Potential model for differential diagnosis between Crohn's disease and primary intestinal lymphoma

Computed tomography-based radiomics combined with machine learning allows differentiation between primary intestinal lymphoma and Crohn's disease

BACKGROUND

Due to similar clinical manifestations and imaging signs, differential diagnosis of primary intestinal lymphoma (PIL) and Crohn's disease (CD) is a challenge in clinical practice.

AIM

To investigate the ability of radiomics combined with machine learning methods to differentiate PIL from CD.

METHODS

We collected contrast-enhanced computed tomography (CECT) and clinical data from 120 patients form center 1. A total of 944 features were extracted single-phase images of CECT scans. Using the last absolute shrinkage and selection operator model, the best predictive radiographic features and clinical indications were screened. Data from 54 patients were collected at center 2 as an external validation set to verify the robustness of the model. The area under the receiver operating characteristic curve, accuracy, sensitivity and specificity were used for evaluation.

RESULTS

A total of five machine learning models were built to distinguish PIL from CD. Based on the results from the test group, most models performed well with a large area under the curve (AUC) (> 0.850) and high accuracy (> 0.900). The combined clinical and radiomics model (AUC = 1.000, accuracy = 1.000) was the best model among all models.

CONCLUSION

Based on machine learning, a model combining clinical data with radiologic features was constructed that can effectively differentiate PIL from CD.

Hypocalcaemic tetany linked to vitamin D deficiency and hypomagnesemia in primary intestinal lymphangiectasia: a literature review

Primary intestinal lymphangiectasia (PIL) is a rare disorder in children causing protein-losing enteropathy. Vitamin D deficiency and hypomagnesemia contributed to the tetany. The literature review reflects the importance of screening for these deficiencies and regular serum magnesium monitoring in PIL cases with neuromuscular or ionic abnormalities.

Nomogram based on computed tomography images and clinical data for distinguishing between primary intestinal lymphoma and Crohn's disease: a retrospective multicenter study

Background

Differential diagnosis of primary intestinal lymphoma (PIL) and Crohn's disease (CD) is a challenge in clinical diagnosis.

Aims

To investigate the validity of the nomogram based on clinical and computed tomography (CT) features to identify PIL and CD.

Methods

This study retrospectively analyzed laboratory parameters, demographic characteristics, clinical manifestations, and CT imaging features of PIL and CD patients from two centers. Univariate logistic analysis was performed for each variable, and laboratory parameter model, clinical model and imaging features model were developed separately. Finally, a nomogram was established. All models were evaluated using the area under the curve (AUC), accuracy, sensitivity, specificity, and decision curve analysis (DCA).

Results

This study collected data from 121 patients (PIL = 69, CD = 52) from Center 1. Data from 43 patients (PIL = 24, CD = 19) were collected at Center 2 as an external validation cohort to validate the robustness of the model. Three models and a nomogram were developed to distinguish PIL from CD. Most models performed well from the external validation cohort. The nomogram showed the best performance with an AUC of 0.921 (95% CI: 0.838-1.000) and sensitivities, specificities, and accuracies of 0.945, 0.792, and 0.860, respectively.

Conclusion

A nomogram combining clinical data and imaging features was constructed, which can effectively distinguish PIL from CD.

Radiologic Review of Small Bowel Malignancies and Their Mimicking Lesions

Because of their small size, small bowel malignancies are often easily missed when radiologists read CT images, which can lead to errors in the normal small bowel due to their similar enhancement to the small bowel or non-specific enhancement. In addition, small bowel malignancies are sometimes mistaken for masses of other origins, such as the uterus, rectum, or omentum. In this article, we describe various small-bowel malignancies, their mimicking lesions and the typical and atypical features on CT imaging along with their clinical manifestations.

The Prevalence of Concomitant Skip Small Bowel Lesions in Crohn's Disease and Their Effects on Reoperation in Patients Undergoing Ileocolic Resection

AIMS

Concomitant lesions in the small intestine are common in Crohn's disease (CD). This study aimed to detect the incidence of small bowel (SB) lesions in patients undergoing surgical resection for symptomatic ileocolic disease and whether concomitant SB lesions are associated with reoperation due to recurrent CD.

METHODS

In this observational, historical cohort study, consecutive patients with CD undergoing primary ileocolic resection (ICR) from 2007 to 2019 were included. Clinical variables and intraoperative findings were extracted from a prospectively maintained database and analyzed by Cox proportional hazards regression models for identifying risk factors of reoperation.

RESULTS

Of the 404 patients included, there were 202 (50%) patients having concomitant SB lesions, and 108 of them underwent concurrent surgical intervention for SB lesions whereas 94 did not. The presence of concomitant SB lesions was a risk factor for reoperation (p = 0.041). Subgroup analysis indicated that patients with concomitant uncomplicated SB lesions left in situ had a comparable rate of reoperation (p = 0.605) whereas patients having concomitant complicated SB lesions undergoing simultaneous surgical intervention showed a higher reoperation rate (P = 0.006) when compared with those without concomitant SB lesions. Interestingly, the adverse effects of concomitant SB lesions can be reversed in the setting of postoperative anti-TNF agents [HR 0.2; 95% CI (0.04-0.9); P=0.040].

CONCLUSIONS

Concomitant SB lesion(s), especially those complicated lesions, could be a risk factor for postoperative surgical recurrence in patients undergoing ICR. Active postoperative management strategies such as anti-TNF agents should be provided for these patients.

Differential Diagnosis of Crohn’s Disease and Ulcerative Primary Intestinal Lymphoma: A Scoring Model Based on a Multicenter Study

Background

Differential diagnosis of Crohn’s disease (CD) and ulcerative primary intestinal lymphoma (UPIL) is a tough problem in clinical practice.

Aims

Our study identified key differences between CD and UPIL patients and aimed to further establish a scoring model for differential diagnosis.

Methods

A total of 91 CD and 50 UPIL patients from 9 tertiary inflammatory bowel disease centers were included. Univariate and multivariate analyses were used to determine significant markers for differentiating CD and UPIL. A differential scoring model was established by logistic regression analysis.

Results

The differential model was based on clinical symptoms, endoscopic and imaging features that were assigned different scores: intestinal bleeding (−2 points), extraintestinal manifestation (2 points), segmental lesions (1 point), cobblestone sign (2 points), homogeneous enhancement (−1 point), mild enhancement (−1 point), engorged vasa recta (1 point). A total score of ≥1 point indicates CD, otherwise UPIL was indicated. This model produced an accuracy of 83.66% and an area under the ROC curve of 0.947. The area under the ROC curve for validation using the 10-fold validation method was 0.901.

Conclusion

This study provided a convenient and useful model to differentiate CD from UPIL.

Mantle cell lymphoma simulating inflammatory bowel disease

We report a case of colorectal involvement by a mantle cell lymphoma (MCL) that had been considered before as inflammatory bowel disease. Diagnosis of low-grade MCL can be difficult, and here we highlight the importance of thorough histopathological examination in case of supposed inflammatory bowel disease that does not react to therapy.

Potential MR Enterography Features to Differentiate Primary Small Intestinal Lymphoma From Crohn Disease

OBJECTIVE. The purpose of this study was to assess the MR enterographic features of primary small intestinal lymphoma (PSIL) and compare them with active Crohn disease (CD) presenting with severe (≥ 10 mm) mural thickening of the small bowel. MATERIALS AND METHODS. This retrospective study included 15 patients with pathologically proven PSIL and 15 patients with active inflammatory CD with severe mural thickening. Various morphologic, enhancement, and diffusion parameters were compared between the two groups at MR enterography. The ratios of the upstream to involved luminal diameter and mural thickness to luminal diameter in the involved segment were calculated. An attempt was made to define a predictive model (morphologic score) for discriminating PSIL from CD with severe mural thickening. RESULTS. Patients with PSIL were more likely than those with CD to have unifocal disease (66.7% vs 20.0%, p = 0.025), circumferential involvement (86.7% vs 26.7%, p < 0.001), luminal dilatation (60.0% vs 7.0%, p = 0.005), and an attenuated fold pattern (53.3% vs none, p < 0.001). They were less likely to have serosal surface involvement (40.0% vs 100%, p = 0.001) and mesenteric fat infiltration (33.3% vs 100%, p < 0.001). Median upstream to involved luminal diameter ratio (1.5 vs 9.6, p < 0.001) and mural thickness to involved luminal diameter ratio (1.1 vs 4.3, p = 0.044) were significantly lower in patients with PSIL than in those with CD with severe mural thickening. No significant difference was observed in enhancement and diffusion measures. Morphologic score was based on the presence of luminal dilatation, unifocal involvement, mesenteric fat infiltration, and luminal stricture, yielding accuracy of 98% for differentiation between PSIL and CD with severe mural thickening. CONCLUSION. Morphologic features seen at MR enterography rather than enhancement or diffusion parameters may be valuable for differentiation of PSIL from active CD with severe mural thickening with significantly lower ratios of upstream to involved luminal diameter and mural thickness to involved luminal diameter in PSIL.

Mucosa-associated lymphoid tissue lymphoma simulating Crohn’s disease: A case report

BACKGROUND

Differential diagnosis between extranodal marginal zone lymphoma of mucosa-associated lymphoid tissue and inflammatory bowel disease is mainly based on histopathologic evaluation of intestinal biopsies, although there is no single definitive diagnostic investigation and that circumstance can lead to misdiagnosis in particular cases. Herein we present a rare, ulcerative form of marginal zone lymphoma which mimics the Crohn’s disease (CD) of upper digestive tract.

CASE SUMMARY

A 50-year-old man was presented with recurrent episodes of malaise and melena also weight loss. Enteroscopy of the small bowel demonstrated an ulcer in the jejunum. Microscopically, biopsies showed lymphoplasmacytic infiltrate. Diagnosis of CD was made. Primary treatment consisted of prednisone and azathioprine and was followed by azathioprine 100 mg per day with good clinical response in the following 2 years until relapse. At this time the results of endoscopic biopsies derived from proximal wall of stomach revealed Helicobacter pylori-negative marginal zone lymphoma of the gastric fundus. Immunophenotyping confirmed atypical CD20-positive cell population. Based on these biopsies, marginal zone lymphoma of mucosa-associated lymphoid tissue was diagnosed. Unfortunately, the contact with the patient was lost until one year later he was hospitalized with nausea, vomiting and severe pain because of gastrointestinal perforation. Four months later after laparotomy, the patient was treated with a course of chemotherapy. Complete remission was observed following 6 cycles of treatment.

CONCLUSION

This case report highlights the clinical relevance of knowledge and awareness of marginal zone lymphoma simulating CD.

MALT lymphoma of the colon: a clinicopathological review

Extranodal marginal zone lymphoma of mucosa-associated lymphoid tissue (MALT lymphoma) occurs in approximately 9% of non-Hodgkin B cell lymphoma. However, it occurs only rarely within the colon. The presentation is often asymptomatic, and can have multiple endoscopic appearances, including a single or multinodular polypoid lesion. Furthermore, small biopsies can make histological evaluation challenging. The 2016 WHO classification update includes many molecular features of entities and expands the differential diagnosis of lymphoid lesions of the colon. In addition to immunohistochemistry, molecular methods may be tempting to use for small difficult cases. Furthermore, treatment approaches are varied for this entity, and not well studied. Therefore, an updated review on MALT lymphoma of the colon is needed.

Diagnostic and clinical significance of antigen-specific pancreatic antibodies in inflammatory bowel diseases: A meta-analysis

BACKGROUND

Non-invasive criteria are needed for Crohn's disease (CD) diagnosis, with several biomarkers being tested. Results of individual diagnostic test accuracy studies assessing the diagnostic value of pancreatic autoantibodies-to-glycoprotein-2 (anti-GP2) tests for the diagnosis of CD appear promising.

AIM

To systematically review and meta-analyze evidence on the diagnostic accuracy of anti-GP2 tests in patients with suspected/confirmed CD.

METHODS

An electronic search was conducted on PubMed, Cochrane-CENTRAL and grey literature (CRD42019125947). The structured research question in PICPTR format was "Population" including patients with symptoms akin to CD, the "Index test" being anti-GP2 testing, the "Comparator" involved standard CD diagnosis, the "Purpose of test" being diagnostic, "Target disorder" was CD, and the "Reference standard" included standard clinical, radiological, endoscopical, and histological CD diagnostic criteria. Quality was assessed with the Quality Assessment of Diagnostic Accuracy Studies-2 tool and hierarchical models were employed to synthesize the data.

RESULTS

Out of 722 studies retrieved, 15 were meta-analyzed. Thirteen studies had industry-related conflicts-of-interest, and most included healthy donors as controls (spectrum bias). For the combination of IgA and/or IgG anti-GP2 test, the summary sensitivity was 20% (95% confidence interval: 10%-29%) at a median specificity of 97%. If the test was applied in 10000 suspected patients, 9669 would be true negatives and in 26, the diagnosis would be missed. In this hypothetical cohort, the anti-GP2 would fail to produce a diagnosis for 81.3% of the positive cases. Low summary points of sensitivity and high specificity were estimated for the IgG or IgA anti-GP2 test. Analogous results were observed when the analyses were restricted using specific cut-offs, or when ulcerative colitis patients were used as comparators.

CONCLUSION

Anti-GP2 tests demonstrate low sensitivity and high specificity. These results indicate that caution is required before relying on its diagnostic value. Additionally, the need for improving the methodology of diagnostic test accuracy studies is evident.

Diffuse large B-cell lymphoma of the colon and rectum in a patient with colonic Crohn's disease treated with infliximab and azathioprine

A 52-year-old woman was treated for colorectal diffuse large B-cell lymphoma (DLBCL) after a prolonged treatment period of azathioprine (AZA) and infliximab (IFX) for Crohn's disease (CD). She had been diagnosed as having colonic CD at the age of 24 years and received AZA from age 29. IFX was added at 47 years of age. She experienced massive hematochezia and anal pain at the age of 52 years and was transferred to our hospital. Endoscopic examination revealed a deep rectal ulcer with arterial bleeding. A stoma constructed at the transverse colon for refractory CD relieved her symptoms. Four months later, computed tomography showed increased thickness of the rectal wall. DLBCL was diagnosed from biopsy specimens of the rectum. Treatment with 6 courses of rituximab plus cyclophosphamide, doxorubicin, vincristine, and prednisolone along with additional radiation therapy for remnant rectal lymphoma has resulted in complete remission for over 5 years. Although colorectal malignant lymphoma coexisting with active CD was rare and the lesions were difficult to detect, intensive therapy for CD helped in the diagnosis and successful treatment of the patient.

Analysis of Phenotypic Variables and Differentiation Between Untypical Crohn's Disease and Untypical Intestinal Tuberculosis

BACKGROUND

The differentiation between untypical intestinal tuberculosis (UITB) and untypical Crohn's disease (UCD) is a challenge.

AIMS

To analyze phenotypic variables and propose a novel prediction model for differential diagnosis of two conditions.

METHODS

A total of 192 patients were prospectively enrolled. The clinical, laboratory, endoscopic, and radiological features were investigated and subjected to univariable and multivariable analyses. The final prediction model for differentiation between UCD and UITB was developed by logistic regression analysis and Fisher discriminant analysis on the training set. The same discriminant function was tested on the validation set.

RESULTS

Twenty-five candidates were selected from 52 phenotypic variables of typical Crohn's disease (TCD), UCD, and UITB patients. UCD's variables overlapped with both TCD and UITB. The percentages of tuberculosis history, positive PPD, and positive T-SPOT result in UCD were all significantly higher than that in TCD (11.6% vs. 0.0%, 27.9% vs. 0.0%, 25.6% vs. 4.5%, respectively, P < 0.05). The regression equations and Fisher discriminant function for discrimination between UCD and UITB were developed. In the training data, the area under the receiver operating characteristic of equations was 0.834, 0.69, and 0.648 in the clinical-laboratory, endoscopic, and radiological model, respectively. The accuracy of Fisher discriminant function for discrimination was 86% in UCD and 73% in UITB in the validation data.

CONCLUSIONS

Phenotypes of UCD patients in TB-endemic countries may be associated with TB infection history. Fisher discriminant analysis is a good choice to differentiate UCD from UITB, which is worthy of verification in clinical practice.

Comparison between Intestinal Behçet's Disease and Crohn's Disease in Characteristics of Symptom, Endoscopy, and Radiology

Aim

To evaluate different parameters in differentiating intestinal BD from CD.

Methods

The medical records of inpatients with intestinal BD and CD were retrospectively reviewed. The univariate value of different parameters was analyzed, respectively. A differentiation model was established by pooling all valuable parameters together. Diagnostic efficacy was evaluated, and a receiver operating curve (ROC) was plotted.

Results

Forty-two BD patients and ninety-seven CD patients were reviewed. Demographic and clinical parameters that showed significant value included diarrhea, fever, perianal disease, oral ulcers, genital ulcers, skin lesions, and musculoskeletal lesions. Endoscopic parameters reaching clinical significance included multiple-site lesions, lesions confined to the ileocecal region, longitudinal ulcers, round or oval ulcers, punch-out ulcers, ulcers with discrete margin, ulcer size > 2 cm, stricture of bowel, and anorectal involvement. Radiologic parameters aiding the differentiation included involvement segments ≤ 3, asymmetrical pattern of involvement, intraluminal pseudopolyp formation, target sign, stricture with proximal dilation, comb sign, and fistula. The sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of the differentiation model were 90.5%, 93.8%, 92.8%, 86.4%, and 95.8%, respectively. The cutoff value was 0.5 while the area under the ROC curve was 0.981.

Conclusion

The differentiation model that integrated the various parameters together may yield a high diagnostic efficacy in the differential diagnosis between intestinal BD and CD.