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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

With the maturity achieved by deep learning techniques, intelligent systemsthat can assist physicians in the daily interpretation of clinical images canplay a very important role. In addition, quantum techniques applied to deeplearning can enhance this performance, and federated learning techniques canrealize privacy-friendly collaborative learning among different participants,solving privacy issues due to the use of sensitive data and reducing the numberof data to be collected for each individual participant. We present in thisstudy a hybrid quantum neural network that can be used to quantifynon-alcoholic liver steatosis and could be useful in the diagnostic process todetermine a liver's suitability for transplantation; at the same time, wepropose a federated learning approach based on a classical deep learningsolution to solve the same problem, but using a reduced data set in each part.The liver steatosis image classification accuracy of the hybrid quantum neuralnetwork, the hybrid quantum ResNet model, consisted of 5 qubits and more than100 variational gates, reaches 97%, which is 1.8% higher than its classicalcounterpart, ResNet. Crucially, that even with a reduced dataset, our hybridapproach consistently outperformed its classical counterpart, indicatingsuperior generalization and less potential for overfitting in medicalapplications. In addition, a federated approach with multiple clients, up to32, despite the lower accuracy, but still higher than 90%, would allow using,for each participant, a very small dataset, i.e., up to one-thirtieth. Ourwork, based over real-word clinical data can be regarded as a scalable andcollaborative starting point, could thus fulfill the need for an effective andreliable computer-assisted system that facilitates the daily diagnostic work ofthe clinical pathologist.

Hybrid quantum image classification and federated learning for hepatic steatosis diagnosis