization is staggering. Dozens of systems feed data across healthcare organizations daily, and IDC predicts that health data volumes will continue to grow at a rate of 48% annually.[1] Yet, despite advances toward becoming a data-rich and data-driven industry, medical errors are still the third-leading cause of death in the US alone.[2] Though artificial intelligence (AI) is still in early stages of adoption in healthcare, its exceptional ability to manage big data makes it a powerful weapon in the fight against medical errors. But don't worry--robots aren't about to replace clinicians anytime soon. Humans and machines are complementary, as humans have ingenuity and emotional intelligence, for example, while machines are better at tackling repetitive, high volume tasks where accuracy is vital.

We are probably still quite some way off from seeing Artificial Intelligence (AI) replace doctors, but there are already lots of proven use-cases where AI is being used to augment the medical profession. One proven area is in medical imaging where AI and computer vision is helping with medical scan and imaging analysis to help support radiologists and other clinicians. One startup operating in this space is AIdoc Medical. The company has built what co-founder and CEO Elad Walach describes as an AI that can spot visual abnormalities in medical scans. The technology is designed to fit into a radiologist's existing workflow to help make their job more efficient.