Publisher of Humanities, Social Science & STEM Books
ai in healthcare and medical imaging

What impact has AI in Healthcare had on Medical Imaging?

Posted on: November 25, 2019

By: Diboro Kanabolo and Mohan S. Gundeti

Today, there is potential in medicine to harness “big data,” utilizing the large quantities of information generated daily in various settings. Clinical practice is now shifting from episodic analysis of disparate datasets to algorithms relying on consistently updated datasets for improved prediction of patient outcomes.

The field of radiomics is built on the premise of converting images into data from which useful details may be extracted, for the ultimate purpose of providing medical utility. Image interpretation, especially in the context of subtle disease states, can be limited by various factors, both extrinsic and intrinsic to the radiologist. This article looks at the various processes and subfields, relating to the roles of artificial intelligence in medical imaging.

AI in Healthcare

AI in Healthcare and Extrinsic Factors to Image Interpretation

Diagnostic error accounts for approximately 10% of patient deaths, and between 6 and 17% of adverse events occurring during hospitalization. Errors in diagnosis have been associated with clinical reasoning, including:

  • Intelligence
  • Knowledge
  • Age
  • Visual psychiatric affect
  • Physical state (fatigue)
  • Clinical history of the patient
  • Gender (male predilection for risk taking)

These factors, and the limited access to radiologic specialists for up to two-thirds of the world, encourage a more urgent role for the use of AI in medical imaging.


Medical Imaging

Intrinsic Factors to Medical Imaging Quality

Intrinsic factors can be grouped into three categories: Geometry, Contrast and Background.

Geometry - Intrinsic object attributes are arranged in three general geometries:

  • Point - Point targets are small, with maximum dimensions typically lower than 1 mm. These may include microcalcifications, calculi, or osteophytes
  • Line - Line targets may have a variable length depending on clinical context. Examples include spicules, septate lines, and lines delineating cortical vs. trabecular bone
  • Extended targets - Extended objects may include tumours, abscesses, and infiltrates

Contrast - Examples of high object contrast within the point, line and extended images include a dense microcalcification, tangential pleural calcifications, and calcified granulomas. Fainter microcalcifications, early spicules, and gallstones comprise inherently low contrast point, line, and extended objects, respectively. Note that high object contrast items do not necessarily indicate artificial contrast dye enhancement, though this is a technicality that may vary with the function of other clinical information (renal and liver function, previous allergic responses).

Background - The premise of background implies that the radiologic “canvas” on which a particular target finding appears influences its perceptibility. This background may in turn be influenced by not only the grayscale for which the lesion is displayed, but also the detail of the image itself.  Grayscale components depend on:

  • Dimensions and anatomical properties
  • Amount of radiation, magnetic resonance, or sound wave frequency to which an area is exposed
  • Densitometric characteristics of the recording system 

These all determine the relative optical densities of the structures under examination. When adding the complexity of anatomic structures in immediate proximity, different levels of attenuation may be seen based on the specific qualities of the medium through which the sound waves, radiation, or magnetic resonance are travelling.  Intuitively, details from the perspective of an observer increase in visibility with proximity to an image. As this distance becomes infinitesimally smaller, the effects of local noise become evident. We see that a significant proportion of the technical factors involved in proper automated interpretation of an image can be overcome with proper allocation of resources to their development. For example, research funds for the role of machine learning in point and line spread function analysis for historically low-resolution imaging, such as radiographs or computed tomography.


AI in Medical

Examples of AI in Medical Imaging

The Kohonen self-organized map (KSOM) may be helpful in the understanding of AI’s capacity and potential. It is ideal for utilizing artificial bias and sensory experience to enhance accuracy of Computer-aided detection (CADe) and Computer-aided diagnosis (CADx) when applied to medical imaging. Briefly, it is an artificial neural network (ANN) developed to decrease complexity by representing multidimensional vectors into as little as one dimension. Yet, data is stored in such a way as to maintain topological relationships. The KSOM is a form of unsupervised feature extraction and classification. Unsupervised feature extraction utilizes images and clinical narrative texts to allow for high throughput application in the analysis of clinical data.

The steps in this process include disease detection, lesion segmentation, diagnosis, treatment selection, response assessment via repeat imaging, and using data about a patient to create clinical predictions in regard to potential patient outcomes.


AI in Healthcare

The Role of Artificial Intelligence in Healthcare 

Gain further insights into the application of artificial intelligence in medicine and healthcare on topics such as; machine learning, 3D imaging, drug safety surveillance and ambient assisted living, with this free downloadable insights guide. Also receive a complimentary 20% discount code to use on your next book order from

Download Now

Artificial Intelligence in Healthcare

Benefits of Artificial Intelligence in Healthcare

The benefits of AI in healthcare are numerous. The first of these includes increased productivity, due in part to absence of need for natural breaks in a 24-hour workday, enabling images to be read continuously. This allows results to be returned to patients quickly, and aids medical decision making. Secondly, the lack of humanistic implications may be a strength as well. The various biases, lack of knowledge, or clerical errors made in the process of observing an image are minimized with computerization. Third, the cost of instituting a new graphics processor or imaging software is fixed. Over time, not only does this benefit allow for saving of human resources, it facilitates a margin of profit for any healthcare administration that only grows with time. Finally, artificial intelligence will continue to progress in its innovative capacities. Because many hospitals apply marketing strategies, AI may enable hospitals to market to their stakeholders, including potential employees and patients.


Artificial Intelligence in Medicine

Disadvantages of Artificial Intelligence in Medicine

The disadvantages of AI in medicine must also be considered. First, AI imaging algorithms and software may be able to compete for existing human labour more cost-effectively — it is estimated that AI will eliminate 1.8 million jobs by 2020. This disadvantage is tempered by the increase in employment — in 2017, it was estimated that AI will generate 2.3 million jobs by 2020 and will have a net gain of 2 million jobs by 2025. Secondly, the personal connection of reviewing an image will continue to be a necessary component of radiology; however, with further development and validation of imaging and interpretation software, there is a reasonable fear concerning the loss of the human review. This is the case of the development of STAR surgery. In the ensuing decades of its development, enhancements of imaging technology may facilitate the automation of surgery. In time, the personal trust patients place in a surgeon’s skills may grow increasingly tenuous.


future of ai

Future of AI in Medical Imaging

AI’s continued development will likely follow Satya Nadella’s three phases for the many technological breakthroughs that have preceded it. The first, invention and design of the technology itself; the second, retrofitting (e.g. engineers receive new training, traditional radiologic equipment is redesigned and rebuilt); the third, navigation of the dissonance, distortion, and dislocation, where challenging novel questions are raised. Many agree that AI should augment, rather than replace human ability. This must also be infused with the applicable protections for transparency, as well as privacy and security. This can be accomplished, but it will require a concerted effort amongst all stakeholders, including the requisite regulatory bodies governing the integration and incorporation of these powerful tools into practice.


This article was cited from Medical Imaging: Artificial Intelligence, Image Recognition, and Machine Learning TechniquesEdited by K.C. Santosh, Sameer Antani, DS Guru, Nilanjan Dey.