cs.CVNov 17, 2026

Classification of Tissues on MALDI-MSI Image Modality for Pancreatic Cancer Studies

Authors: Abubakar Qahir, Jenny Benois-Pineau, Victoria Bourgeais, Fabien Baldacci, Sandrine Dabernat, Nicolas Desbenoit, Mélanie Moreau, Mehdi Boubaddi, 

Organizations: Univ. Bordeaux, CNRS, Bordeaux INP, LabRI, UMR5800 Talence, France · Univ. Bordeaux, INSERM, BRIC, U 1312, F-33000 Bordeaux, France · CHU Bordeaux, 33000 Bordeaux, France · Univ. Bordeaux, CNRS, Bordeaux INP, CBMN, UMR 5248, F-33600 Pessac, France · 

Abstract

Mass Spectrometry Imaging (MSI) spatially maps molecular distributions in tissue sections. Despite the availability of preprocessing tools for MSI data, building end-to-end workflows suitable for deep learning remains challenging. We have developed a fully automated pipeline for transformation of raw Matrix-Assisted Laser Desorption/Ionization Mass Spectrometry imaging (MALDI-MSI) data into deep-learning-ready image patches for binary pancreatic tissue classification (tumoral vs non-tumoral) and built individual models for recognition of tumoral regions in spectral images. Images resulting from the proposed pipeline and from reference interactive workflow are very close in terms of image quality metric mean squared error (MSE). The proposed pipeline computational time is of 20 min in average compared to a full working day of the reference interactive workflow. The models achieved 0.94 accuracy on high-resolution spectra and a mean accuracy of 0.59 on lower-resolution spectra.

Figures & tables

Explore similar work

CardsList
  1. PCLSegNet: Anatomy-Aware Deep Learning Framework for MRI-based Pancreatic Cyst Segmentation and Size Assessment

    Nov 11, 2026Hanyi Zhang, Tongyu Wang, Manuel Debic +21Medical Image SegmentationAnatomy-Guided Medical Image Segmentation

  2. Masked Feature Encoding for Large-Scale Whole Slide Image Representation

    Oct 7, 2026Haoyu He, Basile Tessier-Cloutier, Yang Wang +1Whole-Slide Image AnalysisMedical Image Representation Learning

  3. IonMorphNet: Generalizable Learning of Ion Image Morphologies for Peak Picking in Mass Spectrometry Imaging

    Apr 21, 2026Philipp Weigand, Niels Nawrot, Nikolas Ebert +2Representation LearningMass Spectrometry