Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!

Add to Chrome

Add to Firefox

Add to Edge

Janani Iyer

Self-training of Machine Learning Models for Liver Histopathology: Generalization under Clinical Shifts

Nov 14, 2022
Jin Li, Deepta Rajan, Chintan Shah, Dinkar Juyal, Shreya Chakraborty, Chandan Akiti, Filip Kos, Janani Iyer, Anand Sampat, Ali Behrooz

Figure 1 for Self-training of Machine Learning Models for Liver Histopathology: Generalization under Clinical Shifts

Figure 2 for Self-training of Machine Learning Models for Liver Histopathology: Generalization under Clinical Shifts

Figure 3 for Self-training of Machine Learning Models for Liver Histopathology: Generalization under Clinical Shifts

Figure 4 for Self-training of Machine Learning Models for Liver Histopathology: Generalization under Clinical Shifts

Histopathology images are gigapixel-sized and include features and information at different resolutions. Collecting annotations in histopathology requires highly specialized pathologists, making it expensive and time-consuming. Self-training can alleviate annotation constraints by learning from both labeled and unlabeled data, reducing the amount of annotations required from pathologists. We study the design of teacher-student self-training systems for Non-alcoholic Steatohepatitis (NASH) using clinical histopathology datasets with limited annotations. We evaluate the models on in-distribution and out-of-distribution test data under clinical data shifts. We demonstrate that through self-training, the best student model statistically outperforms the teacher with a $3\%$ absolute difference on the macro F1 score. The best student model also approaches the performance of a fully supervised model trained with twice as many annotations.

* Extended Abstract presented at Machine Learning for Health (ML4H) symposium 2022, November 28th, 2022, New Orleans, United States & Virtual, http://www.ml4h.cc, 6 pages

Via

Access Paper or Ask Questions

Multi stain graph fusion for multimodal integration in pathology

Apr 26, 2022
Chaitanya Dwivedi, Shima Nofallah, Maryam Pouryahya, Janani Iyer, Kenneth Leidal, Chuhan Chung, Timothy Watkins, Andrew Billin, Robert Myers, John Abel, Ali Behrooz

Figure 1 for Multi stain graph fusion for multimodal integration in pathology

Figure 2 for Multi stain graph fusion for multimodal integration in pathology

Figure 3 for Multi stain graph fusion for multimodal integration in pathology

In pathology, tissue samples are assessed using multiple staining techniques to enhance contrast in unique histologic features. In this paper, we introduce a multimodal CNN-GNN based graph fusion approach that leverages complementary information from multiple non-registered histopathology images to predict pathologic scores. We demonstrate this approach in nonalcoholic steatohepatitis (NASH) by predicting CRN fibrosis stage and NAFLD Activity Score (NAS). Primary assessment of NASH typically requires liver biopsy evaluation on two histological stains: Trichrome (TC) and hematoxylin and eosin (H&E). Our multimodal approach learns to extract complementary information from TC and H&E graphs corresponding to each stain while simultaneously learning an optimal policy to combine this information. We report up to 20% improvement in predicting fibrosis stage and NAS component grades over single-stain modeling approaches, measured by computing linearly weighted Cohen's kappa between machine-derived vs. pathologist consensus scores. Broadly, this paper demonstrates the value of leveraging diverse pathology images for improved ML-powered histologic assessment.

Via

Access Paper or Ask Questions