Context

http://www.cell.com/cell/fulltext/S0092-8674(18)30154-5

https://i.imgur.com/jZqpV51.png" alt="">

Figure S6. Illustrative Examples of Chest X-Rays in Patients with Pneumonia, Related to Figure 6 The normal chest X-ray (left panel) depicts clear lungs without any areas of abnormal opacification in the image. Bacterial pneumonia (middle) typically exhibits a focal lobar consolidation, in this case in the right upper lobe (white arrows), whereas viral pneumonia (right) manifests with a more diffuse ‘‘interstitial’’ pattern in both lungs. http://www.cell.com/cell/fulltext/S0092-8674(18)30154-5

Content

The dataset is organized into 3 folders (train, test, val) and contains subfolders for each image category (Pneumonia/Normal). There are 5,863 X-Ray images (JPEG) and 2 categories (Pneumonia/Normal).

Chest X-ray images (anterior-posterior) were selected from retrospective cohorts of pediatric patients of one to five years old from Guangzhou Women and Children’s Medical Center, Guangzhou. All chest X-ray imaging was performed as part of patients’ routine clinical care.

For the analysis of chest x-ray images, all chest radiographs were initially screened for quality control by removing all low quality or unreadable scans. The diagnoses for the images were then graded by two expert physicians before being cleared for training the AI system. In order to account for any grading errors, the evaluation set was also checked by a third expert.

Acknowledgements

Data: https://data.mendeley.com/datasets/rscbjbr9sj/2

License: CC BY 4.0

Citation: http://www.cell.com/cell/fulltext/S0092-8674(18)30154-5

https://i.imgur.com/8AUJkin.png" alt="enter image description here">

Inspiration

Automated methods to detect and classify human diseases from medical images.

The dataset is organized into 3 folders (train, test, val) and contains subfolders for each image category (Pneumonia/Normal). There are 5,855 X-Ray images (JPEG) and 2 categories (Pneumonia/Normal).

Chest X-ray images (anterior-posterior) were selected from retrospective cohorts of pediatric patients of one to five years old from Guangzhou Women and Children’s Medical Center, Guangzhou. All chest X-ray imaging was performed as part of patients’ routine clinical care.

For the analysis of chest x-ray images, all chest radiographs were initially screened for quality control by removing all low quality or unreadable scans. The diagnoses for the images were then graded by two expert physicians before being cleared for training the AI system. In order to account for any grading errors, the evaluation set was also checked by a third expert.

Description

This dataset is derived from the pediatric chest X-ray images originally provided by Kermany et al. (2018) for pneumonia detection. The original dataset can be found on Mendeley and is described in this paper.

In this version, I provide three separate directories:

• chest_xray: The original images (train, val, test) with subfolders for NORMAL and PNEUMONIA.
• chest_xray_low_res: The same images, but downscaled by a factor of 2.
• chest_xray_bicubic: The downscaled images upscaled back to higher resolution using bicubic interpolation.

All three directories have the same folder structure: train, val, test, each containing NORMAL and PNEUMONIA subfolders. The dataset has been re-split into an 80-10-10 ratio to provide a more balanced and representative validation set (the original only contained 16 images in the validation folder).

Use Cases

• Training and evaluating models for pneumonia detection from chest X-rays.
• Comparing how image resolution (low-res vs. upscaled vs. original) affects model performance.
• Experimenting with data augmentation, transfer learning, or other deep learning techniques.

License & Citation

• License: CC BY 4.0
• Please cite the original authors: Kermany et al., 2018 (Cell), and reference the Mendeley repository.

The dataset of Chest X-Ray Images Pneumonia

This dataset is an augmented and partitioned version of paultimothymooney's chest-xray-pneumonia dataset, with the images divided into 10% test, 10% validation, and 80% train folders. These steps were taken to create a more balanced dataset. In its augmented form, the test folder contains 400 PNEUMONIA and 400 NORMAL images; the validation folder contains 400 PNEUMONIA and 400 NORMAL images; and the training folder contains 4000 PNEUMONIA and 4000 NORMAL images.

The dataset is organized into 3 folders (train, test, val) and contains subfolders for each image category (Pneumonia/Normal). There are 5,863 X-Ray images (JPEG) and 2 categories (Pneumonia/Normal). Chest X-ray images (anterior-posterior) were selected from retrospective cohorts of pediatric patients of one to five years old from Guangzhou Women and Children’s Medical Center, Guangzhou. All chest X-ray imaging was performed as part of patients’ routine clinical care. For the analysis of chest x-ray images, all chest radiographs were initially screened for quality control by removing all low quality or unreadable scans. The diagnoses for the images were then graded by two expert physicians before being cleared for training the AI system. In order to account for any grading errors, the evaluation set was also checked by a third expert. Figure S6. Illustrative Examples of Chest X-Rays in Patients with Pneumonia, Related to Figure 6 The normal chest X-r

Content

Adapted version of Paul Mooney's 'Chest X-Ray Images (Pneumonia)' dataset, where the amount of observations for training and validation purposes was redistributed to allow for a more balanced machine learning exercise. Total number of observations (images): 5,856 Training observations: 4,192 (1,082 normal cases, 3,110 lung opacity cases) Validation observations: 1,040 (267 normal cases, 773 lung opacity cases) Testing observations: 624 (234 normal cases, 390 lung opacity cases)

This is a combined curated dataset of COVID-19 Chest X-ray images obtained by collating 15 publically available datasets as listed under the references section. The present dataset contains 1281 COVID-19 X-Rays, 3270 Normal X-Rays, 1656 viral-pneumonia X-Rays, and 3001 bacterial-pneumonia X-Rays. This dataset is developed as a part of the following research publication.

"A deep-learning based multimodal system for Covid-19 diagnosis using breathing sounds and chest X-ray images" https://doi.org/10.1016/j.asoc.2021.107522

The collected datasets—as cited by this dataset—are combined to form an integrated repository. This integrated repository contains a total of 4558 COVID-19 X-Rays, 5403 Normal X-Rays, 4497 Viral pneumonia X-Rays, and 5768 bacterial pneumonia X-Rays. Out of which 1379 COVID-19 X-Rays, 1476 normal X-Rays, 2690 viral pneumonia X-Rays, and 2588 bacterial pneumonia X-Rays are found to be duplicates—based on the image similarities—and thus are removed. Inception V3 architecture is used to obtain the image embeddings, which is followed by the use of unsupervised learning algorithms based on cosine similarity distances. These distances are clustered and then visualized to find different categories of image defects which are listed below:—

1.Noise 2.Pixelated 3.Compressed 4.Medical Implants 5.Washed out image 6.Side View 7.CT (sliced) image 8.Aspect Ratio distortion / Cropped / Zoomed 9.Rotated Images 10.Images with annotations

These clusters of defective images are removed during the curation process and a refined dataset is obtained which is available for download.

This COVID-19 dataset consists of Non-COVID and COVID cases of both X-ray and CT images. The associated dataset is augmented with different augmentation techniques to generate about 17099 X-ray and CT images. The dataset contains two main folders, one for the X-ray images, which includes two separate sub-folders of 5500 Non-COVID images and 4044 COVID images. The other folder contains the CT images. It includes two separate sub-folders of 2628 Non-COVID images and 5427 COVID images.

📌 Steps to Reproduce This dataset contains a collection of primary chest X-ray images acquired from Epic Chittagong, Bangladesh. The dataset is designed for the study and development of deep learning and machine learning models for pneumonia detection and classification. This dataset contains 3,355 primary chest X-ray images collected from Epic Chittagong, Bangladesh, categorized into two classes: (1) Normal (2) Pneumonia

📊 Dataset Composition

Training Data : => Normal: 321 images => Pneumonia: 321 images => Total Training Samples: 642

Testing Data :

Normal: 1,363 images => Pneumonia: 1,350 images => Total Testing Samples: 2,713 👉 Grand Total: 3,355 X-ray images

📂 Folder Structure :

/Chest_Xray_EpicChittagong_Dataset/ ├── train/ │ ├── Normal/ │ └── Pneumonia/ ├── test/ │ ├── Normal/ │ └── Pneumonia/

📷 Image Details :

Format: JPEG / PNG Modality: Chest X-ray (CXR) Color: Grayscale Source: Epic Chittagong, Bangladesh 2025 Status: Primary dataset (raw and unprocessed)

🧪 Applications :

=> Pneumonia vs. Normal chest X-ray classification => Deep learning model training (CNN, transfer learning) => Benchmarking medical imaging algorithms => Computer-aided diagnosis (CAD) => Radiology research and teaching

📬 Contact :

For questions or collaboration Md Irfanul Kabir Hira Email: erfanulkabirhira132@gmail.com 🎓 Department of Computer Science and Engineering

🏛️ Institutions :

Epic Chittagong, Bangladesh National Institute of Textile Engineering and Research University of Dhaka

📚 Categories :

Computer Science, Radiology, Health Sciences, Artificial Intelligence, Computer Vision, Medical Imaging, Pneumonia, Chest X-ray, Deep Learning, Machine Learning

Pediatric Chest X-Ray Dataset

Overview

This dataset consists of pediatric chest X-ray images collected at Guangzhou Women and Children's Medical Center, Guangzhou, China. The dataset contains a total of 5,863 X-ray images in JPEG format, which are categorized into two classes: Pneumonia and Normal. These images have been used for developing an AI system for chest X-ray analysis.

Data Sources

The chest X-ray images were obtained as part of routine clinical care for pediatric patients aged one to five years. Quality control was applied to the images to remove low-quality or unreadable scans. The diagnostic labels for the images were assigned by two expert physicians, and a third expert reviewed an evaluation set to ensure diagnostic accuracy.

Data Preprocessing

To facilitate efficient model training, the dataset has undergone the following preprocessing steps: - Image Normalization: Images have been normalized to ensure consistent pixel values and enhance model convergence during training. - Image Resizing: All images have been resized to 256x256 pixels while preserving the aspect ratio.

Dataset Split

The dataset is divided into three subsets grouped by patient_id: - Training Set (train): Used for training the AI model. - Validation Set (val) : To select your model and tune hyperparameters. - Test Set (test): Employed to evaluate the model's performance.

Categories

• Pneumonia: Chest X-ray images showing signs of pneumonia.
• Normal: Chest X-ray images with no signs of pathology.

License

CC BY 4.0

Acknowledgments

https://data.mendeley.com/datasets/rscbjbr9sj/2 Kermany, Daniel; Zhang, Kang; Goldbaum, Michael (2018), “Labeled Optical Coherence Tomography (OCT) and Chest X-Ray Images for Classification”, Mendeley Data, V2, doi: 10.17632/rscbjbr9sj.2

Dataset

This dataset was created by Jorge Guerra Pires

Released under Attribution 4.0 International (CC BY 4.0)

Contents

Chest X Ray Pneumonia

## Overview

Chest X Ray Pneumonia is a dataset for classification tasks - it contains Objects annotations for 200 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

The dataset is designed for the study and development of deep learning and machine learning models for pneumonia detection and classification. This dataset contains 504 primary chest X-ray images collected from various pathology labs of the Bhopal area into two classes: (1) Normal: 204 images

(2) Pneumonia: 300 images

Image Description Format: JPEG / PNG Modality: Chest X-ray (CXR) Color: Grayscale

Status: Primary dataset (raw and unprocessed)

Applications: • Binary classification for Pneumonia vs. Normal chest X-ray • Train Deep learning models to automate diagnosis • Develop a mechanism for Computer-aided diagnosis (CAD)

• Medical image processing, academic research

Category: Artificial Intelligence, Deep Learning, Computer Vision, Clustering, Image processing, CNN, Classification, Medical Imaging, Pneumonia, Chest X-ray

This dataset contains anatomically segmented and color-enhanced chest X-ray (CXR) images, processed using the ASCE (Anatomical Segmentation and Color-Based Enhancement) pipeline. It includes 934 Normal, 1513 Viral Pneumonia, and 2587 Bacterial Pneumonia cases, originally sourced from Mendeley Data Repository, and used in the study titled “An Anatomically Enhanced and Clinically Validated Framework for Lung Abnormality Classification Using Deep Features and KL Divergence.”

ASCE-Enhanced Chest X-ray Dataset

This dataset contains color-enhanced and anatomically segmented chest X-ray images processed using the ASCE (Anatomical Segmentation and Color-Based Enhancement) framework. It includes three clinically relevant categories:
- Normal (934 images)
- Viral Pneumonia (1513 images)
- Bacterial Pneumonia (2587 images)

Origin and Attribution
This dataset is a derived work based on the original dataset published at:
[Mendeley Data - 8gf9vpkhgy](https://data.mendeley.com/datasets/8gf9vpkhgy/1)

Original Source Citation
> V. Labs, Darwin’s Auto-Annotate AI.
> "Lung Mask and Chest X-ray Data", Mendeley Data, V1.
> [https://data.mendeley.com/datasets/8gf9vpkhgy/1](https://data.mendeley.com/datasets/8gf9vpkhgy/1)

Description
Each image in this dataset has undergone:
1. Contrast and brightness adjustment
2. Histogram equalization
3. Bilateral filtering for texture preservation
4. Selective sharpening
5. Anatomical segmentation of:
- Blood Vessels (Red)
- Bronchial Tree (Green)
- Alveoli (Blue)

These enhanced images were used in the research titled:
"An anatomically enhanced and clinically validated framework for lung abnormality classification using deep features and KL divergence"

Folder Structure

ASCE_Enhanced_Renamed/
├── Normal/
├── Virus/
├── Bacteria/
├── metadata.csv
└── dataset_thumbnail.png

Dataset name Normal COVID-19 Pneumonia Total MOMA- Dataset 234 221 148 603

MOMA Dataset are collected from three resources, in the following links [1] https://github.com/smfai200/Detecting-COVID-19-in-X-ray-images/tree/master/dataset. Accessed at 19/4/2020 2.10 am. [2] https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia?fbclid=IwAR2jzVPSL8-MdEX8_DlFVrN EKJlu0nOUSlaKOxa4kOitv4RPeemEDRqL2E accessed at 27/4/2020 10.20 am.
[3] https://www.kaggle.com/bachrr/covid-chest-xray?fbclid=IwAR2kbLc1R3zqeC9lnBTAv5_lSB6XKVNGQlnilvH7uTI-M1rHGjJxYNLRb0k accessed at 27/4/2020 11.30 am.

RSUA Chest X-Ray dataset is Chest X-Ray image dataset owned by Airlangga University Hospital which has been converted from DICOM format into .BMP format. The dataset consists of X-Ray and Ground Truth images of each image. Images whose ground truth has been validated by radiologists at RSUA are contained in the "Validated" folder, while the complete dataset is contained in the "Annotated" folder. The dataset divided into 3 classes they are: Covid (207 validated data), Non-Covid (32 validated data), and Pneumonia (53 Validated data).

Pneumonia Detection with DenseNet121 🧠

This application uses a pre-trained DenseNet121 model to detect pneumonia from chest X-ray images.

  Features

Built with TensorFlow and Gradio Upload and get instant predictions Model trained on labeled X-ray dataset

  Instructions

Upload a chest X-ray image Wait for the prediction See if pneumonia is detected or not ✅🦠

🔗 Developed by Amir Ali

Same dataset Chest X-Ray Images (Pneumonia), ref: https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia

The dataset has been coded in TFRecords formats for efficiency reasons. Same license and other terms apply.

Discover the RSNA Pneumonia Detection Dataset, featuring pre-processed chest X-ray images, mask annotations, and detailed metadata for AI and machine learning in medical imaging.