ALCNN: Attention based lightweight convolutional neural network for pneumothorax detection in chest X-rays

Agrawal, Tarun; Choudhary, Prakash

doi:10.1016/j.bspc.2022.104126

Cited by 13 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The literature search yielded 835 unique studies, and ultimately 23 met the inclusion criteria, with a total of 34 011 patients and 34 075 CXRs. 16-38 A study flow diagram is shown in Figure 1. The studies were published between 2016 and 2023 from various institutions around the world.…”

Section: Resultsmentioning

confidence: 99%

Deep Learning for Pneumothorax Detection on Chest Radiograph: A Diagnostic Test Accuracy Systematic Review and Meta Analysis

Katzman,

Alabousi,

Islam

et al. 2024

Can Assoc Radiol J

View full text Add to dashboard Cite

Background: Pneumothorax is a common acute presentation in healthcare settings. A chest radiograph (CXR) is often necessary to make the diagnosis, and minimizing the time between presentation and diagnosis is critical to deliver optimal treatment. Deep learning (DL) algorithms have been developed to rapidly identify pathologic findings on various imaging modalities. Purpose: The purpose of this systematic review and meta-analysis was to evaluate the overall performance of studies utilizing DL algorithms to detect pneumothorax on CXR. Methods: A study protocol was created and registered a priori (PROSPERO CRD42023391375). The search strategy included studies published up until January 10, 2023. Inclusion criteria were studies that used adult patients, utilized computer-aided detection of pneumothorax on CXR, dataset was evaluated by a qualified physician, and sufficient data was present to create a 2 × 2 contingency table. Risk of bias was assessed using the QUADAS-2 tool. Bivariate random effects meta-analyses and meta-regression modeling were performed. Results: Twenty-three studies were selected, including 34 011 patients and 34 075 CXRs. The pooled sensitivity and specificity were 87% (95% confidence interval, 81%, 92%) and 95% (95% confidence interval, 92%, 97%), respectively. The study design, use of an institutional/public data set and risk of bias had no significant effect on the sensitivity and specificity of pneumothorax detection. Conclusions: The relatively high sensitivity and specificity of pneumothorax detection by deep-learning showcases the vast potential for implementation in clinical settings to both augment the workflow of radiologists and assist in more rapid diagnoses and subsequent patient treatment.

show abstract

Section: Resultsmentioning

confidence: 99%

Deep Learning for Pneumothorax Detection on Chest Radiograph: A Diagnostic Test Accuracy Systematic Review and Meta Analysis

Katzman,

Alabousi,

Islam

et al. 2024

Can Assoc Radiol J

View full text Add to dashboard Cite

show abstract

“…The transfer learning approach assists in the model's fast convergence but does not necessarily increase the performance of the model 17,18 . A few studies for pneumothorax detection 19 and diabetic retinopathy 20 have also reached the same conclusion. Researchers use both transfer learning and a training from scratch approach for tumour classification in MRI images.…”

Section: Introductionmentioning

confidence: 81%

MultiFeNet: Multi‐scale feature scaling in deep neural network for the brain tumour classification in MRI images

Agrawal,

Choudhary,

Shankar

et al. 2023

Int J Imaging Syst Tech

Self Cite

View full text Add to dashboard Cite

One of the most fatal and prevalent diseases of the central nervous system is a brain tumour. Different subgrades exist for each type of brain tumour because of the broad variety of brain tumours and tumour pathologies. Manual diagnosis may be error‐prone and time‐consuming, both of which are becoming more challenging as the medical community's workload grows. There is a need for automatic diagnosis. In this study, we have proposed a deep learning model (MultiFeNet) based on a convolutional neural network for the classification of brain tumours. MultiFeNet uses multi‐scale feature scaling for feature extraction in magnetic resonance imaging (MRI) images. Multi‐scaling helps to learn the better feature representation of the MRI image for enhanced model performance. To evaluate the proposed model, 3064 MRI scans of three distinct categories of brain tumours (meningiomas, gliomas and pituitary tumours) were used. The MultiFeNet obtained 96.4% sensitivity, 96.4% F1‐score, 96.4% precision and 96.4% accuracy on the benchmark Figshare dataset. In addition, an ablation study is conducted with the objective of evaluating the role of multi‐scaling in model performance.

show abstract

“…This study successfully tackled the shortcomings of previous related research. Agrawal and Choudhary (2023) introduced a CNN model to detect pneumothorax in chest x-ray images, but the accuracy of pneumothorax classification was not high, and there was a lack of relevant analysis on lesion segmentation and classification interpretation. Upasana et al (2023) adopted an improved Xception model to detect pneumothorax, and while incorporating attention mechanisms improved the model's performance, it still could not explain the basis for its classification, which limited its employ in clinical applications.…”

Section: Discussionmentioning

confidence: 99%

Developing an explainable diagnosis system utilizing deep learning model: a case study of spontaneous pneumothorax

Lin,

Wei,

Bai

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective.The trend in the medical field is towards intelligent detection-based medical diagnostic systems. However, these methods are often seen as "black boxes" due to their lack of interpretability. This situation presents challenges in identifying reasons for misdiagnoses and improving accuracy, which leads to potential risks of misdiagnosis and delayed treatment. Therefore, how to enhance the interpretability of diagnostic models is crucial for improving patient outcomes and reducing treatment delays. So far, only limited researches exist on deep learning-based prediction of spontaneous pneumothorax, a pulmonary disease that affects lung ventilation and venous return. Approach. This study develops an integrated medical image analysis system using explainable deep learning model for image recognition and visualization to achieve an interpretable automatic diagnosis process.Main results.The system achieves an impressive 95.56% accuracy in pneumothorax classification, which emphasizes the significance of the blood vessel penetration defect in clinical judgment.Significance.This would lead to improve model trustworthiness, reduce uncertainty, and accurate diagnosis of various lung diseases, which results in better medical outcomes for patients and better utilization of medical resources. Future research can focus on implementing new deep learning models to detect and diagnose other lung diseases that can enhance the generalizability of this system.

show abstract

ALCNN: Attention based lightweight convolutional neural network for pneumothorax detection in chest X-rays

Cited by 13 publications

References 26 publications

Deep Learning for Pneumothorax Detection on Chest Radiograph: A Diagnostic Test Accuracy Systematic Review and Meta Analysis

Deep Learning for Pneumothorax Detection on Chest Radiograph: A Diagnostic Test Accuracy Systematic Review and Meta Analysis

MultiFeNet: Multi‐scale feature scaling in deep neural network for the brain tumour classification in MRI images

Developing an explainable diagnosis system utilizing deep learning model: a case study of spontaneous pneumothorax

Contact Info

Product

Resources

About