The role of deep learning in diagnosing colorectal cancer

An efficient colorectal cancer detection network using atrous convolution with coordinate attention transformer and histopathological images

The second most common type of malignant tumor worldwide is colorectal cancer. Histopathology image analysis offers crucial data for the clinical diagnosis of colorectal cancer. Currently, deep learning techniques are applied to enhance cancer classification and tumor localization in histopathological image analysis. Moreover, traditional deep learning techniques might loss integrated information in the image while evaluating thousands of patches recovered from whole slide images (WSIs). This research proposes a novel colorectal cancer detection network (CCDNet) that combines coordinate attention transformer with atrous convolution. CCDNet first denoises the input histopathological image using a Wiener based Midpoint weighted non-local means filter (WMW-NLM) for guaranteeing precise diagnoses and maintain image features. Also, a novel atrous convolution with coordinate attention transformer (AConvCAT) is introduced, which successfully combines the advantages of two networks to classify colorectal tissue at various scales by capturing local and global information. Further, coordinate attention model is integrated with a Cross-shaped window (CrSWin) transformer for capturing tiny changes in colorectal tissue from multiple angles. The proposed CCDNet achieved accuracy rates of 98.61% and 98.96%, on the colorectal histological image and NCT-CRC-HE-100 K datasets correspondingly. The comparison analysis demonstrates that the suggested framework performed better than the most advanced methods already in use. In hospitals, clinicians can use the proposed CCDNet to verify the diagnosis.

Phase angle is a predictor for postoperative complications in colorectal cancer

Aim

The aim of this study was to develop a validated nomogram to predict the risk of postoperative complications in colorectal cancer (CRC) patients by analyzing the factors that contribute to these complications.

Methods

We retrospectively collected clinical information on patients who underwent CRC surgery at a single clinical center from January 2021 to December 2021. Univariate and multivariate logistic regression analysis to identify independent risk factors for postoperative complications and to develop a predictive model. A receiver operating characteristic (ROC) curve was used to calculate the area under the curve (AUC) to assess the predicted probability. Calibration curve was drawn to compare the predicted probability of the nomogram with the actual probability, and decision curve analysis (DCA) was employed to evaluate the clinical utility of the nomogram.

Results

A total of 190 CRC patients were included in this study. We retrospectively collected baseline information, clinical information, surgical information, and nutrition-related indicators for all patients. Through multivariate logistic regression analysis, preoperative albumin (p = 0.041, OR = 0.906, 95% CI = 0.824-0.996), surgical time (p = 0.009, OR = 1.006, 95% CI = 1.001-1.010), waistline (p = 0.049, OR = 1.011, 95% CI = 1.002-1.020) and phase angle (PA) (p = 0.022, OR = 0.615, 95% CI = 0.405-0.933) were identified as independent risk factors for postoperative complications in CRC, and a nomogram prediction model was established using the above four variables. The AUC of 0.706 for the ROC plot and the high agreement between predicted and actual probabilities in the calibration curves suggested that the prediction model has good predictive power. The DCA also confirmed the good clinical performance of the nomogram.

Conclusion

This study developed a nomogram to predict the risk of postoperative complications in CRC patients, providing surgeons with a reliable reference to personalized patient management in the perioperative period and preoperative nutritional interventions.

Meta-analysis of postoperative incision infection risk factors in colorectal cancer surgery

Objective

To evaluate the risk factors for postoperative incision infection in colorectal cancer, this meta-analysis aimed to identify key variables impacting infection incidence following colorectal cancer surgery.

Methods

Utilizing a meta-analytical approach, studies published from January 2015 to December 2022 were systematically collected and analyzed through the assessment of factors like body mass index, diabetes, albumin levels, malnutrition, and surgical duration.

Results

The meta-analysis of eleven high-quality studies revealed that elevated BMI, diabetes, low albumin levels, malnutrition, and extended surgical duration were associated with increased infection risk, while laparoscopic procedures showed potential for risk reduction.

Conclusions

This study underscores the significance of preoperative risk assessment and management in mitigating postoperative incision infections in colorectal cancer patients. The findings present actionable insights for clinicians to enhance patient prognoses and overall quality of life.

Different impacts of adipose tissue dynamics on prognosis in patients with resectable locally advanced rectal cancer treated with and without neoadjuvant treatment

Background

Body composition is recognized to be associated with clinical outcomes in patients with locally advanced rectal cancer (LARC). This study aimed to determine the prognostic role of regional adipose tissue distribution in patients with resectable LARC treated with or without neoadjuvant chemoradiotherapy (nCRT).

Methods

This retrospective study included 281 consecutive patients who underwent radical surgery for LARC with or without preoperative nCRT between 2013 and 2019. Patients underwent contrast-enhanced CT scans before nCRT and before surgery. Visceral adipose tissue (VAT), abdominal subcutaneous adipose tissue (aSAT), and gluteal subcutaneous adipose tissue (gSAT) were quantified on the CT images. The association of adipose tissue distribution with progression-free survival (PFS) was analyzed using Cox proportional hazards analysis.

Results

A total of 102 nCRT-treated and 179 primarily resected patients were included. During a median follow-up period of 24 months, 74 (26.3%) patients experienced local recurrence or metastasis. Multivariable analysis showed that VAT was associated with PFS in all patients (hazard ratio [HR] 1.28, 95% confidence interval [CI] 1.04-1.57; P = 0.021). This association was only maintained in primarily resected patients (HR 1.31, 95% CI 1.02-1.69; P = 0.037). For patients receiving preoperative nCRT, VAT was not significantly associated with PFS, while the dynamic change in gSAT (ΔgSAT) between nCRT and surgery was associated with PFS (HR 0.43, 95%CI 0.27-0.69, P = 0.001).

Conclusion

Visceral obesity is an adverse prognostic factor in patients with resectable LARC treated by primary resection, while increased gluteal subcutaneous adiposity during preoperative nCRT may indicate favorable clinical outcomes.

Identifying risk and prognostic factors for synchronous liver metastasis in small bowel adenocarcinoma: a predictive analysis using the SEER database

Background

Small bowel adenocarcinoma (SBA) is a rare gastrointestinal malignancy with an increasing incidence and a high propensity for liver metastasis (LM). This study aimed to investigate the risk factors for synchronous LM and prognostic factors in patients with LM.

Methods

Utilizing the Surveillance, Epidemiology, and End Results (SEER) database, this study analyzed data from 2,064 patients diagnosed with SBA between 2010 and 2020. Logistic regression was used to determine risk factors for synchronous LM. A nomogram was developed to predict the risk of LM in SBA patients, and its predictive performance was assessed through receiver operating characteristic (ROC) curves and calibration curves. Kaplan-Meier and Cox regression analyses were conducted to evaluate survival outcomes for SBA patients with LM.

Results

Synchronous LM was present in 13.4% of SBA patients (n = 276). Six independent predictive factors for LM were identified, including tumor location, T stage, N stage, surgical intervention, retrieval of regional lymph nodes (RORLN), and chemotherapy. The nomogram demonstrated good discriminative ability, with an area under the curve (AUC) of 83.8%. Patients with LM had significantly lower survival rates than those without LM (P < 0.001). Survival analysis revealed that advanced age, tumor location in the duodenum, surgery, RORLN and chemotherapy were associated with cancer-specific survival (CSS) in patients with LM originating from SBA.

Conclusions

This study highlights the significant impact of LM on the survival of SBA patients and identifies key risk factors for its occurrence. The developed nomogram aids in targeted screening and personalized treatment planning.

Imaging of colorectal adenomas with pseudoinvasion and malignant polyps using two-photon excitation microscopy

Introduction

Although the incidence and mortality rates of colorectal cancer exhibit significant variability, it remains one of the most prevalent cancers worldwide. Endeavors to prevent colorectal cancer development focus on detecting precursor lesions during colonoscopy. The diagnosis of endoscopically resected polyps relies on hematoxylin and eosin staining examination. For challenging cases like adenomatous polyps with epithelial misplacement, additional diagnostic methods could prove beneficial.

Methods

This paper aims to underscore stromal changes observed in malignant polyps and polyps with pseudoinvasion, leveraging two-photon excitation microscopy (TPEM), a technique extensively employed in the medical field in recent years.

Results and discussions

Both the subjective and quantitative analysis of TPEM images revealed distinct distributions and densities of collagen at the invasion front in malignant polyps compared to areas of pseudoinvasion. TPEM holds potential in discerning true invasion in malignant polyps from pseudoinvasion, offering enhanced visualization of local stromal changes.

Sign of Neck Mass as the Chief Complaint: A Case Report and Literature Review About Thyroid Metastasis of Colorectal Cancer

Background

Commonly, the thyroid gland is regarded as an organ with fewer metastatic diseases, and colorectal metastasis to the thyroid (CMT) is rarely reported, especially, with that the clinical sign of thyroid metastasis nidus is the chief complaint. The CMT occurs in advanced colorectal cancer and is associated with poor prognosis and short survival.

Case Report

In this case, we reported a patient with the sign of neck mass as the first manifestation of CMT. The patient underwent a partial thyroidectomy in June 2019, immunohistochemical findings of thyroid carcinoma suggested the possibility of adenocarcinoma of gastrointestinal tract. The patient underwent a colonoscopy in July 2019 and a colonic mass was found. Pathological examination diagnosed rectal adenocarcinoma. The patient underwent neoadjuvant chemotherapy, surgical treatment, postoperative adjuvant chemotherapy and targeted therapy. The patient died in June 2022.

Conclusion

The metastasis disease would not be ignored at all, when a patient complains at signs of neck mass. Further, the possibility of metastasis cancer should be considered once thyroid nodules occur in patients with colorectal cancer. Even though the biological characteristics and stage of the primary tumor have an important impact on the prognosis, positive standardized treatments can also be helpful.

Comparison of the burden of digestive diseases between China and the United States from 1990 to 2019

Introduction

China has experienced unprecedented transformations unseen in a century and is gradually progressing toward an emerging superpower. The epidemiological trends of digestive diseases in the United States (the US) have significant prescient effects on China.

Methods

We extracted data on 18 digestive diseases from the Global Burden of Diseases 2019 Data Resource. Linear regression analysis conducted by the JoinPoint software assessed the average annual percentage change of the burden. We performed subgroup analyses based on sex and age group.

Results

In 2019, there were 836.01 and 180.91 million new cases of digestive diseases in China and the US, causing 1558.01 and 339.54 thousand deaths. The age-standardized incidence rates of digestive diseases in China and the US were 58417.87/100,000 and 55018.65/100,000 respectively, resulting in age-standardized mortality rates of 81.52/100,000 and 60.88/100,000. The rates in China annually decreased by 2.149% for mortality and 2.611% for disability-adjusted life of year (DALY). The mortality and DALY rates of the US, respectively, had average annual percentage changes of -0.219 and -0.251. Enteric infections and cirrhosis and other chronic liver diseases accounted for the highest incidence and prevalence in both counties, respectively. The burden of multiple digestive diseases exhibited notable sex disparities. The middle-old persons had higher age-standardized prevalence rates.

Conclusion

China bore a greater burden of digestive diseases, and the evolving patterns were more noticeable. Targeted interventions and urgent measures should be taken in both countries to address the specific burden of digestive diseases based on their different epidemic degree.

The efficacy and safety of neoadjuvant chemoradiotherapy combined with immunotherapy for locally advanced rectal cancer patients: a systematic review

Background

Several studies have explored the effectiveness of PD-1/PD-L1 inhibitors combined with neoadjuvant chemoradiotherapy (nCRT) in the treatment of locally advanced rectal cancer(LARC), particularly in microsatellite stable(MSS) or mismatch repair proficient(pMMR) LARC patients. We undertook a single-arm systematic review to comprehensively evaluate the advantages and potential risks associated with the use of PD-1/PD-L1 inhibitors in conjunction with nCRT for patients diagnosed with locally advanced rectal cancer.

Methods

The PubMed, Embase, Cochrane Library, ClinicalTrials.gov, ASCO and ESMO were searched for related studies. The main outcomes were pathologic complete response (pCR), major pathological response (MPR), anal preservation, and adverse effects (AEs).

Results

Fourteen articles including 533 locally advanced rectal cancer (LARC) patients were analyzed. The pooled pCR, MPR, and anal preservation rates were 36%, 66% and 86%. Grade ≥3 adverse events occurred in 20%. Subgroup analysis showed that; dMMR/MSI-H had a pooled pCR (100%) and MPR (100%), pMMR/MSS had a pooled pCR (38%) and MPR (60%); the short-course radiotherapy and long-course radiotherapy had pooled pCR rates of 51% and 30%, respectively. The rates of pCR for the concurrent and sequential immuno-chemoradiotherapy subgroups at 30% and 40%, mirroring pCR rates for the PD-L1 and PD-1 inhibitor subgroups were 32% and 40%, respectively.

Conclusion

In cases of locally advanced rectal cancer, PD-1/PD-L1 inhibitors combined with neoadjuvant chemoradiotherapy have shown promising response rates and acceptable toxicity profiles. PD-1/PD-L1 inhibitors combined with neoadjuvant chemoradiotherapy hence has a positive outcome even in MSS LARC patients.

Systematic Review Registration

https://www.crd.york.ac.uk/prospero/#myprospero, identifier CRD42023465380.

Determinants of survival and recurrence in patients with stage I colorectal cancer

Background

Due to the novel advanced screening methods, the number of patients diagnosed with stage I colorectal cancer (CRC) is increasing. This retrospective cohort study aimed to identify recurrence and survival risk factors of patients with stage I CRC after surgery.

Materials and methods

Patients with stage I CRC were evaluated, and their demographic and clinicopathologic variables were recorded. The log-rank test assessed the association of variables with overall survival (OS), recurrence-free survival (RFS), local recurrence, and distant metastasis.

Results

The median overall survival period was 51 months. The recurrence rate was 13.7%: 7.2% local and 9.3% distant recurrence. One-, two-, three-, and five-year RFS were 92%, 89%, 87%, and 83%, respectively, and OS were 96%, 93%, 90%, and 89%, respectively. Local and distant recurrence rates were higher in patients with higher tumor grades. Additionally, RFS and OS were worse in patients with higher tumor grades, and perforation was associated with worse OS.

Conclusions

The determinants of survival and recurrence identified in the present study can be used to improve patient outcomes by early diagnosis and appropriate management of high-risk patients.

Case report: Successful treatment of advanced colon cancer in an eighty-year-old man with long-term and multi-stage endoscopic minimally invasive therapy

Background

No previous studies have reported on the use of minimally invasive endoscopic therapy for colon cancer in older patients.

Case presentation

An 80-year-old man was admitted to our hospital with haematochezia and diagnosed with advanced colon cancer in 2018. Traditional surgical care was rejected by his family. We successfully treated the patient with multiple minimally invasive endoscopic therapies, such as argon plasma coagulation, from 2018 to 2021.

Conclusion

Invasive endoscopic therapy is a feasible way to treat colon cancer in older patients.

Delays in Colorectal Cancer Screening for Latino Patients: The Role of Immigrant Healthcare in Stemming the Rising Global Incidence of Colorectal Cancer

The significant global burden of colorectal cancer accentuates disparities in access to preventive healthcare in most low- and middle-income countries (LMICs) as well as large sections of underserved populations within high-income countries. The barriers to colorectal cancer screening in economically transitioning Latin America are multiple. At the same time, immigration from these countries to the USA continues to increase. This case highlights the delays in diagnosis experienced by a recent immigrant from a country with no established colorectal cancer screening program, to an immigrant population in the USA with similar poor screening coverage. We discuss common challenges faced by Latinos in their home countries and the USA, as well as strategies that could be implemented to improve screening coverage in US immigrant populations.

Factors Affecting the Efficiency of Near-Infrared Indocyanine Green (NIR/ICG) in Lymphatic Mapping for Colorectal Cancer: A Systematic Review

As laparoscopy gained global popularity in oncologic surgery, the challenge of detecting lymph nodes spurred researchers to explore innovative techniques and approach the situation from a fresh perspective. While many proposed methods have faded into obscurity, the utilization of indocyanine green (ICG) in the surgical treatment of oncologic patients has continued to advance. The immense potential of this dye is widely acknowledged, yet its full extent and limitations in lymphatic mapping for colorectal cancer remain to be precisely determined. This article aims to assess the magnitude of its potential and explore the constraints based on insights from clinical studies published by pioneering researchers. A systematic review of the existing literature, comprising articles in English, was conducted using the Scopus, PubMed, and Springer Link databases. The search employed keywords such as "colorectal cancer" AND/OR "indocyanine green," "fluorescence" AND/OR "lymphatic mapping" AND/OR "lymph nodes." Initially identifying 129 articles, the application of selection criteria narrowed down the pool to 10 articles, which served as the primary sources of data for our review. Despite the absence of a standardized protocol for the application of ICG in colorectal cancer, particularly in the context of lymphatic mapping, the detection rates have exhibited considerable variation across studies. Nevertheless, all authors unanimously regarded this technique as beneficial and promising. Additionally, it is advocated as an adjunctive tool to enhance the accuracy of cancer staging. Near-infrared (NIR)-enhanced surgery holds the promise of transforming the landscape of oncologic surgery, emerging as a valuable tool for surgeons. However, the absence of a standardized technique and the subjective nature of result assessment impose limitations on the potential of this method. Consequently, it can be inferred that the establishment of a universally accepted protocol, encompassing parameters such as dose, concentration, technique, and site of administration of ICG, along with the optimal time needed for fluorescence visualization, would enhance the outcomes. Emphasizing the accurate selection of patients is crucial to prevent the occurrence of false-negative results.

Future of Artificial Intelligence in Surgery: A Narrative Review

Artificial intelligence (AI) is the capability of a machine to execute cognitive processes that are typically considered to be functions of the human brain. It is the study of algorithms that enable machines to reason and perform mental tasks, including problem-solving, object and word recognition, and decision-making. Once considered science fiction, AI today is a fact and an increasingly prevalent subject in both academic and popular literature. It is expected to reshape medicine, benefiting both healthcare professionals and patients. Machine learning (ML) is a subset of AI that allows machines to learn and make predictions by recognizing patterns, thus empowering the medical team to deliver better care to patients through accurate diagnosis and treatment. ML is expanding its footprint in a variety of surgical specialties, including general surgery, ophthalmology, cardiothoracic surgery, and vascular surgery, to name a few. In recent years, we have seen AI make its way into the operating theatres. Though it has not yet been able to replace the surgeon, it has the potential to become a highly valuable surgical tool. Rest assured that the day is not far off when AI shall play a significant intraoperative role, a projection that is currently marred by safety concerns. This review aims to explore the present application of AI in various surgical disciplines and how it benefits both patients and physicians, as well as the current obstacles and limitations facing its seemingly unstoppable rise.

Diffusion-Weighted MRI as a Quantitative Imaging Biomarker in Colon Tumors

PURPOSE

To assess the use of quantitative diffusion-weighted MRI (DW-MRI) as a diagnostic imaging biomarker in differentiating between benign colon adenoma, early, and advanced cancer of the colon, as well as predicting lymph node involvement, and finally comparing mucinous-producing colon cancer with adenomas and non-mucinous colon cancer.

METHOD

Patients with a confirmed tumor on colonoscopy were eligible for inclusion in this study. Using a 3.0 Tesla MRI machine, the main tumor mean apparent diffusion coefficient (mADC) was obtained. Surgically resected tumor specimens served as an endpoint, except in mucinous colon cancers, which were classified based on T2 images.

RESULTS

A total of 152 patients were included in the study population. The mean age was 71 years. A statistically significant mADC mean difference of -282 × 10-6 mm2/s [-419--144 95% CI, p < 0.001] was found between colon adenomas and early colon cancer, with an AUC of 0.80 [0.68-0.93 95% CI] and an optimal cut off value of 1018 × 10-6 mm2/s. Only a small statistically significant difference (p = 0.039) in mADC was found between benign tumors and mucinous colon cancer. We found no statistical difference in mADC mean values between early and advanced colon cancer, and between colon cancer with and without lymph node involvement.

CONCLUSION

Quantitative DW-MRI is potentially useful for determining whether a colonic tumor is benign or malignant. Mucinous colon cancer shows less diffusion restriction when compared to non-mucinous colon cancer, a potential pitfall.

Lymph Node Molecular Analysis with OSNA Enables the Identification of pT1 CRC Patients at Risk of Recurrence: A Multicentre Study

Early-stage colorectal carcinoma (CRC)-pT1-is a therapeutic challenge and presents some histological features related to lymph node metastasis (LNM). A significant proportion of pT1 CRCs are treated surgically, resulting in a non-negligible surgical-associated mortality rate of 1.5-2%. Among these cases, approximately 6-16% exhibit LNM, but the impact on survival is unclear. Therefore, there is an unmet need to establish an objective and reliable lymph node (LN) staging method to optimise the therapeutic management of pT1 CRC patients and to avoid overtreating or undertreating them. In this multicentre study, 89 patients with pT1 CRC were included. All histological features associated with LNM were evaluated. LNs were assessed using two methods, One-Step Nucleic Acid Amplification (OSNA) and the conventional FFPE plus haematoxylin and eosin (H&E) staining. OSNA is an RT-PCR-based method for amplifying CK19 mRNA. Our aim was to assess the performance of OSNA and H&E in evaluating LNs to identify patients at risk of recurrence and to optimise their clinical management. We observed an 80.9% concordance in LN assessment using the two methods. In 9% of cases, LNs were found to be positive using H&E, and in 24.7% of cases, LNs were found to be positive using OSNA. The OSNA results are provided as the total tumour load (TTL), defined as the total tumour burden present in all the LNs of a surgical specimen. In CRC, a TTL ≥ 6000 CK19 m-RNA copies/µL is associated with poor prognosis. Three patients had TTL > 6000 copies/μL, which was associated with higher tumour budding. The discrepancies observed between the OSNA and H&E results were mostly attributed to tumour allocation bias. We concluded that LN assessment with OSNA enables the identification of pT1 CRC patients at some risk of recurrence and helps to optimise their clinical management.

The Antineoplastic Effect of Heparin on Colorectal Cancer: A Review of the Literature

Heparin and derivatives are commonly used for thrombophylaxis in surgical colorectal cancer (CRC) patients. Recent studies have suggested that, besides its protective effect on the incidence of venous thromboembolism, heparin has an anti-cancer effect. The aim of this review was to explore the literature and report the antineoplastic effect of heparin and derivatives on CRC. MEDLINE and EMBASE databases were searched for relevant articles. Nineteen studies were included (n = 19). Fifteen were lab studies conducted in vivo or in vitro on CRC cell lines and/or mice (n = 15). Four were in vivo clinical studies (n = 4). CRC tumor growth was reduced by 78% in one study, (p < 0.01), while tumorigenesis was suppressed in heparin-treated mice in seven studies. A high dose of low molecular weight heparin for extended duration significantly reduced post-operative VEGF, suggesting that such a regime may inhibit tumor angiogenesis and distant metastasis. A randomized trial demonstrated the antineoplastic effect of nadroparin as the 6 month survival in palliative patients increased. Another study has reported that disease-free survival of CRC patients was not affected by a similar tinzaparin regime. The anti-cancer properties of heparin and derivatives are promising, especially in lab studies. Further clinical trials are needed to investigate the anti-cancer benefit of heparin on CRC.

Deep Learning for the Pathologic Diagnosis of Hepatocellular Carcinoma, Cholangiocarcinoma, and Metastatic Colorectal Cancer

Diagnosing primary liver cancers, particularly hepatocellular carcinoma (HCC) and cholangiocarcinoma (CC), is a challenging and labor-intensive process, even for experts, and secondary liver cancers further complicate the diagnosis. Artificial intelligence (AI) offers promising solutions to these diagnostic challenges by facilitating the histopathological classification of tumors using digital whole slide images (WSIs). This study aimed to develop a deep learning model for distinguishing HCC, CC, and metastatic colorectal cancer (mCRC) using histopathological images and to discuss its clinical implications. The WSIs from HCC, CC, and mCRC were used to train the classifiers. For normal/tumor classification, the areas under the curve (AUCs) were 0.989, 0.988, and 0.991 for HCC, CC, and mCRC, respectively. Using proper tumor tissues, the HCC/other cancer type classifier was trained to effectively distinguish HCC from CC and mCRC, with a concatenated AUC of 0.998. Subsequently, the CC/mCRC classifier differentiated CC from mCRC with a concatenated AUC of 0.995. However, testing on an external dataset revealed that the HCC/other cancer type classifier underperformed with an AUC of 0.745. After combining the original training datasets with external datasets and retraining, the classification drastically improved, all achieving AUCs of 1.000. Although these results are promising and offer crucial insights into liver cancer, further research is required for model refinement and validation.

The Prognostic Value of ASPHD1 and ZBTB12 in Colorectal Cancer: A Machine Learning-Based Integrated Bioinformatics Approach

Introduction: Colorectal cancer (CRC) is a common cancer associated with poor outcomes, underscoring a need for the identification of novel prognostic and therapeutic targets to improve outcomes. This study aimed to identify genetic variants and differentially expressed genes (DEGs) using genome-wide DNA and RNA sequencing followed by validation in a large cohort of patients with CRC. Methods: Whole genome and gene expression profiling were used to identify DEGs and genetic alterations in 146 patients with CRC. Gene Ontology, Reactom, GSEA, and Human Disease Ontology were employed to study the biological process and pathways involved in CRC. Survival analysis on dysregulated genes in patients with CRC was conducted using Cox regression and Kaplan-Meier analysis. The STRING database was used to construct a protein-protein interaction (PPI) network. Moreover, candidate genes were subjected to ML-based analysis and the Receiver operating characteristic (ROC) curve. Subsequently, the expression of the identified genes was evaluated by Real-time PCR (RT-PCR) in another cohort of 64 patients with CRC. Gene variants affecting the regulation of candidate gene expressions were further validated followed by Whole Exome Sequencing (WES) in 15 patients with CRC. Results: A total of 3576 DEGs in the early stages of CRC and 2985 DEGs in the advanced stages of CRC were identified. ASPHD1 and ZBTB12 genes were identified as potential prognostic markers. Moreover, the combination of ASPHD and ZBTB12 genes was sensitive, and the two were considered specific markers, with an area under the curve (AUC) of 0.934, 1.00, and 0.986, respectively. The expression levels of these two genes were higher in patients with CRC. Moreover, our data identified two novel genetic variants-the rs925939730 variant in ASPHD1 and the rs1428982750 variant in ZBTB1-as being potentially involved in the regulation of gene expression. Conclusions: Our findings provide a proof of concept for the prognostic values of two novel genes-ASPHD1 and ZBTB12-and their associated variants (rs925939730 and rs1428982750) in CRC, supporting further functional analyses to evaluate the value of emerging biomarkers in colorectal cancer.

Tissue classification and diagnosis of colorectal cancer histopathology images using deep learning algorithms. Is the time ripe for clinical practice implementation?

Colorectal cancer is one of the most prevalent types of cancer, with histopathologic examination of biopsied tissue samples remaining the gold standard for diagnosis. During the past years, artificial intelligence (AI) has steadily found its way into the field of medicine and pathology, especially with the introduction of whole slide imaging (WSI). The main outcome of interest was the composite balanced accuracy (ACC) as well as the F1 score. The average reported ACC from the collected studies was 95.8 ±3.8%. Reported F1 scores reached as high as 0.975, with an average of 89.7 ±9.8%, indicating that existing deep learning algorithms can achieve in silico distinction between malignant and benign. Overall, the available state-of-the-art algorithms are non-inferior to pathologists for image analysis and classification tasks. However, due to their inherent uniqueness in their training and lack of widely accepted external validation datasets, their generalization potential is still limited.