English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Radiologists use time series of medical images to monitor the progression ofa patient condition. They compare information gleaned from sequences of imagesto gain insight on progression or remission of the lesions, thus evaluating theprogress of a patient condition or response to therapy. Visual methods ofdetermining differences between one series of images to another can besubjective or fail to detect very small differences. We propose the use ofquantization errors obtained from Self Organizing Maps for image contentanalysis. We tested this technique with MRI images to which we progressivelyadded synthetic lesions. We have used a global approach that considers changeson the entire image as opposed to changes in segmented lesion regions only. Weclaim that this approach does not suffer from the limitations imposed bysegmentation, which may compromise the results. Results show quantizationerrors increased with the increase in lesions on the images. The results arealso consistent with previous studies using alternative approaches. We thencompared the detectability ability of our method to that of human noviceobservers having to detect very small local differences in random-dot images.The quantization errors of the SOM outputs compared with correct positiverates, after subtraction of false positive rates (guess rates), increasednoticeably and consistently with small increases in local dot size that werenot detectable by humans. We conclude that our method detects very smallchanges in complex images and suggest that it could be implemented to assisthuman operators in image based decision making.

Detection of small changes in medical and random-dot images comparing self-organizing map performance to human detection