DOTmed Home MRI Oncology Ultrasound Molecular Imaging X-Ray Cardiology Health IT Business Affairs
News Home Parts & Service Operating Room CT Women's Health Proton Therapy Endoscopy HTMs Pediatrics
SEARCH
Ubicación actual:
>
> This Story


Conexión o Registro to rate this News Story
Forward Printable StoryPrint Comment
advertisement

 

advertisement

 

More Future Of...

The future of remote monitoring Insights from Harsh Dharwad, chief technology officer for Nihon Kohden America

The future of interventional radiology Insights from Dr. M. Victoria Marx, 2018-2019 president of the Society of Interventional Radiology

The future of pediatric imaging Insights from Dr. Diku Mandavia, chief medical officer for FUJIFILM Medical Systems U.S.A. Inc. and FUJIFILM SonoSite Inc.

Making the invisible visible: The future of AI in imaging Insights from Steve Tolle, vice president of global strategy and business development for IBM Watson Health

DR to meet DNA: The future of X-ray Digital X-ray will soon capture motion and provide a vast array of new insights to diagnostic imaging

See All Future Of...  

More Voices

Q&A with Gil Alejo, exhibition sales manager at Informa Markets The North and Latin American healthcare market is gearing up for another FIME meeting

Hassan El Azzazi in Memoriam The Jacobus Report

The future of C-arms Insights from Gustavo Perez, president and CEO of image guided therapies at GE Healthcare

Q&A with Shane Kearney on alternative equipment maintenance Understanding the emerging role of AEM in HTM

DOTmed has a New President! The Jacobus Report

Leon Chen

The future of AI in radiology

From the November 2017 issue of DOTmed HealthCare Business News magazine
AI, as a field, has undergone numerous periods of exuberance over the past decades.

These waves of promise and excitement invariably make their way into medicine, but in the past, they have been tempered by the realities of medicine, when evidence of real-world performance is sought. Now, there is a palpable sense that this time around, things are different, that we are on the precipice of a revolution, rather than mere incremental evolution of previous technologies. The reason, of course, is deep learning. Broadly speaking, deep learning is not a single technological breakthrough, but rather a collection of accumulated mathematical principles, data structures and optimization algorithms, which when applied to the right data, produce results on certain tasks that far outperform previous methods. While it has seen broad application across almost all data types, visual data is where it has had the greatest tangible successes. Radiology is, therefore, one of its most obvious applications.

Story Continues Below Advertisement

Servicing GE Nuclear Medicine equipment with OEM trained engineers

We offer full service contracts, PM contracts, rapid response, time and material,camera relocation. Nuclear medicine equipment service provider since 1975. Click or call now for more information 800 96 NUMED



One of the attractions of deep learning is that less intensive data preparation is typically required. There is a perception that one can just feed the neural network raw pixels of say, any chest X-ray. In practice, it is not quite this magical. Good data science and engineering practices are still paramount in building such systems. One such data science practice is ensuring the input data is of sufficient quality and quantity. Almost all practical applications of machine learning today are supervised, meaning accurate labels of your ultimate objective is required to train your models on. Not only is obtaining these labels a laborious process, it is an expensive one given the human costs.

We are only in the very early phases of applying deep learning to medical imaging, though the pace of abstracts and papers being published on the topic is rapidly picking up. We are seeing applications of all types, from classification of normal versus pathology, to higher-level tasks such as localization, segmentation and quantification. Most of these current applications are relatively simple and restricted to single-task problems. An article published by Lakhani and Sundaram in Radiology earlier this year demonstrated a 96 percent accuracy rate in classifying tuberculosis on 150 plain chest X-rays in a holdout test set. The authors took off-the-shelf neural networks developed for general image recognition, trained them on this new task and obtained excellent results. One can imagine hundreds of such algorithms that can be trained today in this straightforward manner. This is before we even think about building up the complexity with higher-order reasoning, multi-modal models such as images plus text or images plus genomics, or composition of neural networks in a modular fashion. There are so many potential applications that we can already create using simple off-the-shelf neural networks, so what are the bottlenecks?
  Pages: 1 - 2 >>

Related:


You Must Be Logged In To Post A Comment

Advertise
Aumente su conciencia de marca
Subastas + ventas Privadas
Consigue el mejor precio
Comprar Equipo/Piezas
Encuentra El Precio Más Bajo
Noticias diarias
Lee las últimas noticias
Directorio
Examina todos los usuarios DOTmed
Ética en DOTmed
Ver nuestro programa de ética
El oro parte programa del vendedor
Recibir las solicitudes de PH
Programa de distribuidor con servicio gold
Recibe solicitudes
Proveedores de atención de salud
Ver todos los HCP (abreviatura de asistencia médica) Herramientas
Jobs/Entrenamiento
Encontrar/rellenar un trabajo
Parts Hunter +EasyPay
Obtener presupuestos para piezas
Recently Certified
Ver usuarios certificados recientemente
Recently Rated
Ver usuarios certificados recientemente
Central de alquiler
Alquila equipos por menos
Vende equipos/piezas
Obtén más dinero
Service Technicians Forum
Buscar ayuda y asesoramiento
Petición sencilla de propuestas
Obtén presupuestos para equipos
Feria comercial virtual
Encuentra servicio para el equipo
El acceso y el uso de este sitio está conforme a los términos y a las condiciones de nuestro AVISO LEGAL & AVISO DE LA AISLAMIENTO
Característica de y propietario DOTmeda .com, inc. Copyright ©2001-2019 DOTmed.com, Inc.
TODOS LOS DERECHOS RESERVADOS