The Standard Digital Image Database of chest radiographs with and without a lung nodule was developed as part of the research activities of the Academic Committee of the Japanese Society of Radiological Technology (JSRT) in 1998 (*1), supported by the Japan Radiological Society (JRS) and with the cooperation of healthcare facilities in Japan and the United States for providing case materials. Since then, the JSRT database has been used by a number of researchers in the world for various research purposes such as image processing, image compression, evaluation of image display, picture archiving and communication system (PACS), and computer-aided diagnosis with various machine learnings. After 24 years of distribution for researchers all over the world and their use of this database in various studies (*2-20), the number of citations of this database become 326 (191 articles, 123 proceedings, 15 reviews, and 7 book chapters) by Web of Science Core Collection in February 19, 2021.
Descriptions of the JSRT database
The database includes 154 conventional chest radiographs with a lung nodule (100 malignant and 54 benign nodules) and 93 radiographs without a nodule which were digitized by a laser digitizer with a 2048x2048 matrix size (0.175-mm pixels) and a 12-bit gray scale (no header, big-endian raw data). The database also includes additional information such as; patient age, gender, diagnosis (malignant or benign), X and Y coordinates of nodule, simple diagram of nodule location. Lung nodule images were classified into five groups according to the degrees of subtlety.
In addition, recently, we started to provide a mini JSRT database which can be utilized for beginners to learn various deep learning technique for medical images such as image classification, image segmentation, regression analysis, super resolution, denoise, and autoencoder.
- Shiraishi J, Katsuragawa S, lkezoe J, et al: Development of a digital image database for chest radiographs with and without a lung nodule: Receiver operating characteristic analysis of radiologists' detection of pulmonary nodules. AJR 174:71-74, 2000.
Recent articles cited JSRT-DB
- Wu HT, Huang Q, Cheung YM, Xu LL, Tang SH. Reversible contrast enhancement for medical images with background segmentation. Iet Image Processing 2020; 14(2): 327-336.
- Wang YF, Zhong ZC, Hua J. DeepOrganNet: On-the-Fly Reconstruction and Visualization of 3D / 4D Lung Models from Single-View Projections by Deep Deformation Network. Ieee Transactions on Visualization and Computer Graphics 2020; 26(1): 960-970.
- Wang H, Yang YY, Pan Y, et al. Detecting thoracic diseases via representation learning with adaptive sampling. Neurocomputing 2020; 406: 354-360.
- Park S, Jeong W, Moon YS. X-ray Image Segmentation using Multi-task Learning. Ksii Transactions on Internet and Information Systems 2020; 14(3): 1104-1120.
- Oliveira H, Mota V, Machado AMC, dos Santos JA. From 3D to 2D: Transferring knowledge for rib segmentation in chest X-rays. Pattern Recognition Letters 2020; 140: 10-17.
- Oh Y, Park S, Ye JC. Deep Learning COVID-19 Features on CXR Using Limited Training Data Sets. Ieee Transactions on Medical Imaging 2020; 39(8): 2688-2700.
- Mdletshe S, Oliveira M. The Development of a Computer-Based Teaching Simulation Tool to Aid Medical Imaging Educators in Teaching Pattern Recognition. International Journal of Morphology 2020; 38(5): 1258-1265.
- Matsubara N, Teramoto A, Saito K, Fujita H. Bone suppression for chest X-ray image using a convolutional neural filter. Physical and Engineering Sciences in Medicine 2020; 43(1): 97-108.
- Mansilla L, Milone DH, Ferrante E. Learning deformable registration of medical images with anatomical constraints. Neural Networks 2020; 124: 269-279.
- Larrazabal AJ, Martinez C, Glocker B, Ferrante E. Post-DAE: Anatomically Plausible Segmentation via Post-Processing With Denoising Autoencoders. Ieee Transactions on Medical Imaging 2020; 39(12): 3813-3820.
- Kholiavchenko M, Sirazitdinov I, Kubrak K, et al. Contour-aware multi-label chest X-ray organ segmentation. International Journal of Computer Assisted Radiology and Surgery 2020; 15(3): 425-436.
- Huang X, Fang Y, Lu MM, Yan FQ, Yang J, Xu YL. Dual-Ray Net: Automatic Diagnosis of Thoracic Diseases Using Frontal and Lateral Chest X-rays. Journal of Medical Imaging and Health Informatics 2020; 10(2): 348-355.
- Hooda R, Mittal A, Sofat S. A Novel Ensemble Method for PTB Classification in CXRs. Wireless Personal Communications 2020; 112(2): 809-826.
- Gong Q, Li Q, Gavrielides MA, Petrick N. Data transformations for statistical assessment of quantitative imaging biomarkers: Application to lung nodule volumetry. Statistical Methods in Medical Research 2020; 29(9): 2749-2763.
- Gomez O, Mesejo P, Ibanez O, Valsecchi A, Cordon O. Deep architectures for high-resolution multi-organ chest X-ray image segmentation. Neural Computing & Applications 2020; 32(20): 15949-15963.
- Gao XHW, James-Reynolds C, Currie E. Analysis of tuberculosis severity levels from CT pulmonary images based on enhanced residual deep learning architecture. Neurocomputing 2020; 392: 233-244.
- Eslami M, Tabarestani S, Albarqouni S, Adeli E, Navab N, Adjouadi M. Image-to-Images Translation for Multi-Task Organ Segmentation and Bone Suppression in Chest X-Ray Radiography. Ieee Transactions on Medical Imaging 2020; 39(7): 2553-2565.
- Chen J, Littlefair S, Bourne R, Reed WM. The Effect of Visual Hindsight Bias on Radiologist Perception. Academic Radiology 2020; 27(7): 977-984.
- Chen BZ, Zhang Z, Lin JY, Chen Y, Lu GM. Two -stream collaborative network for multi -label chest X-ray Image classification with lung segmentation. Pattern Recognition Letters 2020; 135: 221-227.
Registration and Download the JSRT database
All users are required to register – by creating a user_name and by obtaining a password to access download site. New registration to start this simple, two-step process. If you already have your user_name and a password, input your user_name and password to login. (Please note that the password will be invalid when you logged in to the download site more than ten times, so please re-register to obtain a new password)
All descriptions on this cite were written by Junji Shiraishi, Ph.D.