The ACROBAT data set consists of 4,212 whole slide images (WSIs) from 1,153 female primary breast cancer patients. The WSIs in the data set are available at 10X magnification and show tissue sections from breast cancer resection specimens stained with hematoxylin and eosin (H&E) or immunohistochemistry (IHC). For each patient, one WSI of H&E stained tissue and at least one one, and up to four, WSIs of corresponding tissue stained with the routine diagnostic stains ER, PGR, HER2 and KI67 are available. The data set was acquired as part of the CHIME study (chimestudy.se) and its primary purpose was to facilitate the ACROBAT WSI registration challenge (acrobat.grand-challenge.org). The histopathology slides originate from routine diagnostic pathology workflows and were digitised for research purposes at Karolinska Institutet (Stockholm, Sweden). The image acquisition process resembles the routine digital pathology image digitisation workflow, using three different Hamamatsu WSI scanners, specifically one NanoZoomer S360 and two NanoZoomer XR. The WSIs in this data set are accompanied by a data table with one row for each WSI, specifying an anonymised patient ID, the stain or IHC antibody type of each WSI, as well as the magnification and microns per pixel at each available resolution level. Automated registration algorithm performance evaluation is possible through the ACROBAT challenge website based on over 37,000 landmark pair annotations from 13 annotators. While the primary purpose of this data set was the development and evaluation of WSI registration methods, this data set has the potential to facilitate further research in the context of computational pathology, for example in the areas of stain-guided learning, virtual staining, unsupervised learning and stain-independent models.

The data set consists of three subsets, the training, validation and test set, based on the ACROBAT WSI registration challenge. There are 750 cases in the training set, for each of which one H&E WSI and one to four IHC WSIs are available, with 3406 WSIs in total. The validation set consists of 100 cases with 200 WSIs in total and the test set of 303 cases with 606 WSIs in total. Both for the validation and test set, one H&E WSI as well as one randomly selected IHC WSI is available.

WSIs were anonymised by deleting the associated macro images, by generating filenames with random case IDs and by overwriting meta data fields with potentially personal information. Hamamatsu NDPI files were then converted using libvips (libvips.org/). WSIs are available as generic tiled TIFF WSIs (openslide.org/formats/generic-tiff/) at 10X magnification and lower image levels.

The data set is available for download in seven separate ZIP archives, five for the training data (train_part1.zip (71.47 GB), train_part2.zip (70.59 GB), train_part3.zip (75.91 GB), train_part4.zip (71.63 GB) and train_part5.zip (69.09 GB)), one for the validation data (valid.zip 21.79 GB) and one for the test data (test.zip 68.11 GB).

File listings and checksums in SHA1 format are available for checking archive/data integrity when downloading.

While it would be helpful to notify SND of any publications using this data set by sending an email to request@snd.gu.se, please note that this is not required to use the data.

Explore the TCGA Whole Slide Image (WSI) SVS files available on Kaggle, offering detailed visual representations of tissue samples from various cancer types. These high-resolution images provide valuable insights into tumor morphology and tissue architecture, facilitating cancer diagnosis, prognosis, and treatment research. Delve into the rich landscape of cancer biology, leveraging the wealth of information contained within these SVS files to drive innovative advancements in oncology. This is a dataset of WSI images downloaded from the TCGA portal.

Bone and soft tissue (BST) tumors are a heterogeneous and rare group of mesenchymal neoplasms that pose significant diagnostic challenges owing to their complex morphologies and overlapping histological features. Despite rapid advances in digital pathology, most publicly available datasets predominantly focus on common epithelial tumors and offer a limited representation of BST tumors. To address this gap, we introduced the Pathologist-Annotated Image Retrieval dataset for Bone and Soft Tissue tumors (PAIR-BST), a dataset consisting of 2,252 pathologist-annotated regions of interest derived from 470 whole slide images obtained from 268 patients diagnosed with BST tumors. Each region was curated and annotated with multi-level labels, including 33 histologic diagnoses, 11 lines of differentiation, and 6 growth patterns, enabling comprehensive characterization of the morphological heterogeneity inherent to BST tumors. Benchmark experiments have demonstrated that pathology foundation models face challenges in identifying these tumors, particularly when distinguishing between tumor subtypes and growth patterns. PAIR-BST offers a high-quality, discriminative benchmark for the development and evaluation of pathology foundation models, specifically focusing on rare mesenchymal tumors.[Metadata Availability] Additional metadata containing specific coordinates for all ROIs (Regions of Interest) within the WSI, along with labels such as diagnosis for each, is available in a separate .csv file at: https://doi.org/10.25452/figshare.plus.31131145 (also linked in the related materials below).Find related datasets in the collection at https://doi.org/10.25452/figshare.plus.c.8223469.

The dataset is comprised of 38 chemically stained Whole slide image samples along with their corresponding ground truth annotated by histopathologists for 12 classes indicating skin layers (Epidermis, Reticular dermis, Papillary dermis, Dermis, Keratin), Skin tissues (Inflammation, Hair follicles, Glands), skin cancer (Basal cell carcinoma, Squamous cell carcinoma, Intraepidermal carcinoma) and background (BKG).

Links to code and bioRxiv pre-print:

1. Multi-lens Neural Machine (MLNM) Code

2. An AI-assisted Tool For Efficient Prostate Cancer Diagnosis (bioRxiv Pre-print)

Digitized hematoxylin and eosin (H&E)-stained whole-slide-images (WSIs) of 40 prostatectomy and 59 core needle biopsy specimens were collected from 99 prostate cancer patients at Tan Tock Seng Hospital, Singapore. There were 99 WSIs in total such that each specimen had one WSI. H&E-stained slides were scanned at 40× magnification (specimen-level pixel size 0·25μm × 0·25μm) using Aperio AT2 Slide Scanner (Leica Biosystems). Institutional board review from the hospital were obtained for this study, and all the data were de-identified.

Prostate glandular structures in core needle biopsy slides were manually annotated and classified using the ASAP annotation tool (ASAP). A senior pathologist reviewed 10% of the annotations in each slide, ensuring that some reference annotations were provided to the researcher at different regions of the core. It is to be noted that partial glands appearing at the edges of the biopsy cores were not annotated.

Patches of size 512 × 512 pixels were cropped from whole slide images at resolutions 5×, 10×, 20×, and 40× with an annotated gland centered at each patch. This dataset contains these cropped images.

This dataset is used to train two AI models for Gland Segmentation (99 patients) and Gland Classification (46 patients). Tables 1 and 2 illustrate both gland segmentation and gland classification datasets. We have put the two corresponding sub-datasets as two zip files as follows:

1. gland_segmentation_dataset.zip
2. gland_classification_dataset.zip

Table 1: The number of slides and patches in training, validation, and test sets for gland segmentation task. There is one H&E stained WSI for each prostatectomy or core needle biopsy specimen.

	#Slides
	Train	Valid	Test	Total
Prostatectomy	17	8	15	40
Biopsy	26	13	20	59
Total	43	21	35	99
	#Patches
	Train	Valid	Test	Total
Prostatectomy	7795	3753	7224	18772
Biopsy	5559	4028	5981	15568
Total	13354	7781	13205	34340

Table 2: The number of slides and patches in training, validation, and test sets for gland classification task. There is one H&E stained WSI for each prostatectomy or core needle biopsy specimen. The gland classification datasets are the subsets of the gland segmentation datasets. GS: Gleason Score. B: Benign. M: Malignant.

	#Slides (GS 3+3:3+4:4+3)
	Train	Valid	Test	Total
Biopsy	10:9:1	3:7:0	6:10:0	19:26:1
	#Patches (B:M)
	Train	Valid	Test	Total
Biopsy	1557:2277	1216:1341	1543:2718	4316:6336

NB: Gland classification folder (gland_classification_dataset.zip) may contain extra patches, labels of which could not be identified from H&E slides. They were not used in the machine learning study.

Precise detection of invasive cancer on whole-slide images (WSI) is a critical first step in digital pathology tasks of diagnosis and grading. Convolutional neural network (CNN) is the most popular representation learning method for computer vision tasks, which have been successfully applied in digital pathology, including tumor and mitosis detection. However, CNNs are typically only tenable with relatively small image sizes (200x200 pixels). Only recently, Fully convolutional networks (FCN) are able to deal with larger image sizes (500x500 pixels) for semantic segmentation. Hence, the direct application of CNNs to WSI is not computationally feasible because for a WSI, a CNN would require billions or trillions of parameters. To alleviate this issue, this paper presents a novel method, High-throughput Adaptive Sampling for whole-slide Histopathology Image analysis (HASHI), which involves: i) a new efficient adaptive sampling method based on probability gradient and quasi-Monte Carlo sampling, and, ii) a powerful representation learning classifier based on CNNs. We applied HASHI to automated detection of invasive breast cancer on WSI. HASHI was trained and validated using three different data cohorts involving near 500 cases and then independently tested on 195 studies from The Cancer Genome Atlas. The results show that (1) the adaptive sampling method is an effective strategy to deal with WSI without compromising prediction accuracy by obtaining comparative results of a dense sampling (~6 million of samples in 24 hours) with far fewer samples (~2,000 samples in 1 minute), and (2) on an independent test dataset, HASHI is effective and robust to data from multiple sites, scanners, and platforms, achieving an average Dice coefficient of 76%.

Convolutional Neural Network - CS256-FC256 Convolutional Neural Network (CNN) trained for patch-based classification of invasive breast cancer from histopathology digital images. The CNN architecture is 256 units in convolution and pooling layers, 256 units of fully connected layer and 2 units for output classification layer of softmax. The model was trained with Torch7. model_epoch25.net XML annotations by HG of WSIs from CINJ XML region-based annotations by HG pathologist of whole-slide images (WSIs) from CINJ institution data cohort. XML_CINJ_HG.zip XML annotations by MF and NS of WSIs from CINJ XML region-based annotations by MF and NS pathologists of whole-slide images (WSIs) from CINJ institution data cohort. XML_CINJ_MF+NS.zip XML annotations by HG of WSIs from TCGA XML region-based annotations by HG pathologist of whole-slide images (WSIs) from TCGA institution data cohort subset used in the paper. XML_TCGA_HG.zip TCGA scaled images 195 TCGA scaled images used as D_test to test HASHI method. TCGA_imgs_idx5.zip UHCMC/CWRU scaled images 110 UHCMC/CWRU scaled images used as D_2 dataset as part of Whole-Slide Image training data set. CWRU_imgs_idx8.zip CINJ scaled images 40 CINJ scaled images used as D_4 dataset as part of Whole-slide Image validation data set. CINJ_imgs_idx5.zip HUP scaled images Part1 120 of 239 HUP scaled images used as D_1 dataset as part of Whole-Slide Image training data set. HUP_imgs_idx5_Part1.zip HUP scaled images Part2 119 of 239 HUP scaled images used as D_1 dataset as part of Whole-Slide Image training data set. HUP_imgs_idx5_Part2.zip HUP binary masks of annotations HUP binary masks of manual annotations from pathologists. HUP_masks.zip UHCMC/CWRU binary masks of annotations UHCMC/CWRU binary masks of manual annotations from pathologists. CWRU_masks.zip CINJ binary masks of annotations CINJ binary masks of manual annotations from pathologists. CINJ_masks_HG.zip TCGA binary masks of annotations TCGA binary masks of manual annotations from pathologists. TCGA_masks.zip

Whole Slide Image Analysis Market Outlook

According to our latest research, the global Whole Slide Image Analysis market size reached USD 1.42 billion in 2024, and it is expected to grow at a remarkable CAGR of 14.7% from 2025 to 2033. By the end of the forecast period, the market is projected to achieve a value of USD 4.35 billion by 2033. The surging adoption of digital pathology solutions, particularly driven by advancements in artificial intelligence and machine learning, is a key growth factor fueling the expansion of the Whole Slide Image Analysis market globally.

The principal growth driver for the Whole Slide Image Analysis market is the increasing prevalence of chronic diseases, notably cancer, which necessitates rapid, accurate, and scalable diagnostic solutions. As healthcare systems worldwide face mounting pressure to deliver timely diagnoses, the digitization of pathology workflows through whole slide imaging has become essential. This technology enables pathologists to analyze high-resolution images remotely, reducing diagnostic turnaround times and minimizing human error. Furthermore, the integration of AI-powered algorithms significantly enhances the accuracy of image interpretation, supporting personalized medicine and improving patient outcomes. The convergence of these factors is leading to widespread adoption of Whole Slide Image Analysis across hospitals, research institutes, and diagnostic laboratories.

Another significant growth factor is the rising investment in healthcare IT infrastructure, particularly in developed economies such as the United States, Germany, and Japan. Governments and private players are increasingly funding initiatives aimed at modernizing pathology laboratories, which includes transitioning from traditional glass slides to digital platforms. The adoption of cloud-based solutions has further accelerated this trend, enabling seamless data storage, sharing, and collaboration among healthcare professionals. Additionally, the COVID-19 pandemic has acted as a catalyst, underscoring the need for remote diagnostics and virtual consultations. This shift has prompted healthcare organizations to embrace digital pathology and whole slide image analysis to ensure continuity in patient care and research activities.

The market is also benefiting from the expansion of applications beyond conventional cancer diagnostics. Whole Slide Image Analysis is now being leveraged in drug discovery, pathology research, and medical education, broadening its scope and utility. Pharmaceutical and biotechnology companies are utilizing these platforms to streamline drug development processes, while academic institutions are incorporating digital slides into their curricula for enhanced learning experiences. The growing awareness about the benefits of digital pathology, coupled with the increasing availability of user-friendly and interoperable software solutions, is expected to further drive market growth over the coming years.

Whole Slide Imaging is a transformative technology that has revolutionized the field of pathology by enabling the digitization of entire tissue slides. This advancement allows pathologists to view and analyze high-resolution images of tissue samples on a computer screen, rather than relying on traditional glass slides and microscopes. The ability to capture and store digital images of entire slides facilitates remote consultations and second opinions, enhancing collaboration among pathologists across different locations. Moreover, Whole Slide Imaging supports the integration of artificial intelligence and machine learning algorithms, which can assist in the automated detection and classification of pathological features, further improving diagnostic accuracy and efficiency.

From a regional perspective, North America currently dominates the Whole Slide Image Analysis market, accounting for the largest revenue share in 2024. This leadership is attributed to the presence of advanced healthcare infrastructure, high adoption rates of digital technologies, and strong government support for healthcare innovation. However, the Asia Pacific region is anticipated to exhibit the fastest growth over the forecast period, fueled by rising healthcare expenditure, increasing awareness about digital pathology, and expanding research and development activities. Europe also holds

Whole Slide Image market valued at $1.29 billion in 2025, projected to reach $3.85 billion by 2034 at 12.8% CAGR. Covers hardware, software, services across telepathology and diagnostics.

This is a representative sample from the dataset that was used to develop resolution-agnostic convolutional neural networks for tissue segmentation1 in whole-slide histopathology images.

The dataset is composed of two parts: development set and dissimilar set.

Sample images from the development set:

• breast_hne_00.tif
• breast_lymph_node_hne_00.tif
• tongue_ae1ae3_00.tif
• tongue_hne_00.tif
• tongue_ki67_00.tif

Sample images from the dissimilar set:

• brain_alcianblue_00.tif
• cornea_grocott_00.tif
• kidney_cab_00.tif
• skin_perls_00.tif
• uterus_vonkossa_00.tif

Large set of whole-slide-images (WSI) of prostatectomy specimens with various grades of prostate cancer (PCa). More information can be found in the corresponding paper: https://doi.org/10.1038/s41598-018-37257-4

The WSIs in this dataset can be viewed using the open-source software ASAP or Open Slide. Due to the large size of the complete dataset, the data has been split up in to multiple archives.

The data from the training set:

• peso_training_masks.zip: Training masks (N=62) that have been used to train the main network of our paper. These masks are generated by a trained U-Net on the corresponding IHC slides.
• peso_training_masks_corrected.zip: A subset of the color deconvolution masks (N=25) on which manual annotations have been made. Within these regions, stain and other artifacts have been removed.
• peso_training_colordeconvolution.zip: Mask files (N=62) containing the P63&CK8/18 channel of the color deconvolution operation. These masks mark all regions that are stained by either P63 or CK8/18 in the IHC version of the slides.
• peso_training_wsi_{1-6}.zip: Zip files containing the whole slide images of the training set (N=62). Each archive contains 10 slides, excluding the last which contains 12. These images are exported at a pixel resolution of 0.48mu/pixels.

The data from the test set:

• peso_testset_regions.zip: Collection of annotation XML files with outlines of the test regions. These can be used to view the test regions in more detail using ASAP.
• peso_testset_png.zip: Export of the test set regions in PNG format (2500x2500 pixels per region).
• peso_testset_png_padded.zip: Export of the test regions in PNG format padded with a 500 pixel wide border (3500x3500 pixels per region). Useful for segmenting pixels at the border of the regions.
• peso_testset_mapping.csv: A csv file mapping files from the test set (numbered 1-160) to regions in the xml files. The csv file also contains the label (benign or cancer) for each region.
• peso_testset_wsi_{1-4}.zip: Zip files containing the whole slide images of the test set (N=40). Each archive contains 10 slides of the test set. These images are exported at a pixel resolution of 0.48mu/pixels.

This study was financed by a grant from the Dutch Cancer Society (KWF), grant number KUN 2015-7970.

If you make use of this dataset please cite both the dataset itself and the corresponding paper: https://doi.org/10.1038/s41598-018-37257-4

The data set consists of 81 registered whole slide image pairs, a pair represents unstained and H&E stained images of the same tissue sample. In addition to that, it also contains a tissue mask for each whole slide image pair. The samples are used for studying the histological feasibility of AI-driven virtual histopathology staining.

Imaging was performed using Thunder Imager 3D Tissue slide scanner (Leica Microsystems, Wetzlar, Germany) equipped with DMC2900 camera and HC PL APO 40x/0.95 DRY objective with an isotropic pixel resolution of 0.353 µm.

The Pathology Images of Scanners and Mobilephones (PLISM) dataset was created for the evaluation of AI models’ robustness to domain shifts. PLISM is the first group-wised pathological image dataset that encompasses diverse tissue types stained under 13 H&E conditions, with multiple imaging media, including smartphones (7 scanners and 6 smartphones).In PLISM-sm, smartphone images were used as queries to create image groups for each staining condition corresponding to each tile image. The PLISM-sm subset contains a total of 57,902 images.Color and texture in digital pathology images are affected by H&E stain conditions (e.g. Harris or Carrazi) and digitalization devices (e.g. slide scanners or smartphones), which cause inter-institutional domain shifts.Please see the files 'stain_condition.png' and 'counterpart.png' for H&E staining conditions and devices used.This tar.gz file contains a collection of files labeled via the following file naming convention:(stain_name)/(device_name)/(top_left_x)_(top_left_y)_(right_lower_x)_(right_lower_y).pngThe csv file included with this dataset contains the following information:Tissue Type: The specific type of human tissue represented in the image, chosen from among 46 possible tissue types.Stain Type: The specific staining condition applied to the image, chosen from among 13 possible conditions.Device Type: The specific type of imaging device used to capture the image, chosen from among 13 possible device typesCoordinate: The xy coordinates of the top left and bottom right corners of each image (e.g., 1000_500_0_0)Image Path: The relative path to each image.See the whole slide images (WSIs) subset of the PLISM dataset in the Collection at https://doi.org/10.25452/figshare.plus.c.6773925

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.

Links to code:
Tissue Region Segmentation Code
This dataset comprises high-quality immunohistochemistry (IHC) and Haematoxylin and Eosin (H&E) whole slide images (WSIs) of breast tissues, provided in .svs format.

• The IHC dataset (labeled as BAU_IHC) consists of 55 zip files, each containing 2–3 WSIs, for a total of 163 slides.
• The H&E dataset (labeled as BAU_HE) consists of 36 zip files, each containing 2 WSIs, for a total of 72 slides.

The data were collected from Bahçeşehir University Medical School and are intended for research in histopathology and computational pathology.

This study was approved by the Bahçeşehir University Clinical Research Institutional Review Board (Approval No: 2022-10/03).

Whole Slide Imaging Market Outlook

According to our latest research, the global Whole Slide Imaging (WSI) market size reached USD 1.29 billion in 2025, driven by rapid digitization in pathology and the growing adoption of telemedicine and remote diagnostic solutions. The market is poised for robust expansion, projected to grow at a CAGR of 14.2% from 2026 to 2034. By the end of 2034, the market is expected to attain a valuation of approximately USD 4.32 billion. This remarkable growth trajectory is primarily attributed to accelerating technological advancements in scanner hardware and AI-powered software, increased healthcare spending globally, and the rising prevalence of chronic diseases that necessitate advanced and reproducible diagnostic solutions.

One of the primary growth drivers for the Whole Slide Imaging market is the increasing demand for digital pathology solutions in clinical and research settings. Healthcare providers and research institutes are rapidly transitioning from traditional glass slides to digital slides, which offer enhanced image quality, easier storage, and improved sharing capabilities. The ability to analyze high-resolution images remotely enables pathologists to collaborate across geographies, significantly reducing diagnostic turnaround times. Moreover, the integration of artificial intelligence and machine learning tools with WSI platforms is facilitating more accurate and efficient diagnosis, further fueling market adoption. These innovations are particularly critical in oncological and rare disease diagnostics, where precision and speed are paramount. Platforms supporting DICOM-based integration of whole slide imaging systems with hospital IT infrastructure are also gaining traction, simplifying interoperability across clinical networks.

Another significant factor propelling the growth of the Whole Slide Imaging market is the continued surge in telepathology applications, building on momentum established during and after the COVID-19 pandemic. Remote diagnostic solutions became a strategic priority for healthcare systems worldwide, prompting sustained investment in digital pathology infrastructure. Telepathology, powered by WSI, enables real-time consultation and second opinions, even in regions with limited access to specialized pathologists. This trend has not only improved patient outcomes but also optimized resource allocation within healthcare systems. Regulatory approvals for digital pathology systems in major markets such as the US, the European Union, Japan, and China have further legitimized and accelerated the adoption of WSI technologies in routine clinical workflows throughout 2025 and beyond.

The expansion of Whole Slide Imaging is also supported by the growing prevalence of chronic diseases, particularly cancer, which require frequent and sophisticated pathological examinations. The aging global population and the consequent rise in disease incidence rates have placed immense pressure on pathology services to deliver faster and more accurate results. WSI addresses these challenges by enabling high-throughput analysis, digital archiving, and seamless integration with laboratory information systems. Furthermore, the increasing focus on personalized medicine and companion diagnostics is driving the need for advanced imaging solutions that can support complex biomarker analysis and tissue profiling, thereby broadening the scope of WSI applications. The emergence of high-throughput slide scanning-as-a-service models is lowering the capital barrier for smaller laboratories, making digital pathology more accessible to a wider range of institutions.

From a regional perspective, North America currently dominates the Whole Slide Imaging market, accounting for the largest share in 2025, followed by Europe and Asia Pacific. The strong presence of key market players, favorable reimbursement policies, and high healthcare technology

The MCO study whole slide image collection consists of 1500 digitised tissue slides of colorectal cancers. From 1994 to 2010, the Molecular and Cellular Oncology (MCO) Study group conducted a study of individuals undergoing treatment for colorectal cancer. For the study, they systematically collected tissue samples and clinical and pathological information from more than 1500 people who had tumours surgically removed from their large bowel. This collection represents one typical section from each tumour case, stained with Hematoxylin and eosin, and scanned using a x40 objective. The resolution of the digitised images approaches that visible under an optical microscope - more than 100,000 dpi. At this resolution, each image is around 2 Gigabytes, bringing the size of the 1500 images in the MCO Whole Slide Image Collection to 3 Terabytes. The MCO whole slide image collection is now available on the Intersect Australia Research Data Storage Infrastructure (RDSI) Node. Originating source(s): MCO research group, UNSW (1993-2011)

An anonymous whole slide image in Philips iSyntax format for running software tests on OpenPhi - Open Pathology Interface (https://zenodo.org/record/4680748#.YNnBxDqxXJU). See the repository (https://gitlab.com/BioimageInformaticsGroup/openphi/) for up to date information.

This dataset was generated under three different magnifications

1. MPP10.tar. MPP = 1.0 µm/px
2. MPP15.tar. MPP = 1.5 µm/px
3. MPP20.tar. MPP = 2.0 µm/px

Each of them contains 4 subfolder: Breast, Colon, Kidney and Prostate, which means that the tiles are extracted from the Whole Slide Image (WSI) of the specific organ:

1. 78 WSIs from Breast
2. 80 WSIs from Colon
3. 80 WSIs from Kidney
4. 80 WSIs from Prostate

Each of the subfolder contains the images and masks from different case. The manual annotations were generated by experts, including 8 classes:

1. Tissue
2. Fold
3. Dark Spot and Foreign Object
4. Pen Marker
5. Edge and Air Bubble
6. Out of Focus
7. Background

and 0 means "Non-annotated pixels (Ignore)".

This dataset is for non-commercial, academic research only.

If you use this dataset, you must cite original publication:

Weng, Z., Seper, A., Pryalukhin, A. et al. GrandQC: A comprehensive solution to quality control problem in digital pathology. Nat Commun 15, 10685 (2024). https://doi.org/10.1038/s41467-024-54769-y

Mouse duodenum fixed in 4% PFA overnight at 4°C, processed for paraffin infiltration using a standard histology procedure and cut at 4 microns were dewaxed, rehydrated, permeabilized with 0.5% Triton X-100 in PBS 1x and stained with Azide - Alexa Fluor 555 (Thermo Fisher) to detect EdU and DAPI for nuclei. The images were taken using a Leica DM5500 microscope with a 40X N.A.1 objective (black&white camera: DFC350FXR2, pixel dimension: 0.161 microns). Next, the slide was unmounted and stained using the fully automated Ventana Discovery xT autostainer (Roche Diagnostics, Rotkreuz, Switzerland). All steps were performed on automate with Ventana solutions. Sections were pretreated with heat using the CC1 solution under mild conditions. The primary rat anti BrDU (clone: BU1/75 (ICR1), Serotec, diluted 1:300) was incubated 1 hour at 37°C. After incubation with a donkey anti rat biotin diluted 1:200 (Jackson ImmunoResearch Laboratories), chromogenic revelation was performed with DabMap kit. The section was counterstained with Harris hematoxylin (J.T. Baker) before a second round of imaging on DM5500 PL Fluotar 40X N.A.1.0 oil (color camera: DFC 320 R2, pixel dimension: 0.1725 microns). Before acquisition, a white-balance as well as a shading correction is performed according to Leica LAS software wizard. The fluorescence and DAB images were converted in ome.tiff multiresolution file with the kheops Fiji Plugin. Sampled prepared in the EPFL histology core facility by Nathalie Müller and Gian-Filippo Mancini. Associated documents: https://c4science.ch/w/bioimaging_and_optics_platform_biop/teaching/dab-intensity/ https://c4science.ch/w/bioimaging_and_optics_platform_biop/image-processing/wsi_registration_fjii_qupath/

A large annotated dataset, composed of both microscopy (classification task) and whole-slide images (segmentation task), was specifically compiled and made publicly available for the BACH challenge. Following a positive response from the scientific community, a total of 64 submissions, out of 677 registrations, effectively entered the competition. From the submitted algorithms it was possible to push forward the state-of-the-art in terms of accuracy (87%) in automatic classification of breast cancer with histopathological images.

There are two main folders for classification task: train and test. In Photos folder, there are totally four classes: benign, in situ, invasive, and normal. There is also a ground truth csv file for labels. Images are tif format.

Paper: https://arxiv.org/abs/1808.04277

Citation: Aresta, G., Araújo, T., Kwok, S., Chennamsetty, S. S., Safwan, M., Alex, V., ... & Aguiar, P. (2019). Bach: Grand challenge on breast cancer histology images. Medical image analysis, 56, 122-139.

Dataset: https://zenodo.org/record/3632035