Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?

How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5,195 training CT scans from 76 hospitals around the world and 5,903 testing CT scans from 11 additional hospitals. This diverse test set enhances the statistical significance of benchmark results and rigorously evaluates AI algorithms across various out-of-distribution scenarios. We invited 14 inventors of 19 AI algorithms to train their algorithms, while our team, as a third party, independently evaluated these algorithms on three test sets. In addition, we also evaluated pre-existing AI frameworks--which, differing from algorithms, are more flexible and can support different algorithms--including MONAI from NVIDIA, nnU-Net from DKFZ, and numerous other open-source frameworks. We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain.

Segmentation of Brain Metastases in MRI: A Two-Stage Deep Learning Approach with Modality Impact Study

Brain metastasis segmentation poses a significant challenge in medical imaging due to the complex presentation and variability in size and location of metastases. In this study, we first investigate the impact of different imaging modalities on segmentation performance using a 3D U-Net. Through a comprehensive analysis, we determine that combining all available modalities does not necessarily enhance performance. Instead, the combination of T1-weighted with contrast enhancement (T1c), T1-weighted (T1), and FLAIR modalities yields superior results. Building on these findings, we propose a two-stage detection and segmentation model specifically designed to accurately segment brain metastases. Our approach demonstrates that leveraging three key modalities (T1c, T1, and FLAIR) achieves significantly higher accuracy compared to single-pass deep learning models. This targeted combination allows for precise segmentation, capturing even small metastases that other models often miss. Our model sets a new benchmark in brain metastasis segmentation, highlighting the importance of strategic modality selection and multi-stage processing in medical imaging. Our implementation is freely accessible to the research community on \href{https://github.com/xmindflow/Met-Seg}{GitHub}.

LHU-Net: A Light Hybrid U-Net for Cost-Efficient, High-Performance Volumetric Medical Image Segmentation

As a result of the rise of Transformer architectures in medical image analysis, specifically in the domain of medical image segmentation, a multitude of hybrid models have been created that merge the advantages of Convolutional Neural Networks (CNNs) and Transformers. These hybrid models have achieved notable success by significantly improving segmentation accuracy. Yet, this progress often comes at the cost of increased model complexity, both in terms of parameters and computational demand. Moreover, many of these models fail to consider the crucial interplay between spatial and channel features, which could further refine and improve segmentation outcomes. To address this, we introduce LHU-Net, a Light Hybrid U-Net architecture optimized for volumetric medical image segmentation. LHU-Net is meticulously designed to prioritize spatial feature analysis in its initial layers before shifting focus to channel-based features in its deeper layers, ensuring a comprehensive feature extraction process. Rigorous evaluation across five benchmark datasets - Synapse, LA, Pancreas, ACDC, and BRaTS 2018 - underscores LHU-Net's superior performance, showcasing its dual capacity for efficiency and accuracy. Notably, LHU-Net sets new performance benchmarks, such as attaining a Dice score of 92.66 on the ACDC dataset, while simultaneously reducing parameters by 85% and quartering the computational load compared to existing state-of-the-art models. Achieved without any reliance on pre-training, additional data, or model ensemble, LHU-Net's effectiveness is further evidenced by its state-of-the-art performance across all evaluated datasets, utilizing fewer than 11 million parameters. This achievement highlights that balancing computational efficiency with high accuracy in medical image segmentation is feasible. Our implementation of LHU-Net is freely accessible to the research community on GitHub.

DermoSegDiff: A Boundary-aware Segmentation Diffusion Model for Skin Lesion Delineation

Skin lesion segmentation plays a critical role in the early detection and accurate diagnosis of dermatological conditions. Denoising Diffusion Probabilistic Models (DDPMs) have recently gained attention for their exceptional image-generation capabilities. Building on these advancements, we propose DermoSegDiff, a novel framework for skin lesion segmentation that incorporates boundary information during the learning process. Our approach introduces a novel loss function that prioritizes the boundaries during training, gradually reducing the significance of other regions. We also introduce a novel U-Net-based denoising network that proficiently integrates noise and semantic information inside the network. Experimental results on multiple skin segmentation datasets demonstrate the superiority of DermoSegDiff over existing CNN, transformer, and diffusion-based approaches, showcasing its effectiveness and generalization in various scenarios. The implementation is publicly accessible on \href{https://github.com/mindflow-institue/dermosegdiff}{GitHub}