Related Experiment Video
Updated: Jun 14, 2025
08:45
A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets
Published on: December 5, 2014
9.2K
ERABiLNet: enhanced residual attention with bidirectional long short-term memory
Koteeswaran Seerangan1, Malarvizhi Nandagopal2, Resmi R Nair3
1S.A. Engineering College (Autonomous), Chennai, Tamil Nadu, 600077, India.
Scientific Reports
|September 4, 2024
Summary
This study introduces Enhanced Residual Attention with Bi-directional Long Short-Term Memory (ERABi-LNet) for early Alzheimer's Disease (AD) detection using MRI scans. The novel deep learning model significantly improves diagnostic accuracy and reduces errors in identifying AD from neuroimages.
Area of Science:
- Medical Imaging and Artificial Intelligence
- Neuroscience and Machine Learning Applications
Background:
- Alzheimer's Disease (AD) leads to progressive brain cell death, often mistaken for age-related changes.
- Magnetic Resonance Imaging (MRI) is a primary tool for AD detection, but distinguishing AD from similar neuro-images remains challenging.
- Artificial Intelligence (AI) enhances brain disease identification, yet subtle phenotypic differences complicate accurate diagnosis.
Purpose of the Study:
- To propose a deep learning method for early-stage Alzheimer's Disease detection using MRI.
- To introduce and evaluate the Enhanced Residual Attention with Bi-directional Long Short-Term Memory (ERABi-LNet) model.
- To improve the performance, accuracy, and error rates of Alzheimer's detection in neuroimages.
Main Methods:
- Utilized a novel deep learning architecture, ERABi-LNet, for Alzheimer's Disease detection from MRI scans.
- Employed a Residual Attention Network (RAN) with atrous, dilated, and Depth-Wise Separable (DWS) convolutional layers to extract relevant features.
- Integrated fused attributes into an Attention-based Bi-LSTM for final outcome generation, with parameter tuning via Modified Search and Rescue Operations (MCDMR-SRO).
Main Results:
- The ERABi-LNet model achieved a median detection efficiency of 26.37% and an accuracy of 97.367%.
- Demonstrated superior performance metrics including sensitivity (97.49%), specificity (97.84%), F1-Score (97.74%), and a low False Positive Rate (2.616%) compared to other deep learning models.
- Showcased enhanced learning capabilities, minimized error rates, and improved model balance for multi-class problem support.
Conclusions:
- The proposed ERABi-LNet model offers enhanced accuracy and reliability for early Alzheimer's Disease detection from MRI.
- The model's ability to handle subtle phenotypic differences and provide balanced predictions makes it a valuable tool in neuroimaging diagnostics.
- ERABi-LNet represents a significant advancement in deep learning for neurodegenerative disease identification, offering improved sensitivity and specificity.
Related Concept Videos
01:24Working Memory
149
Working memory refers to a combination of components, including short-term memory and attention, that allow an individual to hold information temporarily as we perform cognitive tasks. It is an essential cognitive function that enables the execution of complex tasks such as problem-solving, comprehension, and reasoning. Unlike short-term memory, which simply involves the storage of information for a brief period, working memory involves the active manipulation and processing of this...
149
01:22Chunking and Rehearsal in Sensory Memory
186
Improving short-term memory can be achieved through techniques like chunking and rehearsal. Chunking involves organizing information into larger, more manageable units. This technique is particularly useful for information that exceeds the typical memory span of between five and nine items. For instance, logging into an online account with a password like "ta89vq0179gz" involves grouping letters and numbers into three chunks—ta89, vq01, and 79gz. It makes large amounts of...
186
01:07Elaborative Rehearsals
83
Elaborative rehearsal is a crucial cognitive strategy that strengthens information encoding in long-term memory by making meaningful connections between new data and pre-existing knowledge. This approach contrasts with maintenance rehearsal, which involves simple repetition without delving into the significance of the information. While maintenance rehearsal might temporarily keep information active in short-term memory, it is less effective for long-term retention.
The effectiveness of...
The effectiveness of...
83
01:35Long-term Potentiation
55.0K
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre- and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
55.0K