Deep Learning ASPECTS Scoring for Brain CT Stroke Assessment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In Low Middle Income Countries, hospitals often lack radiologists to quickly assess brain CT scans for MCA strokes using the ASPECTS score, leading to delayed decision-making in stroke treatment.

Innovation Solution

A system and method that uses deep learning to resample brain CT scans, identify anatomical regions, segment infarcts, and compute an ASPECTS score in real-time, enabling non-specialist physicians to quickly determine the affected area and recommend a course of action.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If radiologists are used to assess brain CT scans for ASPECTS score, then measurement precision is improved, but loss of time increases due to unavailability in LMICs

Engineering Contradiction:

ImproveASPECTS score assessment accuracyVSAvoidtime for stroke treatment decision

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

A deep learning-based automated ASPECTS scoring system acts as an intermediary tool between general physicians and specialized radiologists. The system processes brain CT scans and provides ASPECTS scores that general physicians can use for stroke treatment decisions, eliminating the need for radiologist availability while maintaining assessment accuracy.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The manual radiologist assessment process is replaced with an automated deep learning system that uses neural networks to analyze CT scan images and compute ASPECTS scores. This substitution of human expertise with an automated computational system enables rapid assessment without requiring specialized personnel.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Loss of time

If general physicians assess brain CT scans without radiologist support, then loss of time is reduced, but measurement precision deteriorates due to inability to quickly decide

Engineering Contradiction:

Improvetime for stroke treatment decisionVSAvoidASPECTS score assessment accuracy

Core Design Contradiction:

Loss of timeVSMeasurement precision

Solution Approach 1:

The automated ASPECTS scoring system enables general physicians to independently perform accurate stroke assessments without requiring radiologist support. The system provides self-contained functionality that allows physicians to quickly obtain reliable ASPECTS scores and make treatment decisions autonomously.

Inventive Principle:

Principle #25Self-service

3Productivity

If automated deep learning system is implemented, then productivity is improved through real-time analysis, but device complexity increases

Engineering Contradiction:

Improvespeed of CT scan analysisVSAvoidcomplexity of deep learning system

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The deep learning system is segmented into distinct functional modules: a neural network model for identifying anatomical regions (basal ganglia, corona radiata), a segmentation module for detecting infarcts, and a scoring module for computing ASPECTS scores. This modular architecture manages system complexity while enabling real-time processing.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11501437B1Monitoring brain CT scan image

Publication Date: 2022.11.15 QURE AI TECH PTE LTD

AI summary

A system and a method for monitoring a brain CT scan image using ASPECTS score. The method includes receiving the brain CT scan image of a patient. Further, a basal ganglia region and a corona radiata level are identified in a plurality of slices in the brain CT scan image. Furthermore, a plurality of anatomical regions and a plurality of infarcts are segmented using deep learning. Subsequently, an overlapping region across the plurality of slices is determined based on the plurality of anatomical regions and the plurality of infarcts. The overlapping region and a predefined threshold are used to compute an ASPECTS score. The ASPECTS score is further used to recommend a course of action to the patient.