(Predictable) performance bias in unsupervised anomaly detection.

BACKGROUND: With the ever-increasing amount of medical imaging data, the demand for algorithms to assist clinicians has amplified. Unsupervised anomaly detection (UAD) models promise to aid in the crucial first step of disease detection. While previous studies have thoroughly explored fairness in supervised models in healthcare, for UAD, this has so far been unexplored. METHODS: In this study, we evaluated how dataset composition regarding subgroups manifests in disparate performance of UAD models along multiple protected variables on three large-scale publicly available chest X-ray datasets. Our experiments were validated using two state-of-the-art UAD models for medical images. Finally, we introduced subgroup-AUROC (sAUROC), which aids in quantifying fairness in machine learning. FINDINGS: Our experiments revealed empirical "fairness laws" (similar to "scaling laws" for Transformers) for training-dataset composition: Linear relationships between anomaly detection performance within a subpopulation and its representation in the training data. Our study further revealed performance disparities, even in the case of balanced training data, and compound effects that exacerbate the drop in performance for subjects associated with multiple adversely affected groups. INTERPRETATION: Our study quantified the disparate performance of UAD models against certain demographic subgroups. Importantly, we showed that this unfairness cannot be mitigated by balanced representation alone. Instead, the representation of some subgroups seems harder to learn by UAD models than that of others. The empirical "fairness laws" discovered in our study make disparate performance in UAD models easier to estimate and aid in determining the most desirable dataset composition. FUNDING: European Research Council Deep4MI.

A distinct stimulatory cDC1 subpopulation amplifies CD8+ T cell responses in tumors for protective anti-cancer immunity.

Type 1 conventional dendritic cells (cDC1) can support T cell responses within tumors but whether this determines protective versus ineffective anti-cancer immunity is poorly understood. Here, we use imaging-based deep learning to identify intratumoral cDC1-CD8+ T cell clustering as a unique feature of protective anti-cancer immunity. These clusters form selectively in stromal tumor regions and constitute niches in which cDC1 activate TCF1+ stem-like CD8+ T cells. We identify a distinct population of immunostimulatory CCR7neg cDC1 that produce CXCL9 to promote cluster formation and cross-present tumor antigens within these niches, which is required for intratumoral CD8+ T cell differentiation and expansion and promotes cancer immune control. Similarly, in human cancers, CCR7neg cDC1 interact with CD8+ T cells in clusters and are associated with patient survival. Our findings reveal an intratumoral phase of the anti-cancer T cell response orchestrated by tumor-residing cDC1 that determines protective versus ineffective immunity and could be exploited for cancer therapy.

Tumor-derived prostaglandin E2 programs cDC1 dysfunction to impair intratumoral orchestration of anti-cancer T cell responses.

Type 1 conventional dendritic cells (cDC1s) are critical for anti-cancer immunity. Protective anti-cancer immunity is thought to require cDC1s to sustain T cell responses within tumors, but it is poorly understood how this function is regulated and whether its subversion contributes to immune evasion. Here, we show that tumor-derived prostaglandin E2 (PGE2) programmed a dysfunctional state in intratumoral cDC1s, disabling their ability to locally orchestrate anti-cancer CD8+ T cell responses. Mechanistically, cAMP signaling downstream of the PGE2-receptors EP2 and EP4 was responsible for the programming of cDC1 dysfunction, which depended on the loss of the transcription factor IRF8. Blockade of the PGE2-EP2/EP4-cDC1 axis prevented cDC1 dysfunction in tumors, locally reinvigorated anti-cancer CD8+ T cell responses, and achieved cancer immune control. In human cDC1s, PGE2-induced dysfunction is conserved and associated with poor cancer patient prognosis. Our findings reveal a cDC1-dependent intratumoral checkpoint for anti-cancer immunity that is targeted by PGE2 for immune evasion.

Efficient, high-performance semantic segmentation using multi-scale feature extraction.

The success of deep learning in recent years has arguably been driven by the availability of large datasets for training powerful predictive algorithms. In medical applications however, the sensitive nature of the data limits the collection and exchange of large-scale datasets. Privacy-preserving and collaborative learning systems can enable the successful application of machine learning in medicine. However, collaborative protocols such as federated learning require the frequent transfer of parameter updates over a network. To enable the deployment of such protocols to a wide range of systems with varying computational performance, efficient deep learning architectures for resource-constrained environments are required. Here we present MoNet, a small, highly optimized neural-network-based segmentation algorithm leveraging efficient multi-scale image features. MoNet is a shallow, U-Net-like architecture based on repeated, dilated convolutions with decreasing dilation rates. We apply and test our architecture on the challenging clinical tasks of pancreatic segmentation in computed tomography (CT) images as well as brain tumor segmentation in magnetic resonance imaging (MRI) data. We assess our model's segmentation performance and demonstrate that it provides performance on par with compared architectures while providing superior out-of-sample generalization performance, outperforming larger architectures on an independent validation set, while utilizing significantly fewer parameters. We furthermore confirm the suitability of our architecture for federated learning applications by demonstrating a substantial reduction in serialized model storage requirement as a surrogate for network data transfer. Finally, we evaluate MoNet's inference latency on the central processing unit (CPU) to determine its utility in environments without access to graphics processing units. Our implementation is publicly available as free and open-source software.