skip to main content

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Interpretable deep learning models for better clinician-AI communication in clinical mammography
There is increasing interest in using deep learning and computer vision to help guide clinical decisions, such as whether to order a biopsy based on a mammogram. Existing networks are typically black box, unable to explain how they make their predictions. We present an interpretable deep-learning network which explains its predictions in terms of BI-RADS features mass shape and mass margin. Our model predicts mass margin and mass shape, then uses the logits from those interpretable models to predict malignancy, also using an interpretable model. The interpretable mass margin model explains its predictions using a prototypical parts model. The interpretable mass shape model predicts segmentations, fits an ellipse, then determines shape based on the goodness of fit and eccentricity of the fitted ellipse. While including mass shape logits in the malignancy prediction model did not improve performance, we present this technique as part of a framework for better clinician-AI communication.  more » « less
Award ID(s):
2222336
PAR ID:
10424536
Author(s) / Creator(s):
; ; ; ; ; ; ;
Editor(s):
Mello-Thoms, Claudia R.; Taylor-Phillips, Sian
Date Published:
Journal Name:
Proc. SPIE 12035, Medical Imaging 2022: Image Perception, Observer Performance, and Technology Assessment,
Volume:
1203507
Page Range / eLocation ID:
16
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ; ( , Medical Imaging 2023: Image Perception, Observer Performance, and Technology Assessment)
    Chen, Yan ; Mello-Thoms, Claudia R. (Ed.)
    Tools for computer-aided diagnosis based on deep learning have become increasingly important in the medical field. Such tools can be useful, but require effective communication of their decision-making process in order to safely and meaningfully guide clinical decisions. We present a user interface that incorporates the IAIA-BL model, which interpretably predicts both mass margin and malignancy for breast lesions. The user interface displays the most relevant aspects of the model’s explanation including the predicted margin value, the AI confidence in the prediction, and the two most highly activated prototypes for each case. In addition, this user interface includes full-field and cropped images of the region of interest, as well as a questionnaire suitable for a reader study. Our preliminary results indicate that the model increases the readers’ confidence and accuracy in their decisions on margin and malignancy. 
    more » « less
  2. ; ; ; ( , Proteins: Structure, Function, and Bioinformatics)
    Abstract

    Deep learning has emerged as a revolutionary technology for protein residue‐residue contact prediction since the 2012 CASP10 competition. Considerable advancements in the predictive power of the deep learning‐based contact predictions have been achieved since then. However, little effort has been put into interpreting the black‐box deep learning methods. Algorithms that can interpret the relationship between predicted contact maps and the internal mechanism of the deep learning architectures are needed to explore the essential components of contact inference and improve their explainability. In this study, we present an attention‐based convolutional neural network for protein contact prediction, which consists of two attention mechanism‐based modules: sequence attention and regional attention. Our benchmark results on the CASP13 free‐modeling targets demonstrate that the two attention modules added on top of existing typical deep learning models exhibit a complementary effect that contributes to prediction improvements. More importantly, the inclusion of the attention mechanism provides interpretable patterns that contain useful insights into the key fold‐determining residues in proteins. We expect the attention‐based model can provide a reliable and practically interpretable technique that helps break the current bottlenecks in explaining deep neural networks for contact prediction. The source code of our method is available athttps://github.com/jianlin-cheng/InterpretContactMap.

     
    more » « less
  3. ; ; ; ; ; ; ; ( , Cancers)

    Deep learning has been applied in precision oncology to address a variety of gene expression-based phenotype predictions. However, gene expression data’s unique characteristics challenge the computer vision-inspired design of popular Deep Learning (DL) models such as Convolutional Neural Network (CNN) and ask for the need to develop interpretable DL models tailored for transcriptomics study. To address the current challenges in developing an interpretable DL model for modeling gene expression data, we propose a novel interpretable deep learning architecture called T-GEM, or Transformer for Gene Expression Modeling. We provided the detailed T-GEM model for modeling gene–gene interactions and demonstrated its utility for gene expression-based predictions of cancer-related phenotypes, including cancer type prediction and immune cell type classification. We carefully analyzed the learning mechanism of T-GEM and showed that the first layer has broader attention while higher layers focus more on phenotype-related genes. We also showed that T-GEM’s self-attention could capture important biological functions associated with the predicted phenotypes. We further devised a method to extract the regulatory network that T-GEM learns by exploiting the attributions of self-attention weights for classifications and showed that the network hub genes were likely markers for the predicted phenotypes.

     
    more » « less
  4. ; ; ; ( , BMC Bioinformatics)
    Abstract Background In the CRISPR-Cas9 system, the efficiency of genetic modifications has been found to vary depending on the single guide RNA (sgRNA) used. A variety of sgRNA properties have been found to be predictive of CRISPR cleavage efficiency, including the position-specific sequence composition of sgRNAs, global sgRNA sequence properties, and thermodynamic features. While prevalent existing deep learning-based approaches provide competitive prediction accuracy, a more interpretable model is desirable to help understand how different features may contribute to CRISPR-Cas9 cleavage efficiency. Results We propose a gradient boosting approach, utilizing LightGBM to develop an integrated tool, BoostMEC (Boosting Model for Efficient CRISPR), for the prediction of wild-type CRISPR-Cas9 editing efficiency. We benchmark BoostMEC against 10 popular models on 13 external datasets and show its competitive performance. Conclusions BoostMEC can provide state-of-the-art predictions of CRISPR-Cas9 cleavage efficiency for sgRNA design and selection. Relying on direct and derived sequence features of sgRNA sequences and based on conventional machine learning, BoostMEC maintains an advantage over other state-of-the-art CRISPR efficiency prediction models that are based on deep learning through its ability to produce more interpretable feature insights and predictions. 
    more » « less
  5. ( , 2021 IEEE 21st International Working Conference on Source Code Analysis and Manipulation)
    null (Ed.)
    Runtime exceptions are inevitable parts of software systems. While developers often write exception handling code to avoid the severe outcomes of these exceptions, such code is most effective if accompanied by accurate runtime exception types. Predicting the runtime exceptions that may occur in a program, however, is difficult as the situations that lead to these exceptions are complex. We propose D-REX (Deep Runtime EXception detector), as an approach for predicting runtime exceptions of Java methods based on the static properties of code. The core of D-REX is a machine learning model that leverages the representation learning ability of neural networks to infer a set of signals from code to predict the related runtime exception types. This model, which we call Location Aware Transformer, adapts a state-of-the-art language model, Transformer, to provide accurate predictions for the exception types, as well as interpretable recommendations for the exception prone elements of code. We curate a benchmark dataset of 200,000 Java projects from GitHub to train and evaluate D-REX. Experiments demonstrate that D-REX predicts runtime exception types with 81% of Top 1 accuracy, outperforming multiple non-Transformer baselines by a margin of at least 12%. Furthermore, it can predict the exception prone elements of code with 75% Top 1 precision. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email