Artificial intelligence in colon cancer: A commentary on advances and challenges.

Lung and colon cancers lead to a significant portion of deaths. Their simultaneous occurrence is uncommon, however, in the absence of early diagnosis, the metastasis of cancer cells is very high between these two organs. Currently, histopathological diagnosis and appropriate treatment are the only way to improve the chances of survival and reduce cancer mortality. Using artificial intelligence in the histopathological diagnosis of colon and lung cancer can provide significant help to specialists in identifying cases of colon and lung cancers with less effort, time and cost. The objective of this study is to set up a computer-aided diagnostic system that can accurately classify five types of colon and lung tissues (two classes for colon cancer and three classes for lung cancer) by analyzing their histopathological images. Using machine learning, features engineering and image processing techniques, the six models XGBoost, SVM, RF, LDA, MLP and LightGBM were used to perform the classification of histopathological images of lung and colon cancers that were acquired from the LC25000 dataset. The main advantage of using machine learning models is that they allow a better interpretability of the classification model since they are based on feature engineering; however, deep learning models are black box networks whose working is very difficult to understand due to the complex network design. The acquired experimental results show that machine learning models give satisfactory results and are very precise in identifying classes of lung and colon cancer subtypes. The XGBoost model gave the best performance with an accuracy of 99% and a F1-score of 98.8%. The implementation and the development of this model will help healthcare specialists identify types of colon and lung cancers. The code will be available upon request.

The brave new world of artificial intelligence: dawn of a new era

AI for colon cancer: A focus on classification, detection, and predictive modeling.

Colon cancer remains a significant global health burden, accounting for approximately 10% of all cancer cases worldwide and ranking as the second leading cause of cancer‐related mortality. Despite advances in treatment, the 5‐year survival rate for late‐stage colorectal cancer remains as low as 14%, whereas early detection can improve survival to over 90%. This review explores recent advancements in image‐based analyses for the morphology and staging of colon cancer, focusing on key imaging modalities, including colonoscopy, computed tomography (CT), magnetic resonance imaging (MRI), endoscopic ultrasound (EUS), histopathological analysis, and the integration of artificial intelligence (AI) and machine learning (ML) algorithms. A systematic literature review was conducted using peer‐reviewed studies from databases such as PubMed, Scopus, and IEEE Xplore. Selection criteria included studies published within the past decade that evaluated imaging techniques for colon cancer detection, staging, and treatment planning. AI and ML applications in colon cancer imaging were also examined, with an emphasis on their diagnostic accuracy, staging precision, and impact on clinical decision‐making. Findings indicate that AI‐assisted imaging techniques enhance lesion detection sensitivity (88%–94%) and improve staging accuracy compared to conventional radiology methods. AI models have also demonstrated superior predictive capabilities in treatment response and prognosis, with deep learning–based algorithms achieving over 90% accuracy in 5‐year survival prediction. Despite these advancements, challenges persist, including interobserver variability, dataset biases, regulatory concerns, and the need for standardized AI validation protocols. Addressing these challenges requires interdisciplinary collaboration among clinicians, researchers, and policymakers to refine AI algorithms, develop standardized imaging protocols, and ensure equitable AI applications across diverse populations. By leveraging advancements in imaging and AI‐driven analysis, colon cancer diagnosis and management can be significantly improved, ultimately enhancing early detection rates, treatment personalization, and patient survival outcomes.

ABSTRACTAccording to the World Health Organization, lung and colon cancers are known for their high mortality rates which necessitate the diagnosis of these cancers at an early stage. However, the limited availability of data such as histopathology images used for diagnosis of these cancers, poses a significant challenge while developing computer‐aided detection system. This makes it necessary to keep a check on the number of parameters in the artificial intelligence (AI) model used for the detection of these cancers considering the limited availability of the data. In this work, a customised compact and efficient convolution transformer architecture, termed, C3‐Transformer has been proposed for the diagnosis of colon and lung cancers using histopathological images. The proposed C3‐Transformer relies on convolutional tokenisation and sequence pooling approach to keep a check on the number of parameters and to combine the advantage of convolution neural network with the advantages of transformer model. The novelty of the proposed method lies in efficient classification of colon and lung cancers using the proposed C3‐Transformer architecture. The performance of the proposed method has been evaluated on the ‘LC25000’ dataset. Experimental results shows that the proposed method has been able to achieve average classification accuracy, precision and recall value of 99.30%, 0.9941 and 0.9950, in classifying the five different classes of colon and lung cancer with only 0.0316 million parameters. Thus, the present computer‐aided detection system developed using proposed C3‐Transformer can efficiently detect the colon and lung cancers using histopathology images with high detection accuracy.

The increasing prevalence of colon and lung cancer presents a considerable challenge to healthcare systems worldwide, emphasizing the critical necessity for early and accurate diagnosis to enhance patient outcomes. The precision of diagnosis heavily relies on the expertise of histopathologists, constituting a demanding task. The health and well‐being of patients are jeopardized in the absence of adequately trained histopathologists, potentially leading to misdiagnoses, unnecessary treatments, and tests, resulting in the inefficient utilization of healthcare resources. However, with substantial technological advancements, deep learning (DL) has emerged as a potent tool in clinical settings, particularly in the realm of medical imaging. This study leveraged the LC25000 dataset, encompassing 25,000 images of lung and colon tissue, introducing an innovative approach by employing a self‐organized operational neural network (Self‐ONN) to accurately detect lung and colon cancer in histopathology images. Subsequently, our novel model underwent comparison with five pretrained convolutional neural network (CNN) models: MobileNetV2‐SelfMLP, Resnet18‐SelfMLP, DenseNet201‐SelfMLP, InceptionV3‐SelfMLP, and MobileViTv2_200‐SelfMLP, where each multilayer perceptron (MLP) was replaced with Self‐MLP. The models’ performance was meticulously assessed using key metrics such as precision, recall, F1 score, accuracy, and area under the receiver operating characteristic (ROC) curve. The proposed model demonstrated exceptional overall accuracy, precision, sensitivity, F1 score, and specificity, achieving 99.74%, 99.74%, 99.74%, 99.74%, and 99.94%, respectively. This underscores the potential of artificial intelligence (AI) to significantly enhance diagnostic precision within clinical settings, portraying a promising avenue for improving patient care and outcomes. The synopsis of the literature provides a thorough examination of several DL and digital image processing methods used in the identification of cancer, with a primary emphasis on lung and colon cancer. The experiments use the LC25000 dataset, which consists of 25,000 photos, for the purposes of training and testing. Various techniques, such as CNNs, transfer learning, ensemble models, and lightweight DL architectures, have been used to accomplish accurate categorization of cancer tissue. Various investigations regularly show exceptional performance, with accuracy rates ranging from 96.19% to 99.97%. DL models such as EfficientNetV2, DHS‐CapsNet, and CNN‐based architectures such as VGG16 and GoogleNet variations have shown remarkable performance in obtaining high levels of accuracy. In addition, methods such as SSL and lightweight DL models provide encouraging outcomes in effectively managing large datasets. In general, the research emphasizes the efficacy of DL methods in successfully diagnosing cancer from histopathological pictures. It therefore indicates that DL has the potential to greatly improve medical diagnostic techniques.

Lung cancers and colon cancers are two of the leading causes of morbidity and mortality in human being. One of the essential elements to determining the type of cancer is the histopathological diagnosis. One of the most hazardous and severe diseases that people experience worldwide is colon and lung cancer, which has spread to become a common medical issue. It is very important to make a reliable and early discovery in order to reduce the danger of death. The difficulty of the task ultimately depends on the histopathologists’ experience. Recent times have seen a rise in the popularity of deep learning, which is now appreciated in the interpretation of medical imaging. As a result, artificial intelligence will soon become a useful technology. In order to identify lung cancers and colon cancer using histopathological pictures and more effective augmentation strategies, this research aims to utilize and modify the current pre-trained Convolutional Neural Network (CNN) based model. From the LC25000 dataset, the results were obtained. Precision, recall, f1score, and accuracy are all used to estimate the model performances. The findings show that the pre-trained and improved pre-trained models produced impressive outcomes ranging from 93% to 97% accuracy.

The correlation of liquid biopsy genomic data to radiomics in colon, pancreatic, lung and prostatic cancer patients.

3616 Background: MSI due to mismatch repair defects accounts for 15-20% of all CC, has high prognostic and predictive value and is broadly utilized in treatment decisions. Artificial intelligence (AI) integrated, label-free quantum cascade laser (QCL) based infrared (IR) imaging resolves spatial and molecular alterations such as MSI in unstained cancer tissue sections. We aimed to evaluate the method for microsatellite instability/stability (MSI/MSS) classification in samples from the prospective multicenter AIO CPP registry trial. Methods: Paraffin-embedded unstained cancer tissue slides from patients (pts.) participating in CPP were measured (avg. 30 min/slide) and analyzed. The cohort was split into training (train), test (test), and validation (vali) sets. Cancer regions were first preselected based on a self-developed convolutional neural network (CNN) CompSegNet (Schuhmacher, medrxiv 2021). A VGG-16 CNN then classified MSI/MSS in these regions. Endpoints were area under receiver operating characteristic (AUROC) and area under precision recall curve (AUPRC). Results: 547 pts. (train n=331, test n=69, vali n=147) were analyzed. The baseline characteristics for the sub-cohorts are illustrated in the table. Mutation (MT) status: RAS MT: train 30% / test 30% / vali 37%; BRAF MT: train 27% / test 23% / vali 14%. The preselection of cancer regions reached a validation AUROC of 1.0. The subsequent MSI/MSS classifier reached a validation AUROC of 0.9 and AUPRC of 0.74 (sensitivity 85%, specificity 84%). Conclusions: Our multicenter approach using AI integrated label-free IR imaging provides an automated, fast, and reliable classification for MSI/MSS with an AUROC of 0.9 (sensitivity 85%, specificity 84%) almost comparable to the present gold standard immunohistochemistry. The method described here requires less samples for training when compared to other AI approaches which could facilitate the development of prognostic/predictive classifiers in the setting of randomized controlled trials. This novel technique may support further understanding of the increasingly important MSI CC cohort and support treatment decisions e.g. in specific subgroups such as targetable fusions. We expect our approach to be a broadly applicable diagnostic tool in the future.[Table: see text]

340P Prediction of relapse in colon cancer patients by machine learning models combining radiomics and deep features extracted from baseline computed tomography

The recurrence rate of colon cancer after radical resection remains high at approximately 14%. Furthermore, evidence regarding the indications for adjuvant chemotherapy (Adj) for stage II/III colon cancer is limited. In this study, we used artificial intelligence (AI) to create a clinicopathological recurrence prediction model after radical resection for colon cancer, and we identified factors that predict disease recurrence. This study included 326 patients who underwent radical resection for stage II/III colon cancer at the Tokyo Medical University Hospital between 2000 and 2015. Analysis was performed using the AI system TabNet, with clinicopathological factors as covariates. The recurrence prediction accuracy was 96% in the Traininig group and 92% in the Test group. TabNet successfully identified the following recurrence prediction factors, ranked in descending order of the contribution importance: TNM-stage, Adj status, N-stage, venous invasion (v), histology, T-stage, sex, lymphatic invasion (Ly), and age. Analysis using AI enabled the creation of a recurrence prediction model with higher accuracy than previously reported models. The application of Adj for colorectal cancer is anticipated to be refined in the future, leading to lower recurrence rates.

Background/Objectives: This systematic review aims to synthesize recent studies on the integration of artificial intelligence (AI) into robotic surgery for oncological patients. It focuses on studies using real patient data and AI tools in robotic oncologic surgery. Methods: This systematic review followed PRISMA guidelines to ensure a robust methodology. A comprehensive search was conducted in June 2025 across Embase, Medline, Web of Science, medRxiv, Google Scholar, and IEEE databases, using MeSH terms, relevant keywords, and Boolean logic. Eligible studies were original research articles published in English between 2024 and 2025, focusing on AI applications in robotic cancer surgery using real patient data. Studies were excluded if they were non-peer-reviewed, used synthetic/preclinical data, addressed non-oncologic indications, or explored non-robotic AI applications. This approach ensured the selection of studies with practical clinical relevance. Results: The search identified 989 articles, with 17 duplicates removed. After screening, 921 were excluded, and 37 others were eliminated for reasons such as misalignment with inclusion criteria or lack of full text. Ultimately, 14 articles were included, with 8 using a retrospective design and 6 based on prospective data. These included articles that varied significantly in terms of the number of participants, ranging from several dozen to several thousand. These studies explored the application of AI across various stages of robotic oncologic surgery, including preoperative planning, intraoperative support, and postoperative predictions. The quality of 11 included studies was very good and good. Conclusions: AI significantly supports robotic oncologic surgery at various stages. In preoperative planning, it helps estimate the risk of conversion from minimally invasive to open colectomy in colon cancer. During surgery, AI enables precise tumor and vascular structure localization, enhancing resection accuracy, preserving healthy tissue, and reducing warm ischemia time. Postoperatively, AI’s flexibility in predicting functional and oncological outcomes through context-specific models demonstrates its value in improving patient care. Due to the relatively small number of cases analyzed, further analysis of the issues presented in this review is necessary.

95 Background: Watson for Oncology (WFO) is an artificial intelligence (AI) based clinical decision-support tool trained by Memorial Sloan Kettering. This retrospective observational study of breast, lung, colon and rectal cancer examined the concordance of treatment options provided by WFO to treatments selected by clinicians at Bumrungrad International Hospital (BIH) as a function of stage or cancer type. Methods: Concordance between WFO treatment options and treatments selected by BIH clinicians (WFO-BIH concordance) was defined as identical or equally acceptable treatments, as determined by a panel of experts blinded to the source of treatment. Relationships between stage or type of cancer and WFO-BIH concordant treatments were evaluated by Chi-squared analysis. Results: Analysis revealed a statistically significant association ( P = 0.02) between cancer stage and concordance. For all 4 cancer types combined, stages I-III demonstrated higher concordance than stage IV. A highly significant association ( P < 0.001) between concordance and cancer type was identified. Colon cancer demonstrated the highest concordance, followed by rectal, lung and breast cancer. Reasons for discordance, when given, related to oncologist or patient preferences, and treatment availability. Conclusions: BIH clinicians tended to agree more with WFO therapeutic options for stage I-III cancers and colon cancer in general, as compared to relatively less agreement for stage IV cancers and breast cancer in general, suggesting the need to understand reasons for discordance among all cancer types and stages. An AI tool, trained by experts in the U.S., provides treatment options consistent with some therapies selected in international settings, but preferences and treatment availability may affect choices made in practice. [Table: see text]

Lung and colon (LC) cancers are among the most deadly types of cancer, often resulting in death. However, the chances of survival significantly increase with the early detection of these cancers. This study addresses the challenge of early detection of LC tumors, which is crucial for effective treatment. LC cancer is one of the most common tumors that require early detection. However, these tumors appear similar in their early stages, making it challenging for doctors to differentiate between them. To overcome this challenge, we propose an AI-based diagnostic model for detecting LC tumors. Artificial intelligence (AI) techniques have been employed to address this challenge. This study proposes two histopathological image analysis strategies for the early detection of LC cancer. The first strategy involves the diagnosis of LC cancer using decision tree (DT) and random forest (RF) networks with CNN model features, namely ResNet50, DenseNet169, and MobileNet, based on geometric active contour (GAC) and ant colony optimization (ACO) algorithms. The second strategy involves the diagnosis of LC cancer using DT and RF classifiers with the features of combined CNN, namely ResNet50-DenseNet169, DenseNet169-MobileNet, DenseNet169-MobileNet, and ResNet50-DenseNet169-MobileNet, based on the GAC and ACO algorithms. All strategies have demonstrated good results for early stage LC cancer detection. The RF network, which utilized the combined features extracted from the ResNet50- MobileNet-DenseNet169 models, demonstrated notable performance with an AUC of 99.7%, sensitivity of 99.72%, accuracy of 99.8%, precision of 99.76%, and specificity of 99.78%.

Background: Colon cancer is a heterogeneous disease, and rare subtypes like triphasic colon cancer are difficult to detect with standard methods. Artificial intelligence (AI)-driven ultrasound combined with genomic analysis offers a promising approach to improve subtype identification and uncover molecular mechanisms. Methods: The authors used an AI-driven ultrasound model to identify rare triphasic colon cancer, characterized by a mix of epithelial, mesenchymal, and proliferative components. The molecular features were validated using immunohistochemistry, targeting classical epithelial markers, mesenchymal markers, and proliferation indices. Subsequently, ultrasound genomic techniques were applied to map transcriptomic alterations in conventional colon cancer onto ultrasound images. Differentially expressed genes were identified using the edgeR package. Pearson correlation analysis was performed to assess the relationship between imaging features and molecular markers. Results: The AI-driven ultrasound model successfully identified rare triphasic features in colon cancer. These imaging features showed significant correlation with immunohistochemical expression of epithelial markers, mesenchymal markers, and proliferation index. Moreover, ultrasound genomic techniques revealed that multiple oncogenic transcripts could be spatially mapped to distinct patterns within the ultrasound images of conventional colon cancer and were involved in classical cancer-related pathway. Conclusions: AI-enhanced ultrasound imaging enables noninvasive identification of rare triphasic colon cancer and reveals functional molecular signatures in general colon cancer. This integrative approach may support future precision diagnostics and image-guided therapies.