Multimodality radiomics prediction of radiotherapy-induced the early proctitis and cystitis in rectal cancer patients: a machine learning study.

Purpose.This study aims to predict radiotherapy-induced rectal and bladder toxicity using computed tomography (CT) and magnetic resonance imaging (MRI) radiomics features in combination with clinical and dosimetric features in rectal cancer patients.Methods.A total of sixty-three patients with locally advanced rectal cancer who underwent three-dimensional conformal radiation therapy (3D-CRT) were included in this study. Radiomics features were extracted from the rectum and bladder walls in pretreatment CT and MR-T2W-weighted images. Feature selection was performed using various methods, including Least Absolute Shrinkage and Selection Operator (Lasso), Minimum Redundancy Maximum Relevance (MRMR), Chi-square (Chi2), Analysis of Variance (ANOVA), Recursive Feature Elimination (RFE), and SelectPercentile. Predictive modeling was carried out using machine learning algorithms, such as K-nearest neighbor (KNN), Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Gradient Boosting (XGB), and Linear Discriminant Analysis (LDA). The impact of the Laplacian of Gaussian (LoG) filter was investigated with sigma values ranging from 0.5 to 2. Model performance was evaluated in terms of the area under the receiver operating characteristic curve (AUC), accuracy, precision, sensitivity, and specificity.Results.A total of 479 radiomics features were extracted, and 59 features were selected. The pre-MRI T2W model exhibited the highest predictive performance with an AUC: 91.0/96.57%, accuracy: 90.38/96.92%, precision: 90.0/97.14%, sensitivity: 93.33/96.50%, and specificity: 88.09/97.14%. These results were achieved with both original image and LoG filter (sigma = 0.5-1.5) based on LDA/DT-RF classifiers for proctitis and cystitis, respectively. Furthermore, for the CT data, AUC: 90.71/96.0%, accuracy: 90.0/96.92%, precision: 88.14/97.14%, sensitivity: 93.0/96.0%, and specificity: 88.09/97.14% were acquired. The highest values were achieved using XGB/DT-XGB classifiers for proctitis and cystitis with LoG filter (sigma = 2)/LoG filter (sigma = 0.5-2), respectively. MRMR/RFE-Chi2 feature selection methods demonstrated the best performance for proctitis and cystitis in the pre-MRI T2W model. MRMR/MRMR-Lasso yielded the highest model performance for CT.Conclusion.Radiomics features extracted from pretreatment CT and MR images can effectively predict radiation-induced proctitis and cystitis. The study found that LDA, DT, RF, and XGB classifiers, combined with MRMR, RFE, Chi2, and Lasso feature selection algorithms, along with the LoG filter, offer strong predictive performance. With the inclusion of a larger training dataset, these models can be valuable tools for personalized radiotherapy decision-making.

CT findings of proctitis in two patients with Mpox.

Mpox (formerly known as Monkeypox) has emerged as a public health crisis in 2022 with recent global spread outside of endemic regions and secondary transmission of this zoonotic disease between humans. The current outbreak predominantly affects men who have sex with men (MSM). Classically, Mpox presents with fever, rash, and lymphadenopathy; however, in the MSM population, genital/perianal skin lesions and rectal pain due to proctitis are commonly present. We present the CT findings of active proctitis in two cases of Mpox infection.

Rectal and perirectal CT findings in patients with monkeypox virus infection.

OBJECTIVE: To analyze the findings of proctitis in patients with laboratory-confirmed Mpox and correlate the patient clinical presentation and laboratory findings. METHODS: 21 patients with PCR-positive Mpox who obtained abdominopelvic CT were retrospectively identified by electronic medical record search. Three radiologists independently evaluated CT images, measuring rectal wall thickness (cm), degree of perirectal fat stranding on a 5-point Likert scale, and size of perirectal lymph nodes (cm, short axis). Mann-Whitney U-test (Wilcoxon rank sum test) was used to assess the association of rectal wall thickness and perirectal fat standing between patients with rectal symptoms and patients without rectal symptoms. RESULTS: 20 of 21 patients presented with perirectal fat stranding, with mean Likert score of 3.0 ± 1.4, indicating moderate perirectal stranding. Mean transverse rectal wall thickness was 1.1 ± 0.5 cm (range 0.3-2.3 cm); it was thicker among patients with HIV (1.2 cm vs 0.7 cm; p = .019). Mean perirectal fat stranding was greater among patients presenting with HIV, and with rectal symptoms, though not significantly so. 17/21 (81%) patients had abnormal mesorectal lymph nodes by at least two of three readers, with mean short-axis measurement 1.0 ± 0.3 cm (range 0.5-1.6 cm). Multiple linear regression showed no significant correlation between rectal thickness and laboratory values or HIV status. CONCLUSION: Nearly all patients with Mpox who presented with additional symptoms warranting a CT demonstrated proctitis. Degree of proctitis varied greatly within the cohort, with greatest thickening among patients with HIV. Physicians should have a high suspicion for proctitis in patients with suspected Mpox.

Machine-learning with region-level radiomic and dosimetric features for predicting radiotherapy-induced rectal toxicities in prostate cancer patients.

BACKGROUND AND PURPOSE: This study aims to build machine learning models to predict radiation-induced rectal toxicities for three clinical endpoints and explore whether the inclusion of radiomic features calculated on radiotherapy planning computerised tomography (CT) scans combined with dosimetric features can enhance the prediction performance. MATERIALS AND METHODS: 183 patients recruited to the VoxTox study (UK-CRN-ID-13716) were included. Toxicity scores were prospectively collected after 2 years with grade ≥ 1 proctitis, haemorrhage (CTCAEv4.03); and gastrointestinal (GI) toxicity (RTOG) recorded as the endpoints of interest. The rectal wall on each slice was divided into 4 regions according to the centroid, and all slices were divided into 4 sections to calculate region-level radiomic and dosimetric features. The patients were split into a training set (75%, N = 137) and a test set (25%, N = 46). Highly correlated features were removed using four feature selection methods. Individual radiomic or dosimetric or combined (radiomic + dosimetric) features were subsequently classified using three machine learning classifiers to explore their association with these radiation-induced rectal toxicities. RESULTS: The test set area under the curve (AUC) values were 0.549, 0.741 and 0.669 for proctitis, haemorrhage and GI toxicity prediction using radiomic combined with dosimetric features. The AUC value reached 0.747 for the ensembled radiomic-dosimetric model for haemorrhage. CONCLUSIONS: Our preliminary results show that region-level pre-treatment planning CT radiomic features have the potential to predict radiation-induced rectal toxicities for prostate cancer. Moreover, when combined with region-level dosimetric features and using ensemble learning, the model prediction performance slightly improved.

Imaging features of anorectal proctitis in monkeypox infection.

The monkeypox outbreak of 2022 saw the first community-sustained transmission of the monkeypox virus outside of Africa, and rapidly developed into multi-country spread. A common presenting sign of monkeypox infection during this outbreak has been rectal pain due to proctitis. Proctitis with large hypoattenuated anorectal ulcers on CT scan should invoke consideration for monkeypox infection in young homosexual or bisexual men with associated skin eruptions.

Proctitis in gay and bisexual men. Are microscopy and proctoscopy worthwhile?

OBJECTIVES: We explored the association between nucleic acid amplification testing (NAAT) and rectal microscopy/proctoscopy findings and correlates of rectal STIs among 150 gay and bisexual men (GBM) diagnosed with proctitis at the Sydney Sexual Health Centre from March 2016 to October 2017. METHODS: From case files, we analysed risk behaviours, microscopy, proctoscopy and NAAT results for rectal STIs (Chlamydia trachomatis, Neisseria gonorrhoeae, Mycoplasma genitalium, herpes simplex virus type 1/2, lymphogranuloma venereum and syphilis). χ2 test assessed the association between microscopy/proctoscopy findings and NAAT results. Linear regression assessed the association between NAAT positivity and correlates of rectal STIs. RESULTS: The mean age was 32.5 (9.8) years, 43% (65/150) were taking pre-exposure prophylaxis, 17% (26/150) were HIV positive and 24% (36/147) had multiple rectal STIs.Among GBM with documented proctoscopy findings (n=113), 58% (65/113) had discharge, 36% (41/113) had anorectal erythema and 25% (28/113) had bleeding. A quarter of GBM (28/113) had negative proctoscopy findings.Discharge found on proctoscopy (p=0.001), positive HIV status (p=0.030) and time since last receptive anal intercourse (p=0.028) were independently associated with NAAT positivity for any rectal STI. Discharge had a positive likelihood ratio of 1.6 (95% CI 1.0 to 2.4).Among those with documented microscopy findings (n=69), 59% (41/69) and 41% (28/69) were NAAT positive and negative, respectively. Among NAAT-positive GBM, 27 (66%) had polymorphonuclear cells (PMNs) (mean number of PMNs, 10 (SD 9) cells per oil immersion field), 1 (2%) had Gram-negative intracellular diplococci and 11 (27%) had negative findings. There was no significant association between microscopy findings and NAAT results (p=0.651) or the number of rectal STI (p=0.279). CONCLUSION: Microscopy does not reliably provide information necessary to tailor the management of GBM diagnosed with proctitis. Discharge found during proctoscopy may identify GBM with rectal STI. Services should consider recommendations to perform these investigations.

Proctitis crónica hemorrágica por radioterapia en el Instituto Nacional de Enfermedades Neoplásicas del Perú, 2011-2013 / Radiotherapy associated chronic hemorrhagic proctitis at the National Institute of Neoplastic Diseases of Peru, 2011-2013

Objetivo: Estudiar las características clínicas y endoscópicas de la proctitis crónica hemorrágica por radioterapia en el Instituto Nacional de Enfermedades Neoplásicas del Perú. Materiales y métodos: Estudio descriptivo, retrospectivo y longitudinal, con una población de 588 pacientes con esta patología, en el periodo 2011-2013, de donde se seleccionaron 114 pacientes por muestreo probabilístico aleatorizado. Se usó la estadística descriptiva e inferencial para el análisis de las variables cualitativas y cuantitativas. Resultados: La investigación encontró como principales resultados, un periodo de latencia de 439,96 días; la severidad de rectorragia clínica fue grado II y III en el 86,84%, la hemoglobina media fue de 11,63 gr/dl, los hallazgos endoscópicos fueron severidad moderada en el 58,77%, extensión solo rectal en el 92,11%, friabilidad leve del 43,86%, compromiso menor del 33% de la superficie rectal en el 71,93% y una longitud media de 7,28 cm. Los hallazgos inflamatorios fueron de cicatrices en el 0,88%, erosiones del 0,88%, de úlceras del 7%, de fístula del 0,88% y del 3,51% de estenosis rectales, el tratamiento de argón plasma coagulación (APC) único o combinado se ofreció en el 96% de los casos. Conclusiones: La proctitis crónica hemorrágica por radioterapia fue una complicación importante de la radioterapia pélvica, con hallazgos clínicos y endoscópicos característicos.

Objective: To study the clinical and endoscopic features of chronic hemorrhagic proctitis by radiotherapy in the National Institute of Neoplastic Diseases of Peru. Materials and methods: The study was descriptive, retrospective and longitudinal, with a population of 588 patients with this pathology, in the period 2011-2013, from which 114 patients were selected by randomized probabilistic sampling. Descriptive and inferential statistics were used for the analysis of qualitative and quantitative variables. Results: The main results were a latency period of 439.96 days; the severity of clinical rectal bleeding was grade 2 and 3 in 86.84%, the mean hemoglobin in chronic hemorrhagic proctitis by radiotherapy was 11.63 g / dl, the endoscopic findings were moderate severity in 58.77%, extension rectal only in 92.11%, slight friability of 43.86%, compromise less than 33% of the rectal surface in 71.93% and an average length of 7.28 cm. The inflammatory findings were 0.88% scars, erosions of 0.88%, ulcers of 7%, fistula of 0.88% and 3.51% of rectal stenosis, single or combined argon plasma coagulation (APC) treatment was offered in 96% of cases. Conclusion: Chronic hemorrhagic proctitis is an important complication of pelvic radiotherapy, with characteristic clinical and endoscopic findings.

[Radiotherapy associated chronic hemorrhagic proctitis at the National Institute of Neoplastic Diseases of Peru, 2011-2013]. / Proctitis crónica hemorrágica por radioterapia en el instituto nacional de enfermedades neoplásicas del Perú, 2011-2013.

OBJECTIVE: To study the clinical and endoscopic features of chronic hemorrhagic proctitis by radiotherapy in the National Institute of Neoplastic Diseases of Peru. MATERIALS AND METHODS: The study was descriptive, retrospective and longitudinal, with a population of 588 patients with this pathology, in the period 2011-2013, from which 114 patients were selected by randomized probabilistic sampling. Descriptive and inferential statistics were used for the analysis of qualitative and quantitative variables. RESULTS: The main results were a latency period of 439.96 days; the severity of clinical rectal bleeding was grade 2 and 3 in 86.84%, the mean hemoglobin in chronic hemorrhagic proctitis by radiotherapy was 11.63 g / dl, the endoscopic findings were moderate severity in 58.77%, extension rectal only in 92.11%, slight friability of 43.86%, compromise less than 33% of the rectal surface in 71.93% and an average length of 7.28 cm. The inflammatory findings were 0.88% scars, erosions of 0.88%, ulcers of 7%, fistula of 0.88% and 3.51% of rectal stenosis, single or combined argon plasma coagulation (APC) treatment was offered in 96% of cases. CONCLUSION: Chronic hemorrhagic proctitis is an important complication of pelvic radiotherapy, with characteristic clinical and endoscopic findings.

Correlation between Disease Activity and Endorectal Ultrasound Findings of Chronic Radiation Proctitis.

The aim of this study was to summarize the imaging features of chronic radiation proctitis (CRP) on endorectal ultrasound (ERUS) and investigate the value of ERUS in the evaluation of disease activity. 40 CRP patients and 30 control patients were investigated by ERUS. Rectal wall thickness and layers, ulcers and rectovaginal fistulas were evaluated by B-mode ultrasound. Power Doppler imaging was used to evaluate the vascularity of the rectal wall using a semiquantitative score. Disease activity was calculated according to the National Cancer Institute Common Terminology Criteria for Adverse Events 4.0 (CTCAE 4.0). Imaging findings for patients with mild and severe CRP were compared. For 30 patients in the control group, the average maximum thickness of the rectal wall was 3.07 ± 0.73 mm, with all exhibiting typical wall stratification and level 0 vascularity. For the 40 CRP patients, there was marked thickening of the rectal wall (average thickness = 9.42 ± 1.94 mm), which was significantly thicker than in the control group (p < 0.05). The rectal walls of the mild group were significantly thinner than those of the severe group (8.71 ± 1.67 mm vs. 10.00 ± 2.00 mm, p < 0.05). Among the 22 severe cases, 19 cases (19/22, 86.4%) exhibited hyper-vascularity (level IV) or blurred wall stratification (including hypo-echoic submucosa, ulcer and fistula); 12 of the 18 mild cases (166.7%) exhibited a vascularity of level III and typical wall stratification. A significant association (p < 0.05) was observed between stratification and vascularity of the rectal wall and CRP activity. When ERUS findings of blurred rectal wall stratification or increasing vascularity (level IV) were used to evaluate CRP activity, the sensitivity was 86.4% (95% confidence interval: 64.0-96.4) and the specificity was 66.7% (95% confidence interval: 41.2-85.6). Thickening of the rectal wall, blurred wall stratification and increased vascularity are characteristic ERUS findings of CRP. ERUS is helpful in the comprehensive evaluation of disease activity and may provide objective evidence during treatment planning and follow-up.

MRI characteristics of proctitis in Crohn's disease on perianal MRI.

PURPOSE: Multiple features have been described for assessing inflammation in Crohn's disease (CD) in MR enterography, but have not been validated in perianal magnetic resonance imaging (MRI). Retrospectively, we studied which MRI features are valuable in assessing proctitis. MATERIALS AND METHODS: CD patients (≥18 years) who underwent colonoscopy (reference standard) and perianal fistula MRI within 8 weeks were included. Seventeen MRI features were blindly scored by three observers and correlated to endoscopy (regression analysis). Reproducibility (multirater kappa, intraclass correlation coefficient) was determined for all three observer pairs. MRI features were considered relevant when significantly correlated to endoscopy for ≥2 observers, and reproducibility was ≥0.40 for ≥2 observer pairs. RESULTS: Perianal MRI of 58 CD patients were included. Wall thickness, rectal mural fat, creeping fat, and size of mesorectal lymph nodes showed a significant correlation with endoscopy for ≥2 observers (p = 0.000-0.023, p = 0.011-0.172, p = 0.007-0.011 and p = 0.000-0.005, respectively) with a kappa/intraclass correlation coefficient of ≥0.60 for ≥2 observer pairs. Perimural T2 signal and perimural enhancement significantly correlated to endoscopy (all p values ≤0.05) for all three observers and the reproducibility was ≥0.40 for ≥2 observer pairs. Mural T2 signal and degree and pattern of T1 enhancement showed significant correlation to endoscopy for two observers, but with poor to moderate reproducibility. CONCLUSION: Wall thickness, mural fat, and mesorectal features (perimural T2 signal, perimural enhancement, creeping fat, and size of mesorectal lymph nodes) had significant correlation to endoscopy and were reproducible in diagnosing proctitis. Some established luminal features in MRE were considered not useful.

Controversies in Pouch Surveillance for Patients with Inflammatory Bowel Disease.

CASE 1: Following 2 years of rectal blood loss, a 31-year-old male was diagnosed with ulcerative pancolitis in 1978. Initial treatment consisted of both topical and systemic 5-aminosalicylic acids [5-ASAs], and remission was achieved. In both 1984 and 1986 he was hospitalised due to exacerbations necessitating treatment with intravenous corticosteroids. The following years went well, without disease activity, under treatment with 5-ASA. In 1997, at the age of 50 years, a surveillance colonoscopy showed a stenotic process with a macroscopic irregularity in the sigmoid region. Histology revealed at least high-grade dysplasia [HGD] and signs of an invasive growth pattern which could indicate colorectal cancer [CRC]. The patient underwent restorative proctocolectomy with ileal pouch-anal anastomosis [IPAA]. Histology of the resection specimen confirmed active inflammation in the colon and rectum and a carcinoma in situ was identified in the sigmoid colon without invasive growth. This patient did not have significant comorbidities-for example primary sclerosing cholangitis [PSC]-and the CRC family history was negative. What pouch surveillance strategy should be recommended? CASE 2: A 34-year-old man presented at our inflammatory bowel disease [IBD] centre with ulcerative proctitis. Ten years later, after an initially mild disease course, his disease progressed to a pancolitis. An 11-year period with multiple exacerbations [on average every 2 year, including hospitalisation] followed and treatment consisted of topical and systemic 5-ASAs with intermittent corticosteroids. In 1998, at the age of 65 years, a two-stage restorative proctocolectomy with IPAA was performed due to disease activity refractory to systemic corticosteroids. The colectomy specimen confirmed the diagnosis of ulcerative pancolitis without evidence for colorectal dysplasia or carcinoma. Other than steroid-induced diabetes mellitus, this patient had no comorbidities. His father died from CRC at unknown age. What pouch surveillance strategy should be recommended?

Cytomegalovirus proctitis mimicking rectal cancer in an immunocompetent elderly patient: a case report.

BACKGROUND: Cytomegalovirus infection is associated with significant morbidity and mortality in immunocompromised patients, but its impact on immunocompetent patients is still poorly understood. Furthermore, there is increasing evidence implying that chronic infection may contribute to a heightened cardiovascular risk. CASE PRESENTATION: We describe the case of incidental diagnosis of Cytomegalovirus proctitis in an immune-competent white British elderly gentleman, admitted following a stroke and investigated for rectal cancer following the development of bloody diarrhoea and persistent systemic inflammatory response. CONCLUSION: This raised some several interesting points; firstly that we must revise our approach to investigating the immunocompetent elderly patient, secondly, could chronic Cytomegalovirus infection have contributed to the presentation of stroke in this patient and lastly what are the existing evidence for treatment in this population? We use this opportunity to try and address some of these questions and feel that this would be of benefit to the wider audience.We discuss the risk factors for disease in immune-competent patients and also a brief overview of the benefits of treatment in this population.

The contribution of the cone beam Kv CT (CBKvCT) to the reduction in toxicity of prostate cancer treatment with external 3D radiotherapy.

OBJECTIVE: Show that verification through cone beam Kv CT (CBKvCT) in a series of patients treated with 3D external radiotherapy (3DRT) for prostate cancer (PC) is related to a reduction in acute and late toxicity levels. MATERIALS AND METHOD: A retrospective, non-randomized study of two homogeneous groups of patients treated between 2005 and 2008, 46 were verified using electronic portal devices (EPIDs) and 48 through CBKvCT. They received 3DRT for localized PC (T1-T3N0M0) and were prescribed the same doses. Treatment was simulated and planned with the same criteria with the same equipment with a median follow-up time of 24 months (12-54 months). Urinary and gastrointestinal toxicity was determined using Common Toxicity Criteria scale, version 4 and RTOG scales. Statistical analysis of data was performed where p < 0.005 being significative. RESULTS AND DISCUSSION: With an overall median follow-up time of 24 months, the levels of proctitis were, respectively, 19.56, 15.21 and 15.2 % in the first group, compared with 4.17, 2.08 and 8.33 % in the second. Statistically, less total and late proctitis, late rectal bleeding, anal fissure, total and acute haematuria, total and acute urinary frequency and total urinary incontinence was observed. No statistically significant evidence of a lowering in toxicity neither in terms of acute and late dysuria nor of a relationship to the TNM, Gleason or PSA or in the grade of stability. CONCLUSION: Verification through CBKvCT in this series is associated with a statistically significant lowering toxicity. This justifies its use. Greater monitoring would be necessary to assess the impact of verification at the level of biochemical control.

Endoanal ultrasonography may distinguish Crohn's anal fistulae from cryptoglandular fistulae in patients with Crohn's disease: a cross-sectional study.

BACKGROUND: The aim of the study was a cross-sectional investigation into the types of anal fistulae in patients with Crohn's disease using 3-dimensional endoanal ultrasonography. METHODS: The study population consisted of 45 patients with established Crohn's disease referred in a 2-year period for treatment of anal fistula. The fistulae were classified according to the presence of three criteria: 1. bifurcation or secondary extension; 2. cross-sectional width ≥ 3 mm; and 3. content of hyperechoic secretions. RESULTS: The fistulae of 24 patients (53%) satisfied two or three criteria and were classified as true Crohn's fistulae, while the fistulae of 21 patients satisfied one or none of the criteria and were the cryptoglandular type. The fistulae in the two or three criteria group had been in existence for 8.4 years on average and those in the cryptoglandular group for 4.5 years on average (P = 0.283). The corresponding numbers of previous operations for fistula were 5.7 (range 0-32) and 1.5 (range 0-6), respectively (P = 0.0211). The presence of colitis or proctitis was similar across the groups, but the perianal Crohn's disease activity index was higher with a Crohn's type of fistula (P = 0.0097). Also, a larger proportion had been treated with anti-TNF-monoclonal antibody (0.0169). CONCLUSIONS: Endoanal ultrasonography was capable of discerning two subgroups of fistula in Crohn's patients. These groups were clinically different indicating that the prospect of surgical cure is also different.

[Normal tissue tolerance to external beam radiation therapy: rectum]. / Dose de tolérance à l'irradiation des tissus sains: le rectum.

Radiation proctitis is among the most frequent radiation-induced toxicities. This is related to the high frequency of pelvic tumours and the key role of radiotherapy in the treatment of these tumours. Late rectal toxicity usually occurs within the first two years after the completion of a radiotherapy course. Rectal bleeding and a rectal syndrome are the main symptoms, and can be associated to fistulas or rectal ulcers. Clinical factors, such as diabetes mellitus, a severe acute radiation toxicity, small rectal volume or radiation hypersensitivity, are associated with late rectal toxicity. Dosimetric factors derived from the analysis of dose-volume histograms can also predict the occurrence of radiation proctitis, and help to adapt the prescribed dose and the ballistic of irradiation.