Robust deep learning model for prognostic stratification of pancreatic ductal adenocarcinoma patients

Histology-Based Radiomics for [18F]FDG PET Identifies Tissue Heterogeneity in Pancreatic Cancer

Radiomics features can reveal hidden patterns in a tumor but usually lack an underlying biologic rationale. In this work, we aimed to investigate whether there is a correlation between radiomics features extracted from [18F]FDG PET images and histologic expression patterns of a glycolytic marker, monocarboxylate transporter-4 (MCT4), in pancreatic cancer. Methods: A cohort of pancreatic ductal adenocarcinoma patients (n = 29) for whom both tumor cross sections and [18F]FDG PET/CT scans were available was used to develop an [18F]FDG PET radiomics signature. By using immunohistochemistry for MCT4, we computed density maps of MCT4 expression and extracted pathomics features. Cluster analysis identified 2 subgroups with distinct MCT4 expression patterns. From corresponding [18F]FDG PET scans, radiomics features that associate with the predefined MCT4 subgroups were identified. Results: Complex heat map visualization showed that the MCT4-high/heterogeneous subgroup was correlating with a higher MCT4 expression level and local variation. This pattern linked to a specific [18F]FDG PET signature, characterized by a higher SUVmean and SUVmax and second-order radiomics features, correlating with local variation. This MCT4-based [18F]FDG PET signature of 7 radiomics features demonstrated prognostic value in an independent cohort of pancreatic cancer patients (n = 71) and identified patients with worse survival. Conclusion: Our cross-modal pipeline allows the development of PET scan signatures based on immunohistochemical analysis of markers of a particular biologic feature, here demonstrated on pancreatic cancer using intratumoral MCT4 expression levels to select [18F]FDG PET radiomics features. This study demonstrated the potential of radiomics scores to noninvasively capture intratumoral marker heterogeneity and identify a subset of pancreatic ductal adenocarcinoma patients with a poor prognosis.

BEYOND TRADITIONAL TOOLS: EXPLORING CONVOLUTIONAL NEURAL NETWORKS AS INNOVATIVE PROGNOSTIC MODELS IN PANCREATIC DUCTAL ADENOCARCINOMA

BACKGROUND

Pancreatic ductal adenocarcinoma (PDAC) is a highly aggressive and lethal form of cancer with limited prognostic accuracy using traditional factors. This has led to the exploration of innovative prognostic models, including convolutional neural networks (CNNs), in PDAC. CNNs, a type of artificial intelligence algorithm, have shown promise in various medical applications, including image analysis and pattern recognition. Their ability to extract complex features from medical images makes them suitable for improving prognostication in PDAC. However, implementing CNNs in clinical practice poses challenges, such as data availability and interpretability. Future research should focus on multi-center studies, integrating multiple data modalities, and combining CNN outputs with biomarker panels. Collaborative efforts and patient autonomy should be considered to ensure the ethical implementation of CNN-based prognostic models. Further validation and optimisation of CNN-based models are necessary to enhance their reliability and clinical utility in PDAC prognostication.

BACKGROUND

•Pancreatic ductal adenocarcinoma (PDAC) is an aggressive cancer with limited prognostic accuracy through traditional methods.

BACKGROUND

•Convolutional neural networks (CNNs) are being explored for prognostic models in PDAC.

BACKGROUND

•They can extract complex features from images, aiding PDAC prognostication.

BACKGROUND

•Further validation and optimization of CNN-based models are needed for better reliability and clinical utility in PDAC.

Mutation-Attention (MuAt): deep representation learning of somatic mutations for tumour typing and subtyping

BACKGROUND

Cancer genome sequencing enables accurate classification of tumours and tumour subtypes. However, prediction performance is still limited using exome-only sequencing and for tumour types with low somatic mutation burden such as many paediatric tumours. Moreover, the ability to leverage deep representation learning in discovery of tumour entities remains unknown.

METHODS

We introduce here Mutation-Attention (MuAt), a deep neural network to learn representations of simple and complex somatic alterations for prediction of tumour types and subtypes. In contrast to many previous methods, MuAt utilizes the attention mechanism on individual mutations instead of aggregated mutation counts.

RESULTS

We trained MuAt models on 2587 whole cancer genomes (24 tumour types) from the Pan-Cancer Analysis of Whole Genomes (PCAWG) and 7352 cancer exomes (20 types) from the Cancer Genome Atlas (TCGA). MuAt achieved prediction accuracy of 89% for whole genomes and 64% for whole exomes, and a top-5 accuracy of 97% and 90%, respectively. MuAt models were found to be well-calibrated and perform well in three independent whole cancer genome cohorts with 10,361 tumours in total. We show MuAt to be able to learn clinically and biologically relevant tumour entities including acral melanoma, SHH-activated medulloblastoma, SPOP-associated prostate cancer, microsatellite instability, POLE proofreading deficiency, and MUTYH-associated pancreatic endocrine tumours without these tumour subtypes and subgroups being provided as training labels. Finally, scrunity of MuAt attention matrices revealed both ubiquitous and tumour-type specific patterns of simple and complex somatic mutations.

CONCLUSIONS

Integrated representations of somatic alterations learnt by MuAt were able to accurately identify histological tumour types and identify tumour entities, with potential to impact precision cancer medicine.

Contrastive learning-based computational histopathology predict differential expression of cancer driver genes

MOTIVATION

Digital pathological analysis is run as the main examination used for cancer diagnosis. Recently, deep learning-driven feature extraction from pathology images is able to detect genetic variations and tumor environment, but few studies focus on differential gene expression in tumor cells.

RESULTS

In this paper, we propose a self-supervised contrastive learning framework, HistCode, to infer differential gene expression from whole slide images (WSIs). We leveraged contrastive learning on large-scale unannotated WSIs to derive slide-level histopathological features in latent space, and then transfer it to tumor diagnosis and prediction of differentially expressed cancer driver genes. Our experiments showed that our method outperformed other state-of-the-art models in tumor diagnosis tasks, and also effectively predicted differential gene expression. Interestingly, we found the genes with higher fold change can be more precisely predicted. To intuitively illustrate the ability to extract informative features from pathological images, we spatially visualized the WSIs colored by the attention scores of image tiles. We found that the tumor and necrosis areas were highly consistent with the annotations of experienced pathologists. Moreover, the spatial heatmap generated by lymphocyte-specific gene expression patterns was also consistent with the manually labeled WSIs.