Misdiagnosis and Mistherapy of Crohn's Disease as Intestinal Tuberculosis: Case Report and Literature Review

Deep Learning Radiomics Analysis of CT Imaging for Differentiating Between Crohn's Disease and Intestinal Tuberculosis

This study aimed to develop and evaluate a CT-based deep learning radiomics model for differentiating between Crohn's disease (CD) and intestinal tuberculosis (ITB). A total of 330 patients with pathologically confirmed as CD or ITB from the First Affiliated Hospital of Zhengzhou University were divided into the validation dataset one (CD: 167; ITB: 57) and validation dataset two (CD: 78; ITB: 28). Based on the validation dataset one, the synthetic minority oversampling technique (SMOTE) was adopted to create balanced dataset as training data for feature selection and model construction. The handcrafted and deep learning (DL) radiomics features were extracted from the arterial and venous phases images, respectively. The interobserver consistency analysis, Spearman's correlation, univariate analysis, and the least absolute shrinkage and selection operator (LASSO) regression were used to select features. Based on extracted multi-phase radiomics features, six logistic regression models were finally constructed. The diagnostic performances of different models were compared using ROC analysis and Delong test. The arterial-venous combined deep learning radiomics model for differentiating between CD and ITB showed a high prediction quality with AUCs of 0.885, 0.877, and 0.800 in SMOTE dataset, validation dataset one, and validation dataset two, respectively. Moreover, the deep learning radiomics model outperformed the handcrafted radiomics model in same phase images. In validation dataset one, the Delong test results indicated that there was a significant difference in the AUC of the arterial models (p = 0.037), while not in venous and arterial-venous combined models (p = 0.398 and p = 0.265) as comparing deep learning radiomics models and handcrafted radiomics models. In our study, the arterial-venous combined model based on deep learning radiomics analysis exhibited good performance in differentiating between CD and ITB.

Differentiation of intestinal tuberculosis and Crohn's disease through an explainable machine learning method

Differentiation between Crohn’s disease and intestinal tuberculosis is difficult but crucial for medical decisions. This study aims to develop an effective framework to distinguish these two diseases through an explainable machine learning (ML) model. After feature selection, a total of nine variables are extracted, including intestinal surgery, abdominal, bloody stool, PPD, knot, ESAT-6, CFP-10, intestinal dilatation and comb sign. Besides, we compared the predictive performance of the ML methods with traditional statistical methods. This work also provides insights into the ML model’s outcome through the SHAP method for the first time. A cohort consisting of 200 patients’ data (CD = 160, ITB = 40) is used in training and validating models. Results illustrate that the XGBoost algorithm outperforms other classifiers in terms of area under the receiver operating characteristic curve (AUC), sensitivity, specificity, precision and Matthews correlation coefficient (MCC), yielding values of 0.891, 0.813, 0.969, 0.867 and 0.801 respectively. More importantly, the prediction outcomes of XGBoost can be effectively explained through the SHAP method. The proposed framework proves that the effectiveness of distinguishing CD from ITB through interpretable machine learning, which can obtain a global explanation but also an explanation for individual patients.

Difficulties in the differential diagnosis of intestinal tuberculosis and Crohn‘s disease

The differential diagnosis of intestinal tuberculosis and Crohn’s disease is a difficult task for most specialists due to their high similarity in clinical manifestations, instrumental diagnosis and histological pattern.

The aim: to consider the clinical and diagnostic features of intestinal tuberculosis and Crohn’s disease, to show the role of various methods of their diagnosis (CT of the abdominal cavity, CT-enterography, colonoscopy with biopsy).

A clinical example shows a case illustrating the difficulties of diagnosing intestinal tuberculosis, initially diagnosed as Crohn’s disease. The features of the course, complex diagnosis and treatment of intestinal tuberculosis and its complications during immunosuppression are demonstrated. At the first stage of treatment, the patient’s data related to CT of the chest organs, colonoscopy and histological examination of biopsy samples were incorrectly interpreted. As a result, a wrong diagnosis of Crohn’s disease was made, and immunosuppressive therapy was prescribed that provoked a generalization of the existing tuberculosis process. Subsequently, repeated surgical interventions were performed for complications of intestinal tuberculosis – perforation of tuberculous ulcers, peritonitis. Based on the analysis of the literature data and our own observation, it is shown that granulomatous inflammation in the study of intestinal biopsies doesn’t always allow us to make a clear diagnosis, first of all, there are intestinal tuberculosis and Crohn’s disease in the differential diagnostic series. The use of histobacterioscopy according to Ziehl – Neelsen, the study of fecal matter by luminescent microscopy, as well as molecular genetic methods for detecting DNA MTB allow us to verify the diagnosis. If Crohn’s disease is misdiagnosed as intestinal tuberculosis, then the prescribed anti-tuberculosis therapy can cause harm and lead to a delay in the underlying disease treatment. The reverse misdiagnosis is potentially more dangerous: if tuberculosis is misdiagnosed as Crohn’s disease, then the appointment of immunosuppressive therapy can lead to the generalization of tuberculosis and the development of fatal complications. 

Application value of tissue tuberculosis antigen combined with Xpert MTB/RIF detection in differential diagnoses of intestinal tuberculosis and Crohn's disease

Background

The purpose of this study was to examine the value of Xpert MTB/RIF assay and detection of additional Mycobacterium tuberculosis complex (MTBC) species antigens from intestinal tissue samples in differentiating intestinal tuberculosis (ITB) from Crohn’s disease (CD).

Methods

Several clinical specimens of intestinal tissue obtained by either endoscopic biopsy or surgical excision were used for mycobacteriologic solid cultures,Xpert MTB/RIF assays, immunohistochemistry, and histological examinations. Four antigens (38KDa, ESAT-6, MPT64, and Ag85 complex) of MTBC in the intestinal tissue were detected by immunohistochemical analysis.

Results

The study included 42 patients with ITB and 46 with CD. Perianal lesions and longitudinal ulcers were more common in patients with CD, while caseating granuloma and annular ulcers were more common in patients with ITB. The positive rate of MTBC detected by Xpert MTB/RIF in intestinal tissues of patients with ITB was 33.33%, which was significantly higher than that in patients with CD and that detected using acid-fast staining smears. It was also higher than that detected by tissue MTBC culture, but the difference was not statistically significant. The positive MPT64 expression rate in patients with ITB was 40.48%, which was significantly higher than that observed in patients with CD. The sensitivity of parallelly combined detection of tuberculosis protein MPT64 and Xpert MTB/RIF in diagnosing ITB was 50.0%.

Conclusions

The detection of Xpert MTB/RIF in intestinal tissue is a rapid and useful method for establishing an early diagnosis of ITB. The detection of MTBC using Xpert MTB/RIF and MPT64 antigen in intestinal tissues has a definitive value in the differential diagnosis ofITB and CD. The combination of these two methods can improve the detection sensitivity.

Distinguishing structural features between Crohn's disease and gastrointestinal luminal tuberculosis using Mueller matrix derived parameters

Recently, the incidence of inflammatory bowel diseases, especially the Crohn's disease (CD) and gastrointestinal luminal tuberculosis (ITB), has grown rapidly worldwide. Currently there is no general gold standard to distinguish between CD and ITB tissues, which both have tuberculosis and surrounding fibrous structures. Mueller matrix imaging technique is suitable for describing the location, density and distribution behavior of such fibrous structures. In this study, we apply the Mueller matrix microscopic imaging to the CD and ITB tissue samples. The 2D Mueller matrix images of the CD and ITB tissue slices are measured using the Mueller matrix microscope developed in our previous study, then the Mueller matrix polar decomposition and Mueller matrix transformation parameters are calculated. To evaluate the distribution features of the fibrous structures surrounding the tuberculosis areas more quantitatively and precisely, we analyze the retardance related Mueller matrix derived parameters, which show clear different distribution behaviors between the CD and ITB tissues, using the Tamura image processing method. It is demonstrated that the Mueller matrix derived parameters can reveal the structural features of tuberculosis areas and be used as quantitative indicators to distinguish between CD and ITB tissues, which may be useful for the clinical diagnosis.

Ten Cases of Intestinal Tuberculosis Which Were Initially Misdiagnosed as Inflammatory Bowel Disease

Objective Intestinal tuberculosis (ITB) and inflammatory bowel disease (IBD) frequently present with similar clinical, endoscopic and pathological features, therefore it is difficult to differentiate between them. The aim of this study was to elucidate the diagnostic delay and prognosis of ITB cases, initially misdiagnosed as IBD. Methods ITB cases were selected from the hospitalized patient list between April 2004 and March 2017 in a tuberculosis center in Japan. We retrospectively evaluated the initial diagnosis, clinical characteristics, endoscopic and pathological findings, bacterial examinations, treatment and prognosis. Results Among 66 ITB patients, ten patients were initially misdiagnosed as IBD. Seven patients were male and the median age was 60.5 years (23-74 years). After the diagnosis of IBD, all the patients were treated with mesalazine, in addition to corticosteroids in two patients and sequential azathioprine and infliximab in one. The median duration of diagnostic delay was 5.5 months (range 0.5-17 months). Eight patients had active pulmonary tuberculosis at the diagnosis of ITB. Acid-fast bacilli were confirmed in four of seven patients by reevaluation of the pathological specimens at the IBD diagnosis. Two patients needed intestinal resection and one with erroneous corticosteroid use for IBD died due to respiratory failure in spite of receiving appropriate treatment for tuberculosis. Conclusion ITB patients were frequently misdiagnosed and treated as IBD, thus resulting in a poor clinical outcome even after finally making a correct diagnosis and administering appropriate treatment. On diagnosis of IBD and/or treatment failure, chest radiograph and acid-fast bacilli of the pathological specimens should be carefully evaluated in order to rule out tuberculosis.

[Gastrointestinal tract diseases induced by medications]

Gastrointestinal symptoms are common side effects of medical drugs. They are usually mild but sometimes require diagnostic endoscopy and histologic evaluation. Due to the rapidly increasing number of drugs developed especially for cancer treatment, pathologists are faced with a spectrum of different drug-associated histologies in all segments of the gastrointestinal tract. Some medication-induced mucosal damage features may mimic classical pathologies of nondrug-associated diseases, while others result in novel phenotypes. The present article focusses on the histologic presentations of gastrointestinal diseases induced by medications that either compromise or induce immune response.

Gastrointestinal Tuberculosis

Gastrointestinal tuberculosis (TB) is a fascinating disease which can be observed both in the clinical context of active pulmonary disease and as a primary infection with no pulmonary involvement. It represents a significant clinical challenge because of the resurgence of TB as well as the diagnostic challenges it poses. A high clinical suspicion remains the most powerful tool in an era of medicine when reliance on diagnostic technology increases. Antimicrobial therapy is the mainstay of therapy, but surgical and endoscopic interventions are frequently required for intestinal TB. Gastrointestinal TB is truly the "great mimic" and continues to require the astute clinical acumen of skillful clinicians to diagnose and treat.