Exploiting histopathological imaging for early detection of lung and colon cancer via ensemble deep learning model.

Cancer seems to have a vast number of deaths due to its heterogeneity, aggressiveness, and significant propensity for metastasis. The predominant categories of cancer that may affect males and females and occur worldwide are colon and lung cancer. A precise and on-time analysis of this cancer can increase the survival rate and improve the appropriate treatment characteristics. An efficient and effective method for the speedy and accurate recognition of tumours in the colon and lung areas is provided as an alternative to cancer recognition methods. Earlier diagnosis of the disease on the front drastically reduces the chance of death. Machine learning (ML) and deep learning (DL) approaches can accelerate this cancer diagnosis, facilitating researcher workers to study a vast majority of patients in a limited period and at a low cost. This research presents Histopathological Imaging for the Early Detection of Lung and Colon Cancer via Ensemble DL (HIELCC-EDL) model. The HIELCC-EDL technique utilizes histopathological images to identify lung and colon cancer (LCC). To achieve this, the HIELCC-EDL technique uses the Wiener filtering (WF) method for noise elimination. In addition, the HIELCC-EDL model uses the channel attention Residual Network (CA-ResNet50) model for learning complex feature patterns. Moreover, the hyperparameter selection of the CA-ResNet50 model is performed using the tuna swarm optimization (TSO) technique. Finally, the detection of LCC is achieved by using the ensemble of three classifiers such as extreme learning machine (ELM), competitive neural networks (CNNs), and long short-term memory (LSTM). To illustrate the promising performance of the HIELCC-EDL model, a complete set of experimentations was performed on a benchmark dataset. The experimental validation of the HIELCC-EDL model portrayed a superior accuracy value of 99.60% over recent approaches.

Incidental finding of intramural splenic heterotopy in the colon mimicking subepithelial neoplasm: a case report.

AIM: The aim of this case report is describe an unprecedented case with histological and immunohistochemical diagnosis of splenic heterotopy in the colon using material obtained by endoscopic ultrasound-guided biopsy. BACKGROUND: Splenic heterotopia is a benign condition characterized by the implantation of splenic tissue in areas distant from its usual anatomical site, such as the peritoneum, omentum, mesentery, liver, pancreas, and subcutaneous tissue and, more rarely, in locations such as the colon and brain. It is generally associated with a history of splenic trauma or splenectomy and typically does not cause specific symptoms. CASE PRESENTATION: A 35-year-old white male patient who was healthy, with no history of trauma or splenectomy, but had a family history of colorectal neoplasia underwent colonoscopy for screening. The examination revealed a large bulge in the proximal descending colon, covered by normal-appearing mucosa. Endoscopic ultrasound-guided puncture was performed with a 22 gauge fine needle biopsy, and the histopathological and immunohistochemical analysis results were consistent with a heterotopic spleen. CONCLUSIONS: This is the first report of a primary intramural colic splenosis case with histological and immunohistochemical diagnosis of splenic heterotopia in the colon, using material obtained by endoscopic ultrasound and ultrasound-guided biopsy.

[Abdominal obstruction revealing colonic lymphoma: a case report]. / Occlusion abdominale révélant un lymphome colique: à propos d'un cas.

Colonic lymphoma is a rare malignant gastrointestinal tumor that can be revealed by an exceptional and serious complication: intestinal obstruction. Treatment is based on surgery and chemotherapy. We here report a case of diffuse colonic large B-cell lymphoma revealed by occlusion and diagnosed based on the examination of surgical specimen in a 64-year-old man who was in complete remission after six courses of R-CHOP.

The Diagnostic Ability of GPT-3.5 and GPT-4.0 in Surgery: Comparative Analysis.

BACKGROUND: ChatGPT (OpenAI) has shown great potential in clinical diagnosis and could become an excellent auxiliary tool in clinical practice. This study investigates and evaluates ChatGPT in diagnostic capabilities by comparing the performance of GPT-3.5 and GPT-4.0 across model iterations. OBJECTIVE: This study aims to evaluate the precise diagnostic ability of GPT-3.5 and GPT-4.0 for colon cancer and its potential as an auxiliary diagnostic tool for surgeons and compare the diagnostic accuracy rates between GTP-3.5 and GPT-4.0. We precisely assess the accuracy of primary and secondary diagnoses and analyze the causes of misdiagnoses in GPT-3.5 and GPT-4.0 according to 7 categories: patient histories, symptoms, physical signs, laboratory examinations, imaging examinations, pathological examinations, and intraoperative findings. METHODS: We retrieved 316 case reports for intestinal cancer from the Chinese Medical Association Publishing House database, of which 286 cases were deemed valid after data cleansing. The cases were translated from Mandarin to English and then input into GPT-3.5 and GPT-4.0 using a simple, direct prompt to elicit primary and secondary diagnoses. We conducted a comparative study to evaluate the diagnostic accuracy of GPT-4.0 and GPT-3.5. Three senior surgeons from the General Surgery Department, specializing in Colorectal Surgery, assessed the diagnostic information at the Chinese PLA (People's Liberation Army) General Hospital. The accuracy of primary and secondary diagnoses was scored based on predefined criteria. Additionally, we analyzed and compared the causes of misdiagnoses in both models according to 7 categories: patient histories, symptoms, physical signs, laboratory examinations, imaging examinations, pathological examinations, and intraoperative findings. RESULTS: Out of 286 cases, GPT-4.0 and GPT-3.5 both demonstrated high diagnostic accuracy for primary diagnoses, but the accuracy rates of GPT-4.0 were significantly higher than GPT-3.5 (mean 0.972, SD 0.137 vs mean 0.855, SD 0.335; t285=5.753; P<.001). For secondary diagnoses, the accuracy rates of GPT-4.0 were also significantly higher than GPT-3.5 (mean 0.908, SD 0.159 vs mean 0.617, SD 0.349; t285=-7.727; P<.001). GPT-3.5 showed limitations in processing patient history, symptom presentation, laboratory tests, and imaging data. While GPT-4.0 improved upon GPT-3.5, it still has limitations in identifying symptoms and laboratory test data. For both primary and secondary diagnoses, there was no significant difference in accuracy related to age, gender, or system group between GPT-4.0 and GPT-3.5. CONCLUSIONS: This study demonstrates that ChatGPT, particularly GPT-4.0, possesses significant diagnostic potential, with GPT-4.0 exhibiting higher accuracy than GPT-3.5. However, GPT-4.0 still has limitations, particularly in recognizing patient symptoms and laboratory data, indicating a need for more research in real-world clinical settings to enhance its diagnostic capabilities.

Neoadjuvant envafolimab in a patient with MSI-H/dMMR colon cancer: a case report and literature review.

Clinical evidences of neoadjuvant immunotherapy in patients with mismatch repair deficient/microsatellite instability-high status (dMMR/MSI-H) colorectal cancer have not been well received. A 36-year-old man complained of recurrent right upper quadrant pain for more than 1 year, and the symptoms were not significantly relieved after 10 days of oral Changyanning tablet. The patient was finally diagnosed as dMMR/MSI-H colon cancer. Tumor regression was achieved after seven cycles of envafolimab treatment, and the patient obtained postoperative pathological complete response (pCR). Here, we report a case of MSI-H/dMMR transverse colon cancer, who obtained pCR after neoadjuvant envafolimab (a novel subcutaneous single-domain anti-PD-L1 antibody) with a favorable safety profile, aiming to enhance the experiences of comprehensive diagnosis and treatment of colon cancer.

Immune checkpoint inhibitors (ICIs) are a type of immunotherapy which can be used in the treatment of colorectal cancer. The authors here report the functions of envafolimab (a type of ICI) used before surgery to shrink tumor volume in colorectal cancer. A 36-year-old man suffered from repeated illness of right upper quadrant for over 1 year, and the illness were not recovered after 10 days of oral Changyanning tablet. The patient was finally diagnosed with colorectal cancer. After seven cycles of envafolimab treatment, tumor volume was significantly decreased, and the patient obtained favorable surgical outcomes with tolerable safety after surgery.

Usefulness of newer testing modalities for the accurate diagnosis of culture-negative endocarditis.

A woman in her 80s with a history of congestive heart failure, atrial arrhythmia treated with atrioventricular nodal ablation and permanent pacemaker (PPM) placement, mitral valve disease status post-repair and colon cancer status post-treatment was admitted for further evaluation of severe dyspnea on exertion. Imaging revealed vegetation on both the prosthetic mitral valve and the PPM lead. Blood cultures were collected without growth, so a cell-free DNA Karius test was performed, which can detect over 1000 pathogens and has a sensitivity between 87% and 93%. Testing returned positive results for Streptococcus bovis subspecies pasteurianus Given its association with colorectal cancer, abdominal imaging and an endoscopic biopsy were performed, showing recurrent colonic malignancy. The patient underwent a right colon resection prior to cardiac intervention. This report describes the clinical application of the novel cell-free DNA Karius test, which led to the diagnosis of recurrent colon cancer associated with S. pasteurianus endocarditis.

Biological and Clinical Characteristics of Proximal Colon Cancer: Far from Its Anatomical Subsite.

Colorectal cancer is a heterogeneous disease which can be divided into proximal colon cancer, distal colon cancer and rectal cancer according to the anatomical location of the tumor. Each anatomical location of colorectal cancer exhibits distinct characteristics in terms of incidence, clinical manifestations, molecular phenotypes, treatment, and prognosis. Notably, proximal colon cancer differs significantly from cancers of other anatomical subsites. An increasing number of studies have highlighted the presence of unique tumor biological characteristics in proximal colon cancer. Gaining a deeper understanding of these characteristics will facilitate accurate diagnosis and treatment approaches.

Income differences in time to colon cancer diagnosis.

INTRODUCTION: People with low income have worse outcomes throughout the cancer care continuum; however, little is known about income and the diagnostic interval. We described diagnostic pathways by neighborhood income and investigated the association between income and the diagnostic interval. METHODS: This was a retrospective cohort study of colon cancer patients diagnosed 2007-2019 in Ontario using routinely collected data. The diagnostic interval was defined as the number of days from the first colon cancer encounter to diagnosis. Asymptomatic pathways were defined as first encounter with a colonoscopy or guaiac fecal occult blood test not occurring in the emergency department and were examined separately from symptomatic pathways. Quantile regression was used to determine the association between neighborhood income quintile and the conditional 50th and 90th percentile diagnostic interval controlling for age, sex, rural residence, and year of diagnosis. RESULTS: A total of 64,303 colon cancer patients were included. Patients residing in the lowest income neighborhoods were more likely to be diagnosed through symptomatic pathways and in the emergency department. Living in low-income neighborhoods was associated with longer 50th and 90th-percentile symptomatic diagnostic intervals compared to patients living in the highest income neighborhoods. For example, the 90th percentile diagnostic interval was 15 days (95% CI 6-23) longer in patients living in the lowest income neighborhoods compared to the highest. CONCLUSION: These findings reveal income inequities during the diagnostic phase of colon cancer. Future work should determine pathways to reducing inequalities along the diagnostic interval and evaluate screening and diagnostic assessment programs from an equity perspective.

Clinical Calculator for Predicting Freedom From Recurrence After Resection of Stage I-III Colon Cancer in Patients With Microsatellite Instability.

PURPOSE: Outcome for patients with nonmetastatic, microsatellite instability (MSI) colon cancer is favorable: however, high-risk cohorts exist. This study was aimed at developing and validating a nomogram model to predict freedom from recurrence (FFR) for patients with resected MSI colon cancer. PATIENTS AND METHODS: Data from patients who underwent curative resection of stage I, II, or III MSI colon cancer in 2014-2021 (model training cohort, 384 patients, 33 events; median follow-up, 38.8 months) were retrospectively collected from institutional databases. Variables associated with recurrence in multivariable analysis were selected for inclusion in the clinical calculator. The calculator's predictive accuracy was measured with the concordance index and validated using data from patients who underwent treatment for MSI colon cancer in 2007-2013 (validation cohort, 164 patients, eight events; median follow-up, 84.8 months). RESULTS: T category and number of positive lymph nodes were significantly associated with recurrence in multivariable analysis and were selected for inclusion in the clinical calculator. The calculator's concordance index for FFR in the model training cohort was 0.812 (95% CI, 0.742 to 0.873), compared with 0.759 (95% CI, 0.683 to 0.840) for the staging schema of the eighth edition of the American Joint Committee on Cancer Staging Manual. The concordance index for the validation cohort was 0.744 (95% CI, 0.666 to 0.822), confirming robust predictive accuracy. CONCLUSION: Although in general patients with nonmetastatic MSI colon cancer had favorable outcome, patients with advanced T category and multiple metastatic lymph nodes had higher risk of recurrence. The clinical calculator identified patients with MSI colon cancer at high risk for recurrence, and this could inform surveillance strategies. In addition, the model could be used in trial design to identify patients suitable for novel adjuvant therapy.

Protein-losing enteropathy as a result of colon polyposis and colon cancer: a multidisciplinary approach to diagnosis and treatment.

A man in his 60s presented to our emergency department with severe peripheral pitting oedema, weight gain, dyspnoea and diarrhoea. Blood tests showed a hypoalbuminaemia of 15 g/L. A suspicion of protein-losing enteropathy arose after the exclusion of albuminuria, cardiac failure, protein deficiency and liver cirrhosis. An abdominal CT scan revealed a wall thickening of the colon, and a subsequent colonoscopy identified multiple large obstructive polyps in the ascending colon. The patient underwent a right hemicolectomy which revealed the presence of tubulovillous polyps and a pT2N0 colon carcinoma. Following surgery, the patient experienced clinical improvement with normalisation of serum albumin and resolution of the oedema.Protein-losing enteropathy should be considered an underlying syndrome in patients with peripheral oedema and hypoalbuminaemia in the absence of cardiac failure, proteinuria, malnutrition and hepatic disease. This diagnostic process requires a multidisciplinary approach. For adequate treatment, the primary cause of protein-losing enteropathy needs to be investigated.

The value of FPR, FAR, CAR, CPR in the auxiliary diagnosis of colon cancer.

Chronic malnutrition, abnormal blood clotting, and systemic inflammation contribute to the occurrence and progression of colon cancer. This study aimed to assess the diagnostic utility of the 100fibrinogen-to-prealbumin ratio (FPR), 100fibrinogen-to-albumin ratio (FAR), 100C-reactive protein-to-albumin ratio (CAR), and 100C-reactive protein-to-prealbumin ratio (CPR) in aiding the diagnosis of colon cancer. A total of 129 patients with colon cancer were enrolled between April 2015 and August 2022. While 129 patients with colon adenoma were selected as the control group. The serum levels of FAR, FPR, CAR, CPR, CEA, and CA125 in the colon cancer group were significantly higher than those in the colon adenoma group (P < .05). In Logistic regression analysis, high FAR and high FPR were identified as independent risk factors for colon cancer. Receiver operating characteristic (ROC) curve analysis results showed that Among the combined measures, FAR, FPR, CAR, and CPR had the highest diagnostic efficacy in distinguishing colon cancer from colon adenomas (AUC = 0.886, Sen = 80.62%, Spe = 81.40%). Thus, FAR, FPR, CAR, and CPR may serve as valuable biomarkers for the diagnosis of colon cancer, and the combined detection of FAR, FPR, CAR, and CPR can enhance the diagnostic efficiency for both colon cancer and colon adenoma.

Colon cancer diagnosis by means of explainable deep learning.

Early detection of the adenocarcinoma cancer in colon tissue by means of explainable deep learning, by classifying histological images and providing visual explainability on model prediction. Considering that in recent years, deep learning techniques have emerged as powerful techniques in medical image analysis, offering unprecedented accuracy and efficiency, in this paper we propose a method to automatically detect the presence of cancerous cells in colon tissue images. Various deep learning architectures are considered, with the aim of considering the best one in terms of quantitative and qualitative results. As a matter of fact, we consider qualitative results by taking into account the so-called prediction explainability, by providing a way to highlight on the tissue images the areas that from the model point of view are related to the presence of colon cancer. The experimental analysis, performed on 10,000 colon issue images, showed the effectiveness of the proposed method by obtaining an accuracy equal to 0.99. The experimental analysis shows that the proposed method can be successfully exploited for colon cancer detection and localisation from tissue images.

Changing colon cancer screening guidelines to age 45: Has it made a difference?

BACKGROUND: A concerning increase in early-onset colorectal cancer led to guideline changes in 2018 by the American Cancer Society to lower the age for initial colorectal cancer screening from 50 to 45 years of age. Although this would be expected to result in increased screening rates and subsequent earlier detection of colorectal cancer, the effect of this guideline change at a national level is not yet fully understood. METHODS: Using the National Cancer Database, we identified patients newly targeted for screening (age 45-49 years) diagnosed with colon cancer in either 2017 (early cohort) or 2019 (late cohort). The relationship between time period and stage of disease at presentation was examined by univariate analysis and in a multivariable logistic regression model. RESULTS: In total, 5,479 patients met inclusion criteria. The median age at diagnosis did not differ between patients in the late and early cohorts (47 years for both cohorts, P = .41). Patients in the late and early cohorts had equal odds of having stage III-IV disease (odds ratio for late cohort to early cohort, 1.05, 95% confidence interval, 0.94-1.17), and patients in the late cohort showed slightly increased odds of having higher T-stage (pT3 or pT4) disease (odds ratio, 1.20, 95% confidence interval, 1.05-1.35). CONCLUSION: Despite recommendations of earlier initial colorectal cancer screening, a clinically meaningful earlier shift in colon cancer stage was not observed in patients newly targeted for screening. Further studies will be needed to assess uptake of these recommendations by providers and patients and identify areas of improvement.

Refining Colon Cancer Screening, Antibody Therapy for Lung Cancer, and More-Highlights From ASCO 2024.

This Medical News article is an interview about JAMA Network highlights from the American Society of Clinical Oncology's annual meeting, hosted by Nora Disis, MD, editor in chief of JAMA Oncology and a JAMA deputy editor.

Identification and validation of the prognostic signature of a novel demethylation-related gene associated with the clinical features of colon cancer.

BACKGROUND: The aim of this study was to construct a prognostic model of colon cancer based on demethylation-related genes. An in-depth understanding of the relationship between the set of demethylated genes and colon cancer not only assists in revealing the pathogenesis of colon cancer but also provides strong support for future therapeutic strategies and individualized medicine. METHODS: Data were obtained from the TCGA database and the GEO-GSE39582 cohort. A risk score model for demethylation-related genes was developed using univariate Cox regression analysis and LASSO regression analysis. The accuracy and reliability of the model were confirmed using K-M survival analysis and ROC curve analysis. Additionally, a nomogram was created by integrating the risk score and clinicopathological variables. Finally, the biological function of the RCOR2 gene was verified by performing qPCR, MTT, colony formation, Transwell, and subcutaneous tumor formation assays in nude mice. RESULTS: We constructed a risk score model containing 30 demethylation-related genes for predicting the survival risk of patients with colon cancer. COAD patients were categorized into high-risk and low-risk groups, and Kaplan-Meier (KM) curve analysis revealed that the high-risk group was associated with a worse prognosis. Univariate and multivariate Cox regression analyses validated the risk score as an independent prognostic factor for COAD. We also analyzed the differences in the sensitivity to nine chemotherapeutic agents and small molecule targeted drugs between the high-risk and low-risk groups. Moreover, we performed experiments in COAD cell lines and nude mice to verify that RCOR2 was differentially expressed between tumor tissues and normal tissues and that high RCOR2 expression promoted a malignant phenotype of colon cancer. CONCLUSION: This study demonstrated the potential roles of demethylation-related genes in colon cancer by conducting a comprehensive analysis and constructing a risk score. These findings also highlight the ability of these genes to indicate patient prognosis and tumor immune microenvironment. Furthermore, this study provides a reliable predictive tool that can assist in guiding the treatment and management of colon cancer patients.

Quantification method of ctDNA using cell-free DNA methylation profile for noninvasive screening and monitoring of colon cancer.

BACKGROUND: Colon cancer ranks as the second most lethal form of cancer globally. In recent years, there has been active investigation into using the methylation profile of circulating tumor DNA (ctDNA), derived from blood, as a promising indicator for diagnosing and monitoring colon cancer. RESULTS: We propose a liquid biopsy-based epigenetic method developed by utilizing 49 patients and 260 healthy controls methylation profile data to screen and monitor colon cancer. Our method initially identified 901 colon cancer-specific hypermethylated (CaSH) regions in the tissues of the 49 cancer patients. We then used these CaSH regions to accurately quantify the amount of circulating tumor DNA (ctDNA) in the blood samples of these same patients, utilizing cell-free DNA methylation profiles. Notably, the methylation profiles of ctDNA in the blood exhibited high sensitivity (82%) and specificity (93%) in distinguishing patients with colon cancer from the control group, with an area under the curve of 0.903. Furthermore, we confirm that our method for ctDNA quantification is effective for monitoring cancer patients and can serve as a valuable tool for postoperative prognosis. CONCLUSIONS: This study demonstrated a successful application of the quantification of ctDNA among cfDNA using the original cancer tissue-derived CaSH region for screening and monitoring colon cancer.

[Gastric and colic localizations of myeloma; 3 case studies and literature review]. / Localisations digestives gastriques et coliques de myélomes ; étude de 3 cas et revue de la littérature.

Multiple myeloma is a malignant plasma cell proliferation located in the bone marrow and bones. It can secondarily manifest with extraosseous involvement, but the gastro-intestinal tract locations are rare. We report 3 cases of gastric and colonic localizations of myeloma in two males and one female, aged 66, 71 and 77years. Multiple myeloma had been diagnosed 1 to 7years before. Digestive symptoms were epigastric pain, rectal bleeding or an obstructive syndrome. Endoscopy revealed ulcerated and budding tumors in the stomach, and nodular pseudo-polypoid tumor formations or an ulcerated erythematous area in the colon. Histopathological examination of the biopsies showed a diffuse tumor cell proliferation in the lamina propria composed of cells with a plasmacytoid or plasmablastic appearance, expressing plasma cell markers such as CD138 on immunohistochemistry. The 3 patients died in the weeks following the diagnosis. The prognosis of digestive localizations of multiple myeloma remains very poor despite new therapies. In the presence of any digestive symptoms in these patients with multiple myeloma, more systematic endoscopy may allow an earlier diagnosis and the implementation of more effective therapies.

PPIH acts as a potential predictive biomarker for patients with common solid tumors.

BACKGROUND: Our previous studies have indicated that mRNA and protein levels of PPIH are significantly upregulated in Hepatocellular Carcinoma (LIHC) and could act as predictive biomarkers for patients with LIHC. Nonetheless, the expression and implications of PPIH in the etiology and progression of common solid tumors have yet to be explored, including its potential as a serum tumor marker. METHODS: We employed bioinformatics analyses, augmented with clinical sample evaluations, to investigate the mRNA and protein expression and gene regulation networks of PPIH in various solid tumors. We also assessed the association between PPIH expression and overall survival (OS) in cancer patients using Kaplan-Meier analysis with TCGA database information. Furthermore, we evaluated the feasibility and diagnostic efficacy of PPIH as a serum marker by integrating serological studies with established clinical tumor markers. RESULTS: Through pan-cancer analysis, we found that the expression levels of PPIH mRNA in multiple tumors were significantly different from those in normal tissues. This study is the first to report that PPIH mRNA and protein levels are markedly elevated in LIHC, Colon adenocarcinoma (COAD), and Breast cancer (BC), and are associated with a worse prognosis in these cancer patients. Conversely, serum PPIH levels are decreased in patients with these tumors (LIHC, COAD, BC, gastric cancer), and when combined with traditional tumor markers, offer enhanced sensitivity and specificity for diagnosis. CONCLUSION: Our findings propose that PPIH may serve as a valuable predictive biomarker in tumor patients, and its secreted protein could be a potential serum marker, providing insights into the role of PPIH in cancer development and progression.