DART@MICCAI Pub Date : 2023-08-24 DOI: 10.48550/arXiv.2308.12679

A. Sadafi, Raheleh Salehi, A. Gruber, Sayedali Shetab Boushehri, Pascal Giehr, N. Navab, Carsten Marr

{"title":"A Continual Learning Approach for Cross-Domain White Blood Cell Classification","authors":"A. Sadafi, Raheleh Salehi, A. Gruber, Sayedali Shetab Boushehri, Pascal Giehr, N. Navab, Carsten Marr","doi":"10.48550/arXiv.2308.12679","DOIUrl":"https://doi.org/10.48550/arXiv.2308.12679","url":null,"abstract":"Accurate classification of white blood cells in peripheral blood is essential for diagnosing hematological diseases. Due to constantly evolving clinical settings, data sources, and disease classifications, it is necessary to update machine learning classification models regularly for practical real-world use. Such models significantly benefit from sequentially learning from incoming data streams without forgetting previously acquired knowledge. However, models can suffer from catastrophic forgetting, causing a drop in performance on previous tasks when fine-tuned on new data. Here, we propose a rehearsal-based continual learning approach for class incremental and domain incremental scenarios in white blood cell classification. To choose representative samples from previous tasks, we employ exemplar set selection based on the model's predictions. This involves selecting the most confident samples and the most challenging samples identified through uncertainty estimation of the model. We thoroughly evaluated our proposed approach on three white blood cell classification datasets that differ in color, resolution, and class composition, including scenarios where new domains or new classes are introduced to the model with every task. We also test a long class incremental experiment with both new domains and new classes. Our results demonstrate that our approach outperforms established baselines in continual learning, including existing iCaRL and EWC methods for classifying white blood cells in cross-domain environments.","PeriodicalId":106540,"journal":{"name":"DART@MICCAI","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121232949","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

Self-Prompting Large Vision Models for Few-Shot Medical Image Segmentation 基于自提示大视觉模型的少镜头医学图像分割

DART@MICCAI Pub Date : 2023-08-15 DOI: 10.48550/arXiv.2308.07624

Qi Wu, Yuyao Zhang, Marawan Elbatel

引用次数: 1

The Performance of Transferability Metrics does not Translate to Medical Tasks 可转移性指标的性能不能转化为医疗任务

DART@MICCAI Pub Date : 2023-08-14 DOI: 10.48550/arXiv.2308.07444

Levy G. Chaves, Alceu Bissoto, Eduardo Valle, S. Avila

引用次数: 0

Seamless Iterative Semi-Supervised Correction of Imperfect Labels in Microscopy Images 显微镜图像中不完美标记的无缝迭代半监督校正

DART@MICCAI Pub Date : 2022-08-05 DOI: 10.48550/arXiv.2208.03327

Marawan Elbatel, Christina Bornberg, Manasi Kattel, E. Almar, C. Marrocco, A. Bria

{"title":"Seamless Iterative Semi-Supervised Correction of Imperfect Labels in Microscopy Images","authors":"Marawan Elbatel, Christina Bornberg, Manasi Kattel, E. Almar, C. Marrocco, A. Bria","doi":"10.48550/arXiv.2208.03327","DOIUrl":"https://doi.org/10.48550/arXiv.2208.03327","url":null,"abstract":". In-vitro tests are an alternative to animal testing for the toxicity of medical devices. Detecting cells as a ﬁrst step, a cell expert evaluates the growth of cells according to cytotoxicity grade under the microscope. Thus, human fatigue plays a role in error making, making the use of deep learning appealing. Due to the high cost of training data annotation, an approach without manual annotation is needed. We propose Seamless Iterative Semi-Supervised correction of Imperfect labels (SISSI) , a new method for training object detection models with noisy and missing annotations in a semi-supervised fashion. Our network learns from noisy labels generated with simple image processing algorithms, which are iteratively corrected during self-training. Due to the nature of missing bounding boxes in the pseudo labels, which would negatively aﬀect the training, we propose to train on dynamically generated synthetic-like images using seamless cloning. Our method successfully provides an adaptive early learning correction technique for object detection. The combination of early learning correction that has been applied in classiﬁcation and semantic segmentation before and synthetic-like image generation proves to be more eﬀective than the usual semi-supervised approach by > 15% AP and > 20% AR across three diﬀerent readers. Our code is available at https://github.com/marwankefah/SISSI.","PeriodicalId":106540,"journal":{"name":"DART@MICCAI","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124349106","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

Feather-Light Fourier Domain Adaptation in Magnetic Resonance Imaging 磁共振成像中的轻羽傅立叶域自适应

DART@MICCAI Pub Date : 2022-07-31 DOI: 10.48550/arXiv.2208.00474

Ivan Zakazov, V. Shaposhnikov, Iaroslav Bespalov, D. Dylov

引用次数: 3

Detecting Melanoma Fairly: Skin Tone Detection and Debiasing for Skin Lesion Classification 公平检测黑色素瘤:肤色检测和皮肤病变分类去偏

DART@MICCAI Pub Date : 2022-02-06 DOI: 10.1007/978-3-031-16852-9_1

Peter J. Bevan, Amir Atapour-Abarghouei

引用次数: 11

MetaMedSeg: Volumetric Meta-learning for Few-Shot Organ Segmentation MetaMedSeg:基于体积元学习的小片段器官分割

DART@MICCAI Pub Date : 2021-09-18 DOI: 10.1007/978-3-031-16852-9_5

A. Makarevich, Azade Farshad, Vasileios Belagiannis, Nassir Navab