Universität zu Köln

Pertzborn, David ORCID: 0000-0002-0230-7765, Arolt, Christoph, Ernst, Gunther, Lechtenfeld, Oliver J. ORCID: 0000-0001-5313-6014, Kaesler, Jan, Pelzel, Daniela, Guntinas-Lichius, Orlando ORCID: 0000-0001-9671-0784, von Eggeling, Ferdinand ORCID: 0000-0002-8062-6999 and Hoffmann, Franziska ORCID: 0000-0002-6872-924X (2022). Multi-Class Cancer Subtyping in Salivary Gland Carcinomas with MALDI Imaging and Deep Learning. Cancers, 14 (17). BASEL: MDPI. ISSN 2072-6694

Full text not available from this repository.

Abstract

Simple Summary The correct diagnosis of different salivary gland carcinomas is important for a prognosis. This diagnosis is imprecise if it is based only on clinical symptoms and histological methods. Mass spectrometry imaging can provide information about the molecular composition of sample tissues. Using a deep-learning method, we analyzed the mass spectrometry imaging data of 25 patients. Using this workflow we could accurately predict the tumor type in each patient sample. Salivary gland carcinomas (SGC) are a heterogeneous group of tumors. The prognosis varies strongly according to its type, and even the distinction between benign and malign tumor is challenging. Adenoid cystic carcinoma (AdCy) is one subgroup of SGCs that is prone to late metastasis. This makes accurate tumor subtyping an important task. Matrix-assisted laser desorption/ionization (MALDI) imaging is a label-free technique capable of providing spatially resolved information about the abundance of biomolecules according to their mass-to-charge ratio. We analyzed tissue micro arrays (TMAs) of 25 patients (including six different SGC subtypes and a healthy control group of six patients) with high mass resolution MALDI imaging using a 12-Tesla magnetic resonance mass spectrometer. The high mass resolution allowed us to accurately detect single masses, with strong contributions to each class prediction. To address the added complexity created by the high mass resolution and multiple classes, we propose a deep-learning model. We showed that our deep-learning model provides a per-class classification accuracy of greater than 80% with little preprocessing. Based on this classification, we employed methods of explainable artificial intelligence (AI) to gain further insights into the spectrometric features of AdCys.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Pertzborn, David UNSPECIFIED orcid.org/0000-0002-0230-7765 UNSPECIFIED Arolt, Christoph UNSPECIFIED UNSPECIFIED UNSPECIFIED Ernst, Gunther UNSPECIFIED UNSPECIFIED UNSPECIFIED Lechtenfeld, Oliver J. UNSPECIFIED orcid.org/0000-0001-5313-6014 UNSPECIFIED Kaesler, Jan UNSPECIFIED UNSPECIFIED UNSPECIFIED Pelzel, Daniela UNSPECIFIED UNSPECIFIED UNSPECIFIED Guntinas-Lichius, Orlando UNSPECIFIED orcid.org/0000-0001-9671-0784 UNSPECIFIED von Eggeling, Ferdinand UNSPECIFIED orcid.org/0000-0002-8062-6999 UNSPECIFIED Hoffmann, Franziska UNSPECIFIED orcid.org/0000-0002-6872-924X UNSPECIFIED
URN:	urn:nbn:de:hbz:38-675805
DOI:	10.3390/cancers14174342
Journal or Publication Title:	Cancers
Volume:	14
Number:	17
Date:	2022
Publisher:	MDPI
Place of Publication:	BASEL
ISSN:	2072-6694
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language MASS-SPECTROMETRY Multiple languages Oncology Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/67580