APIS: a paired CT-MRI dataset for ischemic stroke segmentation - methods and challenges

Abstract

Stroke, the second leading cause of mortality globally, predominantly results from ischemic conditions. Immediate attention and diagnosis, related to the characterization of brain lesions, play a crucial role in patient prognosis. Standard stroke protocols include an initial evaluation from a non-contrast CT to discriminate between hemorrhage and ischemia. However, non-contrast CTs lack sensitivity in detecting subtle ischemic changes in this phase. Alternatively, diffusion-weighted MRI studies provide enhanced capabilities, yet are constrained by limited availability and higher costs. Hence, we idealize new approaches that integrate ADC stroke lesion findings into CT, to enhance the analysis and accelerate stroke patient management. This study details a public challenge where scientists applied top computational strategies to delineate stroke lesions on CT scans, utilizing paired ADC information. Also, it constitutes the first effort to build a paired dataset with NCCT and ADC studies of acute ischemic stroke patients. Submitted algorithms were validated with respect to the references of two expert radiologists. The best achieved Dice score was 0.2 over a test study with 36 patient studies. Despite all the teams employing specialized deep learning tools, results reveal limitations of computational approaches to support the segmentation of small lesions with heterogeneous density.

Keywords: Computed tomography; Deep learning; Image segmentation; Ischemic stroke; Paired dataset.

Fig. 1

Participant selection and demographic distribution for the training and testing partitions of the APIS dataset.

Fig. 2

Examples of images in the APIS dataset. ADC images in axial, coronal, and sagittal planes are displayed in the leftmost columns, while matching views of NCCT images appear in the rightmost columns, both displaying annotations of two experts. The top rows highlight lesions manifesting as hypointense on ADC and hypoattenuated on NCCT. The bottom row presents a case where the lesion is discernible on ADC but less visible on NCCT.

Fig. 3

Histograms of lesion volumes for the annotations of both radiologists over the cases in the test set.

Fig. 4

Volume differences (top) and Dice scores (bottom) achieved by the participant strategies across test subjects, with respect to both expert annotations. The x-axis displays lesion categories based on each radiologist’s mean lesion volume: N for no lesion, T for tiny, S for small, M for medium, and L for large.