Chest X-ray abnormalities localization via ensemble of deep convolutional neural networks

Pham, Van-Tien; Tran, Cong-Minh; Zheng, Stanley; Minh, Vu Tri; Nath, Shantanu

doi:10.1109/atc52653.2021.9598342

Cited by 11 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multiple ensemble techniques are described in the literature for decreasing segmentation errors and optimizing efficiency ( 37 – 39 ). Their utility becomes evident especially when the available training dataset for a new application area is small or highly heterogeneous, such as the case of the OCSCC and OPSCC datasets.…”

Section: Methodsmentioning

confidence: 99%

Videomics of the Upper Aero-Digestive Tract Cancer: Deep Learning Applied to White Light and Narrow Band Imaging for Automatic Segmentation of Endoscopic Images

et al. 2022

View full text Add to dashboard Cite

IntroductionNarrow Band Imaging (NBI) is an endoscopic visualization technique useful for upper aero-digestive tract (UADT) cancer detection and margins evaluation. However, NBI analysis is strongly operator-dependent and requires high expertise, thus limiting its wider implementation. Recently, artificial intelligence (AI) has demonstrated potential for applications in UADT videoendoscopy. Among AI methods, deep learning algorithms, and especially convolutional neural networks (CNNs), are particularly suitable for delineating cancers on videoendoscopy. This study is aimed to develop a CNN for automatic semantic segmentation of UADT cancer on endoscopic images.Materials and MethodsA dataset of white light and NBI videoframes of laryngeal squamous cell carcinoma (LSCC) was collected and manually annotated. A novel DL segmentation model (SegMENT) was designed. SegMENT relies on DeepLabV3+ CNN architecture, modified using Xception as a backbone and incorporating ensemble features from other CNNs. The performance of SegMENT was compared to state-of-the-art CNNs (UNet, ResUNet, and DeepLabv3). SegMENT was then validated on two external datasets of NBI images of oropharyngeal (OPSCC) and oral cavity SCC (OSCC) obtained from a previously published study. The impact of in-domain transfer learning through an ensemble technique was evaluated on the external datasets.Results219 LSCC patients were retrospectively included in the study. A total of 683 videoframes composed the LSCC dataset, while the external validation cohorts of OPSCC and OCSCC contained 116 and 102 images. On the LSCC dataset, SegMENT outperformed the other DL models, obtaining the following median values: 0.68 intersection over union (IoU), 0.81 dice similarity coefficient (DSC), 0.95 recall, 0.78 precision, 0.97 accuracy. For the OCSCC and OPSCC datasets, results were superior compared to previously published data: the median performance metrics were, respectively, improved as follows: DSC=10.3% and 11.9%, recall=15.0% and 5.1%, precision=17.0% and 14.7%, accuracy=4.1% and 10.3%.ConclusionSegMENT achieved promising performances, showing that automatic tumor segmentation in endoscopic images is feasible even within the highly heterogeneous and complex UADT environment. SegMENT outperformed the previously published results on the external validation cohorts. The model demonstrated potential for improved detection of early tumors, more precise biopsies, and better selection of resection margins.

show abstract

Section: Methodsmentioning

confidence: 99%

Videomics of the Upper Aero-Digestive Tract Cancer: Deep Learning Applied to White Light and Narrow Band Imaging for Automatic Segmentation of Endoscopic Images

et al. 2022

View full text Add to dashboard Cite

show abstract

“…To begin, we use a pre-trained Faster-RCNN on the Chest ImaGenome dataset [6,26,30] to extract the anatomical bounding boxes and their corresponding features f 𝑎 from the input images. Subsequently, we train a Faster-RCNN on the VinDr-CXR dataset [24] to detect diseases. Rather than directly detecting diseases on the given input images, we extract the features f 𝑑 from the same anatomical regions by utilizing the previously extracted anatomical bounding boxes.…”

Section: Anatomicalmentioning

confidence: 99%

Expert Knowledge-Aware Image Difference Graph Representation Learning for Difference-Aware Medical Visual Question Answering

et al. 2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

To contribute to automating the medical vision-language model, we propose a novel Chest-Xray Difference Visual Question Answering (VQA) task. Given a pair of main and reference images, this task attempts to answer several questions on both diseases and, more importantly, the differences between them. This is consistent with the radiologist's diagnosis practice that compares the current image with the reference before concluding the report. We collect a new dataset, namely MIMIC-Diff-VQA, including 700,703 QA pairs from 164,324 pairs of main and reference images. Compared to existing medical VQA datasets, our questions are tailored to the Assessment-Diagnosis-Intervention-Evaluation treatment procedure used by clinical professionals. Meanwhile, we also propose a novel expert knowledge-aware graph representation learning model to address this task. The proposed baseline model leverages expert knowledge such as anatomical structure prior, semantic, and spatial knowledge to construct a multi-relationship graph, representing the image differences between two images for the image difference VQA task. The dataset and code can be found at https://github.com/Holipori/MIMIC-Diff-VQA. We believe this work would further push forward the medical vision language model.

show abstract

“…In [11], the authors proposed a computer-aided diagnosis (CAD) system to detect pneumonia using 3 classification methodologies including a hybrid CNN (VGG-16 and VGG-19); the system offered an accuracy of 98%. In [12], the authors proposed a DL model to detect and localize abnormalities in the CXR images, the related algorithm is based on 3 classifier options and 4 model detectors using the VinDr-CXR dataset, which is augmented with Albumentations [13] in order to solve the class imbalance; the model's performance measured approximately 29% in terms of mean average precision (MAP). Likewise, in [14] the authors proposed a set of 2 CNN models: Mask R-CNN and RetinaNet, for the prediction and localization of pneumonia in small areas of CXR images.…”

Section: Related Workmentioning

confidence: 99%

An improvement of the CNN-XGboost model for pneumonia disease classification

Hedhoud,

Mekhaznia,

Amroune

2023

Pol J Radiol

View full text Add to dashboard Cite

PurposeX-ray images are viewed as a vital component in emergency diagnosis. They are often used by deep learning applications for disease prediction, especially for thoracic pathologies. Pneumonia, a fatal thoracic disease induced by bacteria or viruses, generates a pleural effusion where fluids are accumulated inside lungs, leading to breathing difficulty. The utilization of X-ray imaging for pneumonia detection offers several advantages over other modalities such as computed tomography scans or magnetic resonance imaging. X-rays provide a cost-effective and easily accessible method for screening and diagnosing pneumonia, allowing for quicker assessment and timely intervention. However, interpretation of chest X-ray images depends on the radiologist’s competency. Within this study, we aim to suggest new elements leading to good interpretation of chest X-ray images for pneumonia detection, especially for distinguishing between viral and bacterial pneumonia.Material and methodsWe proposed an interpretation model based on convolutional neural networks (CNNs) and extreme gradient boosting (XGboost) for pneumonia classification. The experimental study is processed through various scenarios, using Python as a programming language and a public database obtained from Guangzhou Women and Children’s Medical Centre.ResultsThe results demonstrate an acceptable accuracy of 87% within a mere 7 seconds, thereby endorsing its effectiveness compared to similar existing works.ConclusionsOur study provides a model based on CNN and XGboost to classify images of viral and bacterial pneumonia. The work is a challenging task due to the lack of appropriate data. The experimental process allows a better accuracy of 87%, a specificity of 89%, and a sensitivity of 85%.

show abstract

Chest X-ray abnormalities localization via ensemble of deep convolutional neural networks

Cited by 11 publications

References 19 publications

Videomics of the Upper Aero-Digestive Tract Cancer: Deep Learning Applied to White Light and Narrow Band Imaging for Automatic Segmentation of Endoscopic Images

Videomics of the Upper Aero-Digestive Tract Cancer: Deep Learning Applied to White Light and Narrow Band Imaging for Automatic Segmentation of Endoscopic Images

Expert Knowledge-Aware Image Difference Graph Representation Learning for Difference-Aware Medical Visual Question Answering

An improvement of the CNN-XGboost model for pneumonia disease classification

Contact Info

Product

Resources

About