Bas H. M. van der Velden

Rosa C. J. Kraaijveld, Marielle E. P. Philippens, Wietse S. C. Eppinga et al.

Explainable artificial intelligence (XAI) is increasingly used to analyze the behavior of neural networks. Concept activation uses human-interpretable concepts to explain neural network behavior. This study aimed at assessing the feasibility of regression concept activation to explain detection and classification of multi-modal volumetric data. Proof-of-concept was demonstrated in metastatic prostate cancer patients imaged with positron emission tomography/computed tomography (PET/CT). Multi-modal volumetric concept activation was used to provide global and local explanations. Sensitivity was 80% at 1.78 false positive per patient. Global explanations showed that detection focused on CT for anatomical location and on PET for its confidence in the detection. Local explanations showed promise to aid in distinguishing true positives from false positives. Hence, this study demonstrated feasibility to explain detection and classification of multi-modal volumetric data using regression concept activation.

Denis Kutnar, Bas H. M. van der Velden, Marta Girones Sanguesa et al.

Lacunes of presumed vascular origin are fluid-filled cavities of between 3 - 15 mm in diameter, visible on T1 and FLAIR brain MRI. Quantification of lacunes relies on manual annotation or semi-automatic / interactive approaches; and almost no automatic methods exist for this task. In this work, we present a two-stage approach to segment lacunes of presumed vascular origin: (1) detection with Mask R-CNN followed by (2) segmentation with a U-Net CNN. Data originates from Task 3 of the "Where is VALDO?" challenge and consists of 40 training subjects. We report the mean DICE on the training set of 0.83 and on the validation set of 0.84. Source code is available at: https://github.com/hjkuijf/MixLacune . The docker container hjkuijf/mixlacune can be pulled from https://hub.docker.com/r/hjkuijf/mixlacune .

M. A. D. Buser, D. C. Simons, M. Fitski et al.

Surgery plays an important role within the treatment for neuroblastoma, a common pediatric cancer. This requires careful planning, often via magnetic resonance imaging (MRI)-based anatomical 3D models. However, creating these models is often time-consuming and user dependent. We organized the Surgical Planning in Pediatric Neuroblastoma (SPPIN) challenge, to stimulate developments on this topic, and set a benchmark for fully automatic segmentation of neuroblastoma on multi-model MRI. The challenge started with a training phase, where teams received 78 sets of MRI scans from 34 patients, consisting of both diagnostic and post-chemotherapy MRI scans. The final test phase, consisting of 18 MRI sets from 9 patients, determined the ranking of the teams. Ranking was based on the Dice similarity coefficient (Dice score), the 95th percentile of the Hausdorff distance (HD95) and the volumetric similarity (VS). The SPPIN challenge was hosted at MICCAI 2023. The final leaderboard consisted of 9 teams. The highest-ranking team achieved a median Dice score 0.82, a median HD95 of 7.69 mm and a VS of 0.91, utilizing a large, pretrained network called STU-Net. A significant difference for the segmentation results between diagnostic and post-chemotherapy MRI scans was observed (Dice = 0.89 vs Dice = 0.59, P = 0.01) for the highest-ranking team. SPPIN is the first medical segmentation challenge in extracranial pediatric oncology. The highest-ranking team used a large pre-trained network, suggesting that pretraining can be of use in small, heterogenous datasets. Although the results of the highest-ranking team were high for most patients, segmentation especially in small, pre-treated tumors were insufficient. Therefore, more reliable segmentation methods are needed to create clinically applicable models to aid surgical planning in pediatric neuroblastoma.

Christina B. Lund, Bas H. M. van der Velden

This paper assesses whether using clinical characteristics in addition to imaging can improve automated segmentation of kidney cancer on contrast-enhanced computed tomography (CT). A total of 300 kidney cancer patients with contrast-enhanced CT scans and clinical characteristics were included. A baseline segmentation of the kidney cancer was performed using a 3D U-Net. Input to the U-Net were the contrast-enhanced CT images, output were segmentations of kidney, kidney tumors, and kidney cysts. A cognizant sampling strategy was used to leverage clinical characteristics for improved segmentation. To this end, a Least Absolute Shrinkage and Selection Operator (LASSO) was used. Segmentations were evaluated using Dice and Surface Dice. Improvement in segmentation was assessed using Wilcoxon signed rank test. The baseline 3D U-Net showed a segmentation performance of 0.90 for kidney and kidney masses, i.e., kidney, tumor, and cyst, 0.29 for kidney masses, and 0.28 for kidney tumor, while the 3D U-Net trained with cognizant sampling enhanced the segmentation performance and reached Dice scores of 0.90, 0.39, and 0.38 respectively. To conclude, the cognizant sampling strategy leveraging the clinical characteristics significantly improved kidney cancer segmentation.

Marta Girones Sanguesa, Denis Kutnar, Bas H. M. van der Velden et al.

Cerebral microbleeds are small, dark, round lesions that can be visualised on T2*-weighted MRI or other sequences sensitive to susceptibility effects. In this work, we propose a multi-stage approach to both microbleed detection and segmentation. First, possible microbleed locations are detected with a Mask R-CNN technique. Second, at each possible microbleed location, a simple U-Net performs the final segmentation. This work used the 72 subjects as training data provided by the "Where is VALDO?" challenge of MICCAI 2021.

Bas H. M. van der Velden, Hugo J. Kuijf, Kenneth G. A. Gilhuijs et al.

With an increase in deep learning-based methods, the call for explainability of such methods grows, especially in high-stakes decision making areas such as medical image analysis. This survey presents an overview of eXplainable Artificial Intelligence (XAI) used in deep learning-based medical image analysis. A framework of XAI criteria is introduced to classify deep learning-based medical image analysis methods. Papers on XAI techniques in medical image analysis are then surveyed and categorized according to the framework and according to anatomical location. The paper concludes with an outlook of future opportunities for XAI in medical image analysis.

Bas H. M. van der Velden

Functional behavior of breast cancer - representing underlying biology - can be analyzed using MRI. The most widely used breast MR imaging protocol is dynamic contrast-enhanced T1-weighted imaging. The cancer enhances on dynamic contrast-enhanced MR imaging because the contrast agent leaks from the leaky vessels into the interstitial space. The contrast agent subsequently leaks back into the vascular space, creating a washout effect. The normal parenchymal tissue of the breast can also enhance after contrast injection. This enhancement generally increases over time. Typically, a radiologist assesses this background parenchymal enhancement (BPE) using the Breast Imaging Reporting and Data System (BI-RADS). According to the BI-RADS, BPE refers to the volume of enhancement and the intensity of enhancement and is divided in four incremental categories: minimal, mild, moderate, and marked. Researchers have developed semi-automatic and automatic methods to extract properties of BPE from MR images. For clarity, in this syllabus the BI-RADS definition will be referred to as BPE, whereas the computer-extracted properties will not. Both BPE and computer-extracted parenchymal enhancement properties have been linked to screening and diagnosis, hormone status and age, risk of development of breast cancer, response monitoring, and prognosis.

Pim Moeskops, Jelmer M. Wolterink, Bas H. M. van der Velden et al.

Automatic segmentation of medical images is an important task for many clinical applications. In practice, a wide range of anatomical structures are visualised using different imaging modalities. In this paper, we investigate whether a single convolutional neural network (CNN) can be trained to perform different segmentation tasks. A single CNN is trained to segment six tissues in MR brain images, the pectoral muscle in MR breast images, and the coronary arteries in cardiac CTA. The CNN therefore learns to identify the imaging modality, the visualised anatomical structures, and the tissue classes. For each of the three tasks (brain MRI, breast MRI and cardiac CTA), this combined training procedure resulted in a segmentation performance equivalent to that of a CNN trained specifically for that task, demonstrating the high capacity of CNN architectures. Hence, a single system could be used in clinical practice to automatically perform diverse segmentation tasks without task-specific training.