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.

Automated segmentation is a fundamental medical image analysis task, which enjoys significant advances due to the advent of deep learning. While foundation models have been useful in natural language processing and some vision tasks for some time, the foundation model developed with image segmentation in mind - Segment Anything Model (SAM) - has been developed only recently and has shown similar promise. However, there are still no systematic analyses or "best-practice" guidelines for optimal fine-tuning of SAM for medical image segmentation. This work summarizes existing fine-tuning strategies with various backbone architectures, model components, and fine-tuning algorithms across 18 combinations, and evaluates them on 17 datasets covering all common radiology modalities. Our study reveals that (1) fine-tuning SAM leads to slightly better performance than previous segmentation methods, (2) fine-tuning strategies that use parameter-efficient learning in both the encoder and decoder are superior to other strategies, (3) network architecture has a small impact on final performance, (4) further training SAM with self-supervised learning can improve final model performance. We also demonstrate the ineffectiveness of some methods popular in the literature and further expand our experiments into few-shot and prompt-based settings. Lastly, we released our code and MRI-specific fine-tuned weights, which consistently obtained superior performance over the original SAM, at https://github.com/mazurowski-lab/finetune-SAM.

Training segmentation models for medical images continues to be challenging due to the limited availability of data annotations. Segment Anything Model (SAM) is a foundation model that is intended to segment user-defined objects of interest in an interactive manner. While the performance on natural images is impressive, medical image domains pose their own set of challenges. Here, we perform an extensive evaluation of SAM's ability to segment medical images on a collection of 19 medical imaging datasets from various modalities and anatomies. We report the following findings: (1) SAM's performance based on single prompts highly varies depending on the dataset and the task, from IoU=0.1135 for spine MRI to IoU=0.8650 for hip X-ray. (2) Segmentation performance appears to be better for well-circumscribed objects with prompts with less ambiguity and poorer in various other scenarios such as the segmentation of brain tumors. (3) SAM performs notably better with box prompts than with point prompts. (4) SAM outperforms similar methods RITM, SimpleClick, and FocalClick in almost all single-point prompt settings. (5) When multiple-point prompts are provided iteratively, SAM's performance generally improves only slightly while other methods' performance improves to the level that surpasses SAM's point-based performance. We also provide several illustrations for SAM's performance on all tested datasets, iterative segmentation, and SAM's behavior given prompt ambiguity. We conclude that SAM shows impressive zero-shot segmentation performance for certain medical imaging datasets, but moderate to poor performance for others. SAM has the potential to make a significant impact in automated medical image segmentation in medical imaging, but appropriate care needs to be applied when using it.

Objectives: The purpose is to apply a previously validated deep learning algorithm to a new thyroid nodule ultrasound image dataset and compare its performances with radiologists. Methods: Prior study presented an algorithm which is able to detect thyroid nodules and then make malignancy classifications with two ultrasound images. A multi-task deep convolutional neural network was trained from 1278 nodules and originally tested with 99 separate nodules. The results were comparable with that of radiologists. The algorithm was further tested with 378 nodules imaged with ultrasound machines from different manufacturers and product types than the training cases. Four experienced radiologists were requested to evaluate the nodules for comparison with deep learning. Results: The Area Under Curve (AUC) of the deep learning algorithm and four radiologists were calculated with parametric, binormal estimation. For the deep learning algorithm, the AUC was 0.69 (95% CI: 0.64 - 0.75). The AUC of radiologists were 0.63 (95% CI: 0.59 - 0.67), 0.66 (95% CI:0.61 - 0.71), 0.65 (95% CI: 0.60 - 0.70), and 0.63 (95%CI: 0.58 - 0.67). Conclusion: In the new testing dataset, the deep learning algorithm achieved similar performances with all four radiologists. The relative performance difference between the algorithm and the radiologists is not significantly affected by the difference of ultrasound scanner.

Adversarial examples, intentionally designed inputs tending to mislead deep neural networks, have attracted great attention in the past few years. Although a series of defense strategies have been developed and achieved encouraging model robustness, most of them are still vulnerable to the more commonly witnessed corruptions, e.g., Gaussian noise, blur, etc., in the real world. In this paper, we theoretically and empirically discover the fact that there exists an inherent connection between adversarial robustness and corruption robustness. Based on the fundamental discovery, this paper further proposes a more powerful training method named Progressive Adversarial Training (PAT) that adds diversified adversarial noises progressively during training, and thus obtains robust model against both adversarial examples and corruptions through higher training data complexity. Meanwhile, we also theoretically find that PAT can promise better generalization ability. Experimental evaluation on MNIST, CIFAR-10 and SVHN show that PAT is able to enhance the robustness and generalization of the state-of-the-art network structures, performing comprehensively well compared to various augmentation methods. Moreover, we also propose Mixed Test to evaluate model generalization ability more fairly.

Speaker verification (SV) systems using deep neural network embeddings, so-called the x-vector systems, are becoming popular due to its good performance superior to the i-vector systems. The fusion of these systems provides improved performance benefiting both from the discriminatively trained x-vectors and generative i-vectors capturing distinct speaker characteristics. In this paper, we propose a novel method to include the complementary information of i-vector and x-vector, that is called generative x-vector. The generative x-vector utilizes a transformation model learned from the i-vector and x-vector representations of the background data. Canonical correlation analysis is applied to derive this transformation model, which is later used to transform the standard x-vectors of the enrollment and test segments to the corresponding generative x-vectors. The SV experiments performed on the NIST SRE 2010 dataset demonstrate that the system using generative x-vectors provides considerably better performance than the baseline i-vector and x-vector systems. Furthermore, the generative x-vectors outperform the fusion of i-vector and x-vector systems for long-duration utterances, while yielding comparable results for short-duration utterances.