Integrating artificial intelligence techniques for advancements in colorectal cancer management: navigating past and predicting future direction.

Artificial Intelligence (AI) in the last few years has emerged as a valuable tool in managing colorectal cancer, revolutionizing its management at different stages. In early detection and diagnosis, AI leverages its prowess in imaging analysis, scrutinizing CT scans, MRI, and colonoscopy views to identify polyps and tumors. This ability enables timely and accurate diagnoses, initiating treatment at earlier stages. AI has helped in personalized treatment planning because of its ability to integrate diverse patient data, including tumor characteristics, medical history, and genetic information. Integrating AI into clinical decision support systems guarantees evidence-based treatment strategy suggestions in multidisciplinary clinical settings, thus improving patient outcomes. This narrative review explores the multifaceted role of AI, spanning early detection of colorectal cancer, personalized treatment planning, polyp detection, lymph node evaluation, cancer staging, robotic colorectal surgery, and training of colorectal surgeons.

An effective colorectal polyp classification for histopathological images based on supervised contrastive learning.

Early detection of colon adenomatous polyps is pivotal in reducing colon cancer risk. In this context, accurately distinguishing between adenomatous polyp subtypes, especially tubular and tubulovillous, from hyperplastic variants is crucial. This study introduces a cutting-edge computer-aided diagnosis system optimized for this task. Our system employs advanced Supervised Contrastive learning to ensure precise classification of colon histopathology images. Significantly, we have integrated the Big Transfer model, which has gained prominence for its exemplary adaptability to visual tasks in medical imaging. Our novel approach discerns between in-class and out-of-class images, thereby elevating its discriminatory power for polyp subtypes. We validated our system using two datasets: a specially curated one and the publicly accessible UniToPatho dataset. The results reveal that our model markedly surpasses traditional deep convolutional neural networks, registering classification accuracies of 87.1% and 70.3% for the custom and UniToPatho datasets, respectively. Such results emphasize the transformative potential of our model in polyp classification endeavors.

Unveiling camouflaged and partially occluded colorectal polyps: Introducing CPSNet for accurate colon polyp segmentation.

BACKGROUND: Segmenting colorectal polyps presents a significant challenge due to the diverse variations in their size, shape, texture, and intricate backgrounds. Particularly demanding are the so-called "camouflaged" polyps, which are partially concealed by surrounding tissues or fluids, adding complexity to their detection. METHODS: We present CPSNet, an innovative model designed for camouflaged polyp segmentation. CPSNet incorporates three key modules: the Deep Multi-Scale-Feature Fusion Module, the Camouflaged Object Detection Module, and the Multi-Scale Feature Enhancement Module. These modules work collaboratively to improve the segmentation process, enhancing both robustness and accuracy. RESULTS: Our experiments confirm the effectiveness of CPSNet. When compared to state-of-the-art methods in colon polyp segmentation, CPSNet consistently outperforms the competition. Particularly noteworthy is its performance on the ETIS-LaribPolypDB dataset, where CPSNet achieved a remarkable 2.3% increase in the Dice coefficient compared to the Polyp-PVT model. CONCLUSION: In summary, CPSNet marks a significant advancement in the field of colorectal polyp segmentation. Its innovative approach, encompassing multi-scale feature fusion, camouflaged object detection, and feature enhancement, holds considerable promise for clinical applications.

From Staining Techniques to Artificial Intelligence: A Review of Colorectal Polyps Characterization.

This review article provides a comprehensive overview of the evolving techniques in image-enhanced endoscopy (IEE) for the characterization of colorectal polyps, and the potential of artificial intelligence (AI) in revolutionizing the diagnostic accuracy of endoscopy. We discuss the historical use of dye-spray and virtual chromoendoscopy for the characterization of colorectal polyps, which are now being replaced with more advanced technologies. Specifically, we focus on the application of AI to create a "virtual biopsy" for the detection and characterization of colorectal polyps, with potential for replacing histopathological diagnosis. The incorporation of AI has the potential to provide an evolutionary learning system that aids in the diagnosis and management of patients with the best possible outcomes. A detailed analysis of the literature supporting AI-assisted diagnostic techniques for the detection and characterization of colorectal polyps, with a particular emphasis on AI's characterization mechanism, is provided. The benefits of AI over traditional IEE techniques, including the reduction in human error in diagnosis, and its potential to provide an accurate diagnosis with similar accuracy to the gold standard are presented. However, the need for large-scale testing of AI in clinical practice and the importance of integrating patient data into the diagnostic process are acknowledged. In conclusion, the constant evolution of IEE technology and the potential for AI to revolutionize the field of endoscopy in the future are presented.

Two-stage deep-learning-based colonoscopy polyp detection incorporating fisheye and reflection correction.

BACKGROUND AND AIM: Colonoscopy is a useful method for the diagnosis and management of colorectal diseases. Many computer-aided systems have been developed to assist clinicians in detecting colorectal lesions by analyzing colonoscopy images. However, fisheye-lens distortion and light reflection in colonoscopy images can substantially affect the clarity of these images and their utility in detecting polyps. This study proposed a two-stage deep-learning model to correct distortion and reflections in colonoscopy images and thus facilitate polyp detection. METHODS: Images were collected from the PolypSet dataset, the Kvasir-SEG dataset, and one medical center's patient archiving and communication system. The training, validation, and testing datasets comprised 808, 202, and 1100 images, respectively. The first stage involved the correction of fisheye-related distortion in colonoscopy images and polyp detection, which was performed using a convolutional neural network. The second stage involved the use of generative and adversarial networks for correcting reflective colonoscopy images before the convolutional neural network was used for polyp detection. RESULTS: The model had higher accuracy when it was validated using corrected images than when it was validated using uncorrected images (96.8% vs 90.8%, P < 0.001). The model's accuracy in detecting polyps in the Kvasir-SEG dataset reached 96%, and the area under the receiver operating characteristic curve was 0.94. CONCLUSION: The proposed model can facilitate the clinical diagnosis of colorectal polyps and improve the quality of colonoscopy.

Spatio-Temporal Feature Transformation Based Polyp Recognition for Automatic Detection: Higher Accuracy than Novice Endoscopists in Colorectal Polyp Detection and Diagnosis.

BACKGROUND: Artificial intelligence represents an emerging area with promising potential for improving colonoscopy quality. AIMS: To develop a colon polyp detection model using STFT and evaluate its performance through a randomized sample experiment. METHODS: Colonoscopy videos from the Digestive Endoscopy Center of the First Affiliated Hospital of Anhui Medical University, recorded between January 2018 and November 2022, were selected and divided into two datasets. To verify the model's practical application in clinical settings, 1500 colonoscopy images and 1200 polyp images of various sizes were randomly selected from the test set and compared with the STFT model's and endoscopists' recognition results with different years of experience. RESULTS: In the randomized sample trial involving 1500 colonoscopy images, the STFT model demonstrated significantly higher accuracy and specificity compared to endoscopists with low years of experience (0.902 vs. 0.809, 0.898 vs. 0.826, respectively). Moreover, the model's sensitivity was 0.904, which was higher than that of endoscopists with low, medium, or high years of experience (0.80, 0.896, 0.895, respectively), with statistical significance (P < 0.05). In the randomized sample experiment of 1200 polyp images of different sizes, the accuracy of the STFT model was significantly higher than that of endoscopists with low years of experience when the polyp size was ≤ 0.5 cm and 0.6-1.0 cm (0.902 vs. 0.70, 0.953 vs. 0.865, respectively). CONCLUSIONS: The STFT-based colon polyp detection model exhibits high accuracy in detecting polyps in colonoscopy videos, with a particular efficiency in detecting small polyps (≤ 0.5 cm)(0.902 vs. 0.70, P < 0.001).

Natural History of Colorectal Polyps Undergoing Longitudinal in Vivo CT Colonography Surveillance.

Background The natural history of colorectal polyps is not well characterized due to clinical standards of care and other practical constraints limiting in vivo longitudinal surveillance. Established CT colonography (CTC) clinical screening protocols allow surveillance of small (6-9 mm) polyps. Purpose To assess the natural history of colorectal polyps followed with CTC in a clinical screening program, with histopathologic correlation for resected polyps. Materials and Methods In this retrospective study, CTC was used to longitudinally monitor small colorectal polyps in asymptomatic adult patients from April 1, 2004, to August 31, 2020. All patients underwent at least two CTC examinations. Polyp growth patterns across multiple time points were analyzed, with histopathologic context for resected polyps. Regression analysis was performed to evaluate predictors of advanced histopathology. Results In this study of 475 asymptomatic adult patients (mean age, 56.9 years ± 6.7 [SD]; 263 men), 639 unique polyps (mean initial diameter, 6.3 mm; volume, 50.2 mm3) were followed for a mean of 5.1 years ± 2.9. Of these 639 polyps, 398 (62.3%) underwent resection and histopathologic evaluation, and 41 (6.4%) proved to be histopathologically advanced (adenocarcinoma, high-grade dysplasia, or villous content), including two cancers and 38 tubulovillous adenomas. Advanced polyps showed mean volume growth of +178% per year (752% per year for adenocarcinomas) compared with +33% per year for nonadvanced polyps and -3% per year for unresected, unretrieved, or resolved polyps (P < .001). In addition, 90% of histologically advanced polyps achieved a volume of 100 mm3 and/or volume growth rate of 100% per year, compared with 29% of nonadvanced and 16% of unresected or resolved polyps (P < .001). Polyp volume-to-diameter ratio was also significantly greater for advanced polyps. For polyps observed at three or more time points, most advanced polyps demonstrated an initial slower growth interval, followed by a period of more rapid growth. Conclusion Small colorectal polyps ultimately proving to be histopathologically advanced neoplasms demonstrated substantially faster growth and attained greater overall size compared with nonadvanced polyps. Clinical trial registration no. NCT00204867 © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Dachman in this issue.

A non-aligned translation with a neoplastic classifier regularization to include vascular NBI patterns in standard colonoscopies.

Polyp vascular patterns are key to categorizing colorectal cancer malignancy. These patterns are typically observed in situ from specialized narrow-band images (NBI). Nonetheless, such vascular characterization is lost from standard colonoscopies (the primary attention mechanism). Besides, even for NBI observations, the categorization remains biased for expert observations, reporting errors in classification from 59.5% to 84.2%. This work introduces an end-to-end computational strategy to enhance in situ standard colonoscopy observations, including vascular patterns typically observed from NBI mechanisms. These retrieved synthetic images are achieved by adjusting a deep representation under a non-aligned translation task from optical colonoscopy (OC) to NBI. The introduced scheme includes an architecture to discriminate enhanced neoplastic patterns achieving a remarkable separation into the embedding representation. The proposed approach was validated in a public dataset with a total of 76 sequences, including standard optical sequences and the respective NBI observations. The enhanced optical sequences were automatically classified among adenomas and hyperplastic samples achieving an F1-score of 0.86%. To measure the sensibility capability of the proposed approach, serrated samples were projected to the trained architecture. In this experiment, statistical differences from three classes with a ρ-value <0.05 were reported, following a Mann-Whitney U test. This work showed remarkable polyp discrimination results in enhancing OC sequences regarding typical NBI patterns. This method also learns polyp class distributions under the unpaired criteria (close to real practice), with the capability to separate serrated samples from adenomas and hyperplastic ones.

Linked-color imaging with or without artificial intelligence for adenoma detection: a randomized trial.

BACKGROUND: Adenoma detection rate (ADR) is an important indicator of colonoscopy quality and colorectal cancer incidence. Both linked-color imaging (LCI) with artificial intelligence (LCA) and LCI alone increase adenoma detection during colonoscopy, although it remains unclear whether one modality is superior. This study compared ADR between LCA and LCI alone, including according to endoscopists' experience (experts and trainees) and polyp size. METHODS: Patients undergoing colonoscopy for positive fecal immunochemical tests, follow-up of colon polyps, and abdominal symptoms at a single institution were randomly assigned to the LCA or LCI group. ADR, adenoma per colonoscopy (APC), cecal intubation time, withdrawal time, number of adenomas per location, and adenoma size were compared. RESULTS: The LCA (n=400) and LCI (n=400) groups showed comparable cecal intubation and withdrawal times. The LCA group showed a significantly higher ADR (58.8% vs. 43.5%; P<0.001) and mean (95%CI) APC (1.31 [1.15 to 1.47] vs. 0.94 [0.80 to 1.07]; P<0.001), particularly in the ascending colon (0.30 [0.24 to 0.36] vs. 0.20 [0.15 to 0.25]; P=0.02). Total number of nonpolypoid-type adenomas was also significantly higher in the LCA group (0.15 [0.09 to 0.20] vs. 0.08 [0.05 to 0.10]; P=0.02). Small polyps (≤5, 6-9mm) were detected significantly more frequently in the LCA group (0.75 [0.64 to 0.86] vs. 0.48 [0.40 to 0.57], P<0.001 and 0.34 [0.26 to 0.41] vs. 0.24 [0.18 to 0.29], P=0.04, respectively). In both groups, ADR was not significantly different between experts and trainees. CONCLUSIONS: LCA was significantly superior to LCI alone in terms of ADR.

Evaluating false-positive detection in a computer-aided detection system for colonoscopy.

BACKGROUND AND AIM: Computer-aided detection (CADe) systems can efficiently detect polyps during colonoscopy. However, false-positive (FP) activation is a major limitation of CADe. We aimed to compare the rate and causes of FP using CADe before and after an update designed to reduce FP. METHODS: We analyzed CADe-assisted colonoscopy videos recorded between July 2022 and October 2022. The number and causes of FPs and excessive time spent by the endoscopist on FP (ET) were compared pre- and post-update using 1:1 propensity score matching. RESULTS: During the study period, 191 colonoscopy videos (94 and 97 in the pre- and post-update groups, respectively) were recorded. Propensity score matching resulted in 146 videos (73 in each group). The mean number of FPs and median ET per colonoscopy were significantly lower in the post-update group than those in the pre-update group (4.2 ± 3.7 vs 18.1 ± 11.1; P < 0.001 and 0 vs 16 s; P < 0.001, respectively). Mucosal tags, bubbles, and folds had the strongest association with decreased FP post-update (pre-update vs post-update: 4.3 ± 3.6 vs 0.4 ± 0.8, 0.32 ± 0.70 vs 0.04 ± 0.20, and 8.6 ± 6.7 vs 1.6 ± 1.7, respectively). There was no significant decrease in the true positive rate (post-update vs pre-update: 95.0% vs 99.2%; P = 0.09) or the adenoma detection rate (post-update vs pre-update: 52.1% vs 49.3%; P = 0.87). CONCLUSIONS: The updated CADe can reduce FP without impairing polyp detection. A reduction in FP may help relieve the burden on endoscopists.

Dual-branch multi-information aggregation network with transformer and convolution for polyp segmentation.

Computer-Aided Diagnosis (CAD) for polyp detection offers one of the most notable showcases. By using deep learning technologies, the accuracy of polyp segmentation is surpassing human experts. In such CAD process, a critical step is concerned with segmenting colorectal polyps from colonoscopy images. Despite remarkable successes attained by recent deep learning related works, much improvement is still anticipated to tackle challenging cases. For instance, the effects of motion blur and light reflection can introduce significant noise into the image. The same type of polyps has a diversity of size, color and texture. To address such challenges, this paper proposes a novel dual-branch multi-information aggregation network (DBMIA-Net) for polyp segmentation, which is able to accurately and reliably segment a variety of colorectal polyps with efficiency. Specifically, a dual-branch encoder with transformer and convolutional neural networks (CNN) is employed to extract polyp features, and two multi-information aggregation modules are applied in the decoder to fuse multi-scale features adaptively. Two multi-information aggregation modules include global information aggregation (GIA) module and edge information aggregation (EIA) module. In addition, to enhance the representation learning capability of the potential channel feature association, this paper also proposes a novel adaptive channel graph convolution (ACGC). To validate the effectiveness and advantages of the proposed network, we compare it with several state-of-the-art (SOTA) methods on five public datasets. Experimental results consistently demonstrate that the proposed DBMIA-Net obtains significantly superior segmentation performance across six popularly used evaluation matrices. Especially, we achieve 94.12% mean Dice on CVC-ClinicDB dataset which is 4.22% improvement compared to the previous state-of-the-art method PraNet. Compared with SOTA algorithms, DBMIA-Net has a better fitting ability and stronger generalization ability.

Improvement of adenoma detection rate by two computer-aided colonic polyp detection systems in high adenoma detectors: a randomized multicenter trial.

BACKGROUND: This study aimed to evaluate the benefits of a self-developed computer-aided polyp detection system (SD-CADe) and a commercial system (CM-CADe) for high adenoma detectors compared with white-light endoscopy (WLE) as a control. METHODS: Average-risk 50-75-year-old individuals who underwent screening colonoscopy at five referral centers were randomized to SD-CADe, CM-CADe, or WLE groups (1:1:1 ratio). Trainees and staff with an adenoma detection rate (ADR) of ≥35% were recruited. The primary outcome was ADR. Secondary outcomes were the proximal adenoma detection rate (pADR), advanced adenoma detection rate (AADR), and the number of adenomas, proximal adenomas, and advanced adenomas per colonoscopy (APC, pAPC, and AAPC, respectively). RESULTS: The study enrolled 1200 participants. The ADR in the control, CM-CADe, and SD-CADe groups was 38.3%, 50.0%, and 54.8%, respectively. The pADR was 23.0%, 32.3%, and 38.8%, respectively. AADR was 6.0%, 10.3%, and 9.5%, respectively. After adjustment, the ADR and pADR in both intervention groups were significantly higher than in controls (all P<0.05). The APC in the control, CM-CADe, and SD-CADe groups was 0.66, 1.04, and 1.16, respectively. The pAPC was 0.33, 0.53, and 0.64, respectively, and the AAPC was 0.07, 0.12, and 0.10, respectively. Both CADe systems showed significantly higher APC and pAPC than WLE. AADR and AAPC were improved in both CADe groups versus control, although the differences were not statistically significant. CONCLUSION: Even in high adenoma detectors, CADe significantly improved ADR and APC. The AADR tended to be higher with both systems, and this may enhance colorectal cancer prevention.

Canadian Association of Radiologists Practice Guidelines for Computed Tomography Colonography.

Colon cancer is the third most common malignancy in Canada. Computed tomography colonography (CTC) provides a creditable and validated option for colon screening and assessment of known pathology in patients for whom conventional colonoscopy is contraindicated or where patients self-select to use imaging as their primary modality for initial colonic assessment. This updated guideline aims to provide a toolkit for both experienced imagers (and technologists) and for those considering launching this examination in their practice. There is guidance for reporting, optimal exam preparation, tips for problem solving to attain high quality examinations in challenging scenarios as well as suggestions for ongoing maintenance of competence. We also provide insight into the role of artificial intelligence and the utility of CTC in tumour staging of colorectal cancer. The appendices provide more detailed guidance into bowel preparation and reporting templates as well as useful information on polyp stratification and management strategies. Reading this guideline should equip the reader with the knowledge base to perform colonography but also provide an unbiased overview of its role in colon screening compared with other screening options.

Usefulness and Educational Benefit of a Virtual Scale Endoscope in Measuring Colorectal Polyp Size.

INTRODUCTION: The virtual scale endoscope (VSE) is a newly introduced endoscope that helps endoscopists in measuring colorectal polyp size (CPS) during colonoscopy by displaying a virtual scale. This study aimed to determine the usefulness of the VSE for CPS measurement and the educational benefit of using VSE images to improve CPS estimation accuracy. METHODS: This study included 42 colorectal polyps in 26 patients treated at Hiroshima University Hospital. In study 1, CPS measured using a VSE before endoscopic mucosal resection was compared with CPS measured on resected specimens, and the agreement between the two measurement methods was evaluated via Bland-Altman analysis. In study 2, 14 endoscopists (5 beginners, 5 intermediates, and 4 experts) took a pre-test to determine the size of 42 polyps. After the pre-test, a lecture on CPS measurement using VSE images was given. One month later, the endoscopists took a post-test to compare CPS accuracy before and after the lecture. RESULTS: In study 1, Bland-Altman analysis revealed no fixed or proportional errors. The mean bias ±95% limits of agreement (±1.96 standard deviations) of the measurement error was -0.05 ± 0.21 mm, indicating that the agreement between two measurement methods was sufficient. In study 2, the accuracy of CPS measurement was significantly higher among beginners (59.5% vs. 26.7%, p < 0.01) and intermediates (65.2% vs. 44.3%, p < 0.05) in the post-test than in the pre-test. CONCLUSION: The VSE accurately measures CPS before resection, and its images are useful teaching tools for beginner and intermediate endoscopists.

Direct comparison of multiple computer-aided polyp detection systems.

BACKGROUND AND STUDY AIMS: Artificial intelligence (AI)-based systems for computer-aided detection (CADe) of polyps receive regular updates and occasionally offer customizable detection thresholds, both of which impact their performance, but little is known about these effects. This study aimed to compare the performance of different CADe systems on the same benchmark dataset. METHODS: 101 colonoscopy videos were used as benchmark. Each video frame with a visible polyp was manually annotated with bounding boxes, resulting in 129 705 polyp images. The videos were then analyzed by three different CADe systems, representing five conditions: two versions of GI Genius, Endo-AID with detection Types A and B, and EndoMind, a freely available system. Evaluation included an analysis of sensitivity and false-positive rate, among other metrics. RESULTS: Endo-AID detection Type A, the earlier version of GI Genius, and EndoMind detected all 93 polyps. Both the later version of GI Genius and Endo-AID Type B missed 1 polyp. The mean per-frame sensitivities were 50.63 % and 67.85 %, respectively, for the earlier and later versions of GI Genius, 65.60 % and 52.95 %, respectively, for Endo-AID Types A and B, and 60.22 % for EndoMind. CONCLUSIONS: This study compares the performance of different CADe systems, different updates, and different configuration modes. This might help clinicians to select the most appropriate system for their specific needs.

Boundary uncertainty aware network for automated polyp segmentation.

Recently, leveraging deep neural networks for automated colorectal polyp segmentation has emerged as a hot topic due to the favored advantages in evading the limitations of visual inspection, e.g., overwork and subjectivity. However, most existing methods do not pay enough attention to the uncertain areas of colonoscopy images and often provide unsatisfactory segmentation performance. In this paper, we propose a novel boundary uncertainty aware network (BUNet) for precise and robust colorectal polyp segmentation. Specifically, considering that polyps vary greatly in size and shape, we first adopt a pyramid vision transformer encoder to learn multi-scale feature representations. Then, a simple yet effective boundary exploration module (BEM) is proposed to explore boundary cues from the low-level features. To make the network focus on the ambiguous area where the prediction score is biased to neither the foreground nor the background, we further introduce a boundary uncertainty aware module (BUM) that explores error-prone regions from the high-level features with the assistance of boundary cues provided by the BEM. Through the top-down hybrid deep supervision, our BUNet implements coarse-to-fine polyp segmentation and finally localizes polyp regions precisely. Extensive experiments on five public datasets show that BUNet is superior to thirteen competing methods in terms of both effectiveness and generalization ability.