Deep Learning Prediction of Metastasis in Locally Advanced Colon Cancer Using Binary Histologic Tumor Images

Unselective Measurement of Tumor-to-Stroma Proportion in Colon Cancer at the Invasion Front-An Elusive Prognostic Factor: Original Patient Data and Review of the Literature

The tumor-to-stroma ratio is a highly debated prognostic factor in the management of several solid tumors and there is no universal agreement on its practicality. In our study, we proposed confirming or dismissing the hypothesis that a simple measurement of stroma quantity is an easy-to-use and strong prognostic tool. We have included 74 consecutive patients with colorectal cancer who underwent primary curative abdominal surgery. The tumors have been grouped into stroma-poor (stroma < 10%), medium-stroma (between 10 and 50%) and stroma-rich (over 50%). The proportion of tumor stroma ranged from 5% to 70% with a median of 25%. Very few, only 6.8% of patients, had stroma-rich tumors, 4% had stroma-poor tumors and 89.2% had tumors with a medium quantity of stroma. The proportion of stroma, at any cut-off, had no statistically significant influence on the disease-specific survival. This can be explained by the low proportion of stroma-rich tumors in our patient group and the inverse correlation between stroma proportion and tumor grade. The real-life proportion of stroma-rich tumors and the complex nature of the stroma-tumor interaction has to be further elucidated.

The role of deep learning in diagnosing colorectal cancer

Colon cancer is a major public health issue, affecting a growing number of individuals worldwide. Proper and early diagnosis of colon cancer is the necessary first step toward effective treatment and/or prevention of future disease relapse. Artificial intelligence and its subtypes, deep learning in particular, tend nowadays to have an expanding role in all fields of medicine, and diagnosing colon cancer is no exception. This report aims to summarize the entire application spectrum of deep learning in all diagnostic tests regarding colon cancer, from endoscopy and histologic examination to medical imaging and screening serologic tests.

Multimodal AI for prediction of distant metastasis in carcinoma patients

Metastasis of cancer is directly related to death in almost all cases, however a lot is yet to be understood about this process. Despite advancements in the available radiological investigation techniques, not all cases of Distant Metastasis (DM) are diagnosed at initial clinical presentation. Also, there are currently no standard biomarkers of metastasis. Early, accurate diagnosis of DM is however crucial for clinical decision making, and planning of appropriate management strategies. Previous works have achieved little success in attempts to predict DM from either clinical, genomic, radiology, or histopathology data. In this work we attempt a multimodal approach to predict the presence of DM in cancer patients by combining gene expression data, clinical data and histopathology images. We tested a novel combination of Random Forest (RF) algorithm with an optimization technique for gene selection, and investigated if gene expression pattern in the primary tissues of three cancer types (Bladder Carcinoma, Pancreatic Adenocarcinoma, and Head and Neck Squamous Carcinoma) with DM are similar or different. Gene expression biomarkers of DM identified by our proposed method outperformed Differentially Expressed Genes (DEGs) identified by the DESeq2 software package in the task of predicting presence or absence of DM. Genes involved in DM tend to be more cancer type specific rather than general across all cancers. Our results also indicate that multimodal data is more predictive of metastasis than either of the three unimodal data tested, and genomic data provides the highest contribution by a wide margin. The results re-emphasize the importance for availability of sufficient image data when a weakly supervised training technique is used. Code is made available at: https://github.com/rit-cui-lab/Multimodal-AI-for-Prediction-of-Distant-Metastasis-in-Carcinoma-Patients.

Artificial intelligence and digital biomarker in precision pathology guiding immune therapy selection and precision oncology

BACKGROUND

The currently available immunotherapies already changed the strategy how many cancers are treated from first to last line. Understanding even the most complex heterogeneity in tumor tissue and mapping the spatial cartography of the tumor immunity allows the best and optimized selection of immune modulating agents to (re-)activate the patient's immune system and direct it against the individual cancer in the most effective way.

RECENT FINDINGS

Primary cancer and metastases maintain a high degree of plasticity to escape any immune surveillance and continue to evolve depending on many intrinsic and extrinsic factors In the field of immune-oncology (IO) immune modulating agents are recognized as practice changing therapeutic modalities. Recent studies have shown that an optimal and lasting efficacy of IO therapeutics depends on the understanding of the spatial communication network and functional context of immune and cancer cells within the tumor microenvironment. Artificial intelligence (AI) provides an insight into the immune-cancer-network through the visualization of very complex tumor and immune interactions in cancer tissue specimens and allows the computer-assisted development and clinical validation of such digital biomarker.

CONCLUSIONS

The successful implementation of AI-supported digital biomarker solutions guides the clinical selection of effective immune therapeutics based on the retrieval and visualization of spatial and contextual information from cancer tissue images and standardized data. As such, computational pathology (CP) turns into "precision pathology" delivering individual therapy response prediction. Precision Pathology does not only include digital and computational solutions but also high levels of standardized processes in the routine histopathology workflow and the use of mathematical tools to support clinical and diagnostic decisions as the basic principle of a "precision oncology".

Surgical treatment of locally advanced right colon cancer invading neighboring organs

Purpose

Invasion of the pancreas and/or duodenum with/without neighboring organs by locally advanced right colon cancer (LARCC) is a very rare clinical phenomenon that is difficult to manage. The purpose of this review is to suggest the most reasonable surgical approach for primary right colon cancer invading neighboring organs such as the pancreas and/or duodenum.

Methods

An extensive systematic research was conducted in PubMed, Medline, Embase, Scopus, and the Cochrane Central Register of Controlled Trials (CENTRAL) using the MeSH terms and keywords. Data were extracted from the patients who underwent en bloc resection and local resection with right hemicolectomy (RHC), the analysis was performed with the survival rate as the outcome parameters.

Results

As a result of the analysis of 117 patient data with locally advanced colon cancer (LACC) (73 for males, 39 for females) aged 25-85 years old from 11 articles between 2008 and 2021, the survival rate of en bloc resection was 72% with invasion of the duodenum, 71.43% with invasion of the pancreas, 55.56% with simultaneous invasion of the duodenum and pancreas, and 57.9% with invasion of neighboring organs with/without invasion of duodenum and/or pancreas. These survival results were higher than with local resection of the affected organ plus RHC.

Conclusion

When the LARCC has invaded neighboring organs, particularly when duodenum or pancreas are invaded simultaneously or individually, en bloc resection is a reasonable option to increase patient survival after surgery.

ICOSeg: Real-Time ICOS Protein Expression Segmentation from Immunohistochemistry Slides Using a Lightweight Conv-Transformer Network

Simple Summary

Inducible T-cell COStimulator (ICOS) is a biomarker of interest in checkpoint inhibitor therapy, and as a means of assessing T-cell regulation as part of a complex process of adaptive immunity. The aim of our study is to segment the ICOS positive cells using a lightweight deep-learning segmentation network. We aim to assess the potential of a convolutional neural network and transformer together that permits the capture of relevant features from immunohistochemistry images. The proposed study achieved remarkable results compared to the existing biomedical segmentation methods on our in-house dataset and surpassed our previous analysis by only utilizing the Efficient-UNet network.

Abstract

In this article, we propose ICOSeg, a lightweight deep learning model that accurately segments the immune-checkpoint biomarker, Inducible T-cell COStimulator (ICOS) protein in colon cancer from immunohistochemistry (IHC) slide patches. The proposed model relies on the MobileViT network that includes two main components: convolutional neural network (CNN) layers for extracting spatial features; and a transformer block for capturing a global feature representation from IHC patch images. The ICOSeg uses an encoder and decoder sub-network. The encoder extracts the positive cell’s salient features (i.e., shape, texture, intensity, and margin), and the decoder reconstructs important features into segmentation maps. To improve the model generalization capabilities, we adopted a channel attention mechanism that added to the bottleneck of the encoder layer. This approach highlighted the most relevant cell structures by discriminating between the targeted cell and background tissues. We performed extensive experiments on our in-house dataset. The experimental results confirm that the proposed model achieves more significant results against state-of-the-art methods, together with an 8× reduction in parameters.

Deep Learning on Histopathological Images for Colorectal Cancer Diagnosis: A Systematic Review

Colorectal cancer (CRC) is the second most common cancer in women and the third most common in men, with an increasing incidence. Pathology diagnosis complemented with prognostic and predictive biomarker information is the first step for personalized treatment. The increased diagnostic load in the pathology laboratory, combined with the reported intra- and inter-variability in the assessment of biomarkers, has prompted the quest for reliable machine-based methods to be incorporated into the routine practice. Recently, Artificial Intelligence (AI) has made significant progress in the medical field, showing potential for clinical applications. Herein, we aim to systematically review the current research on AI in CRC image analysis. In histopathology, algorithms based on Deep Learning (DL) have the potential to assist in diagnosis, predict clinically relevant molecular phenotypes and microsatellite instability, identify histological features related to prognosis and correlated to metastasis, and assess the specific components of the tumor microenvironment.

Semiautomatic analysis of tumor proportion in colon cancer: Lessons from a validation study

The tumor stroma ratio (TSR) is a promising histopathologic prognostic biomarker, which could allow for more accurate risk stratification and improved patient management in colorectal cancer. The purpose of our research was to validate the results of a previous study, which had suggested that not only a low but also a high tumor proportion (TP) might be an independent risk factor for occurrence of distant metastasis and worse overall survival using a semiautomatic image analysis approach with the open-source software ImageJ. We investigated 253 pT3 and pT4 adenocarcinomas of no special type. The previously established thresholds (PES-cut-offs) used to classify the patients (previous 3-tiered-classification) according to the tumor proportion (TP) in a highTP (TP ≥ 54%), a mediumTP (TP < 54% ∩ TP >15%) and a lowTP (TP ≤ 15%) group did not show a significant risk stratification. Even the adjustment of these threshold revealed no significant results. Therefore, a receiver-operating characteristic (ROC) analysis was performed to establish the cut-off with the most significant predictive power and a "new 2-tiered-classification" using this cut-off (40% at MinTP) showed a significantly shorter absence of metastasis for patients with a low TP (p = 0.007). These results confirm that a low TP is associated with an adverse prognosis. This study did not confirm the previous assumption that a high TP might also be a risk factor for occurrence of metastasis. Furthermore, it demonstrates that this semiautomatic technique is not superior to the established method, so that approaches to enhance prognostic techniques should continue.