This dataset consists of 142 high-resolution ultrasound images of the temporomandibular joint (TMJ), annotated to segment three key anatomical structures: the mandibular condyle, joint space, and glenoid fossa. The images were acquired using a GE Versana Premier ultrasound system with an 8–18 MHz hockey stick probe. Patients were scanned in a relaxed, supine position, ensuring accurate representation of the joint in habitual occlusion. Each image was preprocessed by cropping to the diagnostic field of view and saved in 8-bit grayscale format. The dataset is divided into 107 training images and 35 test images, making it suitable for machine learning applications in medical imaging and TMJ analysis.Please cite the following articles, if you are using this dataset:Lasek, J.; Nurzynska, K.; Piórkowski, A.; Strzelecki, M.; Obuchowicz, R. Deep Learning for Ultrasonographic Assessment of Temporomandibular Joint Morphology. Tomography 2025, 11, x. https://doi.org/10.3390/tomography11030027

This dataset consists of 142 high-resolution ultrasound images of the temporomandibular joint (TMJ), annotated to segment three key anatomical structures: the mandibular condyle, joint space, and glenoid fossa. The images were acquired using a GE Versana Premier ultrasound system with an 8–18 MHz hockey stick probe. Patients were scanned in a relaxed, supine position, ensuring accurate representation of the joint in habitual occlusion. Each image was preprocessed by cropping to the diagnostic field of view and saved in 8-bit grayscale format. The dataset is divided into 107 training images and 35 test images, making it suitable for machine learning applications in medical imaging and TMJ analysis.Please cite the following articles, if you are using this dataset:Lasek, J.; Nurzynska, K.; Piórkowski, A.; Strzelecki, M.; Obuchowicz, R. Deep Learning for Ultrasonographic Assessment of Temporomandibular Joint Morphology. Tomography 2025, 11, x. https://doi.org/10.3390/tomography11030027

This dataset contains 114 t2-weighted MRI images of the prostate with corresponding segmentations.The segmentations include two labels, 1 - Transition Zone, 2 - Peripherial Zone. Most of the images include corresponding PIRADS and PSA values, which are available in the file PSA_PIRADS.csv. For more information concerning the images, see the following article. Please cite the following articles, if you are using this dataset: Gibala, S.; Obuchowicz, R.; Lasek, J.; Schneider, Z.; Piorkowski, A.; Pociask, E.; Nurzynska, K. Textural Features of MR Images Correlate with an Increased Risk of Clinically Significant Cancer in Patients with High PSA Levels. J. Clin. Med. 2023, 12, 2836. https://doi.org/10.3390/jcm12082836 Gibała, S.; Obuchowicz, R.; Lasek, J.; Piórkowski, A.; Nurzynska, K. Textural Analysis Supports Prostate MR Diagnosis in PIRADS Protocol. Appl. Sci. 2023, 13, 9871. https://doi.org/10.3390/app13179871

This dataset contains 114 t2-weighted MRI images of the prostate with corresponding segmentations.The segmentations include two labels, 1 - Transition Zone, 2 - Peripherial Zone. Most of the images include corresponding PIRADS and PSA values, which are available in the file PSA_PIRADS.csv. For more information concerning the images, see the following article. Please cite the following articles, if you are using this dataset: Gibala, S.; Obuchowicz, R.; Lasek, J.; Schneider, Z.; Piorkowski, A.; Pociask, E.; Nurzynska, K. Textural Features of MR Images Correlate with an Increased Risk of Clinically Significant Cancer in Patients with High PSA Levels. J. Clin. Med. 2023, 12, 2836. https://doi.org/10.3390/jcm12082836 Gibała, S.; Obuchowicz, R.; Lasek, J.; Piórkowski, A.; Nurzynska, K. Textural Analysis Supports Prostate MR Diagnosis in PIRADS Protocol. Appl. Sci. 2023, 13, 9871. https://doi.org/10.3390/app13179871