The dataset consists of 99 H&E-stained whole slide skin images (WSI) - 49 abnormal and 50 normal cases. All significant abnormal findings identified are outlined and categorized into 13 types such as actinic keratosis, basal cell carcinoma and dermatofibroma. Other tissue components, such as epidermis, adnexal structures, as well as the surgical margin are delineated to create a complete histological map. In total, 16741 separate annotations have been made to segment the different tissue structures and link them to ontological information.

Whole slide imaging of 396 full cases of axillary lymph nodes in breast cancer cases. Included are both sentinel node surgery and axillary dissections pre, peri or post breast cancer surgery or treatment. Sentinel node cases are cut in three levels (stained with HE) and one additional slide immunohistochemically stained with CKAE1/AE3. The number of sentinel node cases with complete immunohistochemical staining is 321. The axillary dissections are cut with one cut level as default. No frozen sections included. The cases are anonymised and exported from the digital archive at the Department of Clinical Pathology in Linköping, Region Östergötland. Included are both positive and negative cases. Some metadata on case level is available (positive or negative case, number of nodes, primary tumour and if neoadjuvant treatment in axillary dissections was given).

Radiotherapy treatment for prostate cancer relies on computed tomography (CT) and/or magnetic resonance imaging (MRI) for delineation of radiation targets and organs at risk (OARs). Manual delineation of these volumes is regarded as the gold standard for ground truth in machine learning applications but to acquire such data is tedious and time-consuming. A publicly available clinical dataset is introduced comprising MRI images, synthetic CT (sCT) images, target and OARs delineations, and radiotherapy dose distributions for 432 prostate cancer patients treated with an MRI-only radiotherapy workflow. An extended dataset with 35 patients is also included, containing the data mentioned above together with deep learning (DL)-generated delineations, DL uncertainty maps, and DL structures manually edited by four radiation oncologists. The publication of these resources aims to aid research within the fields of automated radiotherapy planning and structure delineation, inter-observer analyses, and DL uncertainty investigation.

Whole slide pathology images from excision specimens of cutaneous basal cell carcinomas (BCC) collected at the Department of Pathology at Sahlgrenska University Hospital, Sweden. The dataset contains 1832 WSIs from 479 excised BCCs and 261 punch biopsies representing BCCs annotated on a slide level. Furthermore the dataset contains 253 tumor-free skin biopsies.

This AIDA document is related to rezone petition: 18-07

Atypical femoral fracture is a well-documented adverse reaction to bisphosphonate treatment, but may also have other causes. This dataset contains 433 radiographs from 149 patients with complete AFF, and 549 radiographs from 224 patients with normal femur fractures. There are no diagnoses of cancer, to reduce the risk of confounding by indication.

This dataset consists of 361 whole slide images (WSI) - 296 malignant from women with invasive breast cancer (HER2 neg) and 65 benign. The tumours have been classified with four SNOMED-CT categories based on morphology: invasive duct carcinoma, invasive lobular carcinoma, in situ carcinoma, and others. 4144 separate annotations have been made to segment different tissue structures connected to ontologies.

The dataset consists of 101 H&E-stained colon whole slide images (WSI) - 52 abnormal and 49 benign cases. All significant abnormal findings identified are outlined and categorized into 15 types such as hyperplastic polyp, high grade adenocarcinoma and necrosis. Other tissue components such as mucosa, submucosa, as well as the surgical margin are delineated to create a complete histological map. In total, 756 separate annotations have been made to segment the different tissue structures and link them to ontological information.

The data contains 300 skulls. The data is divided into three groups with 100 scans in three categories Females, Males, and Mix. The purpose of the project was to generate a machine learning algorithm to be able reconstruct missing parts of the skull for cranioplasty. Each scan was verified to ensure normal skull shape. To ensure data privacy the faces have been deblurred with an in-house developed algorithm.

Test set used for knee fracture classification using the AO/OTA 2018 classification. 2472 images from 600 examinations. OpenAccess article available here.

The Ankle Fracture dataset includes radiological images for diagnosing and evaluating ankle fractures. The dataset focuses on X-ray imaging, providing annotations for fracture identification, classification, and severity grading.

Rezone petition document for petition ID: 17-13

This AIDA document is related to rezone petition: 22-31

36 radiology cases showing lytic and lytic/sclerotic (blastic) metastases i.e. bone regenerative and degenerative. These cases have all been punctured and pathologically analyzed to verify the diagnose. The metastases were segmented accurately by a radiologist and the annotations were confirmed by a second radiologist.

14711 digital mammography (DM) examinations from screening, usually including two projections (mediolateral oblique and craniocaudal) of each breast. Categorized cancer positive/negative. 95 cancer cases diagnosed on DM.

Part of this dataset is directly available for inspection for partners on the AIDA platform, and the rest can be made available on request.

This dataset is an anonymized excerpt from a dataset with richer associated data, collected in a research project which is still ongoing. The authors welcome proposals for new impactful research collaborations.

Whole slide pathology images from regional lymph node metastasis in colon adenocarcinoma produced at Region Gävleborg Clinical Pathology and Cytology department and Region Östergötland Clinical Pathology department. Annotations for AI training produced as part of AIDA clinical fellowship project investigating AI decision support in metastasis detection. This dataset has been extended with a second collection series in the LNCO2 dataset using different collection and annotation parameters.

This dataset is a collection of synthetic images generated by 5 generative models (Progressive GAN, StyleGAN1, StyleGAN2, StyleGAN3, diffusion model) trained on the BraTS 2020 and 2021 datasets 1,2,3,4,5. The trained generative models are also shared in this dataset. See our recent work [6] for more information, and a comparison of training segmentation networks with real and synthetic images.

This AIDA document is related to rezone petition: 17-09

MR-images of the prostate region from healthy volunteers acquired at Elekta unity MR-Linac at Uppsala University Hospital. Data from each volunteer consist of an initial T2-weighted scan, followed by a number of groups of paired low and high resolution data approximately 5 minutes apart with a 3D balanced steady state free precession sequence. The initial T2-image and all high resolution images are segmented by a single observer including prostate, bladder and rectum.

30 clinical routine CTPA examinations, performed on a Philips Brilliance 64 CT or GE Lightspeed VCT. 14317 axial images (1 or 0,625mm) plus additional reformats. 5 of the CTPAs are positive for pulmonary embolism and have all the emboli carefully delineated by an experienced radiologist.