Potential and Limitations of Various Ultrasonic Medical Imaging Algorithms

Abstract Artificial intelligence (AI) systems have increasingly achieved expert-level performance, particularly in medical imaging (‎1). However, there is growing concern that AI systems will reflect and amplify human bias against under-served subpopulations (‎2-‎7). Such biases are especially troubling in the context of underdiagnosis: if AI systems falsely predict that patients are healthy, patients would be denied care when they need it most. This use case is particularly relevant in the context of existing health disparities where high underdiagnosis rates for under-served subgroups are well documented (‎8-‎11). Although bias in underdiagnosis can potentially delay access to medical treatment unequally, underdiagnosis due of AI has been relatively unexplored. In this work we examine algorithmic underdiagnosis in chest X-ray pathology classifiers and find that classifiers consistently and selectively underdiagnose under-served patients, actively amplifying the existing biases in clinical care. These effects are worse on intersectional subpopulations, e.g., Black females, and persist across three large and a multi-source chest X-ray dataset. Our work demonstrates that deploying AI systems risks exacerbating biases present in current care practices. Developers, clinical staff, and regulators must address the serious ethical concerns of -- and barriers to -- effective deployment of these models in the clinic.

Download Full-text

Performance evaluation of medical imaging algorithms on Intel® MIC platform

20th Annual International Conference on High Performance Computing ◽

10.1109/hipc.2013.6799121 ◽

2013 ◽

Cited By ~ 2

Author(s):

Jyotsna Khemka ◽

Mrugesh Gajjar ◽

Sharan Vaswani ◽

Naga Vydyanathan ◽

Rama Malladi ◽

...

Keyword(s):

Performance Evaluation ◽

Medical Imaging ◽

Imaging Algorithms

Download Full-text

A Review of Microrobot’s System: Towards System Integration for Autonomous Actuation In Vivo

Micromachines ◽

10.3390/mi12101249 ◽

2021 ◽

Vol 12 (10) ◽

pp. 1249

Author(s):

Zhongyi Li ◽

Chunyang Li ◽

Lixin Dong ◽

Jing Zhao

Keyword(s):

Medical Imaging ◽

System Integration ◽

Working Environment ◽

Delivery Methods ◽

Actuation System ◽

Imaging Algorithms ◽

Hybrid Actuation ◽

Actuation Systems ◽

And Control

Microrobots have received great attention due to their great potential in the biomedical field, and there has been extraordinary progress on them in many respects, making it possible to use them in vivo clinically. However, the most important question is how to get microrobots to a given position accurately. Therefore, autonomous actuation technology based on medical imaging has become the solution receiving the most attention considering its low precision and efficiency of manual control. This paper investigates key components of microrobot’s autonomous actuation systems, including actuation systems, medical imaging systems, and control systems, hoping to help realize system integration of them. The hardware integration has two situations according to sharing the transmitting equipment or not, with the consideration of interference, efficiency, microrobot’s material and structure. Furthermore, system integration of hybrid actuation and multimodal imaging can improve the navigation effect of the microrobot. The software integration needs to consider the characteristics and deficiencies of the existing actuation algorithms, imaging algorithms, and the complex 3D working environment in vivo. Additionally, considering the moving distance in the human body, the autonomous actuation system combined with rapid delivery methods can deliver microrobots to specify position rapidly and precisely.

Download Full-text

Mapping Iterative Medical Imaging Algorithm on Cell Accelerator

International Journal of Biomedical Imaging ◽

10.1155/2011/843924 ◽

2011 ◽

Vol 2011 ◽

pp. 1-11 ◽

Cited By ~ 5

Author(s):

Meilian Xu ◽

Parimala Thulasiraman

Keyword(s):

Medical Imaging ◽

Optimization Techniques ◽

Main Memory ◽

Memory Storage ◽

Parallel Applications ◽

Reconstruction Technique ◽

Multicore Architectures ◽

Improved Performance ◽

Imaging Algorithms ◽

Algebraic Reconstruction

Algebraic reconstruction techniques require about half the number of projections as that of Fourier backprojection methods, which makes these methods safer in terms of required radiation dose. Algebraic reconstruction technique (ART) and its variant OS-SART (ordered subset simultaneous ART) are techniques that provide faster convergence with comparatively good image quality. However, the prohibitively long processing time of these techniques prevents their adoption in commercial CT machines. Parallel computing is one solution to this problem. With the advent of heterogeneous multicore architectures that exploit data parallel applications, medical imaging algorithms such as OS-SART can be studied to produce increased performance. In this paper, we map OS-SART on cell broadband engine (Cell BE). We effectively use the architectural features of Cell BE to provide an efficient mapping. The Cell BE consists of one powerPC processor element (PPE) and eight SIMD coprocessors known as synergetic processor elements (SPEs). The limited memory storage on each of the SPEs makes the mapping challenging. Therefore, we present optimization techniques to efficiently map the algorithm on the Cell BE for improved performance over CPU version. We compare the performance of our proposed algorithm on Cell BE to that of Sun Fire×4600, a shared memory machine. The Cell BE is five times faster than AMD Opteron dual-core processor. The speedup of the algorithm on Cell BE increases with the increase in the number of SPEs. We also experiment with various parameters, such as number of subsets, number of processing elements, and number of DMA transfers between main memory and local memory, that impact the performance of the algorithm.

Download Full-text

Numerical and experimental simulations to quantify the potential and limitations of various ultrasonic medical imaging algorithms

10.1109/ultsym.1990.171482 ◽

2002 ◽

Author(s):

H. Morbitzer ◽

K.J. Langenberg ◽

R.M. Schmitt

Keyword(s):

Medical Imaging ◽

Imaging Algorithms

Download Full-text

A new implementation of itk::ImageToImageFilter for efficient parallelization of image processing algorithms using Intel Threading Building Blocks

The Insight Journal ◽

10.54294/mq1gt4 ◽

2016 ◽

Author(s):

Amir Jaberzadeh ◽

Benoit Scherrer ◽

Simon Warfield

Keyword(s):

Image Processing ◽

Image Analysis ◽

Medical Imaging ◽

Open Source ◽

High Performance ◽

Job Scheduling ◽

Building Blocks ◽

Reconstruction Image ◽

Imaging Algorithms ◽

Very High

Modern medical imaging makes use of high performance computing to accelerate image acquisition, image reconstruction, image visualization and image analysis. Software libraries that provide implementations of key medical imaging algorithms need to efficiently exploit modern CPU architectures. In particular, workstations with small numbers of cores are being replaced by very high core count architectures, and by many integrated core architectures, which offer acceleration by vectorization and multi-threading.The Insight Toolkit (ITK) is the premier open source implementation of medical imaging algorithms, with a generic design for image processing filters that allows for many developers to rapidly incorporate these algorithms in to new applications. While ITK filters benefit from a generic, platform independent multithreading capability, the current implementation is difficult to exploit to achieve very high performance. Specifically, ITK relies on a static decomposition of the image into subsets of equal size which can be highly inefficient. Threads that terminate early due to uneven work throughout the image finish early and do not contribute further to the processing of more complex regions, leading to idle computational resources and longer execution times. Performance is also difficult to coordinate across multiple algorithms, as the ITK filter assumes each filter operates independently but the global implementation has an impact across filters.In this work, we propose a novel, simple to use, high performance multithreading capability for ITK that accelerates the itk::ImageToImageFilter. We utilise a workpile data decomposition strategy, and leave the task of optimal job scheduling on CPU cores to the library called Threading Building Blocks (TBB). We demonstrate the efficacy of multi-threading with TBB in comparison to the itk::Multithreader class, through three simple example image analysis algorithms.Our implementation provides a new multi-threaded itk::ImageToImageFilter that can be conveniently reused to provide simple and efficient multi-threaded code across applications and algorithm libraries. Our new implementation is distributed as open-source software to the community and is straightforward to adopt.

Download Full-text