Facts and Hopes on the Use of Artificial Intelligence for Predictive Immunotherapy Biomarkers in Cancer

Deep feature batch correction using ComBat for machine learning applications in computational pathology

Background

Developing artificial intelligence (AI) models for digital pathology requires large datasets from multiple sources. However, without careful implementation, AI models risk learning confounding site-specific features in datasets instead of clinically relevant information, leading to overestimated performance, poor generalizability to real-world data, and potential misdiagnosis.

Methods

Whole-slide images (WSIs) from The Cancer Genome Atlas (TCGA) colon (COAD), and stomach adenocarcinoma datasets were selected for inclusion in this study. Patch embeddings were obtained using three feature extraction models, followed by ComBat harmonization. Attention-based multiple instance learning models were trained to predict tissue-source site (TSS), as well as clinical and genetic attributes, using raw, Macenko normalized, and Combat-harmonized patch embeddings.

Results

TSS prediction achieved high accuracy (AUROC > 0.95) with all three feature extraction models. ComBat harmonization significantly reduced the AUROC for TSS prediction, with mean AUROCs dropping to approximately 0.5 for most models, indicating successful mitigation of batch effects (e.g., CCL-ResNet50 in TCGA-COAD: Pre-ComBat AUROC = 0.960, Post-ComBat AUROC = 0.506, p < 0.001). Clinical attributes associated with TSS, such as race and treatment response, showed decreased predictability post-harmonization. Notably, the prediction of genetic features like MSI status remained robust after harmonization (e.g., MSI in TCGA-COAD: Pre-ComBat AUROC = 0.667, Post-ComBat AUROC = 0.669, p=0.952), indicating the preservation of true histological signals.

Conclusion

ComBat harmonization of deep learning-derived histology features effectively reduces the risk of AI models learning confounding features in WSIs, ensuring more reliable performance estimates. This approach is promising for the integration of large-scale digital pathology datasets.

Peripheral blood immune parameters, response, and adverse events after neoadjuvant chemotherapy plus durvalumab in early-stage triple-negative breast cancer

PURPOSE

We evaluated T- and B-cell receptor (TCR and BCR) repertoire diversity and 38 serum cytokines in pre- and post-treatment peripheral blood of 66 patients with triple-negative breast cancer (TNBC) who received neoadjuvant chemotherapy plus durvalumab and assessed associations with pathologic response and immune-related adverse events (irAEs) during treatment.

METHODS

Genomic DNA was isolated from buffy coat for TCR and BCR clonotype profiling using the Immunoseq platform and diversity was quantified with Pielou's evenness index. MILLIPLEX MAP Human Cytokine/Chemokine Magnetic Bead Panel was used to measure serum cytokine levels, which were compared between groups using moderated t-statistic with Benjamini-Hochberg correction for multiple testing.

RESULTS

TCR and BCR diversity was high (Pielou's index > 0.75) in all samples. Baseline receptor diversities and change in diversity pre- and post-treatment were not associated with pathologic response or irAE status, except for BCR diversity that was significantly lower post-treatment in patients who developed irAE (unadjusted p = 0.0321). Five cytokines increased after treatment in patients with pathologic complete response (pCR) but decreased in patients with RD, most prominently IL-8. IFNγ, IL-7, and GM-CSF levels were higher in pre-treatment than in post-treatment samples of patients who developed irAEs but were lower in those without irAEs.

CONCLUSION

Baseline peripheral blood cytokine levels may predict irAEs in patients treated with immune checkpoint inhibitors and chemotherapy, and increased post-treatment B-cell clonal expansion might mediate irAEs.

Ten challenges and opportunities in computational immuno-oncology

Immuno-oncology has transformed the treatment of cancer, with several immunotherapies becoming the standard treatment across histologies. Despite these advancements, the majority of patients do not experience durable clinical benefits, highlighting the imperative for ongoing advancement in immuno-oncology. Computational immuno-oncology emerges as a forefront discipline that draws on biomedical data science and intersects with oncology, immunology, and clinical research, with the overarching goal to accelerate the development of effective and safe immuno-oncology treatments from the laboratory to the clinic. In this review, we outline 10 critical challenges and opportunities in computational immuno-oncology, emphasizing the importance of robust computational strategies and interdisciplinary collaborations amid the constantly evolving interplay between clinical needs and technological innovation.

Assessment of PD-L1 expression and tumour infiltrating lymphocytes in early-stage non-small cell lung carcinoma with artificial intelligence algorithms

AIMS

To study programmed death ligand 1 (PD-L1) expression and tumour infiltrating lymphocytes (TILs) in patients with early-stage non-small cell lung carcinoma (NSCLC) with artificial intelligence (AI) algorithms.

METHODS

The study included samples from 50 early-stage NSCLCs. PD-L1 immunohistochemistry (IHC) stained slides (clone SP263) were scored manually and with two different AI tools (PathAI and Navify Digital Pathology) by three pathologists. TILs were digitally assessed on H&E and CD8 IHC stained sections with two different algorithms (PathAI and Navify Digital Pathology, respectively). The agreement between observers and methods for each biomarker was analysed. For PD-L1, the turn-around time (TAT) for manual versus AI-assisted scoring was recorded.

RESULTS

Agreement was higher in tumours with low PD-L1 expression regardless of the approach. Both AI-powered tools identified a significantly higher number of cases equal or above 1% PD-L1 tumour proportion score as compared with manual scoring (p=0.00015), a finding with potential therapeutic implications. Regarding TAT, there were significant differences between manual scoring and AI use (p value <0.0001 for all comparisons). The total TILs density with the PathAI algorithm and the total density of CD8+ cells with the Navify Digital Pathology software were significantly correlated (τ=0.49 (95% CI 0.37, 0.61), p value<0.0001).

CONCLUSIONS

This preliminary study supports the use of AI algorithms for the scoring of PD-L1 and TILs in patients with NSCLC.

Multimodal data integration for oncology in the era of deep neural networks: a review

Cancer research encompasses data across various scales, modalities, and resolutions, from screening and diagnostic imaging to digitized histopathology slides to various types of molecular data and clinical records. The integration of these diverse data types for personalized cancer care and predictive modeling holds the promise of enhancing the accuracy and reliability of cancer screening, diagnosis, and treatment. Traditional analytical methods, which often focus on isolated or unimodal information, fall short of capturing the complex and heterogeneous nature of cancer data. The advent of deep neural networks has spurred the development of sophisticated multimodal data fusion techniques capable of extracting and synthesizing information from disparate sources. Among these, Graph Neural Networks (GNNs) and Transformers have emerged as powerful tools for multimodal learning, demonstrating significant success. This review presents the foundational principles of multimodal learning including oncology data modalities, taxonomy of multimodal learning, and fusion strategies. We delve into the recent advancements in GNNs and Transformers for the fusion of multimodal data in oncology, spotlighting key studies and their pivotal findings. We discuss the unique challenges of multimodal learning, such as data heterogeneity and integration complexities, alongside the opportunities it presents for a more nuanced and comprehensive understanding of cancer. Finally, we present some of the latest comprehensive multimodal pan-cancer data sources. By surveying the landscape of multimodal data integration in oncology, our goal is to underline the transformative potential of multimodal GNNs and Transformers. Through technological advancements and the methodological innovations presented in this review, we aim to chart a course for future research in this promising field. This review may be the first that highlights the current state of multimodal modeling applications in cancer using GNNs and transformers, presents comprehensive multimodal oncology data sources, and sets the stage for multimodal evolution, encouraging further exploration and development in personalized cancer care.

Biosimilars in the Era of Artificial Intelligence-International Regulations and the Use in Oncological Treatments

This research is based on three fundamental aspects of successful biosimilar development in the challenging biopharmaceutical market. First, biosimilar regulations in eight selected countries: Japan, South Korea, the United States, Canada, Brazil, Argentina, Australia, and South Africa, represent the four continents. The regulatory aspects of the countries studied are analyzed, highlighting the challenges facing biosimilars, including their complex approval processes and the need for standardized regulatory guidelines. There is an inconsistency depending on whether the biosimilar is used in a developed or developing country. In the countries observed, biosimilars are considered excellent alternatives to patent-protected biological products for the treatment of chronic diseases. In the second aspect addressed, various analytical AI modeling methods (such as machine learning tools, reinforcement learning, supervised, unsupervised, and deep learning tools) were analyzed to observe patterns that lead to the prevalence of biosimilars used in cancer to model the behaviors of the most prominent active compounds with spectroscopy. Finally, an analysis of the use of active compounds of biosimilars used in cancer and approved by the FDA and EMA was proposed.

Programmed Death Ligand-1 and Tumor Mutation Burden Testing of Patients With Lung Cancer for Selection of Immune Checkpoint Inhibitor Therapies: Guideline From the College of American Pathologists, Association for Molecular Pathology, International Association for the Study of Lung Cancer, Pulmonary Pathology Society, and LUNGevity Foundation

CONTEXT.—

Rapid advancements in the understanding and manipulation of tumor-immune interactions have led to the approval of immune therapies for patients with non-small cell lung cancer. Certain immune checkpoint inhibitor therapies require the use of companion diagnostics, but methodologic variability has led to uncertainty around test selection and implementation in practice.

OBJECTIVE.—

To develop evidence-based guideline recommendations for the testing of immunotherapy/immunomodulatory biomarkers, including programmed death ligand-1 (PD-L1) and tumor mutation burden (TMB), in patients with lung cancer.

DESIGN.—

The College of American Pathologists convened a panel of experts in non-small cell lung cancer and biomarker testing to develop evidence-based recommendations in accordance with the standards for trustworthy clinical practice guidelines established by the National Academy of Medicine. A systematic literature review was conducted to address 8 key questions. Using the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) approach, recommendations were created from the available evidence, certainty of that evidence, and key judgments as defined in the GRADE Evidence to Decision framework.

RESULTS.—

Six recommendation statements were developed.

CONCLUSIONS.—

This guideline summarizes the current understanding and hurdles associated with the use of PD-L1 expression and TMB testing for immune checkpoint inhibitor therapy selection in patients with advanced non-small cell lung cancer and presents evidence-based recommendations for PD-L1 and TMB testing in the clinical setting.

A guide to artificial intelligence for cancer researchers

Artificial intelligence (AI) has been commoditized. It has evolved from a specialty resource to a readily accessible tool for cancer researchers. AI-based tools can boost research productivity in daily workflows, but can also extract hidden information from existing data, thereby enabling new scientific discoveries. Building a basic literacy in these tools is useful for every cancer researcher. Researchers with a traditional biological science focus can use AI-based tools through off-the-shelf software, whereas those who are more computationally inclined can develop their own AI-based software pipelines. In this article, we provide a practical guide for non-computational cancer researchers to understand how AI-based tools can benefit them. We convey general principles of AI for applications in image analysis, natural language processing and drug discovery. In addition, we give examples of how non-computational researchers can get started on the journey to productively use AI in their own work.

Surrogate Biomarker Prediction from Whole-Slide Images for Evaluating Overall Survival in Lung Adenocarcinoma

BACKGROUND

Recent advances in computational pathology have shown potential in predicting biomarkers from haematoxylin and eosin (H&E) whole-slide images (WSI). However, predicting the outcome directly from WSIs remains a substantial challenge. In this study, we aimed to investigate how gene expression, predicted from WSIs, could be used to evaluate overall survival (OS) in patients with lung adenocarcinoma (LUAD).

METHODS

Differentially expressed genes (DEGs) were identified from The Cancer Genome Atlas (TCGA)-LUAD cohort. Cox regression analysis was performed on DEGs to identify the gene prognostics of OS. Attention-based multiple instance learning (AMIL) models were trained to predict the expression of identified prognostic genes from WSIs using the TCGA-LUAD dataset. Models were externally validated in the Clinical Proteomic Tumour Analysis Consortium (CPTAC)-LUAD dataset. The prognostic value of predicted gene expression values was then compared to the true gene expression measurements.

RESULTS

The expression of 239 prognostic genes could be predicted in TCGA-LUAD with cross-validated Pearson's R > 0.4. Predicted gene expression demonstrated prognostic performance, attaining a cross-validated concordance index of up to 0.615 in TCGA-LUAD through Cox regression. In total, 36 genes had predicted expression in the external validation cohort that was prognostic of OS.

CONCLUSIONS

Gene expression predicted from WSIs is an effective method of evaluating OS in patients with LUAD. These results may open up new avenues of cost- and time-efficient prognosis assessment in LUAD treatment.

Non-invasive decision support for clinical treatment of non-small cell lung cancer using a multiscale radiomics approach

BACKGROUND

Selecting therapeutic strategies for cancer patients is typically based on key target-molecule biomarkers that play an important role in cancer onset, progression, and prognosis. Thus, there is a pressing need for novel biomarkers that can be utilized longitudinally to guide treatment selection.

METHODS

Using data from 508 non-small cell lung cancer (NSCLC) patients across three institutions, we developed and validated a comprehensive predictive biomarker that distinguishes six genotypes and infiltrative immune phenotypes. These features were analyzed to establish the association between radiological phenotypes and tumor genotypes/immune phenotypes and to create a radiological interpretation of molecular features. In addition, we assessed the sensitivity of the models by evaluating their performance at five different voxel intervals, resulting in improved generalizability of the proposed approach.

FINDINGS

The radiomics model we developed, which integrates clinical factors and multi-regional features, outperformed the conventional model that only uses clinical and intratumoral features. Our combined model showed significant performance for EGFR, KRAS, ALK, TP53, PIK3CA, and ROS1 mutation status with AUCs of 0.866, 0.874, 0.902, 0.850, 0.860, and 0.900, respectively. Additionally, the predictive performance for PD-1/PD-L1 was 0.852. Although the performance of all models decreased to different degrees at five different voxel space resolutions, the performance advantage of the combined model did not change.

CONCLUSIONS

We validated multiscale radiomic signatures across tumor genotypes and immunophenotypes in a multi-institutional cohort. This imaging-based biomarker offers a non-invasive approach to select patients with NSCLC who are sensitive to targeted therapies or immunotherapy, which is promising for developing personalized treatment strategies during therapy.

Artificial intelligence in cancer diagnosis: Opportunities and challenges

Since cancer is one of the world's top causes of death, early diagnosis is critical to improving patient outcomes. Artificial intelligence (AI) has become a viable technique for cancer diagnosis by using machine learning algorithms to examine large volumes of data for accurate and efficient diagnosis. AI has the potential to alter the way cancer is detected fundamentally. Still, it has several disadvantages, such as requiring a large amount of data, technological limitations, and ethical concerns. This overview looks at the possibilities and restrictions of AI in cancer detection, as well as current applications and possible future developments. We can better understand how to use AI to improve patient outcomes and reduce cancer mortality rates by looking at its potential for cancer detection.

Prediction models for hormone receptor status in female breast cancer do not extend to males: further evidence of sex-based disparity in breast cancer

Breast cancer prognosis and management for both men and women are reliant upon estrogen receptor alpha (ERα) and progesterone receptor (PR) expression to inform therapy. Previous studies have shown that there are sex-specific binding characteristics of ERα and PR in breast cancer and, counterintuitively, ERα expression is more common in male than female breast cancer. We hypothesized that these differences could have morphological manifestations that are undetectable to human observers but could be elucidated computationally. To investigate this, we trained attention-based multiple instance learning prediction models for ERα and PR using H&E-stained images of female breast cancer from the Cancer Genome Atlas (TCGA) (n = 1085) and deployed them on external female (n = 192) and male breast cancer images (n = 245). Both targets were predicted in the internal (AUROC for ERα prediction: 0.86 ± 0.02, p < 0.001; AUROC for PR prediction = 0.76 ± 0.03, p < 0.001) and external female cohorts (AUROC for ERα prediction: 0.78 ± 0.03, p < 0.001; AUROC for PR prediction = 0.80 ± 0.04, p < 0.001) but not the male cohort (AUROC for ERα prediction: 0.66 ± 0.14, p = 0.43; AUROC for PR prediction = 0.63 ± 0.04, p = 0.05). This suggests that subtle morphological differences invisible upon visual inspection may exist between the sexes, supporting previous immunohistochemical, genomic, and transcriptomic analyses.

Enhancing head and neck tumor management with artificial intelligence: Integration and perspectives

Head and neck tumors (HNTs) constitute a multifaceted ensemble of pathologies that primarily involve regions such as the oral cavity, pharynx, and nasal cavity. The intricate anatomical structure of these regions poses considerable challenges to efficacious treatment strategies. Despite the availability of myriad treatment modalities, the overall therapeutic efficacy for HNTs continues to remain subdued. In recent years, the deployment of artificial intelligence (AI) in healthcare practices has garnered noteworthy attention. AI modalities, inclusive of machine learning (ML), neural networks (NNs), and deep learning (DL), when amalgamated into the holistic management of HNTs, promise to augment the precision, safety, and efficacy of treatment regimens. The integration of AI within HNT management is intricately intertwined with domains such as medical imaging, bioinformatics, and medical robotics. This article intends to scrutinize the cutting-edge advancements and prospective applications of AI in the realm of HNTs, elucidating AI's indispensable role in prevention, diagnosis, treatment, prognostication, research, and inter-sectoral integration. The overarching objective is to stimulate scholarly discourse and invigorate insights among medical practitioners and researchers to propel further exploration, thereby facilitating superior therapeutic alternatives for patients.

Quantitative multiplexed imaging technologies for single-cell analysis to assess predictive markers for immunotherapy in thoracic immuno-oncology: promises and challenges

The past decade has witnessed a revolution in cancer treatment by the shift from conventional drugs (chemotherapies) towards targeted molecular therapies and immune-based therapies, in particular the immune-checkpoint inhibitors (ICIs). These immunotherapies selectively release the host immune system against the tumour and have shown unprecedented durable remission for patients with cancers that were thought incurable such as advanced non-small cell lung cancer (aNSCLC). The prediction of therapy response is based since the first anti-PD-1/PD-L1 molecules FDA and EMA approvals on the level of PD-L1 tumour cells expression evaluated by immunohistochemistry, and recently more or less on tumour mutation burden in the USA. However, not all aNSCLC patients benefit from immunotherapy equally, since only around 30% of them received ICIs and among them 30% have an initial response to these treatments. Conversely, a few aNSCLC patients could have an efficacy ICIs response despite low PD-L1 tumour cells expression. In this context, there is an urgent need to look for additional robust predictive markers for ICIs efficacy in thoracic oncology. Understanding of the mechanisms that enable cancer cells to adapt to and eventually overcome therapy and identifying such mechanisms can help circumvent resistance and improve treatment. However, more than a unique universal marker, the evaluation of several molecules in the tumour at the same time, particularly by using multiplex immunostaining is a promising open room to optimise the selection of patients who benefit from ICIs. Therefore, urgent further efforts are needed to optimise to individualise immunotherapy based on both patient-specific and tumour-specific characteristics. This review aims to rethink the role of multiplex immunostaining in immuno-thoracic oncology, with the current advantages and limitations in the near-daily practice use.

Recent Developments in Inertial and Centrifugal Microfluidic Systems along with the Involved Forces for Cancer Cell Separation: A Review

The treatment of cancers is a significant challenge in the healthcare context today. Spreading circulating tumor cells (CTCs) throughout the body will eventually lead to cancer metastasis and produce new tumors near the healthy tissues. Therefore, separating these invading cells and extracting cues from them is extremely important for determining the rate of cancer progression inside the body and for the development of individualized treatments, especially at the beginning of the metastasis process. The continuous and fast separation of CTCs has recently been achieved using numerous separation techniques, some of which involve multiple high-level operational protocols. Although a simple blood test can detect the presence of CTCs in the blood circulation system, the detection is still restricted due to the scarcity and heterogeneity of CTCs. The development of more reliable and effective techniques is thus highly desired. The technology of microfluidic devices is promising among many other bio-chemical and bio-physical technologies. This paper reviews recent developments in the two types of microfluidic devices, which are based on the size and/or density of cells, for separating cancer cells. The goal of this review is to identify knowledge or technology gaps and to suggest future works.

Prediction of heart transplant rejection from routine pathology slides with self-supervised deep learning

Aims

One of the most important complications of heart transplantation is organ rejection, which is diagnosed on endomyocardial biopsies by pathologists. Computer-based systems could assist in the diagnostic process and potentially improve reproducibility. Here, we evaluated the feasibility of using deep learning in predicting the degree of cellular rejection from pathology slides as defined by the International Society for Heart and Lung Transplantation (ISHLT) grading system.

Methods and results

We collected 1079 histopathology slides from 325 patients from three transplant centres in Germany. We trained an attention-based deep neural network to predict rejection in the primary cohort and evaluated its performance using cross-validation and by deploying it to three cohorts. For binary prediction (rejection yes/no), the mean area under the receiver operating curve (AUROC) was 0.849 in the cross-validated experiment and 0.734, 0.729, and 0.716 in external validation cohorts. For a prediction of the ISHLT grade (0R, 1R, 2/3R), AUROCs were 0.835, 0.633, and 0.905 in the cross-validated experiment and 0.764, 0.597, and 0.913; 0.631, 0.633, and 0.682; and 0.722, 0.601, and 0.805 in the validation cohorts, respectively. The predictions of the artificial intelligence model were interpretable by human experts and highlighted plausible morphological patterns.

Conclusion

We conclude that artificial intelligence can detect patterns of cellular transplant rejection in routine pathology, even when trained on small cohorts.

Self-supervised attention-based deep learning for pan-cancer mutation prediction from histopathology

The histopathological phenotype of tumors reflects the underlying genetic makeup. Deep learning can predict genetic alterations from pathology slides, but it is unclear how well these predictions generalize to external datasets. We performed a systematic study on Deep-Learning-based prediction of genetic alterations from histology, using two large datasets of multiple tumor types. We show that an analysis pipeline that integrates self-supervised feature extraction and attention-based multiple instance learning achieves a robust predictability and generalizability.

Predicting melanoma survival and metastasis with interpretable histopathological features and machine learning models

Introduction

Melanoma is the fifth most common cancer in US, and the incidence is increasing 1.4% annually. The overall survival rate for early-stage disease is 99.4%. However, melanoma can recur years later (in the same region of the body or as distant metastasis), and results in a dramatically lower survival rate. Currently there is no reliable method to predict tumor recurrence and metastasis on early primary tumor histological images.

Methods

To identify rapid, accurate, and cost-effective predictors of metastasis and survival, in this work, we applied various interpretable machine learning approaches to analyze melanoma histopathological H&E images. The result is a set of image features that can help clinicians identify high-risk-of-metastasis patients for increased clinical follow-up and precision treatment. We use simple models (i.e., logarithmic classification and KNN) and "human-interpretable" measures of cell morphology and tissue architecture (e.g., cell size, staining intensity, and cell density) to predict the melanoma survival on public and local Stage I-III cohorts as well as the metastasis risk on a local cohort.

Results

We use penalized survival regression to limit features available to downstream classifiers and investigate the utility of convolutional neural networks in isolating tumor regions to focus morphology extraction on only the tumor region. This approach allows us to predict survival and metastasis with a maximum F1 score of 0.72 and 0.73, respectively, and to visualize several high-risk cell morphologies.

Discussion

This lays the foundation for future work, which will focus on using our interpretable pipeline to predict metastasis in Stage I & II melanoma.