Search

Recent advances in artificial intelligence (AI), in particular self-supervised learning of foundation models (FMs), are revolutionizing medical imaging and computational pathology (CPath). A constant challenge in the analysis of digital Whole Slide Images (WSIs) is the problem of aggregating tens of thousands of tile-level image embeddings to a slide-level representation. Due to the prevalent use of datasets created for genomic research, such as TCGA, for method development, the performance of these techniques on diagnostic slides from clinical practice has been inadequately explored. This study conducts a thorough benchmarking analysis of ten slide-level aggregation techniques across nine clinically relevant tasks, including diagnostic assessment, biomarker classification, and outcome prediction. The results yield following key insights: (1) Embeddings derived from domain-specific (histological images) FMs outperform those from generic ImageNet-based models across aggregation methods. (2) Spatial-aware aggregators enhance the performance significantly when using ImageNet pre-trained models but not when using FMs. (3) No single model excels in all tasks and spatially-aware models do not show general superiority as it would be expected. These findings underscore the need for more adaptable and universally applicable aggregation techniques, guiding future research towards tools that better meet the evolving needs of clinical-AI in pathology. The code used in this work is available at \url{https://github.com/fuchs-lab-public/CPath_SABenchmark}., Comment: 10 pages, 2 figures

Foundation models in computational pathology promise to unlock the development of new clinical decision support systems and models for precision medicine. However, there is a mismatch between most clinical analysis, which is defined at the level of one or more whole slide images, and foundation models to date, which process the thousands of image tiles contained in a whole slide image separately. The requirement to train a network to aggregate information across a large number of tiles in multiple whole slide images limits these models' impact. In this work, we present a slide-level foundation model for H&E-stained histopathology, PRISM, that builds on Virchow tile embeddings and leverages clinical report text for pre-training. Using the tile embeddings, PRISM produces slide-level embeddings with the ability to generate clinical reports, resulting in several modes of use. Using text prompts, PRISM achieves zero-shot cancer detection and sub-typing performance approaching and surpassing that of a supervised aggregator model. Using the slide embeddings with linear classifiers, PRISM surpasses supervised aggregator models. Furthermore, we demonstrate that fine-tuning of the PRISM slide encoder yields label-efficient training for biomarker prediction, a task that typically suffers from low availability of training data; an aggregator initialized with PRISM and trained on as little as 10% of the training data can outperform a supervised baseline that uses all of the data.

Artificial Intelligence (AI) has great potential to improve health outcomes by training systems on vast digitized clinical datasets. Computational Pathology, with its massive amounts of microscopy image data and impact on diagnostics and biomarkers, is at the forefront of this development. Gigapixel pathology slides pose a unique challenge due to their enormous size and are usually divided into tens of thousands of smaller tiles for analysis. This results in a discontinuity in the machine learning process by separating the training of tile-level encoders from slide-level aggregators and the need to adopt weakly supervised learning strategies. Training models from entire pathology slides end-to-end has been largely unexplored due to its computational challenges. To overcome this problem, we propose a novel approach to jointly train both a tile encoder and a slide-aggregator fully in memory and end-to-end at high-resolution, bridging the gap between input and slide-level supervision. While more computationally expensive, detailed quantitative validation shows promise for large-scale pre-training and fine-tuning of pathology foundation models.

Clinical note classification is a common clinical NLP task. However, annotated data-sets are scarse. Prompt-based learning has recently emerged as an effective method to adapt pre-trained models for text classification using only few training examples. A critical component of prompt design is the definition of the template (i.e. prompt text). The effect of template position, however, has been insufficiently investigated. This seems particularly important in the clinical setting, where task-relevant information is usually sparse in clinical notes. In this study we develop a keyword-optimized template insertion method (KOTI) and show how optimizing position can improve performance on several clinical tasks in a zero-shot and few-shot training setting.

Recent breakthroughs in self-supervised learning have enabled the use of large unlabeled datasets to train visual foundation models that can generalize to a variety of downstream tasks. While this training paradigm is well suited for the medical domain where annotations are scarce, large-scale pre-training in the medical domain, and in particular pathology, has not been extensively studied. Previous work in self-supervised learning in pathology has leveraged smaller datasets for both pre-training and evaluating downstream performance. The aim of this project is to train the largest academic foundation model and benchmark the most prominent self-supervised learning algorithms by pre-training and evaluating downstream performance on large clinical pathology datasets. We collected the largest pathology dataset to date, consisting of over 3 billion images from over 423 thousand microscopy slides. We compared pre-training of visual transformer models using the masked autoencoder (MAE) and DINO algorithms. We evaluated performance on six clinically relevant tasks from three anatomic sites and two institutions: breast cancer detection, inflammatory bowel disease detection, breast cancer estrogen receptor prediction, lung adenocarcinoma EGFR mutation prediction, and lung cancer immunotherapy response prediction. Our results demonstrate that pre-training on pathology data is beneficial for downstream performance compared to pre-training on natural images. Additionally, the DINO algorithm achieved better generalization performance across all tasks tested. The presented results signify a phase change in computational pathology research, paving the way into a new era of more performant models based on large-scale, parallel pre-training at the billion-image scale.

The use of artificial intelligence to enable precision medicine and decision support systems through the analysis of pathology images has the potential to revolutionize the diagnosis and treatment of cancer. Such applications will depend on models' abilities to capture the diverse patterns observed in pathology images. To address this challenge, we present Virchow, a foundation model for computational pathology. Using self-supervised learning empowered by the DINOv2 algorithm, Virchow is a vision transformer model with 632 million parameters trained on 1.5 million hematoxylin and eosin stained whole slide images from diverse tissue and specimen types, which is orders of magnitude more data than previous works. The Virchow model enables the development of a pan-cancer detection system with 0.949 overall specimen-level AUC across 17 different cancer types, while also achieving 0.937 AUC on 7 rare cancer types. The Virchow model sets the state-of-the-art on the internal and external image tile level benchmarks and slide level biomarker prediction tasks. The gains in performance highlight the importance of training on massive pathology image datasets, suggesting scaling up the data and network architecture can improve the accuracy for many high-impact computational pathology applications where limited amounts of training data are available.

An every increasing number of clinical trials features a time-to-event outcome and records non-tabular patient data, such as magnetic resonance imaging or text data in the form of electronic health records. Recently, several neural-network based solutions have been proposed, some of which are binary classifiers. Parametric, distribution-free approaches which make full use of survival time and censoring status have not received much attention. We present deep conditional transformation models (DCTMs) for survival outcomes as a unifying approach to parametric and semiparametric survival analysis. DCTMs allow the specification of non-linear and non-proportional hazards for both tabular and non-tabular data and extend to all types of censoring and truncation. On real and semi-synthetic data, we show that DCTMs compete with state-of-the-art DL approaches to survival analysis.

Osteosarcoma is the most common primary bone cancer whose standard treatment includes pre-operative chemotherapy followed by resection. Chemotherapy response is used for predicting prognosis and further management of patients. Necrosis is routinely assessed post-chemotherapy from histology slides on resection specimens where necrosis ratio is defined as the ratio of necrotic tumor to overall tumor. Patients with necrosis ratio >=90% are known to have better outcome. Manual microscopic review of necrosis ratio from multiple glass slides is semi-quantitative and can have intra- and inter-observer variability. We propose an objective and reproducible deep learning-based approach to estimate necrosis ratio with outcome prediction from scanned hematoxylin and eosin whole slide images. We collected 103 osteosarcoma cases with 3134 WSIs to train our deep learning model, to validate necrosis ratio assessment, and to evaluate outcome prediction. We trained Deep Multi-Magnification Network to segment multiple tissue subtypes including viable tumor and necrotic tumor in pixel-level and to calculate case-level necrosis ratio from multiple WSIs. We showed necrosis ratio estimated by our segmentation model highly correlates with necrosis ratio from pathology reports manually assessed by experts where mean absolute differences for Grades IV (100%), III (>=90%), and II (>=50% and <90%) necrosis response are 4.4%, 4.5%, and 17.8%, respectively. We successfully stratified patients to predict overall survival with p=10^-6 and progression-free survival with p=0.012. Our reproducible approach without variability enabled us to tune cutoff thresholds, specifically for our model and our data set, to 80% for OS and 60% for PFS. Our study indicates deep learning can support pathologists as an objective tool to analyze osteosarcoma from histology for assessing treatment response and predicting patient outcome.

Lung cancer is the leading cause of cancer death worldwide, with lung adenocarcinoma being the most prevalent form of lung cancer. EGFR positive lung adenocarcinomas have been shown to have high response rates to TKI therapy, underlying the essential nature of molecular testing for lung cancers. Despite current guidelines consider testing necessary, a large portion of patients are not routinely profiled, resulting in millions of people not receiving the optimal treatment for their lung cancer. Sequencing is the gold standard for molecular testing of EGFR mutations, but it can take several weeks for results to come back, which is not ideal in a time constrained scenario. The development of alternative screening tools capable of detecting EGFR mutations quickly and cheaply while preserving tissue for sequencing could help reduce the amount of sub-optimally treated patients. We propose a multi-modal approach which integrates pathology images and clinical variables to predict EGFR mutational status achieving an AUC of 84% on the largest clinical cohort to date. Such a computational model could be deployed at large at little additional cost. Its clinical application could reduce the number of patients who receive sub-optimal treatments by 53.1% in China, and up to 96.6% in the US.

AIMS: Clinical radiographic imaging is seated upon the principle of differential keV photon transmission through an object. At clinical x-ray energies the scattering of photons causes signal noise and is utilized solely for transmission measurements. However, scatter - particularly Compton scatter, is characterizable. In this work we hypothesized that modern radiation sources and detectors paired with deep learning techniques can use scattered photon information constructively to resolve superimposed attenuators in planar x-ray imaging. METHODS: We simulated a monoenergetic x-ray imaging system consisting of a pencil beam x-ray source directed at an imaging target positioned in front of a high spatial- and energy-resolution detector array. The signal was analyzed by a convolutional neural network, and a description of scattering material along the axis of the beam was derived. The system was virtually designed/tested using Monte Carlo processing of simple phantoms consisting of 10 pseudo-randomly stacked air/bone/water materials, and the network was trained by solving a classification problem. RESULTS: The average accuracy of the material identification along the beam was 0.91 +- 0.01, with slightly higher accuracy towards the entrance/exit peripheral surfaces of the object. The average sensitivity and specificity was 0.91 and 0.95, respectively. CONCLUSIONS: Our work provides proof of principle that deep learning techniques can be used to analyze scattered photon patterns which can constructively contribute to the information content in radiography, here used to infer depth information in a traditional 2D planar setup. This principle, and our results, demonstrate that the information in Compton scattered photons may provide a basis for further development. The ability to scale performance to the clinic remains unexplored and requires further study., Comment: 10 pages, 6 figures. To be published in Journal of Instrumentation

Deep learning has been widely used to analyze digitized hematoxylin and eosin (H&E)-stained histopathology whole slide images. Automated cancer segmentation using deep learning can be used to diagnose malignancy and to find novel morphological patterns to predict molecular subtypes. To train pixel-wise cancer segmentation models, manual annotation from pathologists is generally a bottleneck due to its time-consuming nature. In this paper, we propose Deep Interactive Learning with a pretrained segmentation model from a different cancer type to reduce manual annotation time. Instead of annotating all pixels from cancer and non-cancer regions on giga-pixel whole slide images, an iterative process of annotating mislabeled regions from a segmentation model and training/finetuning the model with the additional annotation can reduce the time. Especially, employing a pretrained segmentation model can further reduce the time than starting annotation from scratch. We trained an accurate ovarian cancer segmentation model with a pretrained breast segmentation model by 3.5 hours of manual annotation which achieved intersection-over-union of 0.74, recall of 0.86, and precision of 0.84. With automatically extracted high-grade serous ovarian cancer patches, we attempted to train another deep learning model to predict BRCA mutation. The segmentation model and code have been released at https://github.com/MSKCC-Computational-Pathology/DMMN-ovary.

Histopathology-based survival modelling has two major hurdles. Firstly, a well-performing survival model has minimal clinical application if it does not contribute to the stratification of a cancer patient cohort into different risk groups, preferably driven by histologic morphologies. In the clinical setting, individuals are not given specific prognostic predictions, but are rather predicted to lie within a risk group which has a general survival trend. Thus, It is imperative that a survival model produces well-stratified risk groups. Secondly, until now, survival modelling was done in a two-stage approach (encoding and aggregation). The massive amount of pixels in digitized whole slide images were never utilized to their fullest extent due to technological constraints on data processing, forcing decoupled learning. EPIC-Survival bridges encoding and aggregation into an end-to-end survival modelling approach, while introducing stratification boosting to encourage the model to not only optimize ranking, but also to discriminate between risk groups. In this study we show that EPIC-Survival performs better than other approaches in modelling intrahepatic cholangiocarcinoma, a historically difficult cancer to model. Further, we show that stratification boosting improves further improves model performance, resulting in a concordance-index of 0.880 on a held-out test set. Finally, we were able to identify specific histologic differences, not commonly sought out in ICC, between low and high risk groups., Comment: co-first authors: Hassan Muhammad and Chensu Xie

Osteosarcoma is the most common malignant primary bone tumor. Standard treatment includes pre-operative chemotherapy followed by surgical resection. The response to treatment as measured by ratio of necrotic tumor area to overall tumor area is a known prognostic factor for overall survival. This assessment is currently done manually by pathologists by looking at glass slides under the microscope which may not be reproducible due to its subjective nature. Convolutional neural networks (CNNs) can be used for automated segmentation of viable and necrotic tumor on osteosarcoma whole slide images. One bottleneck for supervised learning is that large amounts of accurate annotations are required for training which is a time-consuming and expensive process. In this paper, we describe Deep Interactive Learning (DIaL) as an efficient labeling approach for training CNNs. After an initial labeling step is done, annotators only need to correct mislabeled regions from previous segmentation predictions to improve the CNN model until the satisfactory predictions are achieved. Our experiments show that our CNN model trained by only 7 hours of annotation using DIaL can successfully estimate ratios of necrosis within expected inter-observer variation rate for non-standardized manual surgical pathology task., Comment: Accepted at MICCAI 2020

Pathologic analysis of surgical excision specimens for breast carcinoma is important to evaluate the completeness of surgical excision and has implications for future treatment. This analysis is performed manually by pathologists reviewing histologic slides prepared from formalin-fixed tissue. In this paper, we present Deep Multi-Magnification Network trained by partial annotation for automated multi-class tissue segmentation by a set of patches from multiple magnifications in digitized whole slide images. Our proposed architecture with multi-encoder, multi-decoder, and multi-concatenation outperforms other single and multi-magnification-based architectures by achieving the highest mean intersection-over-union, and can be used to facilitate pathologists' assessments of breast cancer., Comment: Accepted at Computerized Medical Imaging and Graphics

Unlike common cancers, such as those of the prostate and breast, tumor grading in rare cancers is difficult and largely undefined because of small sample sizes, the sheer volume of time needed to undertake on such a task, and the inherent difficulty of extracting human-observed patterns. One of the most challenging examples is intrahepatic cholangiocarcinoma (ICC), a primary liver cancer arising from the biliary system, for which there is well-recognized tumor heterogeneity and no grading paradigm or prognostic biomarkers. In this paper, we propose a new unsupervised deep convolutional autoencoder-based clustering model that groups together cellular and structural morphologies of tumor in 246 ICC digitized whole slides, based on visual similarity. From this visual dictionary of histologic patterns, we use the clusters as covariates to train Cox-proportional hazard survival models. In univariate analysis, three clusters were significantly associated with recurrence-free survival. Combinations of these clusters were significant in multivariate analysis. In a multivariate analysis of all clusters, five showed significance to recurrence-free survival, however the overall model was not measured to be significant. Finally, a pathologist assigned clinical terminology to the significant clusters in the visual dictionary and found evidence supporting the hypothesis that collagen-enriched fibrosis plays a role in disease severity. These results offer insight into the future of cancer subtyping and show that computational pathology can contribute to disease prognostication, especially in rare cancers., Comment: 10 pages, 6 figures

In the field of computational pathology, the use of decision support systems powered by state-of-the-art deep learning solutions has been hampered by the lack of large labeled datasets. Until recently, studies relied on datasets in the order of few hundreds of slides which are not enough to train a model that can work at scale in the clinic. Here, we have gathered a dataset consisting of 12,160 slides, two orders of magnitude larger than previous datasets in pathology and equivalent to 25 times the pixel count of the entire ImageNet dataset. Given the size of our dataset it is possible for us to train a deep learning model under the Multiple Instance Learning (MIL) assumption where only the overall slide diagnosis is necessary for training, avoiding all the expensive pixel-wise annotations that are usually part of supervised learning approaches. We test our framework on a complex task, that of prostate cancer diagnosis on needle biopsies. We performed a thorough evaluation of the performance of our MIL pipeline under several conditions achieving an AUC of 0.98 on a held-out test set of 1,824 slides. These results open the way for training accurate diagnosis prediction models at scale, laying the foundation for decision support system deployment in the clinic.

Positron emission tomography (PET) is a cornerstone of modern radiology. The ability to detect cancer and metastases in whole body scans fundamentally changed cancer diagnosis and treatment. One of the main bottlenecks in the clinical application is the time it takes to reconstruct the anatomical image from the deluge of data in PET imaging. State-of-the art methods based on expectation maximization can take hours for a single patient and depend on manual fine-tuning. This results not only in financial burden for hospitals but more importantly leads to less efficient patient handling, evaluation, and ultimately diagnosis and treatment for patients. To overcome this problem we present a novel PET image reconstruction technique based on a deep convolutional encoder-decoder network, that takes PET sinogram data as input and directly outputs full PET images. Using realistic simulated data, we demonstrate that our network is able to reconstruct images >100 times faster, and with comparable image quality (in terms of root mean squared error) relative to conventional iterative reconstruction techniques.

Accurate subtyping of renal cell carcinoma (RCC) is of crucial importance for understanding disease progression and for making informed treatment decisions. New discoveries of significant alterations to mitochondria between subtypes make immunohistochemical (IHC) staining based image classification an imperative. Until now, accurate quantification and subtyping was made impossible by huge IHC variations, the absence of cell membrane staining for cytoplasm segmentation as well as the complete lack of systems for robust and reproducible image based classification. In this paper we present a comprehensive classification framework to overcome these challenges for tissue microarrays (TMA) of RCCs. We compare and evaluate models based on domain specific hand-crafted "flat"-features versus "deep" feature representations from various layers of a pre-trained convolutional neural network (CNN). The best model reaches a cross-validation accuracy of 89%, which demonstrates for the first time, that robust mitochondria-based subtyping of renal cancer is feasible, Comment: Presented at 2016 Machine Learning and Healthcare Conference (MLHC 2016), Los Angeles, CA

The histological assessment of human tissue has emerged as the key challenge for detection and treatment of cancer. A plethora of different data sources ranging from tissue microarray data to gene expression, proteomics or metabolomics data provide a detailed overview of the health status of a patient. Medical doctors need to assess these information sources and they rely on data driven automatic analysis tools. Methods for classification, grouping and segmentation of heterogeneous data sources as well as regression of noisy dependencies and estimation of survival probabilities enter the processing workflow of a pathology diagnosis system at various stages. This paper reports on state-of-the-art of the design and effectiveness of computational pathology workflows and it discusses future research directions in this emergent field of medical informatics and diagnostic machine learning.

Deep Convolutional Neural Networks (CNNs) have demonstrated excellent performance in image classification, but still show room for improvement in object-detection tasks with many categories, in particular for cluttered scenes and occlusion. Modern detection algorithms like Regions with CNNs (Girshick et al., 2014) rely on Selective Search (Uijlings et al., 2013) to propose regions which with high probability represent objects, where in turn CNNs are deployed for classification. Selective Search represents a family of sophisticated algorithms that are engineered with multiple segmentation, appearance and saliency cues, typically coming with a significant run-time overhead. Furthermore, (Hosang et al., 2014) have shown that most methods suffer from low reproducibility due to unstable superpixels, even for slight image perturbations. Although CNNs are subsequently used for classification in top-performing object-detection pipelines, current proposal methods are agnostic to how these models parse objects and their rich learned representations. As a result they may propose regions which may not resemble high-level objects or totally miss some of them. To overcome these drawbacks we propose a boosting approach which directly takes advantage of hierarchical CNN features for detecting regions of interest fast. We demonstrate its performance on ImageNet 2013 detection benchmark and compare it with state-of-the-art methods., Comment: 9 pages, 4 figures, 2 tables, 42 references

In this paper, we propose a methodology for early recognition of human activities from videos taken with a first-person viewpoint. Early recognition, which is also known as activity prediction, is an ability to infer an ongoing activity at its early stage. We present an algorithm to perform recognition of activities targeted at the camera from streaming videos, making the system to predict intended activities of the interacting person and avoid harmful events before they actually happen. We introduce the novel concept of 'onset' that efficiently summarizes pre-activity observations, and design an approach to consider event history in addition to ongoing video observation for early first-person recognition of activities. We propose to represent onset using cascade histograms of time series gradients, and we describe a novel algorithmic setup to take advantage of onset for early recognition of activities. The experimental results clearly illustrate that the proposed concept of onset enables better/earlier recognition of human activities from first-person videos.

The amount of collected data in many scientific fields is increasing, all of them requiring a common task: extract knowledge from massive, multi parametric data sets, as rapidly and efficiently possible. This is especially true in astronomy where synoptic sky surveys are enabling new research frontiers in the time domain astronomy and posing several new object classification challenges in multi dimensional spaces; given the high number of parameters available for each object, feature selection is quickly becoming a crucial task in analyzing astronomical data sets. Using data sets extracted from the ongoing Catalina Real-Time Transient Surveys (CRTS) and the Kepler Mission we illustrate a variety of feature selection strategies used to identify the subsets that give the most information and the results achieved applying these techniques to three major astronomical problems., Comment: 7 pages, to appear in refereed proceedings of Scalable Machine Learning: Theory and Applications, IEEE BigData 2013