Bayesian collaborative learning for whole-slide image classification
JG Yu, Z Wu, Y Ming, S Deng, Q Wu… - … on Medical Imaging, 2023 - ieeexplore.ieee.org
Whole-slide image (WSI) classification is fundamental to computational pathology, which is
challenging in extra-high resolution, expensive manual annotation, data heterogeneity, etc …
challenging in extra-high resolution, expensive manual annotation, data heterogeneity, etc …
Exploring Multiple Instance Learning (MIL): A brief survey
Abstract Multiple Instance Learning (MIL) is a learning paradigm, where training instances
are arranged in sets, called bags, and only bag-level labels are available during training …
are arranged in sets, called bags, and only bag-level labels are available during training …
Context label learning: improving background class representations in semantic segmentation
Background samples provide key contextual information for segmenting regions of interest
(ROIs). However, they always cover a diverse set of structures, causing difficulties for the …
(ROIs). However, they always cover a diverse set of structures, causing difficulties for the …
[PDF][PDF] Dual Space Multiple Instance Representative Learning for Medical Image Classification.
Medical image classification plays a vital role in AI-aided medical diagnosis and is often
addressed as a Multiple Instance Learning (MIL) issue (ie, each sample is a bag of …
addressed as a Multiple Instance Learning (MIL) issue (ie, each sample is a bag of …
Registration‐enhanced multiple instance learning for cervical cancer whole slide image classification
Q He, C Wang, S Zeng, Z Liang, H Duan… - … Journal of Imaging …, 2024 - Wiley Online Library
Histopathological diagnosis is the golden standard for cancer diagnosis and grading. The
past decade has witnessed great successes of vision‐based deep learning in computer …
past decade has witnessed great successes of vision‐based deep learning in computer …
[HTML][HTML] Deep Learning for Delineation of the Spinal Canal in Whole-Body Diffusion-Weighted Imaging: Normalising Inter-and Intra-Patient Intensity Signal in Multi …
Background: Whole-Body Diffusion-Weighted Imaging (WBDWI) is an established technique
for staging and evaluating treatment response in patients with multiple myeloma (MM) and …
for staging and evaluating treatment response in patients with multiple myeloma (MM) and …
[HTML][HTML] Curation of myeloma observational study MALIMAR using XNAT: solving the challenges posed by real-world data
Abstract Objectives MAchine Learning In MyelomA Response (MALIMAR) is an
observational clinical study combining “real-world” and clinical trial data, both retrospective …
observational clinical study combining “real-world” and clinical trial data, both retrospective …
Metastatic cancer outcome prediction with injective multiple instance pooling
Cancer stage is a large determinant of patient prognosis and management in many cancer
types, and is often assessed using medical imaging modalities, such as CT and MRI. These …
types, and is often assessed using medical imaging modalities, such as CT and MRI. These …
Volume is All You Need: Improving Multi-task Multiple Instance Learning for WMH Segmentation and Severity Estimation
White matter hyperintensities (WMHs) are lesions with unusually high intensity detected in
T2 fluid-attenuated inversion recovery (T2-FLAIR) MRI images, commonly attributed to …
T2 fluid-attenuated inversion recovery (T2-FLAIR) MRI images, commonly attributed to …
[PDF][PDF] Learning strategies for improving neural networks for image segmentation under class imbalance
Z Li - 2023 - zerojumpline.github.io
Conclusion➢ Overfitting under class imbalance leads to loss of sensitivity.➢ The distribution
of logit activations when processing unseen test samples of an under-represented class …
of logit activations when processing unseen test samples of an under-represented class …