Pathologist Validation of a Machine Learning-Derived Feature for Colon Cancer Risk Stratification

Classification of cancer types based on microRNA expression using a hybrid radial basis function and particle swarm optimization algorithm

The diagnosis and treatment of cancer is one of the most challenging aspects of the medical profession, despite advances in disease diagnosis. MicroRNAs are small noncoding RNA molecules involved in regulating gene expression and are associated with several cancer types. Therefore, the analysis of microRNA data has become one of the most important areas of cancer research in recent years. This paper presents an improved method for cancer-type classification based on microRNA expression data using a hybrid radial basis function (RBF) and particle swarm optimization (PSO) algorithm. Two datasets containing microRNA information were used, and preprocessing and normalization operations were performed on the raw data. Feature selection was carried out by using the PSO algorithm, which can identify the most relevant and informative features in the data along with helping to prioritize them. Using a PSO algorithm for feature selection is an effective approach to microRNA analysis. This enhances the accuracy and reliability of cancer-type classifications based on microRNA expression data. In the proposed method, we, respectively, achieved an accuracy of 0.95% and 0.91% on both datasets, with an average of 0.93%, using an improved RBF neural network classifier. These results demonstrate that the proposed method outperforms previous works. RESEARCH HIGHLIGHTS: To enhance the accuracy of cancer-type classifications based on microRNA expression data. We present a minimal feature selection method using particle swarm optimization to reduce computational load & radial basis function to improve accuracy.

Artificial Intelligence in Oncology: Current Landscape, Challenges, and Future Directions

Artificial intelligence (AI) in oncology is advancing beyond algorithm development to integration into clinical practice. This review describes the current state of the field, with a specific focus on clinical integration. AI applications are structured according to cancer type and clinical domain, focusing on the four most common cancers and tasks of detection, diagnosis, and treatment. These applications encompass various data modalities, including imaging, genomics, and medical records. We conclude with a summary of existing challenges, evolving solutions, and potential future directions for the field.

SIGNIFICANCE

AI is increasingly being applied to all aspects of oncology, where several applications are maturing beyond research and development to direct clinical integration. This review summarizes the current state of the field through the lens of clinical translation along the clinical care continuum. Emerging areas are also highlighted, along with common challenges, evolving solutions, and potential future directions for the field.

Using generative AI to investigate medical imagery models and datasets

BACKGROUND

AI models have shown promise in performing many medical imaging tasks. However, our ability to explain what signals these models have learned is severely lacking. Explanations are needed in order to increase the trust of doctors in AI-based models, especially in domains where AI prediction capabilities surpass those of humans. Moreover, such explanations could enable novel scientific discovery by uncovering signals in the data that aren't yet known to experts.

METHODS

In this paper, we present a workflow for generating hypotheses to understand which visual signals in images are correlated with a classification model's predictions for a given task. This approach leverages an automatic visual explanation algorithm followed by interdisciplinary expert review. We propose the following 4 steps: (i) Train a classifier to perform a given task to assess whether the imagery indeed contains signals relevant to the task; (ii) Train a StyleGAN-based image generator with an architecture that enables guidance by the classifier ("StylEx"); (iii) Automatically detect, extract, and visualize the top visual attributes that the classifier is sensitive towards. For visualization, we independently modify each of these attributes to generate counterfactual visualizations for a set of images (i.e., what the image would look like with the attribute increased or decreased); (iv) Formulate hypotheses for the underlying mechanisms, to stimulate future research. Specifically, present the discovered attributes and corresponding counterfactual visualizations to an interdisciplinary panel of experts so that hypotheses can account for social and structural determinants of health (e.g., whether the attributes correspond to known patho-physiological or socio-cultural phenomena, or could be novel discoveries).

FINDINGS

To demonstrate the broad applicability of our approach, we present results on eight prediction tasks across three medical imaging modalities-retinal fundus photographs, external eye photographs, and chest radiographs. We showcase examples where many of the automatically-learned attributes clearly capture clinically known features (e.g., types of cataract, enlarged heart), and demonstrate automatically-learned confounders that arise from factors beyond physiological mechanisms (e.g., chest X-ray underexposure is correlated with the classifier predicting abnormality, and eye makeup is correlated with the classifier predicting low hemoglobin levels). We further show that our method reveals a number of physiologically plausible, previously-unknown attributes based on the literature (e.g., differences in the fundus associated with self-reported sex, which were previously unknown).

INTERPRETATION

Our approach enables hypotheses generation via attribute visualizations and has the potential to enable researchers to better understand, improve their assessment, and extract new knowledge from AI-based models, as well as debug and design better datasets. Though not designed to infer causality, importantly, we highlight that attributes generated by our framework can capture phenomena beyond physiology or pathophysiology, reflecting the real world nature of healthcare delivery and socio-cultural factors, and hence interdisciplinary perspectives are critical in these investigations. Finally, we will release code to help researchers train their own StylEx models and analyze their predictive tasks of interest, and use the methodology presented in this paper for responsible interpretation of the revealed attributes.

FUNDING

Google.

Digital counting of tissue cells for molecular analysis: the QuANTUM pipeline

The estimation of tumor cellular fraction (TCF) is a crucial step in predictive molecular pathology, representing an entry adequacy criterion also in the next-generation sequencing (NGS) era. However, heterogeneity of quantification practices and inter-pathologist variability hamper the robustness of its evaluation, stressing the need for more reliable results. Here, 121 routine histological samples from non-small cell lung cancer (NSCLC) cases with complete NGS profiling were used to evaluate TCF interobserver variability among three different pathologists (pTCF), developing a computational tool (cTCF) and assessing its reliability vs ground truth (GT) tumor cellularity and potential impact on the final molecular results. Inter-pathologist reproducibility was fair to good, with overall Wk ranging between 0.46 and 0.83 (avg. 0.59). The obtained cTCF was comparable to the GT (p = 0.129, 0.502, and 0.130 for surgical, biopsies, and cell block, respectively) and demonstrated good reliability if elaborated by different pathologists (Wk = 0.9). Overall cTCF was lower as compared to pTCF (30 ± 10 vs 52 ± 19, p < 0.001), with more cases < 20% (17, 14%, p = 0.690), but none containing < 100 cells for the algorithm. Similarities were noted between tumor area estimation and pTCF (36 ± 29, p < 0.001), partly explaining variability in the human assessment of tumor cellularity. Finally, the cTCF allowed a reduction of the copy number variations (CNVs) called (27 vs 29, - 6.9%) with an increase of effective CNVs detection (13 vs 7, + 85.7%), some with potential clinical impact previously undetected with pTCF. An automated computational pipeline (Qupath Analysis of Nuclei from Tumor to Uniform Molecular tests, QuANTUM) has been created and is freely available as a QuPath extension. The computational method used in this study has the potential to improve efficacy and reliability of TCF estimation in NSCLC, with demonstrated impact on the final molecular results.

Novel biomarker SARIFA in colorectal cancer: highly prognostic, not genetically driven and histologic indicator of a distinct tumor biology

SARIFA (Stroma AReactive Invasion Front Areas) has recently emerged as a promising histopathological biomarker for colon and gastric cancer. To elucidate the underlying tumor biology, we assessed SARIFA-status in tissue specimens from The-Cancer-Genome-Atlas (TCGA) cohorts COAD (colonic adenocarcinoma) and READ (rectal adenocarcinoma). For the final analysis, 207 CRC patients could be included, consisting of 69 SARIFA-positive and 138 SARIFA-negative cases. In this external validation cohort, H&E-based SARIFA-positivity was strongly correlated with unfavorable overall, disease-specific, and progression-free survival, partly outperforming conventional prognostic factors. SARIFA-positivity was not associated with known high-risk genetic profiles, such as BRAF V600E mutations or microsatellite-stable status. Transcriptionally, SARIFA-positive CRCs exhibited an overlap with CRC consensus molecular subtypes CMS1 and CMS4, along with distinct differential gene expression patterns, linked to lipid metabolism and increased stromal cell infiltration scores (SIIS). Gene-expression-based drug sensitivity prediction revealed a differential treatment response in SARIFA-positive CRCs. In conclusion, SARIFA represents the H&E-based counterpart of an aggressive tumor biology, demonstrating a partial overlap with CMS1/4 and also adding a further biological layer related to lipid metabolism. Our findings underscore SARIFA-status as an ideal biomarker for refined patient stratification and novel drug developments, particularly given its cost-effective assessment based on routinely available H&E slides.

SARIFA as a new histopathological biomarker is associated with adverse clinicopathological characteristics, tumor-promoting fatty-acid metabolism, and might predict a metastatic pattern in pT3a prostate cancer

BACKGROUND

Recently, we introduced Stroma-AReactive-Invasion-Front-Areas (SARIFA) as a novel hematoxylin-eosin (H&E)-based histopathologic prognostic biomarker for various gastrointestinal cancers, closely related to lipid metabolism. To date, no studies on SARIFA, which is defined as direct tumor-adipocyte-interaction, beyond the alimentary tract exist. Hence, the objective of our current investigation was to study the significance of SARIFA in pT3a prostate cancer (PCa) and explore its association with lipid metabolism in PCa as lipid metabolism plays a key role in PCa development and progression.

METHODS

To this end, we evaluated SARIFA-status in 301 radical prostatectomy specimens and examined the relationship between SARIFA-status, clinicopathological characteristics, overall survival, and immunohistochemical expression of FABP4 and CD36 (proteins closely involved in fatty-acid metabolism). Additionally, we investigated the correlation between SARIFA and biochemical recurrence-free survival (BRFS) and PSMA-positive recurrences in PET/CT imaging in a patient subgroup. Moreover, a quantitative SARIFA cut-off was established to further understand the underlying tumor biology.

RESULTS

SARIFA positivity occurred in 59.1% (n = 178) of pT3a PCas. Our analysis demonstrated that SARIFA positivity is strongly associated with established high-risk features, such as R1 status, extraprostatic extension, and higher initial PSA values. Additionally, we observed an upregulation of immunohistochemical CD36 expression specifically at SARIFAs (p = 0.00014). Kaplan-Meier analyses revealed a trend toward poorer outcomes, particularly in terms of BRFS (p = 0.1). More extensive tumor-adipocyte interaction, assessed as quantity-dependent SARIFA-status on H&E slides, is also significantly associated with high-risk features, such as lymph node metastasis, and seems to be associated with worse survival outcomes (p = 0.16). Moreover, SARIFA positivity appeared to be linked to more distant lymph node and bone metastasis, although statistical significance was slightly not achieved (both p > 0.05).

CONCLUSIONS

This is the first study to introduce SARIFA as easy-and-fast-to-assess H&E-based biomarker in locally advanced PCa. SARIFA as the histopathologic correlate of a distinct tumor biology, closely related to lipid metabolism, could pave the way to a more detailed patient stratification and to the development of novel drugs targeting lipid metabolism in pT3a PCa. On the basis of this biomarker discovery study, further research efforts on the prognostic and predictive role of SARIFA in PCa can be designed.

Natural Language Processing to extract SNOMED-CT codes from pathological reports

Objective

The use of standardized structured reports (SSR) and suitable terminologies like SNOMED-CT can enhance data retrieval and analysis, fostering large-scale studies and collaboration. However, the still large prevalence of narrative reports in our laboratories warrants alternative and automated labeling approaches. In this project, natural language processing (NLP) methods were used to associate SNOMED-CT codes to structured and unstructured reports from an Italian Digital Pathology Department.

Methods

Two NLP-based automatic coding systems (support vector machine, SVM, and long-short term memory, LSTM) were trained and applied to a series of narrative reports.

Results

The 1163 cases were tested with both algorithms, showing good performances in terms of accuracy, precision, recall, and F1 score, with SVM showing slightly better performances as compared to LSTM (0.84, 0.87, 0.83, 0.82 vs 0.83, 0.85, 0.83, 0.82, respectively). The integration of an explainability allowed identification of terms and groups of words of importance, enabling fine-tuning, balancing semantic meaning and model performance.

Conclusions

AI tools allow the automatic SNOMED-CT labeling of the pathology archives, providing a retrospective fix to the large lack of organization of narrative reports.

Paving the path toward multi-omics approaches in the diagnostic challenges faced in thyroid pathology

INTRODUCTION

Despite advancements in diagnostic methods, the classification of indeterminate thyroid nodules still poses diagnostic challenges not only in pre-surgical evaluation but even after histological evaluation of surgical specimens. Proteomics, aided by mass spectrometry and integrated with artificial intelligence and machine learning algorithms, shows great promise in identifying diagnostic markers for thyroid lesions.

AREAS COVERED

This review provides in-depth exploration of how proteomics has contributed to the understanding of thyroid pathology. It discusses the technical advancements related to immunohistochemistry, genetic and proteomic techniques, such as mass spectrometry, which have greatly improved sensitivity and spatial resolution up to single-cell level. These improvements allowed the identification of specific protein signatures associated with different types of thyroid lesions.

EXPERT COMMENTARY

Among all the proteomics approaches, spatial proteomics stands out due to its unique ability to capture the spatial context of proteins in both cytological and tissue thyroid samples. The integration of multi-layers of molecular information combining spatial proteomics, genomics, immunohistochemistry or metabolomics and the implementation of artificial intelligence and machine learning approaches, represent hugely promising steps forward toward the possibility to uncover intricate relationships and interactions among various molecular components, providing a complete picture of the biological landscape whilst fostering thyroid nodule diagnosis.