MS-CLAM: Mixed supervision for the classification and localization of tumors in Whole Slide Images

Article Computer Science, Information Systems

Efficient Cancer Classification by Coupling Semi Supervised and Multiple Instance Learning

Arne Schmidt et al.

Summary: In this research, SSL and MIL are combined to create a deep learning classifier that can learn from large datasets. By utilizing global diagnosis and labeled/unlabeled patches, the proposed model achieves competitive performance on various tasks with only a small percentage of patch labels.

IEEE ACCESS (2022)

Add to Collection

Review Computer Science, Artificial Intelligence

DigestPath: A benchmark dataset with challenge review for the pathological detection and segmentation of digestive-system

Qian Da et al.

Summary: This paper emphasizes the importance of pathological image examination in diagnosing and screening cancers, and presents two well-annotated benchmark datasets and challenges for digestive-system pathological detection and segmentation. The top-performing methods and results obtained from the challenges offer new opportunities for computer-aided diagnosis of digestive pathology.

MEDICAL IMAGE ANALYSIS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Semi-supervised training of deep convolutional neural networks with heterogeneous data and few local annotations: An experiment on prostate histopathology image classification

Niccolo Marini et al.

Summary: This paper introduces a novel method for training CNNs to generalize to heterogeneous datasets from different sources without local annotations. By employing a teacher/student paradigm, it improves the models' generalization capabilities and enhances classification performance across different datasets.

MEDICAL IMAGE ANALYSIS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Learning to segment images with classification labels

Ozan Ciga et al.

Summary: This study proposes an architecture that reduces the time spent on data curation and eases the requirements for segmentation level ground truth by utilizing image-level labels. It also helps unlock the potential of previously acquired image-level datasets for segmentation tasks.

MEDICAL IMAGE ANALYSIS (2021)

Add to Collection

Article Engineering, Biomedical

Data-efficient and weakly supervised computational pathology on whole-slide images

Ming Y. Lu et al.

Summary: The CLAM method utilizes attention-based learning to identify subregions with high diagnostic value for accurate classification of whole-slide images. It can localize well-known morphological features without the need for spatial labels, outperforming standard weakly supervised classification algorithms, and adapt to independent test cohorts, smartphone microscopy, and varying tissue content.

NATURE BIOMEDICAL ENGINEERING (2021)

Add to Collection

Article Oncology