Analysing cerebrospinal fluid with explainable deep learning: From diagnostics to insights. Issue 1 (17th January 2023)

• Record Type: Journal Article
• Authors: Schweizer, Leonille; Seegerer, Philipp; Kim, Hee‐yeong; Saitenmacher, René; Muench, Amos; Barnick, Liane; Osterloh, Anja; Dittmayer, Carsten; Jödicke, Ruben; Pehl, Debora; Reinhardt, Annekathrin; Ruprecht, Klemens; Stenzel, Werner; Wefers, Annika K.; Harter, Patrick N.; Schüller, Ulrich; Heppner, Frank L.; Alber, Maximilian; Müller, Klaus‐Robert; Klauschen, Frederick
• Is Part Of: Neuropathology & applied neurobiology. Volume 49:Issue 1(2023)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2023-01-17
• Subjects: cell detection -- cerebrospinal fluid -- deep learning -- explainable AI -- heatmaps; Nervous system -- Diseases -- Pathology -- Periodicals; Nervous system -- Diseases -- Periodicals; 616.8
• DOI: 10.1111/nan.12866
• Languages: English
• ISSNs: 0305-1846

Abstract

Abstract: Aim: Analysis of cerebrospinal fluid (CSF) is essential for diagnostic workup of patients with neurological diseases and includes differential cell typing. The current gold standard is based on microscopic examination by specialised technicians and neuropathologists, which is time‐consuming, labour‐intensive and subjective. Methods: We, therefore, developed an image analysis approach based on expert annotations of 123, 181 digitised CSF objects from 78 patients corresponding to 15 clinically relevant categories and trained a multiclass convolutional neural network (CNN). Results: The CNN classified the 15 categories with high accuracy (mean AUC 97.3%). By using explainable artificial intelligence (XAI), we demonstrate that the CNN identified meaningful cellular substructures in CSF cells recapitulating human pattern recognition. Based on the evaluation of 511 cells selected from 12 different CSF samples, we validated the CNN by comparing it with seven board‐certified neuropathologists blinded for clinical information. Inter‐rater agreement between the CNN and the ground truth was non‐inferior (Krippendorff's alpha 0.79) compared with the agreement of seven human raters and the ground truth (mean Krippendorff's alpha 0.72, range 0.56–0.81). The CNN assigned the correct diagnostic label (inflammatory, haemorrhagic or neoplastic) in 10 out of 11 clinical samples, compared with 7–11 out of 11 by human raters. Conclusions: Our approach provides the basis to overcome current limitations in automated cell classification for routine diagnostics and demonstrates how a visual explanation framework can connect machine decision‐making with cell properties and thus provide a novel versatile and quantitative method for investigating CSF manifestations of various neurological diseases. Abstract : We developed a deep learning‐based image analysis approach for the classification of cerebrospinal fluid cells. The convolutional neural network was able to identify 15 diagnostically relevant categories and performed equally good in assigning the correct diagnostic label compared to seven neuropathologists. Explainable AI methods showed evidence that the machine employs meaningful cytological features that are also relevant for humans.