google ads
Small Bowel: Artificial Intelligence Imaging Pearls - Educational Tools | CT Scanning | CT Imaging | CT Scan Protocols - CTisus
Imaging Pearls ❯ Small Bowel ❯ Artificial Intelligence

-- OR --

  •  ”Artificial intelligence (AI) promises to be a transformative technology for medicine and health care. As such, there is an increasing interest in ensuring its ethical use. In this perspective, we consider the employment of AI for medical diagnostics, where the goal is the detection and classification of an underlying pathology, based on data such as patient information, clinical presentation, tests, and imaging. We argue that instead of prioritizing fairness criteria that measure disparities between protected groups, the primary goal should be to assess and enhance diagnostic accuracy within each subpopulation. This approach shifts the focus from optimizing overall population accuracy to ensuring maximal accuracy in each subpopulation. Our perspective implies that we should be using all available information, including protected group identity, in our methods. We decouple the goal of accurate diagnosis from fairness considerations in screening and postdiagnosis clinical decisions, which often require the allocation of finite resources.” 
  •  “It is important to realize that the more fine-grained these subsets are, the more challenging it will be to track and optimize performance in all of them. As subpopulations become more granular, data scarcity will become a major constraint that will limit model training and hinder performance evaluation. Furthermore, a higher number of subpopulations will demand more resources to train, evaluate, and maintain models. Thus, there will always be a practical trade-off between the level of detail we aim for and how it enables us to maximize and evaluate performance.”  
    Ethical Use of Artificial Intelligence in Medical Diagnostics Demands a Focus on Accuracy, Not Fairness  
    Mert R. Sabuncu et al.
    NEJM AI 2025;2(1)   
  • “Furthermore, we believe that AI models developed for diagnostic purposes should consider subpopulations and, in particular, should not be blinded to sensitive attributes. The objective of maximizing performance in each subpopulation requires that all available information should be utilized. Specifically, sensitive attributes can be critically informative about underlying risks and thus can significantly shift a model’s prior to reach a better prediction. The emphasis should be on tracking performance and continuously improving it by collecting more high-quality, informative data, training better models, and guarding against distribution shifts.”  
    Ethical Use of Artificial Intelligence in Medical Diagnostics Demands a Focus on Accuracy, Not Fairness  
    Mert R. Sabuncu et al.
    NEJM AI 2025;2(1) 
  • “Artificial intelligence is rapidly changing our world at an exponential rate and its transformative power has extensively reached important sectors like healthcare. In the fight against cancer, AI proved to be a novel and powerful tool, offering new hope for prevention and early detection. In this review, we will comprehensively explore the medical applications of AI, including early cancer detection through pathological and imaging analysis, risk stratification, patient triage, and the development of personalized prevention approaches. However, despite the successful impact AI has contributed to, we will also discuss the myriad of challenges that we have faced so far toward optimal AI implementation. There are problems when it comes to the best way in which we can use AI systemically. Having the correct data that can be understood easily must remain one of the most significant concerns in all its uses including sharing information.”
    Empowering cancer prevention with AI: unlocking new frontiers in prediction, diagnosis, and intervention
    Cancer Causes & Control https://doi.org/10.1007/s10552-024-01942-9
  • “One of the pillars that cancer prevention tremendously stands on is early diagnosis. Given the highly intricatennature of cancer biology, the conventional ways we rely on today to detect cancer are no longer sufficient to level up proportionally with the advancing personalized medicine . New pathways to further progress cancer research are possible today thanks to Artificial Intelligence (AI). ΑΙ can work as an assistive tool for the doctor in the context of diagnosis decisions and it has the potential for accurate diagnosis at an early stage which eventually improves the survival outcome and success rate of the treatment in cancer patients . Based on large amounts of medical data and new computing technologies, AI, especially high-performing algorithms such as Deep Learning (DL), is being applied to various aspects of oncology research and has the potential to improve cancer diagnosis and treatment . Machine learning (ML), in which computers analyze complicated data patterns to make predictions, has the potential to enhance the accuracy for cancer susceptibility, recurrence, and survival— three factors crucial to early detection and prognosis in cancer research . Many early diagnosis models have taken advantage of convolutional neural network (CNN) designs, which allowed the use of colored images as input data and revolutionized computer-vision research.”
    Empowering cancer prevention with AI: unlocking new frontiers in prediction, diagnosis, and intervention
    Cancer Causes & Control https://doi.org/10.1007/s10552-024-01942-9
  • “Automated screening programs that utilize Artificial Neural Networks (ANNs) are computational models composed of interconnected groups of nodes. The biologically inspired system that emulates the way that neurons interact in the brain, proved the ability to automatically generate information through a learning process. The basic structure of this network consists of three layers: an input layer, single or multiple hidden layers, and lastly, an output layer which presents a prediction based on the weighted sum of values in the hidden layer nodes. Ismail Saritas developed an ANN to predict breast cancer based on the patient’s age and characteristics of the mass’ shape, border, and density based on ‘Breast Imaging Reporting and Data System (BI-RADS) features.”
    Empowering cancer prevention with AI: unlocking new frontiers in prediction, diagnosis, and intervention
    Cancer Causes & Control https://doi.org/10.1007/s10552-024-01942-9 

Privacy Policy

Copyright © 2025 The Johns Hopkins University, The Johns Hopkins Hospital, and The Johns Hopkins Health System Corporation. All rights reserved.