Demystifying evidential Dempster Shafer-based CNN architecture for fetal plane detection from 2D ultrasound images leveraging fuzzy-contrast enhancement and explainable AI

Article Computer Science, Information Systems

A Novel Approach for Classifying Brain Tumours Combining a SqueezeNet Model with SVM and Fine-Tuning

Mohammed Rasool et al.

Summary: Cancer of the brain is most common in the elderly and young and can be fatal in both. The deep learning method is crucial in aiding doctors to diagnose different diseases using medical images. Establishing a smart system for detecting and classifying brain tumours through MRI scans is essential for non-invasive diagnosis.

ELECTRONICS (2023)

添加到收藏夹

Article Chemistry, Multidisciplinary

Detection of Cardiac Structural Abnormalities in Fetal Ultrasound Videos Using Deep Learning

Masaaki Komatsu et al.

Summary: This study proposed a Supervised Object detection with Normal data Only (SONO) architecture based on convolutional neural network for automatic detection of cardiac substructures and structural abnormalities in fetal ultrasound videos, showing higher performance evaluations. The use of a barcode-like timeline for visualizing detection probability is informative for examiners to capture clinical characteristics of each case.

APPLIED SCIENCES-BASEL (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

An evidential classifier based on Dempster-Shafer theory and deep learning

Zheng Tong et al.

Summary: The study introduces a new classifier based on DS theory and CNN architecture, named the evidential deep-learning classifier. It aims to improve classification accuracy through feature extraction, mass function conversion, and set-valued classification, while also enabling cautious decision-making. The research also proposes an end-to-end learning strategy and a method for selecting partial multi-class acts.

NEUROCOMPUTING (2021)

添加到收藏夹

Review Environmental Sciences

Skin Cancer Detection: A Review Using Deep Learning Techniques

Mehwish Dildar et al.

Summary: Skin cancer, caused by un-repaired DNA in skin cells, can be cured in initial stages through early detection. Researchers have developed various early detection techniques, including deep learning, to address the increasing rate of skin cancer cases. Analysis of lesion parameters can accurately diagnose skin cancer.

INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

A Deep Attentive Convolutional Neural Network for Automatic Cortical Plate Segmentation in Fetal MRI

Haoran Dou et al.

Summary: Automatic segmentation of fetal cortical plate is challenging due to low resolution of MRI scans and variations in morphology, our deep learning method outperforms state-of-the-art models with high accuracy, facilitating large-scale studies on fetal brain development.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence