PXD028949

PXD028949 is an original dataset announced via ProteomeXchange.

Title	Machine learning for grading and prognosis of esophageal dysplasia using mass spectrometry and histological imaging
Description	Background: Barrett’s esophagus (BE) is a precursor lesion of esophageal adenocarcinoma and may progress from non-dysplastic through low-grade dysplasia (LGD) to high-grade dysplasia (HGD) and cancer. Grading BE is of crucial prognostic value and is currently based on the subjective evaluation of biopsies. This study aims to investigate the potential of machine learning (ML) using spatially resolved molecular data from mass spectrometry imaging (MSI) and histological data from microscopic haematoxylin and eosin (H&E)-stained imaging for computer-aided diagnosis and prognosis of BE. Methods: Biopsies from 57 patients were considered, divided into non-dysplastic (n=15), LGD non-progressive (n=14), LGD progressive (n=14), and HGD (n=14). MSI experiments were conducted at 50x50 μm spatial resolution per pixel corresponding to a tile size of 96x96 pixels in the co-registered H&E images, making a total of 144,823 tiles for the whole dataset. Results: ML models were trained to distinguish epithelial tissue from stroma with area-under-the-curve (AUC) values of 0.89 (MSI) and 0.95 (H&E)) and dysplastic grade (AUC of 0.97 (MSI) and 0.85 (H&E)) on a tile level, and low-grade progressors from non-progressors on a patient level (accuracies of 0.72 (MSI) and 0.48 (H&E)). Conclusions: In summary, while the H&E-based classifier was best at distinguishing tissue types, the MSI-based model was more accurate at distinguishing dysplastic grades and patients at progression risk, which demonstrates the complementarity of both approaches.
HostingRepository	PRIDE
AnnounceDate	2023-11-14
AnnouncementXML	Submission_2023-11-14_08:53:56.138.xml
DigitalObjectIdentifier
ReviewLevel	Peer-reviewed dataset
DatasetOrigin	Original dataset
RepositorySupport	Unsupported dataset by repository
PrimarySubmitter	Benjamin Balluff
SpeciesList	scientific name: Homo sapiens (Human); NCBI TaxID: 9606;
ModificationList	No PTMs are included in the dataset
Instrument	ultraflex

Revision	Datetime	Status	ChangeLog Entry
0	2021-10-05 02:47:52	ID requested
1	2021-11-15 01:49:12	announced
⏵ 2	2023-11-14 08:53:57	announced	2023-11-14: Updated project metadata.

Beuque M, Martin-Lorenzo M, Balluff B, Woodruff HC, Lucas M, de Bruin DM, van Timmeren JE, Boer OJ, Heeren RM, Meijer SL, Lambin P, Machine learning for grading and prognosis of esophageal dysplasia using mass spectrometry and histological imaging. Comput Biol Med, 138():104918(2021) [pubmed]

submitter keyword: Deep learning, Mass spectrometry imaging, H&E staining, Barrett’s esophagus, Machine learning

Benjamin Balluff
contact affiliation	Maastricht MultiModal Molecular Imaging institute (M4i), Maastricht University, The Netherlands
contact email	b.balluff@maastrichtuniversity.nl
lab head
Benjamin Balluff
contact affiliation	Maastricht University
contact email	b.balluff@maastrichtuniversity.nl
dataset submitter

Dataset FTP location NOTE: Most web browsers have now discontinued native support for FTP access within the browser window. But you can usually install another FTP app (we recommend FileZilla) and configure your browser to launch the external application when you click on this FTP link. Or otherwise, launch an app that supports FTP (like FileZilla) and use this address: ftp://ftp.pride.ebi.ac.uk/pride/data/archive/2021/11/PXD028949

PRIDE project URI

• PRIDE
  1. PXD028949
     1. Label: PRIDE project
     2. Name: Machine learning for grading and prognosis of esophageal dysplasia using mass spectrometry and histological imaging