School of EE Seminar-Speaker- David Sriker- Class-Based Attention Mechanism for Chest Radiograph Multi-Label Categorization

https://tau-ac-il.zoom.us/j/88978668716?pwd=cXVLT0ZvNWI2QkRINmNUOWYzVW9C...
Meeting ID:   889 7866 8716
Passcode:       249211

Electrical Engineering Systems Seminar

Speaker: David Sriker

M.Sc. student under the supervision of Prof. Hayit Greenspan and Prof. Jacob Goldberger

Wednesday, February 9th, 2022, at 15:00

Class-Based Attention Mechanism for Chest Radiograph Multi-Label Categorization

Abstract

Chest X-ray (CXR) imaging is the most common examination type in a radiology department, today. Automatic disease classification can assist radiologists to reduce workload and to improve the quality of patient care. Medical image analysis has undergone a paradigm shift over the last decade, which is largely due to the tremendous success of convolutional neural networks (CNNs) that achieve superhuman performance in many image classification, segmentation, and quantification tasks. CNNs are being applied to CXR images, but the high spatial resolution, the lack of large datasets with reliable ground truth, and the large variety of diseases are significant research challenges when moving towards applications in a clinical environment. This work focuses on a new methodology for class-based attention, which is an extension to the more common image-based attention mechanism. The class-based attention mechanism learns a different attention mask for each class. This enables to simultaneously apply a different localization procedure for different pathologies in the same image, thus important for a multilabel categorization. We apply the method to detect and localize a set of pathologies in chest radiographs. The proposed method was incorporated with the ResNet network architecture and was evaluated on publicly available X-ray datasets and yielded improved classification results compared to standard image based attention.

השתתפות בסמינר תיתן קרדיט שמיעה = עפ"י רישום שם מלא + מספר ת.ז.  בצ'ט