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

In the field of medical sciences, reliable detection and classification ofbrain tumors from images remains a formidable challenge due to the rarity oftumors within the population of patients. Therefore, the ability to detecttumors in anomaly scenarios is paramount for ensuring timely interventions andimproved patient outcomes. This study addresses the issue by leveraging deeplearning (DL) techniques to detect and classify brain tumors in challengingsituations. The curated data set from the National Brain Mapping Lab (NBML)comprises 81 patients, including 30 Tumor cases and 51 Normal cases. Thedetection and classification pipelines are separated into two consecutivetasks. The detection phase involved comprehensive data analysis andpre-processing to modify the number of image samples and the number of patientsof each class to anomaly distribution (9 Normal per 1 Tumor) to comply withreal world scenarios. Next, in addition to common evaluation metrics for thetesting, we employed a novel performance evaluation method called Patient toPatient (PTP), focusing on the realistic evaluation of the model. In thedetection phase, we fine-tuned a YOLOv8n detection model to detect the tumorregion. Subsequent testing and evaluation yielded competitive performance bothin Common Evaluation Metrics and PTP metrics. Furthermore, using the DataEfficient Image Transformer (DeiT) module, we distilled a Vision Transformer(ViT) model from a fine-tuned ResNet152 as a teacher in the classificationphase. This approach demonstrates promising strides in reliable tumor detectionand classification, offering potential advancements in tumor diagnosis forreal-world medical imaging scenarios.

Realism in Action: Anomaly-Aware Diagnosis of Brain Tumors from Medical Images Using YOLOv8 and DeiT