Poster Presentation 27th Annual Lorne Proteomics Symposium 2022

Cancer Tissue Classification Using Supervised Machine Learning Applied to MALDI Mass Spectrometry Imaging (#154)

Parul Mittal 1 , Mark R Condina 2 , Manuela Klinger-Hoffmann 1 , Gurjeet Kaur 3 , Martin K Oehler 4 5 , Oliver M Sieber 6 7 8 , Michelle Palmieri 6 8 , Stefan Kommoss 9 , Sara Brucker 9 , Mark D McDonnell 10 , Peter Hoffmann 1
  1. Clinical & Health Sciences, University of South Australia, Adelaide, SA, Australia
  2. Future Industries Institute, University of South Australia, Adelaide, SA, Australia
  3. Institute for Research in Molecular Medicine, Universiti Sains Malaysia, 11800 Minden, Pulau , Pinang, Malaysia
  4. Department of Gynaecological Oncology, Royal Adelaide Hospital, Adelaide, SA, Australia
  5. Discipline of Obstetrics and Gynaecology, Adelaide Medical School, University of Adelaide, Adelaide, SA, Australia
  6. Department of Medical Biology, The University of Melbourne, Parkville, Victoria, Australia
  7. Department of Biochemistry and Molecular Biology, Monash University, Clayton , Victoria, Australia
  8. Personalised Oncology Division, The Walter and Eliza Hall Institute of Medial Research, Parkville, Victoria, Australia
  9. Department of Women’s Health, Tübingen University Hospital, Calwerstr. 7, 72076 Tübingen, Germany
  10. Computational Learning Systems Laboratory, University of South Australia, Adelaide, SA, Australia

Classic histopathological examination of tissues remains the mainstay for cancer diagnosis and staging. However, in some cases histopathologic analysis yields ambiguous results, leading to inconclusive disease classification. We set out to explore the diagnostic potential of mass spectrometry-based imaging for tumour classification based on proteomic fingerprints. Combining mass spectrometry with supervised machine learning, we were able to distinguish colorectal tumor from normal tissue with an overall accuracy of 98%. In addition, this approach was able to predict the presence of lymph node metastasis in primary tumour of endometrial cancer with an overall accuracy of 80%. These results highlight the potential of this technology to determine the optimal treatment for cancer patients to reduce morbidity and improve patients’ outcomes.