Attention2majority: Weak multiple instance learning for regenerative kidney grading on whole slide images

Su, Ziyu; Tavolara, Thomas E.; Carreno-Galeano, Gabriel; Lee, Sang Jin; Gürcan, Metin N.; Niazi, M. Khalid Khan

doi:10.1016/j.media.2022.102462

Cited by 34 publications

(29 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For histopathological analyses, bags consist of tessellated WSIs, in which each tile is a small unannotated image sampled from the WSI. It is popular for WSI analyses [ 4 , 17 , 19 , 20 , 86 , 87 ], as only slide-level labels are required for its training and implementation, thus negating the need for tissue-level annotations.…”

Section: Methodsmentioning

confidence: 99%

“…Arguably, the most successful adaptation of MIL within WSI analysis is attention-based (AB) MIL [ 17 , 18 , 19 , 20 , 21 , 86 , 87 ]. The attention-based pooling mechanism [ 88 ] automatically learns to dynamically weight embedded instances into a bag-level feature vector.…”

Section: Methodsmentioning

confidence: 99%

“…Then, we (2) freeze the resulting contrastively MIL model and train a new fully connected layer along with slide-level labels, and (3) perform an ablation study in which only 25%, 50%, and 75% of the labels are utilized for both (1) and (2). Finally, we (4) compare with fully-supervised attention-based MIL, CLAM [ 17 ] and Attention2majority [ 20 ], using both SimCLR embeddings as well as generic ImageNet embeddings derived from a pre-trained ResNet50. For Attention2majority, we test different numbers of instances, as in the original study.…”

Section: Methodsmentioning

confidence: 99%

“…This was notable at the time, as previous methods had relied on tediously annotated tissue ROIs. Several studies have since followed suit [ 4 , 17 , 20 , 25 , 67 , 68 , 69 , 70 ].…”

Section: Related Workmentioning

confidence: 99%

“…Finally, medical image datasets are vanishingly small compared to general-purpose computer vision datasets [ 14 , 16 ]. It is no wonder that recent high-profile publications in computational pathology have moved away from fully-supervised methods to semi- and weakly-supervised methods [ 17 , 18 , 19 , 20 ].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Contrastive Multiple Instance Learning: An Unsupervised Framework for Learning Slide-Level Representations of Whole Slide Histopathology Images without Labels

Tavolara

Gürcan

Niazi

2022

Cancers

Self Cite

View full text Add to dashboard Cite

Recent methods in computational pathology have trended towards semi- and weakly-supervised methods requiring only slide-level labels. Yet, even slide-level labels may be absent or irrelevant to the application of interest, such as in clinical trials. Hence, we present a fully unsupervised method to learn meaningful, compact representations of WSIs. Our method initially trains a tile-wise encoder using SimCLR, from which subsets of tile-wise embeddings are extracted and fused via an attention-based multiple-instance learning framework to yield slide-level representations. The resulting set of intra-slide-level and inter-slide-level embeddings are attracted and repelled via contrastive loss, respectively. This resulted in slide-level representations with self-supervision. We applied our method to two tasks— (1) non-small cell lung cancer subtyping (NSCLC) as a classification prototype and (2) breast cancer proliferation scoring (TUPAC16) as a regression prototype—and achieved an AUC of 0.8641 ± 0.0115 and correlation (R2) of 0.5740 ± 0.0970, respectively. Ablation experiments demonstrate that the resulting unsupervised slide-level feature space can be fine-tuned with small datasets for both tasks. Overall, our method approaches computational pathology in a novel manner, where meaningful features can be learned from whole-slide images without the need for annotations of slide-level labels. The proposed method stands to benefit computational pathology, as it theoretically enables researchers to benefit from completely unlabeled whole-slide images.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

“…This was notable at the time, as previous methods had relied on tediously annotated tissue ROIs. Several studies have since followed suit [ 4 , 17 , 20 , 25 , 67 , 68 , 69 , 70 ].…”

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Contrastive Multiple Instance Learning: An Unsupervised Framework for Learning Slide-Level Representations of Whole Slide Histopathology Images without Labels

Tavolara

Gürcan

Niazi

2022

Cancers

Self Cite

View full text Add to dashboard Cite

show abstract

Employing machine learning to enhance fracture recovery insights through gait analysis

Rezapour,

Seymour,

Sims

et al. 2024

Journal Orthopaedic Research

View full text Add to dashboard Cite

This study aimed to explore the potential of gait analysis coupled with supervised machine learning models as a predictive tool for assessing post‐injury complications such as infection, malunion, or hardware irritation among individuals with lower extremity fractures. We prospectively identified participants with lower extremity fractures at a tertiary academic center. These participants underwent gait analysis with a chest‐mounted inertial measurement unit device. Using customized software, the raw gait data were preprocessed, emphasizing 12 essential gait variables. The data were standardized, and several machine learning models, including XGBoost, logistic regression, support vector machine, LightGBM, and Random Forest, were trained, tested, and evaluated. Special attention was given to class imbalance, addressed using the synthetic minority oversampling technique (SMOTE). Additionally, we introduced a novel methodology to compute the post‐injury recovery rate for gait variables, which operates independently of the time difference between the gait analyses of different participants. XGBoost was identified as the optimal model both before and after the application of SMOTE. Before using SMOTE, the model achieved an average test area under the ROC curve (AUC) of 0.90, with a 95% confidence interval (CI) of [0.79, 1.00], and an average test accuracy of 86%, with a 95% CI of [75%, 97%]. Through feature importance analysis, a pivotal role was attributed to the duration between the occurrence of the injury and the initial gait analysis. Data patterns over time revealed early aggressive physiological compensations, followed by stabilization phases, underscoring the importance of prompt gait analysis. χ2 analysis indicated a statistically significant higher readmission rate among participants with underlying medical conditions (p = 0.04). Although the complication rate was also higher in this group, the association did not reach statistical significance (p = 0.06), suggesting a more pronounced impact of medical conditions on readmission rates rather than on complications. This study highlights the transformative potential of integrating advanced machine learning techniques like XGBoost with gait analysis for orthopedic care. The findings underscore a shift toward a data‐informed, proactive approach in orthopedics, enhancing patient outcomes through early detection and intervention. The χ2 analysis added crucial insights into the broader clinical implications, advocating for a comprehensive treatment strategy that accounts for the patient's overall health profile. The research paves the way for personalized, predictive medical care in orthopedics, emphasizing the importance of timely and tailored patient assessments.

show abstract

Improved DeTraC Binary Coyote Net‐Based Multiple Instance Learning for Predicting Lymph Node Metastasis of Breast Cancer From Whole‐Slide Pathological Images

Ramkumar,

Sarath Kumar,

Padmapriya

et al. 2024

Robotics Computer Surgery

View full text Add to dashboard Cite

BackgroundEarly detection of lymph node metastasis in breast cancer is vital for improving treatment outcomes and prognosis.MethodsThis study introduces an Improved Decompose, Transfer, and Compose Binary Coyote Net‐based Multiple Instance Learning (ImDeTraC‐BCNet‐MIL) method for predicting lymph node metastasis from Whole Slide Images (WSIs) using multiple instance learning. The method involves segmenting WSIs into patches using Otsu and double‐dimensional clustering techniques. The developed multiple instance learning approach introduces a paradigm into computational pathology by shaping pathological data and constructing features. ImDeTraC‐BCNet‐MIL was utilised for feature generation during both training and testing to differentiate lymph node metastasis in WSIs.ResultsThe proposed model achieves the highest accuracy of 95.3% and 99.8%, precision values of 98% and 99.8%, and recall rates of 92.9% and 99.8% on the Camelyon16 and Camelyon17 datasets.ConclusionsThese findings underscore the effectiveness of ImDeTraC‐BCNet‐MIL in enhancing the early detection of lymph node metastasis in breast cancer.

show abstract

Attention2majority: Weak multiple instance learning for regenerative kidney grading on whole slide images

Cited by 34 publications

References 57 publications

Contrastive Multiple Instance Learning: An Unsupervised Framework for Learning Slide-Level Representations of Whole Slide Histopathology Images without Labels

Contrastive Multiple Instance Learning: An Unsupervised Framework for Learning Slide-Level Representations of Whole Slide Histopathology Images without Labels

Employing machine learning to enhance fracture recovery insights through gait analysis

Improved DeTraC Binary Coyote Net‐Based Multiple Instance Learning for Predicting Lymph Node Metastasis of Breast Cancer From Whole‐Slide Pathological Images

Contact Info

Product

Resources

About