Alert button
Picture for Aaditya Prakash

Aaditya Prakash

Alert button

ContriMix: Unsupervised disentanglement of content and attribute for domain generalization in microscopy image analysis

Jul 03, 2023
Tan H. Nguyen, Dinkar Juyal, Jin Li, Aaditya Prakash, Shima Nofallah, Chintan Shah, Sai Chowdary Gullapally, Michael Griffin, Anand Sampat, John Abel, Justin Lee, Amaro Taylor-Weiner

Figure 1 for ContriMix: Unsupervised disentanglement of content and attribute for domain generalization in microscopy image analysis
Figure 2 for ContriMix: Unsupervised disentanglement of content and attribute for domain generalization in microscopy image analysis
Figure 3 for ContriMix: Unsupervised disentanglement of content and attribute for domain generalization in microscopy image analysis
Figure 4 for ContriMix: Unsupervised disentanglement of content and attribute for domain generalization in microscopy image analysis

Domain generalization is critical for real-world applications of machine learning models to microscopy images, including histopathology and fluorescence imaging. Artifacts in histopathology arise through a complex combination of factors relating to tissue collection and laboratory processing, as well as factors intrinsic to patient samples. In fluorescence imaging, these artifacts stem from variations across experimental batches. The complexity and subtlety of these artifacts make the enumeration of data domains intractable. Therefore, augmentation-based methods of domain generalization that require domain identifiers and manual fine-tuning are inadequate in this setting. To overcome this challenge, we introduce ContriMix, a domain generalization technique that learns to generate synthetic images by disentangling and permuting the biological content ("content") and technical variations ("attributes") in microscopy images. ContriMix does not rely on domain identifiers or handcrafted augmentations and makes no assumptions about the input characteristics of images. We assess the performance of ContriMix on two pathology datasets (Camelyon17-WILDS and a prostate cell classification dataset) and one fluorescence microscopy dataset (RxRx1-WILDS). ContriMix outperforms current state-of-the-art methods in all datasets, motivating its usage for microscopy image analysis in real-world settings where domain information is hard to come by.

Viaarxiv icon

Synthetic DOmain-Targeted Augmentation (S-DOTA) Improves Model Generalization in Digital Pathology

May 03, 2023
Sai Chowdary Gullapally, Yibo Zhang, Nitin Kumar Mittal, Deeksha Kartik, Sandhya Srinivasan, Kevin Rose, Daniel Shenker, Dinkar Juyal, Harshith Padigela, Raymond Biju, Victor Minden, Chirag Maheshwari, Marc Thibault, Zvi Goldstein, Luke Novak, Nidhi Chandra, Justin Lee, Aaditya Prakash, Chintan Shah, John Abel, Darren Fahy, Amaro Taylor-Weiner, Anand Sampat

Figure 1 for Synthetic DOmain-Targeted Augmentation (S-DOTA) Improves Model Generalization in Digital Pathology
Figure 2 for Synthetic DOmain-Targeted Augmentation (S-DOTA) Improves Model Generalization in Digital Pathology
Figure 3 for Synthetic DOmain-Targeted Augmentation (S-DOTA) Improves Model Generalization in Digital Pathology
Figure 4 for Synthetic DOmain-Targeted Augmentation (S-DOTA) Improves Model Generalization in Digital Pathology

Machine learning algorithms have the potential to improve patient outcomes in digital pathology. However, generalization of these tools is currently limited by sensitivity to variations in tissue preparation, staining procedures and scanning equipment that lead to domain shift in digitized slides. To overcome this limitation and improve model generalization, we studied the effectiveness of two Synthetic DOmain-Targeted Augmentation (S-DOTA) methods, namely CycleGAN-enabled Scanner Transform (ST) and targeted Stain Vector Augmentation (SVA), and compared them against the International Color Consortium (ICC) profile-based color calibration (ICC Cal) method and a baseline method using traditional brightness, color and noise augmentations. We evaluated the ability of these techniques to improve model generalization to various tasks and settings: four models, two model types (tissue segmentation and cell classification), two loss functions, six labs, six scanners, and three indications (hepatocellular carcinoma (HCC), nonalcoholic steatohepatitis (NASH), prostate adenocarcinoma). We compared these methods based on the macro-averaged F1 scores on in-distribution (ID) and out-of-distribution (OOD) test sets across multiple domains, and found that S-DOTA methods (i.e., ST and SVA) led to significant improvements over ICC Cal and baseline on OOD data while maintaining comparable performance on ID data. Thus, we demonstrate that S-DOTA may help address generalization due to domain shift in real world applications.

Viaarxiv icon

Additive MIL: Intrinsic Interpretability for Pathology

Jun 03, 2022
Syed Ashar Javed, Dinkar Juyal, Harshith Padigela, Amaro Taylor-Weiner, Limin Yu, Aaditya Prakash

Figure 1 for Additive MIL: Intrinsic Interpretability for Pathology
Figure 2 for Additive MIL: Intrinsic Interpretability for Pathology
Figure 3 for Additive MIL: Intrinsic Interpretability for Pathology
Figure 4 for Additive MIL: Intrinsic Interpretability for Pathology

Multiple Instance Learning (MIL) has been widely applied in pathology towards solving critical problems such as automating cancer diagnosis and grading, predicting patient prognosis, and therapy response. Deploying these models in a clinical setting requires careful inspection of these black boxes during development and deployment to identify failures and maintain physician trust. In this work, we propose a simple formulation of MIL models, which enables interpretability while maintaining similar predictive performance. Our Additive MIL models enable spatial credit assignment such that the contribution of each region in the image can be exactly computed and visualized. We show that our spatial credit assignment coincides with regions used by pathologists during diagnosis and improves upon classical attention heatmaps from attention MIL models. We show that any existing MIL model can be made additive with a simple change in function composition. We also show how these models can debug model failures, identify spurious features, and highlight class-wise regions of interest, enabling their use in high-stakes environments such as clinical decision-making.

Viaarxiv icon

Rethinking Machine Learning Model Evaluation in Pathology

Apr 18, 2022
Syed Ashar Javed, Dinkar Juyal, Zahil Shanis, Shreya Chakraborty, Harsha Pokkalla, Aaditya Prakash

Figure 1 for Rethinking Machine Learning Model Evaluation in Pathology
Figure 2 for Rethinking Machine Learning Model Evaluation in Pathology

Machine Learning has been applied to pathology images in research and clinical practice with promising outcomes. However, standard ML models often lack the rigorous evaluation required for clinical decisions. Machine learning techniques for natural images are ill-equipped to deal with pathology images that are significantly large and noisy, require expensive labeling, are hard to interpret, and are susceptible to spurious correlations. We propose a set of practical guidelines for ML evaluation in pathology that address the above concerns. The paper includes measures for setting up the evaluation framework, effectively dealing with variability in labels, and a recommended suite of tests to address issues related to domain shift, robustness, and confounding variables. We hope that the proposed framework will bridge the gap between ML researchers and domain experts, leading to wider adoption of ML techniques in pathology and improving patient outcomes.

* ICLR 2022 ML Evaluation Workshop 
Viaarxiv icon

RePr: Improved Training of Convolutional Filters

Nov 26, 2018
Aaditya Prakash, James Storer, Dinei Florencio, Cha Zhang

Figure 1 for RePr: Improved Training of Convolutional Filters
Figure 2 for RePr: Improved Training of Convolutional Filters
Figure 3 for RePr: Improved Training of Convolutional Filters
Figure 4 for RePr: Improved Training of Convolutional Filters

A well-trained Convolutional Neural Network can easily be pruned without significant loss of performance. This is because of unnecessary overlap in the features captured by the network's filters. Innovations in network architecture such as skip/dense connections and Inception units have mitigated this problem to some extent, but these improvements come with increased computation and memory requirements at run-time. We attempt to address this problem from another angle - not by changing the network structure but by altering the training method. We show that by temporarily pruning and then restoring a subset of the model's filters, and repeating this process cyclically, overlap in the learned features is reduced, producing improved generalization. We show that the existing model-pruning criteria are not optimal for selecting filters to prune in this context and introduce inter-filter orthogonality as the ranking criteria to determine under-expressive filters. Our method is applicable both to vanilla convolutional networks and more complex modern architectures, and improves the performance across a variety of tasks, especially when applied to smaller networks.

Viaarxiv icon

DR-BiLSTM: Dependent Reading Bidirectional LSTM for Natural Language Inference

Apr 11, 2018
Reza Ghaeini, Sadid A. Hasan, Vivek Datla, Joey Liu, Kathy Lee, Ashequl Qadir, Yuan Ling, Aaditya Prakash, Xiaoli Z. Fern, Oladimeji Farri

Figure 1 for DR-BiLSTM: Dependent Reading Bidirectional LSTM for Natural Language Inference
Figure 2 for DR-BiLSTM: Dependent Reading Bidirectional LSTM for Natural Language Inference
Figure 3 for DR-BiLSTM: Dependent Reading Bidirectional LSTM for Natural Language Inference
Figure 4 for DR-BiLSTM: Dependent Reading Bidirectional LSTM for Natural Language Inference

We present a novel deep learning architecture to address the natural language inference (NLI) task. Existing approaches mostly rely on simple reading mechanisms for independent encoding of the premise and hypothesis. Instead, we propose a novel dependent reading bidirectional LSTM network (DR-BiLSTM) to efficiently model the relationship between a premise and a hypothesis during encoding and inference. We also introduce a sophisticated ensemble strategy to combine our proposed models, which noticeably improves final predictions. Finally, we demonstrate how the results can be improved further with an additional preprocessing step. Our evaluation shows that DR-BiLSTM obtains the best single model and ensemble model results achieving the new state-of-the-art scores on the Stanford NLI dataset.

* 18 pages, Accepted as a long paper at NAACL HLT 2018 
Viaarxiv icon

Deflecting Adversarial Attacks with Pixel Deflection

Mar 30, 2018
Aaditya Prakash, Nick Moran, Solomon Garber, Antonella DiLillo, James Storer

Figure 1 for Deflecting Adversarial Attacks with Pixel Deflection
Figure 2 for Deflecting Adversarial Attacks with Pixel Deflection
Figure 3 for Deflecting Adversarial Attacks with Pixel Deflection
Figure 4 for Deflecting Adversarial Attacks with Pixel Deflection

CNNs are poised to become integral parts of many critical systems. Despite their robustness to natural variations, image pixel values can be manipulated, via small, carefully crafted, imperceptible perturbations, to cause a model to misclassify images. We present an algorithm to process an image so that classification accuracy is significantly preserved in the presence of such adversarial manipulations. Image classifiers tend to be robust to natural noise, and adversarial attacks tend to be agnostic to object location. These observations motivate our strategy, which leverages model robustness to defend against adversarial perturbations by forcing the image to match natural image statistics. Our algorithm locally corrupts the image by redistributing pixel values via a process we term pixel deflection. A subsequent wavelet-based denoising operation softens this corruption, as well as some of the adversarial changes. We demonstrate experimentally that the combination of these techniques enables the effective recovery of the true class, against a variety of robust attacks. Our results compare favorably with current state-of-the-art defenses, without requiring retraining or modifying the CNN.

* Accepted to IEEE CVPR 2018 as Spotlight 
Viaarxiv icon