Intestinal ganglioneuromatosis represents a rare intestinal neuroendocrine disorder, typically identified incidentally during colonoscopy. Isolated ganglioneuromas are clinically rare and generally demonstrate no clear association with hereditary syndromes. Current clinical guidelines offer no specific diagnostic or therapeutic recommendations for solitary polypoid ganglioneuromas. This report details the discovery of an isolated colonic ganglioneuroma during a routine screening colonoscopy. Complete resection of the lesion via colonic endoscopic submucosal dissection resulted in favorable outcomes. This case aimed to offer clinical insights for the management of such lesions.

Accurate and efficient polyp segmentation is essential for computer-aided colorectal cancer screening, yet achieving a favorable balance among segmentation accuracy, computational efficiency, and cross-dataset generalization remains challenging. Recent studies suggest that Mamba-based state-space modeling can enhance long-range dependency modeling with relatively low complexity, but how lightweight Mamba integration strategies affect dense prediction frameworks for polyp segmentation remains insufficiently understood. In this study, we present LiteMamba-Seg, a lightweight polyp segmentation framework built on a U-Net-like encoder-decoder architecture with a ResNet34 backbone, and conduct an empirical evaluation of different lightweight Mamba integration strategies. Specifically, we investigate bottleneck-only integration as well as alternative second-stage placements at an encoder-side intermediate stage and a decoder-side reconstruction stage. Experimental results on four public benchmark datasets show that LiteMamba-Seg achieves competitive segmentation performance while maintaining a lightweight design and real-time model-level inference, with 26.81 M parameters, 13.89 GFLOPs, and 167.73 FPS. Further ablation, controlled placement, multi-seed, robustness, boundary, calibration, and false-positive analyses indicate that the effect of Mamba integration depends on its placement within the network. In particular, decoder-side reconstruction-stage integration yields more favorable quantitative and qualitative results than encoder-side intermediate placement across the evaluated benchmarks. These findings suggest that, for lightweight polyp segmentation frameworks, Mamba integration should be considered jointly with placement strategy rather than simply increasing the number of sequence modeling blocks.

Inflammatory cloacogenic polyps are rare and often discovered either during routine colorectal cancer screenings or in symptomatic patients presenting with hematochezia. In unusual cases, they can present as an adhesive obstruction with radiological and clinical findings suggestive of a suspicious recurrent colorectal malignancy lesion. Because these polyps can mimic cancer during endoscopy, a detailed tissue examination is crucial for making the correct diagnosis and planning treatment. In this report, we share a challenging case where a patient with a history of cancer presented with signs that strongly suggested a malignant recurrence, but the final diagnosis was an inflammatory cloacogenic polyp. This case highlights the critical role of regular endoscopic monitoring in managing such complex conditions.

CT colonography (CTC) is a validated screening test for detection and prevention of colorectal cancer (CRC). In the United States, screening CTC has been covered for Medicare beneficiaries since 2025, elevating it to equal status with other reimbursed CRC screening tests and ending a 15-year policy stalemate. Screening CTC is a highly accurate examination with an immaculate safety record and equivalent sensitivity to colonoscopy for clinically significant polyps. Long-term observational CTC cohorts confirm safety for established polyp size thresholds in terms of test positivity and screening and surveillance intervals. Excellent technique with cathartic bowel preparation, stool tagging, and colonic distention is necessary for high-quality imaging and interpretation, particularly in detection of flat sessile serrated lesions (SSLs). Large SSLs and adenomatous polyps are the most relevant benign precursor lesions to CRC and are the main target of a primary prevention screening strategy. Only CTC and colonoscopy are sufficiently accurate for primary prevention, whereas stool-based and recently approved blood-based tests are limited to detection of cancer in a shorter screening window. CTC allows for selective polypectomy by risk-stratifying large polyps for removal, surveilling small polyps, and ignoring diminutive lesions. CTC is more efficient at identifying advanced neoplasia compared with a universal polypectomy strategy of colonoscopy only, which removes more pseudodisease and incurs excess risk of colonic perforation without benefit. Despite abundant evidence supporting CTC as an ideal screening test, it suffers from widespread and worsening underutilization due to barriers affecting radiology practice and physician support. Opportunistic screening and national trends in the CRC screening landscape will impact future uptake of CTC.

To record the incidence of polyps, new primary tumours or other pathologies and thus evaluate the value of colorectal cancer (CRC) surveillance beyond standard 5-years period. The American Society of Colon and Rectal Surgeons (ASCRS) recommend surveillance for 5-years following colorectal cancer (CRC) resection. The oncological value of extended surveillance remains controversial.

Enterococcus faecalis bacteremia presents a diagnostic challenge, particularly in elderly patients with multiple comorbidities and cardiac implantable electronic devices. We present the case of an 88-year-old woman with atrial fibrillation on anticoagulation, pacemaker placement, hypertension, hypothyroidism, and anxiety who presented with five days of abdominal pain, nausea, vomiting, and upper back/right shoulder pain. Initial evaluation raised concern for pneumonia due to the patient's chest X-ray and elevated temperature, and she was admitted for further management. Blood cultures at 48 hours grew Gram-positive cocci in pairs and chains and Enterococcus faecalis, prompting treatment with ceftriaxone and ampicillin and an extensive search for an infectious source. Transthoracic and transesophageal echocardiography showed no evidence of infective endocarditis or pacemaker-associated infection. Abdominal imaging was unrevealing. During hospitalization, the patient developed a declining hemoglobin and reported melena, prompting gastrointestinal evaluation. Colonoscopy revealed multiple colonic polyps, including tubular adenomas in the cecum and rectum, without evidence of malignancy. These adenomas were considered the most plausible portal of entry for bacteremia. Repeat blood cultures cleared, and the patient was transitioned to oral amoxicillin on discharge with outpatient follow-up. This case highlights the importance of considering gastrointestinal sources, including colorectal neoplasia, in patients with E. faecalis bacteremia of unclear origin. It also supports the role of multidisciplinary evaluation, including infectious disease, cardiology, and gastroenterology, in guiding workup and management.

Accurate segmentation of colorectal polyps is important for colorectal cancer prevention. However, domain shifts across medical centers and blurred boundaries of diminutive lesions remain major challenges for robust polyp segmentation. We propose FreqPolyp, a frequency-domain polyp segmentation framework designed for single-source domain generalization. At the input stage, the frequency domain augmentation module perturbs amplitude-related appearance statistics while preserving phase-related structural information, thereby reducing dependence on source-domain photometric styles without using target-domain data. At the decoding stage, the wavelet dual-stream fusion module uses discrete wavelet transform to extract high-frequency boundary cues and semantic-guided cross-attention to refine low-contrast lesion boundaries. In addition, a hybrid spatial-frequency supervision strategy combines amplitude-domain spectral consistency with phase-aware structural consistency. Experiments on five public benchmarks show that FreqPolyp achieves mDice/mIoU scores of 0.849/0.738 on ColonDB and 0.831/0.711 on ETIS, with an average unseen-domain mDice/mIoU of 0.865/0.765 across ColonDB, ETIS, and CVC-300. Under the tested RTX 3090 setting, FreqPolyp contains 26.2 M parameters and reaches 58 FPS. These results suggest that FreqPolyp provides a favorable accuracy-efficiency trade-off under public benchmark and controlled GPU evaluation settings.

PTEN Hamartoma Tumor Syndrome (PHTS) is a rare condition characterized by a complex phenotype including gastrointestinal hamartomas and increased lifetime malignancy risk. To characterize the clinical phenotype, genetic landscape, and spectrum of malignancies within a large cohort of adult PHTS carriers. A retrospective cohort study of adult patients (≥ 18 years) followed at specialized high-risk clinics who met PHTS diagnostic criteria based on either: (1) identification of a germline PTEN pathogenic/likely pathogenic variant, or (2) fulfillment of clinical criteria according to National Comprehensive Cancer Network (NCCN) guidelines. A total of 62 individuals were included (62.9% male; median age at inclusion 39.5, IQR, 28-52). All fulfilled diagnostic criteria for PHTS. PTEN pathogenic or likely pathogenic variant were identified in 50 individuals (80.6%). Colonic polyps were present in 40 patients. Malignancies were reported in 61% (n = 38), most frequently breast (n=13) and thyroid (n=7). Three individuals (4.8%) had rare soft tissue tumors: one with a desmoid tumor at age 18, one with concurrent axillary osteosarcoma and bilateral chest liposarcoma, and one with a skull-base sarcoma. Macrocephaly was observed in 33.8% (n = 21), and developmental delay, including autism spectrum disorder, in 8 patients (12.9%). One case of PTEN mosaicism was identified through tumor sequencing after negative blood genetic testing. Five individuals (8%) were treated with Sirolimus. This large cohort highlights the broad clinical spectrum and substantial cancer burden in PHTS, including rare soft tissue tumors. Constitutional mosaicism should be considered when clinical suspicion persists despite negative germline testing.