Radiomics-based machine-learning method to diagnose prostate cancer using mp-MRI: a comparison between conventional and fused models.

OBJECTIVES: Multiparametric MRI (mp-MRI) has been significantly used for detection, localization and staging of Prostate cancer (PCa). However, all the assessment suffers from poor reproducibility among the readers. The aim of this study was to evaluate radiomics models to diagnose PCa using high-resolution T2-weighted (T2-W) and dynamic contrast-enhanced (DCE) MRI. MATERIALS AND METHODS: Thirty two patients who had high prostate specific antigen level were recruited. The prostate biopsies considered as the reference to differentiate between 66 benign and 36 malignant prostate lesions. 181 features were extracted from each modality. K-nearest neighbors, artificial neural network, decision tree, and linear discriminant analysis were used for machine-learning study. The leave-one-out cross-validation method was used to prevent overfitting and build robust models. RESULTS: Radiomics analysis showed that T2-W images were more effective in PCa detection compare to DCE images. Local binary pattern features and speeded up robust features had the highest ability for prediction in T2-W and DCE images, respectively. The classifier fusion using decision template method showed the highest performance with accuracy, specificity, and sensitivity of 100%. DISCUSSION: The findings of this framework provide researchers on PCa with a promising method for reliable detection of prostate lesions in MR images by fused model.

Quantification of Multi-Parametric Magnetic Resonance Imaging Based on Radiomics Analysis for Differentiation of Benign and Malignant Lesions of Prostate.

Background: The most common cancer (non-cutaneous) malignancy among men is prostate cancer. Management of prostate cancer, including staging and treatment, playing an important role in decreasing mortality rates. Among all current diagnostic tools, multiparametric MRI (mp-MRI) has shown high potential in localizing and staging prostate cancer. Quantification of mp-MRI helps to decrease the dependency of diagnosis on readers' opinions. Objective: The aim of this research is to set a method based on quantification of mp-MRI images for discrimination between benign and malignant prostatic lesions with fusion-guided MR imaging/transrectal ultrasonography biopsy as a pathology validation reference. Material and Methods: It is an analytical research that 27 patients underwent the mp-MRI examination, including T1- and T2- weighted and diffusion weighted imaging (DWI). Quantification was done by calculating radiomic features from mp-MRI images. Receiver-operating-characteristic curve was done for each feature to evaluate the discriminatory capacity and linear discriminant analysis (LDA) and leave-one-out cross-validation for feature filtering to estimate the sensitivity, specificity and accuracy of the benign and malignant lesion differentiation process is used. Results: An accuracy, sensitivity and specificity of 92.6%, 95.2% and 83.3%, respectively, were achieved from a subset of radiomics features obtained from T2-weighted images and apparent diffusion coefficient (ADC) maps for distinguishing benign and malignant prostate lesions. Conclusion: Quantification of mp-MRI (T2-weighted images and ADC-maps) based on radiomics feature has potential to distinguish benign with appropriate accuracy from malignant prostate lesions. This technique is helpful in preventing needless biopsies in patients and provides an assisted diagnosis for classifications of prostate lesions.

Ultrasound/MRI-targeted biopsy versus saturated trans-rectal ultrasound guided biopsy of prostate in patients with primary negative conventional biopsy and still elevated PSA: a prospective randomized clinical trial.

INTRODUCTION: To evaluate and compare the rate of cancer detection by two methods Saturated TRUS guided biopsy and ultrasound/magnetic resonance imaging (US/MRI)-targeted biopsy in patients with primary negative prostate cancer in standard 12 cores biopsy evaluation but still have elevated prostate specific antigen (PSA). MATERIALS AND METHODS: From 105 patients who met our inclusion criteria, 53 patients underwent US/MRI-targeted biopsy and 52 remaining patients underwent Saturated 20 core TRUS guided biopsy in a prospective randomized clinical trial. RESULTS: The mean age (±SD) was 62.2 (±8.2) year. The mean PSA (±SD) was 11.8 (±7.5) ng/ml. The mean prostate volume was 56.1 (±24.8) ml. Adenocarcinoma of prostate was detected in 9/52 (17.3%) patients in groups saturated biopsy and 14/53 (26.4%) patients in US/MRI-targeted biopsy group and there was no difference in cancer detection rate between 2 groups (P=0.252). except four patients with fever (two in each group), there was no other serious complication (Clavien grade 3 or higher) occurred in the patients. In the multivariate analysis, higher pre-procedure PSA, lower size of the prostate, pathology of ASAP and presence of nodule in DRE were independent predictors for cancer detection in second biopsy (P=0.036, P<0.001, P=0.013 and P=0.031, respectively). CONCLUSION: We didn't find any superiority in cancer detection rate and any different in complication rate between these two methods saturated TRUS guided biopsy and US/MRI-targeted biopsy.

Predicting survival of Iranian COVID-19 patients infected by various variants including omicron from CT Scan images and clinical data using deep neural networks.

Purpose: The rapid spread of the COVID-19 omicron variant virus has resulted in an overload of hospitals around the globe. As a result, many patients are deprived of hospital facilities, increasing mortality rates. Therefore, mortality rates can be reduced by efficiently assigning facilities to higher-risk patients. Therefore, it is crucial to estimate patients' survival probability based on their conditions at the time of admission so that the minimum required facilities can be provided, allowing more opportunities to be available for those who need them. Although radiologic findings in chest computerized tomography scans show various patterns, considering the individual risk factors and other underlying diseases, it is difficult to predict patient prognosis through routine clinical or statistical analysis. Method: In this study, a deep neural network model is proposed for predicting survival based on simple clinical features, blood tests, axial computerized tomography scan images of lungs, and the patients' planned treatment. The model's architecture combines a Convolutional Neural Network and a Long Short Term Memory network. The model was trained using 390 survivors and 108 deceased patients from the Rasoul Akram Hospital and evaluated 109 surviving and 36 deceased patients infected by the omicron variant. Results: The proposed model reached an accuracy of 87.5% on the test data, indicating survival prediction possibility. The accuracy was significantly higher than the accuracy achieved by classical machine learning methods without considering computerized tomography scan images (p-value <= 4E-5). The images were also replaced with hand-crafted features related to the ratio of infected lung lobes used in classical machine-learning models. The highest-performing model reached an accuracy of 84.5%, which was considerably higher than the models trained on mere clinical information (p-value <= 0.006). However, the performance was still significantly less than the deep model (p-value <= 0.016). Conclusion: The proposed deep model achieved a higher accuracy than classical machine learning methods trained on features other than computerized tomography scan images. This proves the images contain extra information. Meanwhile, Artificial Intelligence methods with multimodal inputs can be more reliable and accurate than computerized tomography severity scores.

Multiparametric MRI for the Diagnosis of Tumor Type in Patients Suspicious of Inner Gland Prostate Cancer.

PURPOSE: The current study aimed to evaluate multiparametric MRI for the diagnosis of type of tumor (benign ormalignant) in patients suspicious of inner gland prostate cancer. MATERIALS AND METHODS: This cross-sectional study was conducted on 44 consecutive patients with a clinicalimpression of prostate cancer who were referred to the MRI department of Payambaran Hospital, Tehran, Iranfor confirmative diagnostic evaluation. Cases suspected of tumor relapse and those who previously underwenttreatment for prostate cancer were excluded. Multiparametric MRI was performed for every patient by using a 1.5Tesla device with an integrated endorectal and pelvic-phased array coil. All patients subsequently underwent MRItransrectalultrasound fusion biopsy. The diagnostic value of each sequence was then investigated individually andin combination with other techniques by comparing the results with histological findings from MRI-TRUS fusionbiopsy. RESULTS: Among the techniques, T2-weighted imaging (T2W) had the highest sensitivity and specificity whiledynamic contrast enhanced (DCE) technique had the least. Diffusion-weighted imaging (DWI) and magnetic resonancespectroscopy (MRS) had a similar sensitivity and specificity and did not significantly differ from T2W.Adding functional techniques to T2W did not improve diagnostic indices compared to T2W alone. Quantitativeevaluation of apparent diffusion coefficient (ADC), DWI, and MRS showed that all techniques were able to differentiatebetween benign and malignant tumors. However, the quantitative combination of these sequences decreaseddiagnostic performance. CONCLUSION: T2W is the best technique for the diagnosis of type of tumor in terms of benignancy or malignancyin patients suspicious of inner gland prostate cancer. Adding functional imaging measurements to T2W does notimprove its diagnostic value.

Wavelet-enhanced convolutional neural network: a new idea in a deep learning paradigm.

PURPOSE: Manual brain tumor segmentation is a challenging task that requires the use of machine learning techniques. One of the machine learning techniques that has been given much attention is the convolutional neural network (CNN). The performance of the CNN can be enhanced by combining other data analysis tools such as wavelet transform. MATERIALS AND METHODS: In this study, one of the famous implementations of CNN, a fully convolutional network (FCN), was used in brain tumor segmentation and its architecture was enhanced by wavelet transform. In this combination, a wavelet transform was used as a complementary and enhancing tool for CNN in brain tumor segmentation. RESULTS: Comparing the performance of basic FCN architecture against the wavelet-enhanced form revealed a remarkable superiority of enhanced architecture in brain tumor segmentation tasks. CONCLUSION: Using mathematical functions and enhancing tools such as wavelet transform and other mathematical functions can improve the performance of CNN in any image processing task such as segmentation and classification.

Sonographic Evaluation of Cervical Lymphadenopathy; Comparison of Metastatic and Reactive Lymph Nodes in Patients With Head and Neck Squamous Cell Carcinoma Using Gray Scale and Doppler Techniques.

BACKGROUND: Cervical lymphadenopathy could be seen in several pathologic processes. An accurate differentiation between these conditions is of utmost importance to select an appropriate therapy and assess the prognosis. Gray scale and Doppler are appropriate sonographic techniques for evaluating internal and external features of lymph nodes. Although, various criteria have been proposed to differentiate metastatic lymph nodes from benign ones, the most valuable and specific sonographic features are still under dispute. OBJECTIVES: The present study was designed to determine valuable sonographic features for differentiating metastasis from benign nodes using gray scale and Doppler sonography. PATIENTS AND METHODS: A prospective diagnostic study was performed on 63 patients with head and neck squamous cell carcinoma (SCC) treated and referred to surgery clinic of Hazrat Rasoul Akram hospital from November 2010 to June 2012 with complaint of palpable cervical lymph node. All patients' necks were scanned multidirectionally by gray-scale and Doppler techniques. After sonography, lymph nodes were biopsied and investigated to find out whether they were metastatic or reactive. Finally, demographic, sonographic and pathologic data were statistically analyzed by SPSS ver. 16 software using t-test, a nonparametric test and ROC analysis. Ninety five percent confidence interval was considered for all parameters. RESULTS: The study included 41 males and 22 females with a mean age of 57.56 ± 13.79 years. The number of metastatic lymph nodes was 47, while the remaining 16 were reactive. There were significant differences in length (P = 0.037), width (P = 0.001), resistance index (P < 0.001), pulsatility index (P < 0.001) and systolic velocity (P < 0.001) of metastatic and reactive lymph nodes. Cut points for resistive and pulsatility indexes and systolic velocity were calculated as 0.695, 1.35 and 16.5, respectively. The most valuable factor for defining a lymph node as metastatic was circulation pattern with accuracy, sensitivity and specificity of 94%, 85% and 93%, respectively. CONCLUSION: Gray scale sonography in combination with Doppler sonography could be a trustworthy technique in differentiating metastatic lymph nodes from reactive ones. Although, circulation pattern had a higher diagnostic accuracy in the present study, combination of sonographic characteristics could be more beneficial in differentiating metastatic cervical nodes from reactive ones.

The value of prostate MRI with endorectal coil in detecting seminal vesicle involvement in patients with prostate cancer.

BACKGROUND: In prostate cancer, detection of seminal vesicle involvement is important because it influences the treatment planning and prognosis of the patients. OBJECTIVES: The objective of this study was to determine the value of prostate MRI with endorectal coil in the detection of seminal vesicle involvement in patients with prostate cancer. PATIENTS AND METHODS: A total number of 238 biopsy-proven prostate cancer patients were examined by 1.5 Tesla MRI with a combination of pelvic and endorectal coils to detect seminal vesicle involvement. After radical prostatectomy, the MRI results were compared with pathology results. RESULTS: Seminal vesicle involvement was detected in 67 (28.1%) patients. Pathology confirmed the involvement of seminal vesicles by prostate cancer in 63 patients. In two patients, seminal vesicle involvement was diagnosed by pathology but not detected by MRI. The sensitivity was 0.97 [95% confidence interval = 0.89-0.99], the specificity was 0.98 [95% confidence interval = 0.94-0.99], the positive predictive value was 0.94 [95% confidence interval = 0.85-0.98], and the negative predictive value was 0.99 [95% confidence interval = 0.96-0.99]. CONCLUSIONS: MRI with endorectal coil is a valuable imaging technique with suitable accuracy in detecting seminal vesicle involvement in prostate cancer.

Prostate Biopsy Using Transrectal Ultrasonography; The Optimal Number of Cores Regarding Cancer Detection Rate and Complications.

BACKGROUND: Transrectal ultrasound guided biopsy of the prostate is the most common modality used to diagnose prostate cancer. OBJECTIVES: The aim of this study was to evaluate the optimal number of cores at prostate biopsy, which have the most diagnostic value with least adverse effects. PATIENTS AND MATERIALS: Transrectal ultrasonography (TRUS) guided biopsy was performed in 180 patients suspicious for prostate cancer due to either abnormal rectal examination or elevated PSA. The patients were divided randomly into three groups of six-core, twelve-core and eighteen-core biopsies. The detection rate of prostate cancer in each group with the rate of post biopsy urinary infection and prostatitis were compared. RESULTS: Prostate cancer was diagnosed in 8 (13.3%), 21 (35%) and 24 (40%) patients in six, twelve and eighteen core biopsy groups, respectively. Urinary tract infection and prostatitis occurred in 17 (28.3%), 23 (38.3%) and 35 (58.3%) patients in six, twelve and eighteen core biopsy groups, respectively. Considering the detection rate of prostate cancer, there was a significant difference between 6 and 12 core biopsy groups (P = 0.006) and 12-core biopsies detected more cases of prostate cancer, but there was no significant difference between 12 and 18 core biopsy groups (P = 0.572). Considering the infection rate, there was no significant difference between 6 and 12 core biopsy groups (P = 0.254), but there was a significant difference between 12 and 18 core biopsy groups (P = 0.028) and infectious complications occurred more frequently in 18-core biopsy group. CONCLUSIONS: The best balance between detection rate of prostate cancer and infectious complications of biopsies achieved in twelve-core biopsy protocol. Twelve-core biopsy enhances the rate of prostate cancer detection with minimum adverse effects.

Quantitative evaluation of Iranian radiology papers and its comparison with selected countries.

BACKGROUND: Recent technological developments in medicine, including modern radiology have promoted the impact of scientific researches on social life. The scientific outputs such as article and patents are products that show the scientists' attempt to access these achievements. OBJECTIVES: In the current study, we evaluate the current situation of Iranian scientists in the field of radiology and compare it with the selected countries in terms of scientific papers. For this purpose, we used scientometric tools to quantitatively assess the scientific papers in the field of radiology. MATERIALS AND METHODS: Radiology papers were evaluated in the context of medical field audit using retrospective model. We used the related databases of biomedical sciences for extraction of articles related to radiology. In the next step, the situation of radiology scientific products of the country were determined with respect to the under study regional countries. RESULTS: Results of the current study showed a ratio of 0.19% for Iranian papers in PubMed database published in 2009. In addition, in 2009, Iranian papers constituted 0.29% of the Scopus scientific database. The proportion of Iranian papers in the understudy region was 7.6%. CONCLUSION: To diminish the gap between Iranian scientific radiology papers and other competitor countries in the region and achievement of document 2025 goals, multifold effort of the society of radiology is necessary.

MRI in prostate cancer.

Imaging studies play an important role in detection and management of prostate cancer and MRI especially with the use of endorectal coil because of high contrast resolution is recognized as the best imaging modality in evaluation of prostate cancer. Multiparametric MR study including T1 and T2 weighted images, diffusion weighted images, dynamic contrast study and MR spectroscopy is useful for detection and local staging of prostate cancer as well as posts treatment evaluation of patients either after surgery or radiation therapy for detection of local recurrence.

Value of MRI in local staging of bladder cancer.

PURPOSE: To evaluate the accuracy of magnetic resonance imaging (MRI) in bladder cancer staging as well as differentiating superficial from invasive tumors and organ-confined from non-organ-confined tumors. MATERIALS AND METHODS: A total number of 108 bladder tumors in 86 patients (86% men and 14% women) were evaluated by 1.5 Tesla MRI machine. The tumor stages that were determined by MRI study were compared with pathology results after resection of the tumor. RESULTS: The most common stage determined by both MRI and pathology was T2a. Considering stages in details, the kappa agreement coefficient between MRI and pathology was 0.8 (P < .0001). Combining groups a and b in each stage, the kappa agreement coefficient between MRI and pathology was 0.87 (P < .0001). Considering stages in details, we had 22 (20.3%) mismatches in staging between MRI and pathology; 10 (45.5%) were underestimation and 12 (54.5%) were overestimation. Combining groups a and b in each stage, we had 14 (13%) mismatch cases; 6 (46.2%) were underestimation and 8 (53.8%) were overestimation. The detection rate of MRI was 0% in stage Ta, 80% in stage T1, 88.1% in stage T2, 81.2% in stage T3, and 100% in stage T4. The sensitivity and specificity of MRI in differentiating superficial from deep tumors were 0.98 and 0.82, respectively. The sensitivity and specificity of MRI in differentiating organ-confined from non-organ-confined tumors were 0.93 and 0.94, respectively. CONCLUSION: Magnetic resonance imaging is a reliable modality for determining the stage of bladder tumors with high accuracy, and could show the depth of invasion and extension of tumor that is useful for treatment planning.

Decrease in infection rate following use of povidone-iodine during transrectal ultrasound guided biopsy of the prostate: a double blind randomized clinical trial.

BACKGROUND: Infection after transrectal ultrasound (TRUS) guided biopsy of the prostate is a major and potentially life-threatening problem. Using antibiotic premedication can not completely eliminate infection after biopsy. OBJECTIVES: We performed this study to determine the value of using povidone-iodine in prevention of post biopsy infection. PATIENTS AND METHODS: Totally, 280 patients who were referred for TRUS guided biopsy of the prostate were divided randomly into two equal groups. The case group received an intrarectal mixture of povidone-iodine and lidocaine gel before performing biopsy, while the control group received only lidocaine gel. Patients were followed up for 30 days for possible signs of infection including fever, chills and dysuria. RESULTS: The mean age in the case group was 68.7 ± 7 years and 68.1 ± 7 years in the control group (P = 0.78). Overall, there were signs and symptoms of infection in 78 patients (27.9%), of which 27 (19.3%) were in the case group, while 51 (36.4%) were in the control group (P = 0.001, OR = 2.4, 95% CI = 1.4-4.1). CONCLUSION: Simple use of widely available povidone-iodine for cleaning the rectum before TRUS guided prostate biopsy can reduce the infection rate.

Value of prostate-specific antigen and prostate-specific antigen density in detection of prostate cancer in an Iranian population of men.

INTRODUCTION: The objective of this study was to evaluate the value of serum prostate-specific antigen (PSA) and prostate-specific antigen density (PSAD) in the diagnosis of prostate cancer. MATERIALS AND METHODS: A total of 330 consecutive patients suspected of having prostate cancer due to either abnormal digital rectal examination or elevated serum PSA levels underwent transrectal ultrasonography-guided sextant biopsy of the prostate. The PSA and PSAD values were assessed based on the biopsy results. RESULTS: One hundred and twenty-one patients (36.7%) had prostate cancer. In this group, the mean PSA was 31.60 +/- 30.85 ng/mL (range, 1.9 ng/mL to 166.0 ng/mL) and the mean PSAD was 0.83 +/- 1.01 (range, 0.04 ng/mL/cm3 to 6.38 ng/mL/cm3). In those without prostate cancer the mean PSA and PSAD levels were 13.80 +/- 18.72 ng/mL (range, 0.4 ng/mL to 130.0 ng/mL; P < .001) and 0.24 +/- 0.32 (range of 0.01 ng/mL/cm3 to 2.29 ng/mL/cm3; P < .001). The receiver operating characteristic curve analysis revealed that the discriminating power of serum PSA for detecting prostate cancer, as estimated by the area under the curve, was 0.74 while that for PSAD was 0.81 (P < .001). For the PSA range of 3.5 ng/mL to 41 ng/mL (gray zone) the areas under the curve was 0.68 for PSA, while it was 0.78 for PSAD (P < .001). CONCLUSION: The use of PSAD instead of PSA in the diagnosis of prostatic cancer improves the diagnostic accuracy.

Systemic air embolism after percutaneous transthorasic needle biopsy of the lung.

Computed tomography (CT)-guided percutaneous transthoracic biopsy of the lung is a well-established diagnostic technique, but it can pose complications to the patients. Air embolism is one of the rarest but potentially fatal complications of this procedure. The authors report a fatal case of systemic and massive air embolism to the coronary and cerebral arteries after the performance of lung biopsy. Careful reviewing of the obtained CT images during the procedure may avoid a missing systemic air embolism and can immediately provide an adequate therapy also in asymptomatic patients. This extremely rare complication is an inevitable event and may happen in spite of appropriate experience and meticulous care.

MRI in the diagnosis of diphallia.

Diphallia or duplication of the penis is an extremely rare but well-documented anomaly. According to the presence of one or two corpora cavernosa in each of the penises, diphallia is classified into two major groups of bifid phallus or true diphallia, respectively. We report a 5-year-old boy with duplication of the penis. Significant separation of the penises and their morphology made them appear as true complete phalluses, but MRI established the definitive diagnosis of bifid phallus by demonstrating the presence of one corpus cavernosum in each penis. MRI is a valuable method for achieving the accurate diagnosis of these anomalies and associated malformations. It also provides the appropriate knowledge regarding anatomical detail and assists the surgeon in decision making and preoperative planning for the optimal surgical approach.