Deep learning image reconstruction of diffusion-weighted imaging in evaluation of prostate cancer focusing on its clinical implications

Background

Image-based assessment of prostate cancer (PCa) is increasingly emphasized in the diagnostic workflow for selecting biopsy targets and possibly predicting clinically significant prostate cancer (csPCa). Assessment is based on Prostate Imaging-Reporting and Data System (PI-RADS) which is largely dependent on T2-weighted image (T2WI) and diffusion weighted image (DWI). This study aims to determine whether deep learning reconstruction (DLR) can improve the image quality of DWI and affect the assessment of PI-RADS ≥4 in patients with PCa.

Methods

In this retrospective study, 3.0T post-biopsy prostate magnetic resonance imaging (MRI) of 70 patients with PCa in Korea University Ansan Hospital from November 2021 to July 2022 was reconstructed with and without using DLR. Four DWI image sets were made: (I) conventional DWI (CDWI): DWI with acceleration factor 2 and conventional parallel imaging reconstruction, (II) DL1: DWI with acceleration factor 2 using DLR, (III) DL2: DWI with acceleration factor 3 using DLR, and (IV) DL3: DWI with acceleration factor 3 and half average b-value using DLR. Apparent diffusion coefficient (ADC) value, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were measured by one reviewer, while two reviewers independently assessed overall image quality, noise, and lesion conspicuity using a four-point visual scoring system from each DWI image set. Two reviewers also performed PI-RADSv2.1 scoring on lesions suspected of malignancy.

Results

A total of 70 patients (mean age, 70.8±9.7 years) were analyzed. The image acquisition time was 4:46 min for CDWI and DL1, 3:40 min for DL2, and 2:00 min for DL3. DL1 and DL2 images resulted in better lesion conspicuity compared to CDWI images assessed by both readers (P<0.05). DLR resulted in a significant increase in SNR, from 38.4±14.7 in CDWI to 56.9±21.0 in DL1. CNR increased from 25.1±11.5 in CDWI to 43.1±17.8 in DL1 (P<0.001). PI-RADS v2.1 scoring for PCa lesions was more agreeable with the DL1 reconstruction method than with CDWI (κ value CDWI, DL1; 0.40, 0.61, respectively). A statistically significant number of lesions were upgraded from PI-RADS <4 in CDWI image to PI-RADS ≥4 in DL1 images for both readers (P<0.05). Most of the PI-RADS upgraded lesions were from higher than unfavorable intermediate-risk groups according to the 2023 National Comprehensive Cancer Network guidelines with statistically significant difference of marginal probability in DL1 and DL2 for both readers (P<0.05).

Conclusions

DLR in DWI for PCa can provide options for improving image quality with a significant impact on PI-RADS evaluation or about a 23% reduction in acquisition time without compromising image quality.

Development and multicenter validation of deep convolutional neural network-based detection of colorectal cancer on abdominal CT

OBJECTIVES

This study aims to develop computer-aided detection (CAD) for colorectal cancer (CRC) using abdominal CT based on a deep convolutional neural network.

METHODS

This retrospective study included consecutive patients with colorectal adenocarcinoma who underwent abdominal CT before CRC resection surgery (training set = 379, test set = 103). We customized the 3D U-Net of nnU-Net (CUNET) for CRC detection, which was trained with fivefold cross-validation using annotated CT images. CUNET was validated using datasets covering various clinical situations and institutions: an internal test set (n = 103), internal patients with CRC first determined by CT (n = 54) and asymptomatic CRC (n = 51), and an external validation set from two institutions (n = 60). During each validation, data from the healthy population were added (internal = 60; external = 130). CUNET was compared with other deep CNNs: residual U-Net and EfficientDet. The CAD performances were evaluated using per-CRC sensitivity (true positive/all CRCs), free-response receiver operating characteristic (FROC), and jackknife alternative FROC (JAFROC) curves.

RESULTS

CUNET showed a higher maximum per-CRC sensitivity than residual U-Net and EfficientDet (internal test set 91.3% vs. 61.2%, and 64.1%). The per-CRC sensitivity of CUNET at false-positive rates of 3.0 was as follows: internal CRC determined by CT, 89.3%; internal asymptomatic CRC, 87.3%; and external validation, 89.6%. CUNET detected 69.2% (9/13) of CRCs missed by radiologists and 89.7% (252/281) of CRCs from all validation sets.

CONCLUSIONS

CUNET can detect CRC on abdominal CT in patients with various clinical situations and from external institutions.

KEY POINTS

• Customized 3D U-Net of nnU-Net (CUNET) can be applied to the opportunistic detection of colorectal cancer (CRC) in abdominal CT, helping radiologists detect unexpected CRC. • CUNET showed the best performance at false-positive rates ≥ 3.0, and 30.1% of false-positives were in the colorectum. CUNET detected 69.2% (9/13) of CRCs missed by radiologists and 87.3% (48/55) of asymptomatic CRCs. • CUNET detected CRCs in multiple validation sets composed of varying clinical situations and from different institutions, and CUNET detected 89.7% (252/281) of CRCs from all validation sets.

Feasibility of computed tomography texture analysis of hepatic fibrosis using dual-energy spectral detector computed tomography

PURPOSE

To evaluate feasibility of computer tomography texture analysis (CTTA) at different energy level using dual-energy spectral detector CT for liver fibrosis.

MATERIALS AND METHODS

Eighty-seven patients who underwent a spectral CT examination and had a reference standard of liver fibrosis (histopathologic findings, n = 61, or clinical findings for normal, n = 26) were included. Mean gray-level intensity, mean number of positive pixels (MPP), entropy, skewness, and kurtosis using commercially available software (TexRAD) were compared at different energy levels. Optimal CTTA parameter cutoffs to diagnose liver fibrosis were evaluated. CTTA parameters at different energy levels correlated with liver fibrosis. The association of CTTA parameters with energy level was evaluated.

RESULTS

Mean gray-level intensity, skewness, kurtosis, and entropy showed significant differences between patients with and without clinically significant hepatic fibrosis (P < 0.05). Mean gray-level intensity at 50 keV was significantly positively correlated with liver fibrosis (ρ = 0.502, P < 0.001). To diagnose stages F2-F4, entropy and mean gray-level intensity at low keV level showed the largest area under the curve (AUC; 0.79 and 0.79). Estimated marginal means (EMMs) of mean gray-level intensity showed prominent differences at low energy levels.

CONCLUSION

CTTA parameters from different keV levels demonstrated meaningful accuracy for diagnosis of liver fibrosis or clinically significant hepatic fibrosis.

Feasibility of using computed tomography texture analysis parameters as imaging biomarkers for predicting risk grade of gastrointestinal stromal tumors: comparison with visual inspection

PURPOSE

To evaluate the feasibility of using computed tomography texture analysis (CTTA) parameters for predicting malignant risk grade and mitosis index of gastrointestinal stromal tumors (GISTs), compared with visual inspection.

METHOD AND MATERIALS

CTTA was performed on portal phase CT images of 145 surgically confirmed GISTs (mean size: 42.9 ± 37.5 mm), using TexRAD software. Mean, standard deviation, entropy, mean of positive pixels (MPP), skewness, and kurtosis of CTTA parameters, on spatial scaling factor (SSF), 2-6 were compared by risk grade, mitosis rate, and the presence or absence of necrosis on visual inspection. CTTA parameters were correlated with risk grade. Diagnostic performance was evaluated with receiver operating characteristic curve analysis. Enhancement pattern, necrosis, heterogeneity, calcification, growth pattern, and mucosal ulceration were subjectively evaluated by two observers.

RESULTS

Three to four parameters at different scales were significantly different according to the risk grade, mitosis rate, and the presence or absence of necrosis (p < 0.041). MPP at fine or medium scale (r = - 0.547 to - 393) and kurtosis at coarse scale (r = 0.424-0.454) correlated significantly with risk grade (p < 0.001). HG-GIST was best differentiated from LG-GIST by MPP at SSF 2 (AUC, 0.782), and kurtosis at SSF 4 (AUC, 0.779) (all p < 0.001). CT features predictive of HG-GIST were density lower than or equal to that of the erector spinae muscles on enhanced images (OR 2.1; p = 0.037; AUC, 0.59), necrosis (OR, 6.1; p < 0.001; AUC, 0.70), heterogeneity (OR, 4.3; p < 0.001; AUC, 0.67), and mucosal ulceration (OR, 3.3; p = 0.002; AUC, 0.62).

CONCLUSION

Using TexRAD, MPP and kurtosis are feasible in predicting risk grade and mitosis index of GISTs. CTTA demonstrated meaningful accuracy in preoperative risk stratification of GISTs.

A case report of intrahepatic bile duct confluence anomalies in VACTERL syndrome

RATIONALE

The clinical manifestations of VACTERL association include vertebral anomalies, anal atresia, congenital heart diseases, tracheoesophageal fistula, renal dysplasia, and limb abnormalities. The association of intrahepatic anomalies and VACTERL syndrome is a rare coincidence. VACTER syndrome and intrahepatic bile drainage anomalies might be genetically related.

PATIENT CONCERNS

A 12-year-old girl presented with episodic colicky abdominal pain, nausea, and vomiting for several years. The individual episodes resolved spontaneously within a few days. She had a history of VACTERL syndrome, including a butterfly shape of the L3 vertebra, anal atresia, and an atrial septal defect.

DIAGNOSES

On laboratory findings, abnormal liver function tests included elevated total bilirubin, alanine aminotransferase, aspartate aminotransferase, and gamma-glutamyltransferase. There was no significant abnormal finding in hepatobiliary system sonography except mild gallbladder wall thickening. We performed magnetic resonance cholangiopancreatography and demonstrated an abnormal intrahepatic bile duct confluence, which showed 3 bile ducts draining directly into the neck of the gallbladder.

INTERVENTION

Her symptoms related to bile reflux during gallbladder contraction. Cholecystectomy with choledochojejunostomy was undertaken because segments of the bile drainage were intertwined.

OUTCOMES

After surgery, her symptoms decreased, but abdominal discomfort remained due to uncorrected left intrahepatic anomalies.

LESSONS

Although hepatobiliary anomalies are not included in VACTERL association diagnostic criteria, detailed hepatobiliary work up is needed when gastrointestinal symptoms are present in VACTERL association patients.

An Innovative Ultrasound Technique for Evaluation of Tumor Vascularity in Breast Cancers: Superb Micro-Vascular Imaging

Tumor vascularity is an important indicator for differential diagnosis, tumor growth, and prognosis. Superb micro-vascular imaging (SMI) is an innovative ultrasound technique for vascular examination that uses a multidimensional filter to eliminate clutter and preserve extremely low-velocity flows. Theoretically, SMI could depict more vessels and more detailed vascular morphology, due to the increased sensitivity of slow blood flow. Here, we report the early experience of using SMI in 21 breast cancer patients. We evaluated tumor vascular features in breast cancer and compared SMI and conventional color or power Doppler imaging. SMI was superior to color or power Doppler imaging in detecting tumor vessels, the details of vessel morphology, and both peripheral and central vascular distribution. In conclusion, SMI is a promising ultrasound technique for evaluating microvascular information of breast cancers.

Small (<4 cm) clear cell renal cell carcinoma: correlation between CT findings and histologic grade

PURPOSE

To evaluate the correlation between CT findings and histologic grade of small clear cell renal cell carcinoma (ccRCC).

METHODS

CT scans of 101 patients with small ccRCC were reviewed independently by two radiologists for tumor size, shape, margin, encapsulation, enhancement pattern, and visual relative enhancement. Enhancement patterns were defined according to the percentage of uniform enhancement [pattern 1, homogeneous (≥90%); pattern 2, relatively homogeneous (≥75 and <90%); and pattern 3, heterogeneous (<75%)]. Quantitative parameters representing attenuation and degree of enhancement were calculated. Histologic grade was classified as low (Fuhrman grade I or II) and high (Fuhrman grade III or IV). CT imaging variables were analyzed using univariate and multivariate analyses.

RESULTS

A total of 63 low-grade and 38 high-grade small ccRCCs were assessed. Low-grade tumors differed from high-grade tumors with respect to enhancement pattern 1 or 2 (p < 0.001 and p < 0.001), smaller size (p = 0.002 and p = 0.001), and lower attenuation on unenhanced scan (p < 0.001 and p = 0.008). In multivariate analysis, enhancement pattern 1 or 2 and low attenuation (≤30 HU) were identified as independent predictors of low-grade ccRCC. Accuracy derived from logistic regression analysis was 79.2% for reader 1 and 70.3% for reader 2.

CONCLUSIONS

CT imaging features including tumor attenuation and enhancement pattern can be useful to predict the biologic behavior of small ccRCC for adequate treatment strategy.

Comparison on Response and Dissolution Rates Between Ursodeoxycholic Acid Alone or in Combination With Chenodeoxycholic Acid for Gallstone Dissolution According to Stone Density on CT Scan: Strobe Compliant Observation Study

Medical dissolution of gallstone is usually performed on radiolucent gallstones in a functioning gallbladder. However, absence of visible gallstone on plain abdominal x-ray does not always preclude calcification. This study aims to compare the response and dissolution rates between ursodeoxycholic acid (UDCA) alone or in combination with chenodeoxycholic acid (CDCA) according to stone density on computed tomography (CT) scan. A total of 126 patients underwent dissolution therapy with either UDCA alone or combination of CDCA and UDCA (CNU) from December 2010 to March 2014 at Korea University Ansan Hospital. In the end, 81 patients (CNU group = 44, UDCA group = 37) completed dissolution therapy for 6 months. Dissolution rate (percentage reduction in the gallstone volume) and response to therapy (complete dissolution or partial dissolution defined as reduction in stone volume of >50%) were compared between the 2 groups. Dissolution and response rates of sludge was also compared between the 2 groups. The overall response rate was 50.6% (CNU group 43.2% vs UDCA group 59.5%, P = 0.14), and the overall dissolution rate was 48.34% (CNU group 41.5% vs UDCA group 56.5%, P = 0.13). When analyzed according to stone density, response rate was 33.3%, 87.1%, 30.0%, and 6.2% for hypodense, isodense, hyperdense, and calcified stones, respectively. Response rate (85.7% vs 88.2%, P = 0.83) and dissolution rate (81.01% vs 85.38%, P = 0.17) of isodense stones were similar between CNU and UDCA group. When only sludge was considered, the overall response rate was 87.5% (CNU group 71.4% vs UDCA group 94.1%, P = 0.19), and the overall dissolution rate was 85.42% (CNU group 67.9% vs UDCA group 92.7%, P = 0.23). Patients with isodense gallstones and sludge showed much better response to dissolution therapy with CNU and UDCA showing comparable efficacy. Therefore, CT scan should be performed before medication therapy if stone dissolution is intended.

Prediction of liver cirrhosis, using diagnostic imaging tools

Early diagnosis of liver cirrhosis is important. Ultrasound-guided liver biopsy is the gold standard for diagnosis of liver cirrhosis. However, its invasiveness and sampling bias limit the applicability of the method. Basic imaging for the diagnosis of liver cirrhosis has developed over the last few decades, enabling early detection of morphological changes of the liver by ultrasonography (US), computed tomography, and magnetic resonance imaging (MRI). They are also accurate diagnostic methods for advanced liver cirrhosis, for which early diagnosis is difficult. There are a number of ways to compensate for this difficulty, including texture analysis to more closely identify the homogeneity of hepatic parenchyma, elastography to measure the stiffness and elasticity of the liver, and perfusion studies to determine the blood flow volume, transit time, and velocity. Amongst these methods, elastography using US and MRI was found to be slightly easier, faster, and able to provide an accurate diagnosis. Early diagnosis of liver cirrhosis using MRI or US elastography is therefore a realistic alternative, but further research is still needed.

Usefulness of Digital Tomosynthesis for the Detection of Airway Obstruction: A Case Report of Bronchial Carcinosarcoma

Bronchial carcinosarcoma is a very rare malignant tumor that is composed of carcinomatous and sarcomatous elements. We describe the first case in which digital tomosynthesis was useful for the evaluation of airway obstruction by bronchial carcinosarcoma that was overlooked on initial chest radiography.

Localized pulmonary alveolar proteinosis: two case reports

BACKGROUND

Pulmonary alveolar proteinosis (PAP) is a relatively rare disease characterized by abnormal accumulation of surfactant-like material in the alveolar spaces. The classic radiologic findings of PAP include bilateral, symmetric, diffuse ground-glass opacity (GGO) or consolidation. The most common computed tomography (CT) feature of PAP is widespread GGO with thickened interlobular septa, the so-called crazy-paving pattern, which strongly suggests the diagnosis.

CASE REPORT

Here, we report the cases of two young male patients with unusual presentations of PAP. One patient showed localized PAP in the left lower lobe on CT images and the other patient presented with unilateral PAP involving the right lower lung field and recurrence in the same area with the same pattern as the initial manifestation.

CONCLUSION

In conclusion, it is important for radiologists to be aware of potential atypical imaging findings of PAP in order to provide a correct diagnosis. Along these lines, PAP can present as a solitary nodular lesion or unilateral focal lesion, and can recur in the same pattern and location.

Functional magnetic resonance cholangiography with Gd-EOB-DTPA: a study in healthy volunteers

PURPOSE

To describe the patterns of bile distribution in the biliary tree, duodenum, jejunum, and stomach, and to determine the gallbladder ejection fraction (GBEF) by using functional magnetic resonance cholangiography (MRC) with gadolinium-ethoxybenzyl-diethylenetriamine penta-acetic acid (Gd-EOB-DTPA) in healthy volunteers.

MATERIALS AND METHODS

Forty subjects were included in this study. After conventional MRC, pre-fatty meal MRC (PRFM) was obtained at 30, 40, 50, and 60min after contrast agent injection. Then, post-fatty meal MRC (POFM) was obtained every 10min for 1h. We assessed the PRFM and POFM for opacification of contrast agent in the first- and second-order intrahepatic ducts (IHDs) and the common bile duct (CBD). Contrast agent opacification in the cystic duct was assessed, and the percentage volume of contrast agent filling in the gallbladder (GB) was calculated on PRFM. We calculated the GBEF and assessed the presence of contrast agent in the GB, duodenum, jejunum, and stomach.

RESULTS

Thirty-six (90%) subjects showed grade 3 CBD opacification (visible contrast and well-defined bile duct border) on 60-min PRFM. Thirty-four (85%) subjects showed grade 3 first-order IHD opacification on 60-min PRFM. All (100%) subjects showed cystic duct opacification of contrast agent, and the average percentage volume of contrast agent filling in the GB was 68.81%±16.84% on 60-min PRFM. The GBEF at 30-min POFM was 35.00%±18.26%. Ten (25%) subjects had no contrast agent in the stomach and small bowel on all PRFMs. Twelve (30%) subjects had contrast medium in the stomach on PRFM and/or POFM.

CONCLUSIONS

Functional MRC with Gd-EOB-DTPA can allow determining the distribution of bile in the biliary tree and small intestine, as well as the GBEF.

Diagnosis of biliary stone disease: T1-weighted magnetic resonance cholangiography with Gd-EOB-DTPA versus T2-weighted magnetic resonance cholangiography

OBJECTIVE

We aimed to compare diagnostic performance of gadoxetic-acid-enhanced-T1-weighted-MR cholangiography (MRC) with that of conventional T2-weighted-MRC in diagnosing biliary stone disease.

MATERIALS AND METHODS

Ninety patients who underwent MRC for evaluation of biliary disease were included. Presence of stones in extrahepatic duct, gallbladder and intrahepatic duct, and presence of acute cholecystitis were evaluated. Sensitivity, specificity, and accuracy of biliary stone disease diagnosis in each biliary duct location according to each image sets were measured.

RESULTS

There was no significant difference in diagnostic performance between two sets of MRC in diagnosing biliary stone disease.

CONCLUSIONS

Diagnostic performance of T1-MRC with gadoxetic-acid in diagnosing biliary stone disease is comparable to that of T2-MRC.

Diagnosis of acute cholecystitis: value of contrast agent in the gallbladder and cystic duct on Gd-EOB-DTPA enhanced MR cholangiography

To evaluate value of %volume of contrast agent in gallbladder and contrast in cystic duct in diagnosis of acute cholecysititis with Gd-EOB-DTPA MRC obtained 60 min after contrast injection (T1-MRC60min). We included 16 acute cholecystitis (AC), 23 chronic cholecystitis (CC), and 40 healthy volunteers. Receiver operating characteristic analysis showed cutoff value of 30.5% as predictor of AC comparing with healthy volunteers (sensitivity 93.8%, specificity 100%, AUC 0.958) and cutoff of 0% as predictor of AC comparing CC (sensitivity 81.2%, specificity 82.6%, AUC 0.823). In AC absent or obliterated cystic duct on T1-MRC60min showed 81.3%, 100%, sensitivity and specificity, respectively. These can be helpful for diagnosis of AC.

Endovascular repair of growing chronic type B aortic dissection with a vascular plug

We report the successful endovascular repair of a growing chronic type B aortic dissection using an Amplatzer Vascular Plug II. A 44-year-old man, with previous medical history of aortic surgery and stenting complained of vague back pain. An approximately 5-mm entry remained in the stented segment of the aorta on computed tomography (CT). Endovascular closure of the entry with a Vascular Plug was uneventful. A 3-month follow-up CT showed no leak, complete false lumen thrombosis in the thoracic segment, shrinkage of the false lumen, and a reduced diameter of thoracic aorta.

Biliary reflux detection in anomalous union of the pancreatico-biliary duct patients

AIM: To demonstrate the imaging findings of biliopancreatic and pancreatico-biliary reflux in patients with anomalous union of the pancreatico-biliary duct (AUPBD) on gadoxetic acid-enhanced functional magnetic resonance cholangiography (fMRC).

METHODS: This study included six consecutive patients (two men and four women; mean age 47.5 years) with AUPBD. All subjects underwent endoscopic retrograde cholangiopancreatography (ERCP); one subject also underwent bile sampling of the common bile duct (CBD) to measure the amylase level because his gadoxetic acid-enhanced fMRC images showed evidence of pancreatico-biliary reflux of pancreatic secretions. Of the five patients with choledochal cysts, four underwent pylorus-preserving pancreaticoduodenectomy.

RESULTS: The five cases of choledochal cysts were classified as Todani classification I. In three of the six patients with AUPBD, injected contrast media reached the distal CBD and pancreatic duct on delay images, suggesting biliopancreatic reflux. In two of these six patients, a band-like filling defect was noted in the CBD on pre-fatty meal images, which decreased in size on delayed post-fatty meal images, suggesting pancreatico-biliary reflux of pancreatic secretions, and the bile sampled from the CBD in one patient had an amylase level of 113 000 IU/L. In one of the six patients with AUPBD, contrast media did not reach the distal CBD due to multiple CBD stones.

CONCLUSION: Gadoxetic acid-enhanced fMRC successfully demonstrated biliopancreatic reflux of bile and pancreatico-biliary reflux of pancreatic secretions in patients with AUPBD with and without choledochal cysts.