Visual Attention Analysis Of Pathologists Examining Whole Slide Images Of Prostate Cancer

Chakraborty, Souradeep; Ma, Ke; Gupta, Rajarsi; Knudsen, Beatrice S.; Zelinsky, Gregory J.; Saltz, Joel; Samaras, Dimitris

doi:10.1109/isbi52829.2022.9761489

Cited by 5 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The process of narrative annotation also contains helpful information in essence. By exploring the visual attention of doctors browsing and the process of scanning trajectories, Chakraborty et al ( 34 ) found there are strongly correlated between the feature regions of algorithm tasks and lesions in the image to a certain extent, which reflects their diagnostic logic. The annotators draw the object’s bounding box with the mouse and add class labels through voice.…”

Section: Related Studymentioning

confidence: 99%

PathNarratives: Data annotation for pathological human-AI collaborative diagnosis

Zhang

He²,

Wu³

et al. 2023

Front. Med.

View full text Add to dashboard Cite

Pathology is the gold standard of clinical diagnosis. Artificial intelligence (AI) in pathology becomes a new trend, but it is still not widely used due to the lack of necessary explanations for pathologists to understand the rationale. Clinic-compliant explanations besides the diagnostic decision of pathological images are essential for AI model training to provide diagnostic suggestions assisting pathologists practice. In this study, we propose a new annotation form, PathNarratives, that includes a hierarchical decision-to-reason data structure, a narrative annotation process, and a multimodal interactive annotation tool. Following PathNarratives, we recruited 8 pathologist annotators to build a colorectal pathological dataset, CR-PathNarratives, containing 174 whole-slide images (WSIs). We further experiment on the dataset with classification and captioning tasks to explore the clinical scenarios of human-AI-collaborative pathological diagnosis. The classification tasks show that fine-grain prediction enhances the overall classification accuracy from 79.56 to 85.26%. In Human-AI collaboration experience, the trust and confidence scores from 8 pathologists raised from 3.88 to 4.63 with providing more details. Results show that the classification and captioning tasks achieve better results with reason labels, provide explainable clues for doctors to understand and make the final decision and thus can support a better experience of human-AI collaboration in pathological diagnosis. In the future, we plan to optimize the tools for the annotation process, and expand the datasets with more WSIs and covering more pathological domains.

show abstract

Section: Related Studymentioning

confidence: 99%

PathNarratives: Data annotation for pathological human-AI collaborative diagnosis

Zhang

He²,

Wu³

et al. 2023

Front. Med.

View full text Add to dashboard Cite

show abstract

“…In Ref. 27, Chakraborty et al employed a custom‐built CNN model called Prostate AttentionNet (ProstAttNet) to predict visual attention. Nagpal et al developed a DL system to classify between three Gleason patterns and non‐tumor.…”

Section: Related Workmentioning

confidence: 99%

“…In Ref. 27 classify between three Gleason patterns and non-tumor. The system was based on a custom version of the InceptionV3 architecture and a categorical prediction system based on class selection using the highest calibrated likelihood.…”

Section: Related Workmentioning

confidence: 99%

HMARNET—A Hierarchical Multi‐Attention Residual Network for Gleason scoring of prostate cancer

Karthik,

Menaka,

Siddharth

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Manual delineation of prostate cancer (PCa) from whole slide images (WSIs) demands requires pathologists with adequate domain knowledge. This process is generally strenuous and may be subjected to poor inter‐pathologist reproducibility. Accurate Gleason scoring is an important step in the computer‐aided diagnosis of PCa. This work proposes a novel lightweight convolutional neural networks (CNN) to extract significant hierarchical features from the histopathology images. It learns meticulous attention‐guided feature representations through the convolutional layers for precise scoring of Gleason grades. The Hierarchical Multi‐Attention Residual (HMAR) block extracts attention‐guided features and fuses the resulting feature maps from multiple levels with a reduced number of trainable parameters. We have also proposed a new lightweight channel‐attention module, enhanced channel attention (ECA) to extract inter‐channel features from different receptive fields. With the presence of different attention mechanisms, the network learns to focus on more significant features rather than unnecessary ones. Additionally, mixed FocalOHEM loss is proposed to optimize the CNN and efficiently minimize the error. While the focal loss helps to address the class imbalance present in the TCGA‐PRAD dataset, the online hard example mining (OHEM) loss focuses on optimizing hard negative samples. It achieved an accuracy of 89.19% with a Kappa score of 86% on the TCGA‐PRAD dataset.

show abstract

Predicting the Visual Attention of Pathologists Evaluating Whole Slide Images of Cancer

Chakraborty

Gupta

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Visual Attention Analysis Of Pathologists Examining Whole Slide Images Of Prostate Cancer

Cited by 5 publications

References 12 publications

PathNarratives: Data annotation for pathological human-AI collaborative diagnosis

PathNarratives: Data annotation for pathological human-AI collaborative diagnosis

HMARNET—A Hierarchical Multi‐Attention Residual Network for Gleason scoring of prostate cancer

Predicting the Visual Attention of Pathologists Evaluating Whole Slide Images of Cancer

Contact Info

Product

Resources

About