The clinical interest is often to measure the volume of a structure, which is typically derived from a segmentation. In order to evaluate and compare segmentation methods, the similarity between a segmentation and a predefined ground truth is measured using popular discrete metrics, such as the Dice score. Recent segmentation methods use a differentiable surrogate metric, such as soft Dice, as part of the loss function during the learning phase. In this work, we first briefly describe how to derive volume estimates from a segmentation that is, potentially, inherently uncertain or ambiguous. This is followed by a theoretical analysis and an experimental validation linking the inherent uncertainty to common loss functions for training CNNs, namely cross-entropy and soft Dice. We find that, even though soft Dice optimization leads to an improved performance with respect to the Dice score and other measures, it may introduce a volume bias for tasks with high inherent uncertainty. These findings indicate some of the method's clinical limitations and suggest doing a closer ad-hoc volume analysis with an optional re-calibration step.
Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Index
Department of Electrical Engineering (ESAT), Center for Processing Speech and Images, KU Leuven(比利时鲁汶大学(KU Leuven)电气工程系(ESAT)、语音与图像处理中心);Department of Gastroenterology and Hepatology, UZ Leuven(比利时鲁汶大学UZ(UZ Leuven)消化内科和肝病科)
PEFT-MedSAM: Efficient Fine-Tuning of Medical Foundation Models for Explainable Skin Lesion Segmentation
Department of Computer Science, Quaid-e-Awam University of Engineering, Sciences & Technology(计算机科学系,卡迪尔-阿瓦姆工程、科学与技术大学);Department of Artificial Intelligence, Quaid-e-Awam University of Engineering, Sciences & Technology(人工智能系,卡迪尔-阿瓦姆工程、科学与技术大学);Department of Computer Science, Sindh Madressatul Islam University, City Campus, Karachi(计算机科学系, Sind 阿里斯坦伊斯兰大学,卡拉奇城校区);Department of Computer Science and Digital Technologies, School of Architecture, Computing and Engineering, University of East London(计算机科学与数字技术系,建筑、计算与工程学院,东伦敦大学)
AutoPET Challenge III: Testing the Robustness of Generalized Dice Focal Loss trained 3D Residual UNet for FDG and PSMA Lesion Segmentation from Whole-Body PET/CT Images
University of British Columbia(不列颠哥伦比亚大学);BC Cancer Research Institute(不列颠哥伦比亚癌症研究所)
Comparative Validation of AI and non-AI Methods in MRI Volumetry to Diagnose Parkinsonian Syndromes
Samsung Medical Center(三星医疗中心);Sungkyunkwan University School of Medicine(成均馆大学医学院);Sungkyunkwan University(成均馆大学);Columbia University(哥伦比亚大学);University of Maryland(马里兰大学)
Topology-Aware Training and Spatial Diagnostics for Fiber Bundle Segmentation in Tracer Histology
Universidad Nacional Mayor de San Marcos(圣马科斯国立大学);Athinoula A. Martinos Center for Biomedical Imaging(阿西诺拉·A.马蒂诺斯生物医学成像中心);Massachusetts General Hospital(麻省总医院);Harvard Medical School(哈佛医学院);University of Rochester School of Medicine(罗切斯特大学医学院);McLean Hospital(麦克莱恩医院)
Parameter-efficient Fine-tuning for improved Convolutional Baseline for Brain Tumor Segmentation in Sub-Saharan Africa Adult Glioma Dataset
Nepal Research and Collaboration Center (NRCC)(尼泊尔研究与合作中心);Birendra Multiple Campus, Tribhuvan University(特里布万大学比伦德拉多校区);Institute of Engineering, Purbanchal Campus, Tribhuvan University(特里布万大学普尔班查尔校区工程学院);Bhaktapur Multiple Campus, Tribhuvan University(特里布万大学巴克塔普尔多校区);Gandaki College of Engineering and Science, Pokhara University(博卡拉大学甘达基工程与科学学院);McGill University(麦吉尔大学);Lawson Health Research Institute(劳森健康研究所);Medical Artificial Intelligence Laboratory (MAI Lab), Lagos(拉各斯医学人工智能实验室);University of British Columbia(不列颠哥伦比亚大学);Montreal Neurological Institute, McGill University(麦吉尔大学蒙特利尔神经学研究所)
Brain tumour segmentation using a triplanar ensemble of U-Nets
University of Oxford(牛津大学);Australian Institute for Machine Learning(澳大利亚机器学习研究所);The University of Adelaide(阿德莱德大学);South Australian Health and Medical Research Institute(南澳大利亚健康与医学研究所)
Diffusion-Based Data Augmentation for Medical Image Segmentation
School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院);Dept. of Engineering for Innovation Medicine, University of Verona(威尼斯大学创新医学工程系)
HyFormer-Net: A Synergistic CNN-Transformer with Interpretable Multi-Scale Fusion for Breast Lesion Segmentation and Classification in Ultrasound Images
Department of Computer Science and Engineering, Ahsanullah University of Science and Technology(计算机科学与工程系,阿沙努尔大学科学与技术学院)
Parameter-Efficient 3D Segmentation of Liver and Liver tumors: Depthwise factorization Scales Better Than Dense Convolution with Spatial Dimensionality
An Improved Approach for Cardiac MRI Segmentation based on 3D UNet Combined with Papillary Muscle Exclusion
Higher Institute of Medical Technologies of Tunis(突尼斯高等医疗技术学院);University of Tunis El Manar(突尼斯埃尔马纳尔大学);Faculty of Medicine of Monastir(莫纳斯提尔医学院);University of Monastir(莫纳斯提尔大学);Artificial Intelligence Research Centre, Ajman University(阿治曼大学人工智能研究中心);Ajman University(阿治曼大学);National Engineering School of Tunis(突尼斯国立工程师学院);IPEIEM(突尼斯高等预科工程与技术学院(IPEIEM))
Performance Evaluation of Deep Learning for Tree Branch Segmentation in Autonomous Forestry Systems
Centre for Data Science and Artificial Intelligence(数据科学与人工智能中心);Victoria University of Wellington(惠灵顿维多利亚大学);Department of Computer Science and Software Engineering(计算机科学与软件工程系);University of Canterbury(坎特伯雷大学)
Towards Fully Automated Medical Imaging Code Generation via Validation-based Context Engineering
University of Auckland(奥克兰大学);Griffith University(格里菲斯大学);Suzhou Industrial Park Monash Research Institute of Science and Technology(苏州工业园区莫纳什科技研究院);Beijing Institute of Technology(北京理工大学);National University of Singapore(新加坡国立大学)
MedNet-PVS: A MedNeXt-Based Deep Learning Model for Automated Segmentation of Perivascular Spaces
Monash University Malaysia(莫纳什大学马来西亚校区);Melbourne Bioinnovation Student Initiative(墨尔本生物创新学生计划);CSIRO Australian e-Health Research Centre(澳大利亚联邦科学与工业研究组织电子健康研究中心);University of New South Wales(新南威尔士大学);Monash University(莫纳什大学);Alfred Health(阿尔弗雷德健康中心);Monash Biomedical Imaging(莫纳什生物医学影像中心);University of Sydney(悉尼大学);Charles Perkins Centre(查尔斯·珀金斯中心)
Quantification of pulmonary involvement in COVID-19 pneumonia by means of a cascade oftwo U-nets: training and assessment on multipledatasets using different annotation criteria
Scuola Normale Superiore(比萨高等师范学校);National Institute of Nuclear Physics (INFN)(国家核物理研究所);University of Pavia(帕维亚大学);University of Pisa(比萨大学);University of Sassari(萨萨里大学);University of Florence(佛罗伦萨大学)
Impact of Labeling Inaccuracy and Image Noise on Tooth Segmentation in Panoramic Radiographs using Federated, Centralized and Local Learning
Department of Dentistry and Oral Health(牙科与口腔健康系);Aarhus University(奥胡斯大学);Department of Electrical- and Computer Engineering(电气与计算机工程系);Faculty of Information Technology and Communications Sciences(信息科技与通讯科学学院);Tampere University(塔尔库大学)
A Fully Automated Pipeline Using Swin Transformers for Deep Learning-Based Blood Segmentation on Head CT Scans After Aneurysmal Subarachnoid Hemorrhage