Avoiding misdiagnosis of multilocular thymic cysts as malignant tumors on computer tomography

This editorial provides insights from a case report by Sun et al published in the World Journal of Clinical Cases.The case report focuses on a case where a multilocular thymic cyst(MTC)was misdiagnosed as a thymic tumor,resulting in an unnecessary surgical procedure.Both MTCs and thymic tumors are rare conditions that heavily rely on radiological imaging for accurate diagnosis.However,the similarity in their imaging presentations can lead to misinterpretation,resulting in unnecessary surgical procedures.Due to the ongoing lack of comprehensive knowledge about MTCs and thymic tumors,we offer a summary of diagnostic techniques documented in recent literature and examine potential causes of misdiagnosis.When computer tomography(CT)values surpass 20 Hounsfield units and display comparable morphology,there is a risk of misdiagnosing MTCs as thymic tumors.Employing various differential diagnostic methods like biopsy,molecular biology,multi-slice CT,CT functional imaging,positron emission tomography/CT molecular functional imaging,magnetic resonance imaging and radiomics,proves advantageous in reducing clinical misdiagnosis.A deeper understanding of these conditions requires increased attention and exploration by healthcare providers.Moreover,the continued advancement and utilization of various diagnostic methods are expected to enhance precise diagnoses,provide appropriate treatment options,and improve the quality of life for patients with thymic tumors and MTCs in the future.continued advancement and utilization of various diagnostic methods are expected to enhance precise diagnoses,provide appropriate treatment options,and improve the quality of life for patients with thymic tumors and MTCs in the future.

Multi-slice spiral computed tomography in differential diagnosis of gastric stromal tumors and benign gastric polyps,and gastric stromal tumor risk stratification assessment

BACKGROUND The biological characteristics of gastric stromal tumors are complex,and their incidence has increased in recent years.Gastric stromal tumors(GST)have potential malignant tendencies,and the probability of transformation into malignant tumors is as high as 20%-30%.AIM To investigate the value of multi-slice spiral computed tomography(MSCT)in the differential diagnosis of GST and benign gastric polyps,and GST risk stratification assessment.METHODS We included 64 patients with GST(GST group)and 60 with benign gastric polyps(control group),confirmed by pathological examination after surgery in PLA General Hospital,from January 2016 to June 2021.The differences in the MSCT imaging characteristic parameters and enhanced CT values between the two groups before surgery were compared.According to the National Institutes of Health’s standard,GST is divided into low-and high-risk groups for MSCT imaging characteristic parameters and enhanced CT values.RESULTS The incidences of extraluminal growth,blurred boundaries,and ulceration in the GST group were significantly higher than those in the control group(P<0.05).The CT values and enhanced peak CT values in the arterial phase in the CST group were higher than those in the control group(P<0.05).The MSCT differential diagnosis of GST and gastric polyp sensitivity,specificity,misdiagnosis rate,missed diagnosis rate,and areas under the curve(AUCs)were 73.44%,83.33%,26.56%,16.67%,0.784,respectively.The receiver operating characteristic curves were plotted with the arterial CT value and enhanced peak CT value,with a statistical difference.The results showed that the sensitivity,specificity,misdiagnosis rate,missed diagnosis rate,and AUC value of arterial CT in the differential diagnosis of GST and gastric polyps were 80.18%,62.20%,19.82%,37.80%,and 0.710,respectively.The sensitivity,specificity,misdiagnosis rate,missed diagnosis rate,and AUC value of the enhanced peak CT value in the differential diagnosis of GST and gastric polyps were 67.63%,60.40%,32.37%,39.60%,and 0.710,respectively.The incidence of blurred lesion boundaries and ulceration in the high-risk group was significantly higher than that in the low-risk group(P<0.05).The arterial phase and enhanced peak CT values in the high-risk group were significantly higher than those in the low-risk group(P<0.05).CONCLUSION Presurgical MSCT examination has important value in the differential diagnosis of GST and gastric benign polyps and can effectively evaluate the risk grade of GST patients.

Deep learning model combined with computed tomography features to preoperatively predicting the risk stratification of gastrointestinal stromal tumors

BACKGROUND Gastrointestinal stromal tumors(GIST)are prevalent neoplasm originating from the gastrointestinal mesenchyme.Approximately 50%of GIST patients experience tumor recurrence within 5 years.Thus,there is a pressing need to accurately evaluate risk stratification preoperatively.AIM To assess the application of a deep learning model(DLM)combined with computed tomography features for predicting risk stratification of GISTs.METHODS Preoperative contrast-enhanced computed tomography(CECT)images of 551 GIST patients were retrospectively analyzed.All image features were independently analyzed by two radiologists.Quantitative parameters were statistically analyzed to identify significant predictors of high-risk malignancy.Patients were randomly assigned to the training(n=386)and validation cohorts(n=165).A DLM and a combined DLM were established for predicting the GIST risk stratification using convolutional neural network and subsequently evaluated in the validation cohort.RESULTS Among the analyzed CECT image features,tumor size,ulceration,and enlarged feeding vessels were identified as significant risk predictors(P<0.05).In DLM,the overall area under the receiver operating characteristic curve(AUROC)was 0.88,with the accuracy(ACC)and AUROCs for each stratification being 87%and 0.96 for low-risk,79%and 0.74 for intermediate-risk,and 84%and 0.90 for high-risk,respectively.The overall ACC and AUROC were 84%and 0.94 in the combined model.The ACC and AUROCs for each risk stratification were 92%and 0.97 for low-risk,87%and 0.83 for intermediate-risk,and 90%and 0.96 for high-risk,respectively.Differences in AUROCs for each risk stratification between the two models were significant(P<0.05).CONCLUSION A combined DLM with satisfactory performance for preoperatively predicting GIST stratifications was developed using routine computed tomography data,demonstrating superiority compared to DLM.

The practical value of 3-dimensional computed tomography on diagnosis of bladder tumor

Objective To study the practical value of 3-dimensional computed tomography on diagnosis of bladder tumor, Methods Fifteen patients with bladder masses were examined by thin-layer computed tomography. The results of 3-dimensional reconstructed images were compared with the final diagnosis and the pathological stages. Results According to 3-dimensional reconstructed images, among the 15 cases, 12 cases of bladder cancer were diagnosed, and the pathological types were transitional carcinoma. Two cases were diagnosed as benign tumor (leiomyoma), and the other one was colon cancer, which invaded bladder. The accuracy was 100% . The clinical stages were determined. Of the 12 bladder carcinomas,5 was in stage T1, 3 in T2,, 3 in T3 and 1 in T4.The accuracy of staging was up to 83% (10/12) compared with pathological stages. Conclusion The 3-dimensional reconstructed technology may improve the accuracy of staging of bladder carcinoma, and to provide important evidence for surgery options. 3 refs,2 figs.

A correlation of computed tomography perfusion and histopathology in tumor edges of hepatocellular carcinoma

BACKGROUND： The peripheral morphologic characteristics of hepatocellular carcinoma （HCC） reflect tumor growth patterns. Computed tomography （CT） perfusion is a new method to analyze hemodynamic changes in tissues. We assessed the relationship between CT perfusion and histopathologic findings in the periphery of HCC lesions. METHODS： Non-contrast CT, enhanced dual-phase CT, and CT perfusion were performed on 77 subjects （47 patients and 30 controls）. Based on the imaging findings of enhanced dual- phase CT, the tumor edges were classified into three types： type Ⅰ （sharp）; type Ⅱ （blurry）; and type Ⅲ （mixed）. The CT perfusion parameters included hepatic blood flow, hepatic arterial fraction, hepatic arterial perfusion, and hepatic portal perfusion. The tissue sections from resected specimens were subjected to routine hematoxylin and eosin staining and immunohistochemical staining for CD34. The correlations between microvessel density （MVD） and the CT perfusion parameters were analyzed using Pearson＇s product-moment correlation coefficient. Changes in the perfusion parameters in tumor edges of different tumor types were evaluated. RESULTS： Type Ⅰ （sharp）： the pathologic findings showed fibrous connective tissue capsules in the tumor edges, and an MVD 〈30/ram2. Type Ⅱ （blurry）： the histology showed that the edges were clear with no capsules and an MVD 〉30/ram2. Type Ⅲ （mixed）： the pathology was similar to that of types I and II, and an MVD 〉30/mm~. Hepatic blood flow, hepatic arterial fraction, hepatic arterial perfusion, and hepatic portal perfusion were significantly increased in the tumor edges of HCC patients compared to those of the controls （P〈0.05）. The correlation between CT perfusion parameters and MVD was higher in blurry tumor edges of type II than in those of types Ⅰ or Ⅲ. CONCLUSION： CT perfusion imaging of tumor edges may be helpful in revealing histopathological features, and indirectly reflect angiogenic changes of HCCs.

Pancreatic neuroendocrine tumor detected by technetium-99m methoxy-2-isobutylisonitrile single photon emission computed tomography/computed tomography:A case report

BACKGROUND Pancreatic neuroendocrine tumors(NETs)account for about 1%–2%of pancreatic tumors and about 8%of all NETs.Computed tomography(CT),magnetic resonance imaging,and endoscopic ultrasound are common imaging modalities for the diagnosis of pancreatic NETs.Furthermore,somatostatin receptor imaging is of great value for diagnosing pancreatic NETs.Herein,we report the efficacy of technetium-99m methoxy-2-isobutylisonitrile(99mTc-MIBI)single photon emission CT(SPECT)/CT for detecting pancreatic NETs.CASE SUMMARY A 57-year-old woman presented to our hospital with a 1-d history of persistent upper abdominal distending pain.The distending pain in the upper abdomen was aggravated after eating,with nausea and retching.Routine blood test results showed a high neutrophil percentage,low leukomonocyte and monocyte percentages,and low leukomonocyte and eosinophil counts.Amylase,liver and kidney function,and tumor markers alpha-fetoprotein,carcinoembryonic antigen,and cancer antigen(CA)125,CA72-4,CA19-9,and CA153 were normal.Abdominal CT showed a mass,with multiple calcifications between the pancreas and the spleen.The boundary between the mass and the pancreas and spleen was poorly defined.Contrast-enhanced CT revealed that the upper abdominal mass was unevenly and gradually enhanced.99mTc-MIBI SPECT/CT revealed that a focal radioactive concentration,with mild radioactive concentration extending into the upper abdominal mass,was present at the pancreatic body and tail.The 99mTc-MIBI SPECT/CT manifestations were consistent with the final pathological diagnosis of pancreatic NET.CONCLUSION 99mTc-MIBI SPECT/CT appears to be a valuable tool for detecting pancreatic NETs.

Prenatal Diagnosis of Proximal Femoral Focal Deficiency Combining Ultrasound and Computer Tomography

Four cases of proximal femoral focal deficiency (PFFD) in an otherwise healthy infant are described. Antenatal diagnosis was made at 27, 23, 23 and 18 weeks of gestation by routine ultrasound (US) examination. Computer Tomography (CT) was performed after 30 weeks of gestation and confirmed the images obtained by US. The diagnosis was confirmed after delivery. These cases illustrate the importance of combining US and CT to improve accuracy of prenatal diagnosis of skeletal disorders.

Imaging of the Extra-axial Tumors and Tumor-like Lesions Involving both Middle and Posterior Cranial Fossae: Classification and Diagnosis

Objective: To study the imaging features of extra-axial tumors and tumor-likelesions involving both middle and posterior cranial fossae and to make a classification. Methods:Sixty cases of pathologically confirmed extra-axil tumors and tumor-like lesions involving bothmiddle and posterior cranial fossae were analyzed. They were divided into central and lateral types,the latter of which were subdivided into three types: middle cranial fossae type, posterior cranialfossae type and the over-riding type. The constitution and imaging features of each type wereanalyzed. Results: There were 12 cases of central type, including chordoma (n=5), pituitary adenoma(n=3), nasopharyngeal carcinoma (n=2), craniopharyn-gioma (n=1) and meningioma (n=l). 48 cases oflateral type including trigeminal nerve tumors (n=14), meningioma (n=12), epidermoid cyst (n=11),dural cavernous hemangioma (n=4), dermoid cyst (n=2), metastasis (n=2), hemangiopericytoma (n=1),paraganglioma of glonius jugular (n=1) and nasopharyngeal carcinoma (n=1). Each type of the lesionshad its own shape features, some of which were characteristic for some specific tumors. Most of thetumors and tumor-like lesions could be qualitatively diagnosed according to their imagingcharacteristics and the extent of the lesions could be defined definitely. Conclusion: It is helpfulto categorize extra-axial tumors and tumor-like lesions involving both middle and posterior cranialfossae according to their location for qualitative diagnosis and description of the extent of theselesions. It is of great clinical value in providing more precise and thorough imaging informationfor planning therapeutic methods and route of operation.

Value of Multi-slice spiral CT in diagnosis of malignant gastrointestinal stromal tumors

Objective： The aim of this study was to investigate the value of multi-slice spiral CT （MSCT） in the diagnosis of malignant gastrointestinal stromal tumors （GISTs）. Methods： Twenty-seven cases of MSCT images of malignant GIST proved by surgery and pathology were retrospectively analyzed. Both plain and enhanced CT scan was performed and multiplanar reconstruction was made in all cases. Results： The lesions originated from the stomach （n = 11）, small intestine （n = 9）, colon （n = 4）, rectum （n = 1）, and mesentery （n = 2）. The transverse diameters of mass were 4.2-22 cm, the edges clearly （n = 12）, unclearly （n = 15）. The mass were mainly irregular in shape Iobulated （n = 19）. The lesions were mainly heterogeneity on plain scan, moderate to marked enhancement in arterial phase and durative enhanced in venous phase. Cystic necrosis were observed in all the lesions, 9 cases were cystic and solid mixed mass. Hepatic metastases （n = 4）, pulmonary metastasis （n = 1）, lymphatic metastasis （n = 2） were detected. The accuracy rate of MSCT diagnosis for location and pathologic features of GISTs were 85.2% （23/27） and 77.8% （21/27）. Conclusion： Two-phase MSCT examination and axial images combined with multiplanar reconstruction images have important value for diagnosis of malignant GIST.

An automated deep learning based pancreatic tumor diagnosis and classification model using computed tomography images

Purpose-The advancements of deep learning(DL)models demonstrate significant performance on accurate pancreatic tumor segmentation and classification.Design/methodology/approach-The presented model involves different stages of operations,namely preprocessing,image segmentation,feature extraction and image classification.Primarily,bilateral filtering(BF)technique is applied for image preprocessing to eradicate the noise present in the CT pancreatic image.Besides,noninteractive GrabCut(NIGC)algorithm is applied for the image segmentation process.Subsequently,residual network 152(ResNet152)model is utilized as a feature extractor to originate a valuable set of feature vectors.At last,the red deer optimization algorithm(RDA)tuned backpropagation neural network(BPNN),called RDA-BPNN model,is employed as a classification model to determine the existence of pancreatic tumor.Findings-The experimental results are validated in terms of different performance measures and a detailed comparative results analysis ensured the betterment of the RDA-BPNN model with the sensitivity of 98.54%,specificity of 98.46%,accuracy of 98.51% and F-score of 98.23%.Originality/value-The study also identifies several novel automated deep learning based approaches used by researchers to assess the performance of the RDA-BPNN model on benchmark dataset and analyze the results in terms of several measures.

Value of CT scan in the diagnosis of primary large bowel lymphoma

Objective: To study the CT imaging of primary large bowel lymphoma and evaluate the value of CT scan. Methods: CT reports of 8 patients with proven primary large bowel lymphoma were retrospectively reviewed. Plain CT scans were done on all patients, enhanced CT scans simultaneously with 5-10 mm section thickness, and 5-10 mm table increments in 6 cases. Results: Primary involved sites were on the cecum (n=3), the ascending colon (n=2), and the rectum (n=1). The tumor was found in multiple areas of the large bowel in 2 cases. CT appearance fell into 3 typical patterns in our study. The first was focal mass type in 2 cases, with one combined with intussusception and retroperitoneal adenopathy; the second was segmental annular involvement type in 3 cases, with one of them combined with mesenteric adenopathy; the last was diffuse involvement type in 2 cases. Multiple nodules were seen in the rectum in 1 case. Conclusion: CT was found to be accurate in detecting the primary sites and complications of lymphoma, and evaluating invasion of adjacent structures; Focal mass type, segmental annular involvement type and diffuse involvement type are the main patterns of CT features in the primary large bowel lymphoma; The features revealed by CT scan are suggestive of primary large bowel lymphoma in some cases.

A controlled study of positron-emission-tomography and positron-emission-tomography/computed tomography in differential diagnosis of solitary pulmonary nodules—report of 60 cases

The differential diagnosis of solitary pulmonary nodules （SPNs） remains a challenge. It is acknowledged that combining positron-emission tomography （PET） and computed tomography （CT） offers the most reliable noninvasive method for the diagnosis of SPNs. Since Townsend et al1 developed integrated PET/CT in 1999, this technique has increasingly been introduced into clinical practice. To date, nuclear medicine physicians have usually undertaken PET/CT diagnosis, but the question is surfacing as how to make full use of the information of CT image to improve the accuracy of SPN diagnosis. To answer this question, we performed a retrospective study on 60 patients with SPNs.

Differential diagnosis of coronavirus disease 2019 from community-acquired-pneumonia by computed tomography scan and follow-up

Objective Coronavirus disease 2019(COVID-19)is currently the most serious infectious disease in the world.An accurate diagnosis of this disease in the clinic is very important.This study aims to improve the differential ability of computed tomography(CT)to diagnose COVID-19 and other community-acquired pneumonias(CAPs)and evaluate the short-term prognosis of these patients.Methods The clinical and imaging data of 165 COVID-19 and 118 CAP patients diagnosed in seven hospitals in Anhui Province,China from January 21 to February 28,2020 were retrospectively analysed.The CT manifestations of the two groups were recorded and compared.A correlation analysis was used to examine the relationship between COVID-19 and age,size of lung lesions,number of involved lobes,and CT findings of patients.The factors that were helpful in diagnosing the two groups of patients were identified based on specificity and sensitivity.Results The typical CT findings of COVID-19 are simple ground-glass opacities(GGO),GGO with consolidation or grid-like changes.The sensitivity and specificity of the combination of age,white blood cell count,and ground-glass opacity in the diagnosis of COVID-19 were 92.7 and 66.1%,respectively.Pulmonary consolidation,fibrous cords,and bronchial wall thickening were used as indicators to exclude COVID-19.The sensitivity and specificity of the combination of these findings were 78.0 and 63.6%,respectively.The follow-up results showed that 67.8%(112/165)of COVID-19 patients had abnormal changes in their lung parameters,and the severity of the pulmonary sequelae of patients over 60 years of age worsened with age.Conclusions Age,white blood cell count and ground-glass opacity have high accuracy in the early diagnosis of COVID-19 and the differential diagnosis from CAP.Patients aged over 60 years with COVID-19 have a poor prognosis.This result provides certain significant guidance for the diagnosis and treatment of new coronavirus pneumonia.

Primary Malignant Renal Tumors in Infancy and Childhood: CT Appearances

Objective： To investigate the imaging manifestation of primary malignant renal tumor with CT. Methods： Forty-three cases of surgically and pathologically confirmed primary malignant renal tumor were retrospectively reviewed. Un-contrast and contrast CT was performed in all 43 patients in which 15 patients received MRI examination. Results： The residual normal renal tissue of 29 cases out of 34 cases of Wilms＇ tumor was enhanced and manifested ＂crescent sign＂ or ＂ring sign＂. Four cases of malignant rabdoid tumor （RTK） manifested as large mass with notable necrosis and subcapsular fluid collection; Two cases of clear cell sarcoma （CCS） showed metastases to the skull which could indicate the diagnosis; Renal cell carcinoma （RCC） （n=3） showed calcification in 1 case. Conclusion： CT can precisely delineate the location, size, extent of involvement, imaging characteristics and metastases of renal tumor, which can provide information necessary to the clinical staging, therapy planning and prognosis of the tumors.

Comparing Gross Tumor Volume of Delineation between CT and MRI for Nasopharyngeal Carcinoma

Objective: To study the accuracy between CT and MRI in delineating gross tumor volume (GTV) of nasopharyngeal carcinoma (NPC) in making radiotherapy plan. Methods: The clinical data of 39 cases pathologically proven as nasopharyngeal carcinoma selected from April 2003 to September 2004 were retrospectively analyzed. All were subjected to CT and MR examination one week before treatment. CT scanning was performed with GE Light speed 16, and axial scan was parallel to the OM line routinely from soft palate to the suprasellar cistern. MR scanning was performed by GE Signa super-conducting magnetic resonance imaging system (1.5 Tesla). The standard quadrature head coil was used. Routine axial, sagittal and coronal image with SE sequence were obtained, and FLAIR was used in 10 of 21 cases. Scanned field ranged from the soft palate to the suprasellar cistern. Part of all cases underwent enhanced scanned with Ultravist in CT group or/and GD-DTPA in MR group. All data were analyzed by using the paired-samples t test. Results: The media primary tumor volume (cm3) in CT group and MR group was 32.49±19.91, 29.06±18.75, respectively, and the difference between the two groups were significant (t=5.268, P=0.000). There was significant difference between the two groups in early stage (T1+T2) and advanced stage (T3+T4) by Fuzhou Staging System (t=5.677, P=0.000; t=3.310, P=0.005, respectively). There was significant difference in stage T1, T2, T3 (P=0.005, P=0.001, P=0.004, respectively), and not in stage T4 (P=0.146) between the two groups. Conclusion: MR was more accurate than CT in delineating GTV of NPC, so, is more valuable in making radiotherapy plan.

Diagnostic procedures for submucosal tumors in the gastrointestinal tract

This review is part one of three, which will present an update on diagnostic procedures for gastrointestinal (GI) submucosal tumors (SMTs). Part two identifies the classification and part three the therapeutic methods regarding GI SMTs. Submucosal tumors are typically asymptomatic and therefore encountered incidentally. Advances in diagnostic tools for gastrointestinal submucosal tumors have emerged over the past decade. The aim of this paper is to provide the readers with guidelines for the use of diagnostic procedures, when a submucosal tumor is suspected. Literature searches were performed to find information on diagnostics for gastrointestinal submucosal tumors. Based on the searches, the optimal diagnostic procedures and specific features of the submucosal tumors could be outlined. Standard endoscppy, capsule endoscopy and push-and-pull enteroscopy (PPE) together with barium contrast X-ray do not alone provide sufficient information, when examining submucosal tumors. Endoscopic ultrasound (EUS), computed tomography (CT), magnetic resonance imaging (MRI) and fluorodeoxyglucose-labeled positron emission tomography (FDG-PET) are recommended as supplementary tools.

Ischemic colitis masquerading as colonic tumor:Case report with review of literature

Ischemic colitis can mimic a carcinoma on computed tomographic (CT) imaging or endoscopic examination. A coexisting colonic carcinoma or another potentially obstructing lesion has also been described in 20% of the cases of ischemic colitis. CT scan can differentiate it from colon cancer in 75% of cases. However, colonoscopy is the preferred method for diagnosing ischemic colitis as it allows for direct visualization with tissue sampling. Varied presentations of ischemic colitis have been described as an ulcerated or submucosal mass or as a narrowed segment of colon with ulcerated mucosa on colonoscopy. Awareness and early recognition of such varied presentations of a common condition is necessary to differentiate from a colonic carcinoma, and to avoid unnecessary surgery and related complications.

CT manifestations and features of solid cystic tumors of the pancreas

Objective: To study retrospectively the manifestations and characteristics of solid cystic tumor of the pan- creas(SCTP) on CT. Methods: Nine patients with solid cystic tumor of the pancreas underwent resection with pathological and immunohistochemical confirmation. All the patients were female, aged 27.7 years on average at onset of the disease. CT scan was performed in patients with or without intravenous injection of contrast medium; it was also performed in the arterial phase in 4 pa- tients. Results: Solid and cystic structures were observed in tumors of the pancreas. Solid structure demonstrated low or iso-density on unenhanced CT, poor enhance- ment in the arterial phase and marked enhancement in the portal venous phase on contrast material-en- hanced CT. Cystic structure showed low density on both pre- and pro-contrast views. The CT findings of tumors with predominantly cystic or equal propor- tion of solid and cystic structure: mural nodules for solid structure, 'floating cloud' signs, or solid and cystic crossing distributions. Cystic structure of tumors predominately solid presenting as a beading appearance under capsule. In round, oval and com- pletely encapsulated tumors in the pancreas, the greater vessel enhanced with well-defined margins on pro-contrast images. No dilatation was observed of the common bile and pancreatic ducts. Conclusion: The characteristics of solid cystic tumor of the pancreas revealed by CT could confirm the di- agnosis of the disease in combination with onset age and sex of patients.

Gastro-entero-pancreatic neuroendocrine tumors:Is now time for a new approach?

Gastro-entero-pancreatic tumors(GEP-NETs) are rare neoplasms often characterized by an overexpression of somatostatin receptors.Thus,radiolabeled somatostatin analogues have showed an increasing relevance both in diagnosis and treatment,especially in low-and intermediate-differentiated GEP-NETs.These evidences have led to a growing development of new functional imaging techniques as 68 Ga-DOTATATE positron emission tomography/computed tomography(PET/CT) proved useful in the management of these neoplasms.However these tumors have a heterogeneous behavior also modifying their aggressiveness through time.Therefore sometimes 18 F-fluorodeoxyglucose PET/CT appears to be more appropriate to obtain a better assessment of the disease.According to these considerations,the combination of different functional imaging techniques should be considered in the management of GEP-NETs patients allowing clinicians to choose the tailored therapeutic approach among available options.

Radiomics for differentiating tumor deposits from lymph node metastasis in rectal cancer

BACKGROUND Tumor deposits(TDs)are not equivalent to lymph node(LN)metastasis(LNM)but have become independent adverse prognostic factors in patients with rectal cancer(RC).Although preoperatively differentiating TDs and LNMs is helpful in designing individualized treatment strategies and achieving improved prognoses,it is a challenging task.AIM To establish a computed tomography(CT)-based radiomics model for preoperatively differentiating TDs from LNM in patients with RC.METHODS This study retrospectively enrolled 219 patients with RC[TDs+LNM-(n=89);LNM+TDs-(n=115);TDs+LNM+(n=15)]from a single center between September 2016 and September 2021.Single-positive patients(i.e.,TDs+LNM-and LNM+TDs-)were classified into the training(n=163)and validation(n=41)sets.We extracted numerous features from the enhanced CT(region 1:The main tumor;region 2:The largest peritumoral nodule).After deleting redundant features,three feature selection methods and three machine learning methods were used to select the best-performing classifier as the radiomics model(Rad-score).After validating Rad-score,its performance was further evaluated in the field of diagnosing double-positive patients(i.e.,TDs+LNM+)by outlining all peritumoral nodules with diameter(short-axis)>3 mm.RESULTS Rad-score 1(radiomics signature of the main tumor)had an area under the curve(AUC)of 0.768 on the training dataset and 0.700 on the validation dataset.Rad-score 2(radiomics signature of the largest peritumoral nodule)had a higher AUC(training set:0.940;validation set:0.918)than Radscore 1.Clinical factors,including age,gender,location of RC,tumor markers,and radiological features of the largest peritumoral nodule,were excluded by logistic regression.Thus,the combined model was comprised of Rad-scores of 1 and 2.Considering that the combined model had similar AUCs with Rad-score 2(P=0.134 in the training set and 0.594 in the validation set),Rad-score 2 was used as the final model.For the diagnosis of double-positive patients in the mixed group[TDs+LNM+(n=15);single-positive(n=15)],Rad-score 2 demonstrated moderate performance(sensitivity,73.3%;specificity,66.6%;and accuracy,70.0%).CONCLUSION Radiomics analysis based on the largest peritumoral nodule can be helpful in preoperatively differentiating between TDs and LNM.