Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention最新文献_第3页

LOTUS: Learning to Optimize Task-based US representations LOTUS:学习优化基于任务的US表示

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention Pub Date : 2023-07-29 DOI: 10.48550/arXiv.2307.16021

Yordanka Velikova, Mohammad Farid Azampour, Walter Simson, Vanessa Gonzalez Duque, N. Navab

{"title":"LOTUS: Learning to Optimize Task-based US representations","authors":"Yordanka Velikova, Mohammad Farid Azampour, Walter Simson, Vanessa Gonzalez Duque, N. Navab","doi":"10.48550/arXiv.2307.16021","DOIUrl":"https://doi.org/10.48550/arXiv.2307.16021","url":null,"abstract":"Anatomical segmentation of organs in ultrasound images is essential to many clinical applications, particularly for diagnosis and monitoring. Existing deep neural networks require a large amount of labeled data for training in order to achieve clinically acceptable performance. Yet, in ultrasound, due to characteristic properties such as speckle and clutter, it is challenging to obtain accurate segmentation boundaries, and precise pixel-wise labeling of images is highly dependent on the expertise of physicians. In contrast, CT scans have higher resolution and improved contrast, easing organ identification. In this paper, we propose a novel approach for learning to optimize task-based ultra-sound image representations. Given annotated CT segmentation maps as a simulation medium, we model acoustic propagation through tissue via ray-casting to generate ultrasound training data. Our ultrasound simulator is fully differentiable and learns to optimize the parameters for generating physics-based ultrasound images guided by the downstream segmentation task. In addition, we train an image adaptation network between real and simulated images to achieve simultaneous image synthesis and automatic segmentation on US images in an end-to-end training setting. The proposed method is evaluated on aorta and vessel segmentation tasks and shows promising quantitative results. Furthermore, we also conduct qualitative results of optimized image representations on other organs.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"54 1","pages":"435-445"},"PeriodicalIF":0.0,"publicationDate":"2023-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77935210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust vertebra identification using simultaneous node and edge predicting Graph Neural Networks 基于节点和边缘同时预测的图神经网络的鲁棒椎体识别

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention Pub Date : 2023-07-27 DOI: 10.48550/arXiv.2308.02509

Vincent Bürgin, R. Prevost, Marijn F. Stollenga

{"title":"Robust vertebra identification using simultaneous node and edge predicting Graph Neural Networks","authors":"Vincent Bürgin, R. Prevost, Marijn F. Stollenga","doi":"10.48550/arXiv.2308.02509","DOIUrl":"https://doi.org/10.48550/arXiv.2308.02509","url":null,"abstract":"Automatic vertebra localization and identification in CT scans is important for numerous clinical applications. Much progress has been made on this topic, but it mostly targets positional localization of vertebrae, ignoring their orientation. Additionally, most methods employ heuristics in their pipeline that can be sensitive in real clinical images which tend to contain abnormalities. We introduce a simple pipeline that employs a standard prediction with a U-Net, followed by a single graph neural network to associate and classify vertebrae with full orientation. To test our method, we introduce a new vertebra dataset that also contains pedicle detections that are associated with vertebra bodies, creating a more challenging landmark prediction, association and classification task. Our method is able to accurately associate the correct body and pedicle landmarks, ignore false positives and classify vertebrae in a simple, fully trainable pipeline avoiding application-specific heuristics. We show our method outperforms traditional approaches such as Hungarian Matching and Hidden Markov Models. We also show competitive performance on the standard VerSe challenge body identification task.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"43 1","pages":"483-493"},"PeriodicalIF":0.0,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80245364","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

vox2vec: A Framework for Self-supervised Contrastive Learning of Voxel-level Representations in Medical Images vox2vec:医学图像体素级表示的自监督对比学习框架

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention Pub Date : 2023-07-27 DOI: 10.48550/arXiv.2307.14725

M. Goncharov, Vera Soboleva, Anvar Kurmukov, M. Pisov, M. Belyaev

{"title":"vox2vec: A Framework for Self-supervised Contrastive Learning of Voxel-level Representations in Medical Images","authors":"M. Goncharov, Vera Soboleva, Anvar Kurmukov, M. Pisov, M. Belyaev","doi":"10.48550/arXiv.2307.14725","DOIUrl":"https://doi.org/10.48550/arXiv.2307.14725","url":null,"abstract":"This paper introduces vox2vec - a contrastive method for self-supervised learning (SSL) of voxel-level representations. vox2vec representations are modeled by a Feature Pyramid Network (FPN): a voxel representation is a concatenation of the corresponding feature vectors from different pyramid levels. The FPN is pre-trained to produce similar representations for the same voxel in different augmented contexts and distinctive representations for different voxels. This results in unified multi-scale representations that capture both global semantics (e.g., body part) and local semantics (e.g., different small organs or healthy versus tumor tissue). We use vox2vec to pre-train a FPN on more than 6500 publicly available computed tomography images. We evaluate the pre-trained representations by attaching simple heads on top of them and training the resulting models for 22 segmentation tasks. We show that vox2vec outperforms existing medical imaging SSL techniques in three evaluation setups: linear and non-linear probing and end-to-end fine-tuning. Moreover, a non-linear head trained on top of the frozen vox2vec representations achieves competitive performance with the FPN trained from scratch while having 50 times fewer trainable parameters. The code is available at https://github.com/mishgon/vox2vec .","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"87 1","pages":"605-614"},"PeriodicalIF":0.0,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86843413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Centroid-aware feature recalibration for cancer grading in pathology images 质心感知特征重新校准用于病理图像的癌症分级

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention Pub Date : 2023-07-26 DOI: 10.48550/arXiv.2307.13947

Jaeung Lee, Keunho Byeon, J. T. Kwak

{"title":"Centroid-aware feature recalibration for cancer grading in pathology images","authors":"Jaeung Lee, Keunho Byeon, J. T. Kwak","doi":"10.48550/arXiv.2307.13947","DOIUrl":"https://doi.org/10.48550/arXiv.2307.13947","url":null,"abstract":"Cancer grading is an essential task in pathology. The recent developments of artificial neural networks in computational pathology have shown that these methods hold great potential for improving the accuracy and quality of cancer diagnosis. However, the issues with the robustness and reliability of such methods have not been fully resolved yet. Herein, we propose a centroid-aware feature recalibration network that can conduct cancer grading in an accurate and robust manner. The proposed network maps an input pathology image into an embedding space and adjusts it by using centroids embedding vectors of different cancer grades via attention mechanism. Equipped with the recalibrated embedding vector, the proposed network classifiers the input pathology image into a pertinent class label, i.e., cancer grade. We evaluate the proposed network using colorectal cancer datasets that were collected under different environments. The experimental results confirm that the proposed network is able to conduct cancer grading in pathology images with high accuracy regardless of the environmental changes in the datasets.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"11 1","pages":"212-221"},"PeriodicalIF":0.0,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90959424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards multi-modal anatomical landmark detection for ultrasound-guided brain tumor resection with contrastive learning 超声引导下对比学习脑肿瘤切除术的多模态解剖地标检测

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention Pub Date : 2023-07-26 DOI: 10.48550/arXiv.2307.14523

Soorena Salari, Amir Rasoulian, H. Rivaz, Yiming Xiao

{"title":"Towards multi-modal anatomical landmark detection for ultrasound-guided brain tumor resection with contrastive learning","authors":"Soorena Salari, Amir Rasoulian, H. Rivaz, Yiming Xiao","doi":"10.48550/arXiv.2307.14523","DOIUrl":"https://doi.org/10.48550/arXiv.2307.14523","url":null,"abstract":"Homologous anatomical landmarks between medical scans are instrumental in quantitative assessment of image registration quality in various clinical applications, such as MRI-ultrasound registration for tissue shift correction in ultrasound-guided brain tumor resection. While manually identified landmark pairs between MRI and ultrasound (US) have greatly facilitated the validation of different registration algorithms for the task, the procedure requires significant expertise, labor, and time, and can be prone to inter- and intra-rater inconsistency. So far, many traditional and machine learning approaches have been presented for anatomical landmark detection, but they primarily focus on mono-modal applications. Unfortunately, despite the clinical needs, inter-modal/contrast landmark detection has very rarely been attempted. Therefore, we propose a novel contrastive learning framework to detect corresponding landmarks between MRI and intra-operative US scans in neurosurgery. Specifically, two convolutional neural networks were trained jointly to encode image features in MRI and US scans to help match the US image patch that contain the corresponding landmarks in the MRI. We developed and validated the technique using the public RESECT database. With a mean landmark detection accuracy of 5.88+-4.79 mm against 18.78+-4.77 mm with SIFT features, the proposed method offers promising results for MRI-US landmark detection in neurosurgical applications for the first time.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"24 1","pages":"668-678"},"PeriodicalIF":0.0,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81069447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography 超声心动图中固有可解释和不确定性感知主动脉狭窄分类的动态原型

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention Pub Date : 2023-07-26 DOI: 10.48550/arXiv.2307.14433

H. Vaseli, A. Gu, S. Neda, Ahmadi Amiri, M. Tsang, A. Fung, Nima Kondori, Armin Saadat, P. Abolmaesumi, T. Tsang

{"title":"ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography","authors":"H. Vaseli, A. Gu, S. Neda, Ahmadi Amiri, M. Tsang, A. Fung, Nima Kondori, Armin Saadat, P. Abolmaesumi, T. Tsang","doi":"10.48550/arXiv.2307.14433","DOIUrl":"https://doi.org/10.48550/arXiv.2307.14433","url":null,"abstract":"Aortic stenosis (AS) is a common heart valve disease that requires accurate and timely diagnosis for appropriate treatment. Most current automatic AS severity detection methods rely on black-box models with a low level of trustworthiness, which hinders clinical adoption. To address this issue, we propose ProtoASNet, a prototypical network that directly detects AS from B-mode echocardiography videos, while making interpretable predictions based on the similarity between the input and learned spatio-temporal prototypes. This approach provides supporting evidence that is clinically relevant, as the prototypes typically highlight markers such as calcification and restricted movement of aortic valve leaflets. Moreover, ProtoASNet utilizes abstention loss to estimate aleatoric uncertainty by defining a set of prototypes that capture ambiguity and insufficient information in the observed data. This provides a reliable system that can detect and explain when it may fail. We evaluate ProtoASNet on a private dataset and the publicly available TMED-2 dataset, where it outperforms existing state-of-the-art methods with an accuracy of 80.0% and 79.7%, respectively. Furthermore, ProtoASNet provides interpretability and an uncertainty measure for each prediction, which can improve transparency and facilitate the interactive usage of deep networks to aid clinical decision-making. Our source code is available at: https://github.com/hooman007/ProtoASNet.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"23 1","pages":"368-378"},"PeriodicalIF":0.0,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82308171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Client-Level Differential Privacy via Adaptive Intermediary in Federated Medical Imaging 联邦医学成像中基于自适应中介的客户级差异隐私

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention Pub Date : 2023-07-24 DOI: 10.48550/arXiv.2307.12542

Meirui Jiang, Yuan Zhong, Anjie Le, Xiaoxiao Li, Qianming Dou

{"title":"Client-Level Differential Privacy via Adaptive Intermediary in Federated Medical Imaging","authors":"Meirui Jiang, Yuan Zhong, Anjie Le, Xiaoxiao Li, Qianming Dou","doi":"10.48550/arXiv.2307.12542","DOIUrl":"https://doi.org/10.48550/arXiv.2307.12542","url":null,"abstract":"Despite recent progress in enhancing the privacy of federated learning (FL) via differential privacy (DP), the trade-off of DP between privacy protection and performance is still underexplored for real-world medical scenario. In this paper, we propose to optimize the trade-off under the context of client-level DP, which focuses on privacy during communications. However, FL for medical imaging involves typically much fewer participants (hospitals) than other domains (e.g., mobile devices), thus ensuring clients be differentially private is much more challenging. To tackle this problem, we propose an adaptive intermediary strategy to improve performance without harming privacy. Specifically, we theoretically find splitting clients into sub-clients, which serve as intermediaries between hospitals and the server, can mitigate the noises introduced by DP without harming privacy. Our proposed approach is empirically evaluated on both classification and segmentation tasks using two public datasets, and its effectiveness is demonstrated with significant performance improvements and comprehensive analytical studies. Code is available at: https://github.com/med-air/Client-DP-FL.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"61 1","pages":"500-510"},"PeriodicalIF":0.0,"publicationDate":"2023-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79492490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dense Transformer based Enhanced Coding Network for Unsupervised Metal Artifact Reduction 基于密集变压器的增强编码网络无监督金属伪影减少

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention Pub Date : 2023-07-24 DOI: 10.48550/arXiv.2307.12717

Wangduo Xie, Matthew B. Blaschko

{"title":"Dense Transformer based Enhanced Coding Network for Unsupervised Metal Artifact Reduction","authors":"Wangduo Xie, Matthew B. Blaschko","doi":"10.48550/arXiv.2307.12717","DOIUrl":"https://doi.org/10.48550/arXiv.2307.12717","url":null,"abstract":"CT images corrupted by metal artifacts have serious negative effects on clinical diagnosis. Considering the difficulty of collecting paired data with ground truth in clinical settings, unsupervised methods for metal artifact reduction are of high interest. However, it is difficult for previous unsupervised methods to retain structural information from CT images while handling the non-local characteristics of metal artifacts. To address these challenges, we proposed a novel Dense Transformer based Enhanced Coding Network (DTEC-Net) for unsupervised metal artifact reduction. Specifically, we introduce a Hierarchical Disentangling Encoder, supported by the high-order dense process, and transformer to obtain densely encoded sequences with long-range correspondence. Then, we present a second-order disentanglement method to improve the dense sequence's decoding process. Extensive experiments and model discussions illustrate DTEC-Net's effectiveness, which outperforms the previous state-of-the-art methods on a benchmark dataset, and greatly reduces metal artifacts while restoring richer texture details.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"151 1","pages":"77-86"},"PeriodicalIF":0.0,"publicationDate":"2023-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86680007","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AMAE: Adaptation of Pre-Trained Masked Autoencoder for Dual-Distribution Anomaly Detection in Chest X-Rays 基于预训练掩码自编码器的胸部x线双分布异常检测

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention Pub Date : 2023-07-24 DOI: 10.48550/arXiv.2307.12721

B. Bozorgtabar, D. Mahapatra, J. Thiran

{"title":"AMAE: Adaptation of Pre-Trained Masked Autoencoder for Dual-Distribution Anomaly Detection in Chest X-Rays","authors":"B. Bozorgtabar, D. Mahapatra, J. Thiran","doi":"10.48550/arXiv.2307.12721","DOIUrl":"https://doi.org/10.48550/arXiv.2307.12721","url":null,"abstract":"Unsupervised anomaly detection in medical images such as chest radiographs is stepping into the spotlight as it mitigates the scarcity of the labor-intensive and costly expert annotation of anomaly data. However, nearly all existing methods are formulated as a one-class classification trained only on representations from the normal class and discard a potentially significant portion of the unlabeled data. This paper focuses on a more practical setting, dual distribution anomaly detection for chest X-rays, using the entire training data, including both normal and unlabeled images. Inspired by a modern self-supervised vision transformer model trained using partial image inputs to reconstruct missing image regions -- we propose AMAE, a two-stage algorithm for adaptation of the pre-trained masked autoencoder (MAE). Starting from MAE initialization, AMAE first creates synthetic anomalies from only normal training images and trains a lightweight classifier on frozen transformer features. Subsequently, we propose an adaptation strategy to leverage unlabeled images containing anomalies. The adaptation scheme is accomplished by assigning pseudo-labels to unlabeled images and using two separate MAE based modules to model the normative and anomalous distributions of pseudo-labeled images. The effectiveness of the proposed adaptation strategy is evaluated with different anomaly ratios in an unlabeled training set. AMAE leads to consistent performance gains over competing self-supervised and dual distribution anomaly detection methods, setting the new state-of-the-art on three public chest X-ray benchmarks: RSNA, NIH-CXR, and VinDr-CXR.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"109 ","pages":"195-205"},"PeriodicalIF":0.0,"publicationDate":"2023-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91461891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Right for the Wrong Reason: Can Interpretable ML Techniques Detect Spurious Correlations? 正确的错误原因:可解释的ML技术能检测到虚假的相关性吗?

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention Pub Date : 2023-07-23 DOI: 10.48550/arXiv.2307.12344

Susu Sun, Lisa M. Koch, Christian F. Baumgartner

{"title":"Right for the Wrong Reason: Can Interpretable ML Techniques Detect Spurious Correlations?","authors":"Susu Sun, Lisa M. Koch, Christian F. Baumgartner","doi":"10.48550/arXiv.2307.12344","DOIUrl":"https://doi.org/10.48550/arXiv.2307.12344","url":null,"abstract":"While deep neural network models offer unmatched classification performance, they are prone to learning spurious correlations in the data. Such dependencies on confounding information can be difficult to detect using performance metrics if the test data comes from the same distribution as the training data. Interpretable ML methods such as post-hoc explanations or inherently interpretable classifiers promise to identify faulty model reasoning. However, there is mixed evidence whether many of these techniques are actually able to do so. In this paper, we propose a rigorous evaluation strategy to assess an explanation technique's ability to correctly identify spurious correlations. Using this strategy, we evaluate five post-hoc explanation techniques and one inherently interpretable method for their ability to detect three types of artificially added confounders in a chest x-ray diagnosis task. We find that the post-hoc technique SHAP, as well as the inherently interpretable Attri-Net provide the best performance and can be used to reliably identify faulty model behavior.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"72 1","pages":"425-434"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79126303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1