Analysing cerebrospinal fluid with explainable deep learning: From diagnostics to insights

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.

Prevalence of antibodies to Borrelia burgdorferi in serum and cerebrospinal fluid samples from patients with neurological disorders in Berlin

Paired serum and cerebrospinal fluid (CSF) samples from 800 patients of a neurological department were tested for antibodies to Borrelia burgdorferi. A flagellum enzyme-linked immunosorbent assay was used for antibody screening. All serum/CSF pairs with any elevated antibody response were also tested by Western blotting a method for confirmation. 65 patients (8.1%) had serum IgG antibodies in ELISA and 22 of these patients (2.8%) were confirmed by Western blot. 20 patients (2.5%) had elevated antibody titres in CSF by ELISA and 12 (1.5%) reacted in the Western blot. Clinical features of Bannwarth's syndrome were present in 12 patients (1.5%) and 4 patients (0.5%) showed other manifestations of Lyme borreliosis. All patients with Bannwarth's syndrome were seropositive by both methods and 10 had elevated antibody activity in the CSF proved by the two methods. The combination of a sensitive ELISA for screening and a sensitive and specific Western blot for confirmation reduced the number of false positive results but kept its standard in detecting antibodies in patients with active disease.