Although pathology of tauopathies is characterized by abnormal tau protein aggregation in both gray and white matter regions of the brain, neuropathological investigations have generally focused on abnormalities in the cerebral cortex because the canonical aggregates that form the diagnostic criteria for these disorders predominate there. This corticocentric focus tends to deemphasize the relevance of the more complex white matter pathologies, which remain less well characterized and understood. We took a data-driven machine-learning approach to identify novel disease-specific morphologic signatures of white matter aggregates in three tauopathies: Alzheimer disease (AD), progressive supranuclear palsy (PSP), and corticobasal degeneration (CBD). We developed automated approaches using whole slide images of tau immunostained sections from 49 human autopsy brains (16 AD,13 CBD, 20 PSP) to identify cortex/white matter regions and individual tau aggregates, and compared tau-aggregate morphology across these diseases. Tau burden in the gray and white matter for individual subjects strongly correlated in a highly disease-specific fashion. We discovered previously unrecognized tau morphologies for AD, CBD and PSP that may be of importance in disease classification. Intriguingly, our models classified diseases equally well based on either white or gray matter tau staining. Our results suggest that tau pathology in white matter is informative, disease-specific, and linked to gray matter pathology. Machine learning has the potential to reveal latent information in histologic images that may represent previously unrecognized patterns of neuropathology, and additional studies of tau pathology in white matter could improve diagnostic accuracy.
Intratumoral heterogeneity arising from tumor evolution poses significant challenges biologically and clinically. Dissecting this complexity may benefit from deep learning (DL) algorithms, which can infer molecular features from ubiquitous hematoxylin and eosin (H&E)–stained tissue sections. Although DL algorithms have been developed to predict some driver mutations from H&E images, the ability of these DL algorithms to resolve intratumoral mutation heterogeneity at subclonal spatial resolution is unexplored. Here, we apply DL to a paradigm of intratumoral heterogeneity, clear cell renal cell carcinoma (ccRCC), the most common type of kidney cancer. Matched IHC and H&E images were leveraged to develop DL models for predicting intratumoral genetic heterogeneity of the three most frequently mutated ccRCC genes, BAP1, PBRM1, and SETD2. DL models were generated on a large cohort (N = 1,282) and tested on several independent cohorts, including a TCGA cohort (N = 363 patients) and two tissue microarray (TMA) cohorts (N = 118 and 365 patients). These models were also expanded to a patient-derived xenograft (PDX) TMA, affording analysis of homotopic and heterotopic interactions of tumor and stroma. The status of all three genes could be inferred by DL, with BAP1 showing the highest sensitivity and performance within and across tissue samples (AUC = 0.87–0.89 on holdout). BAP1 results were validated on independent human (AUC = 0.77–0.84) and PDX (AUC = 0.80) cohorts. Finally, BAP1 predictions correlated with clinical outputs such as disease-specific survival. Overall, these data show that DL models can resolve intratumoral heterogeneity in cancer with potential diagnostic, prognostic, and biological implications. Significance: This work demonstrates the potential for deep learning analysis of histopathologic images to serve as a fast, low-cost method to assess genetic intratumoral heterogeneity. See related commentary by Song et al., p. 2672
<div>Abstract<p>Intratumoral heterogeneity arising from tumor evolution poses significant challenges biologically and clinically. Dissecting this complexity may benefit from deep learning (DL) algorithms, which can infer molecular features from ubiquitous hematoxylin and eosin (H&E)–stained tissue sections. Although DL algorithms have been developed to predict some driver mutations from H&E images, the ability of these DL algorithms to resolve intratumoral mutation heterogeneity at subclonal spatial resolution is unexplored. Here, we apply DL to a paradigm of intratumoral heterogeneity, clear cell renal cell carcinoma (ccRCC), the most common type of kidney cancer. Matched IHC and H&E images were leveraged to develop DL models for predicting intratumoral genetic heterogeneity of the three most frequently mutated ccRCC genes, <i>BAP1, PBRM1</i>, and <i>SETD2</i>. DL models were generated on a large cohort (<i>N</i> = 1,282) and tested on several independent cohorts, including a TCGA cohort (<i>N</i> = 363 patients) and two tissue microarray (TMA) cohorts (<i>N</i> = 118 and 365 patients). These models were also expanded to a patient-derived xenograft (PDX) TMA, affording analysis of homotopic and heterotopic interactions of tumor and stroma. The status of all three genes could be inferred by DL, with <i>BAP1</i> showing the highest sensitivity and performance within and across tissue samples (AUC = 0.87–0.89 on holdout). <i>BAP1</i> results were validated on independent human (AUC = 0.77–0.84) and PDX (AUC = 0.80) cohorts. Finally, <i>BAP1</i> predictions correlated with clinical outputs such as disease-specific survival. Overall, these data show that DL models can resolve intratumoral heterogeneity in cancer with potential diagnostic, prognostic, and biological implications.</p>Significance:<p>This work demonstrates the potential for deep learning analysis of histopathologic images to serve as a fast, low-cost method to assess genetic intratumoral heterogeneity.</p><p><i><a href="https://aacrjournals.org/cancerres/article/doi/10.1158/0008-5472.CAN-22-2040" target="_blank">See related commentary by Song et al., p. 2672</a></i></p></div>
<div>Abstract<p>Intratumoral heterogeneity arising from tumor evolution poses significant challenges biologically and clinically. Dissecting this complexity may benefit from deep learning (DL) algorithms, which can infer molecular features from ubiquitous hematoxylin and eosin (H&E)–stained tissue sections. Although DL algorithms have been developed to predict some driver mutations from H&E images, the ability of these DL algorithms to resolve intratumoral mutation heterogeneity at subclonal spatial resolution is unexplored. Here, we apply DL to a paradigm of intratumoral heterogeneity, clear cell renal cell carcinoma (ccRCC), the most common type of kidney cancer. Matched IHC and H&E images were leveraged to develop DL models for predicting intratumoral genetic heterogeneity of the three most frequently mutated ccRCC genes, <i>BAP1, PBRM1</i>, and <i>SETD2</i>. DL models were generated on a large cohort (<i>N</i> = 1,282) and tested on several independent cohorts, including a TCGA cohort (<i>N</i> = 363 patients) and two tissue microarray (TMA) cohorts (<i>N</i> = 118 and 365 patients). These models were also expanded to a patient-derived xenograft (PDX) TMA, affording analysis of homotopic and heterotopic interactions of tumor and stroma. The status of all three genes could be inferred by DL, with <i>BAP1</i> showing the highest sensitivity and performance within and across tissue samples (AUC = 0.87–0.89 on holdout). <i>BAP1</i> results were validated on independent human (AUC = 0.77–0.84) and PDX (AUC = 0.80) cohorts. Finally, <i>BAP1</i> predictions correlated with clinical outputs such as disease-specific survival. Overall, these data show that DL models can resolve intratumoral heterogeneity in cancer with potential diagnostic, prognostic, and biological implications.</p>Significance:<p>This work demonstrates the potential for deep learning analysis of histopathologic images to serve as a fast, low-cost method to assess genetic intratumoral heterogeneity.</p><p><i><a href="https://aacrjournals.org/cancerres/article/doi/10.1158/0008-5472.CAN-22-2040" target="_blank">See related commentary by Song et al., p. 2672</a></i></p></div>
Supplementary Figure from Intratumoral Resolution of Driver Gene Mutation Heterogeneity in Renal Cancer Using Deep Learning
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.