Limitations of an automated embolism segmentation method in clinical practice

Related Experiment Video

Updated: Feb 11, 2026

Establishment of a Rat Model of Superior Sagittal-Sinus Occlusion via a Thread-Embolism Method
08:07

Establishment of a Rat Model of Superior Sagittal-Sinus Occlusion via a Thread-Embolism Method

Published on: July 4, 2021

4.0K

Ruifeng Wang1,2, Nan Yu1,2, Sheng Zhou1,3

  • 1Department of Radiology, The First Affiliated Hospital of Medical School of Xi'an Jiaotong University, Xi'an, Shaanxi, China.

Journal of X-Ray Science and Technology
|May 2, 2018
PubMed
Abstract

Insights

Automated pulmonary embolism segmentation has limitations due to various factors like lung diseases and scan protocols. Understanding these failures is key to improving automated analysis of CTPA scans.

Area of Science:

  • Radiology
  • Medical Imaging Analysis
  • Artificial Intelligence in Healthcare

Background:

  • Automated pulmonary embolism (PE) segmentation is a crucial preprocessing step for quantitative analysis.
  • Clinical case studies are essential for evaluating the limitations of automated PE segmentation algorithms.

Purpose of the Study:

  • To analyze the potential limitations of automated pulmonary embolism segmentation.
  • To identify failure reasons in automated PE segmentation using clinical data.

Main Methods:

  • A database of 304 CTPA examinations with confirmed PE was analyzed.
  • Two radiologists classified segmentation results into four groups (A-D).
  • Failure reasons were determined based on image characteristics and CTPA protocols.

Main Results:

  • Segmentation failed in 46.1% of cases (Groups C and D).
  • Fifteen distinct failure reasons were identified, including intrapulmonary abnormalities, scan protocol variations, and artifacts.
  • Failure reasons ranged from 0.3% to 9.2% in case percentages.

Conclusions:

  • Automated segmentation failures stem from lung diseases, anatomical variations, and suboptimal scanning parameters.
  • Recognizing these limitations is vital for developing more robust automated segmentation schemes.
  • Improved automated analysis is needed for large-scale CTPA examination processing.
Keywords:
Automated pulmonary embolism (PE) segmentationComputer tomography pulmonary angiography (CTPA)

More Related Videos

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

25.0K
Laparoscopic Left Liver Sectoriectomy of Caroli's Disease Limited to Segment II and III04:41

Laparoscopic Left Liver Sectoriectomy of Caroli's Disease Limited to Segment II and III

Published on: February 27, 2009

14.7K

Related Concept Videos

Limiting Reactant02:27

Limiting Reactant

The relative amounts of reactants and products represented in a balanced chemical equation are often referred to as stoichiometric amounts. However, in reality, the reactants are not always present in the stoichiometric amounts indicated by the balanced equation.
70.4K
Pulmonary Embolism I: Introduction01:29

Pulmonary Embolism I: Introduction

Pulmonary embolism (PE) occurs when a thrombus, fat or air embolus, amniotic fluid, or tumor tissue blocks one or more pulmonary arteries. These blockages originate in the venous system or the right side of the heart.EtiologyPE primarily arises from deep vein thrombosis (DVT) and other hypercoagulable states, such as inherited thrombophilias. Additional etiological factors include venous stasis, commonly seen in obesity, and endothelial injury from surgery and trauma. Less common causes include...
761
The Number e as a Limit01:29

The Number e as a Limit

The number e is a fundamental constant in calculus, playing a central role in describing continuous change, particularly exponential growth. It is most naturally defined through its relationship with the natural logarithm, which is the inverse of the exponential function with base e. This relationship allows e to be characterized using basic principles of differentiation rather than as an arbitrary numerical constant.A key property of the natural logarithm function, ln x, is that its derivative...
99
Types of Limits I01:23

Types of Limits I

Limits are a key mathematical concept for understanding how functions behave as their input approaches specific values, particularly when the function is undefined. They help reveal trends and discontinuities by examining the values a function approaches rather than its actual value.One-sided limits focus on the direction from which a value is approached. When a function behaves differently depending on whether the input approaches from the left or the right, the two one-sided limits may not...
206
Limit Laws I01:25

Limit Laws I

Limit laws provide essential tools for analyzing how functions behave as their input approaches a specific value. These laws are particularly useful when dealing with combinations of functions, provided the individual limits exist. The Sum and Difference Laws state that the limit of the sum or difference of two functions equals the sum or difference of their respective limits:The Product Law asserts that the limit of the product of two functions equals the product of their individual limits:A...
232
Limits at Infinity01:24

Limits at Infinity

The function that decreases as the input becomes very large provides a clear example of how mathematical functions can behave at extreme values. When the input increases continuously, the output becomes smaller and smaller, getting closer to a particular fixed value. Although the output never actually reaches this value, it moves nearer to it without limit. This behavior is a fundamental concept in understanding how functions behave as the input grows indefinitely. The graphical representation...
330