The Evidence for Using Artificial Intelligence to Enhance Prostate Cancer MR Imaging.

PURPOSE OF REVIEW: The purpose of this review is to summarize the current status of artificial intelligence applied to prostate cancer MR imaging. RECENT FINDINGS: Artificial intelligence has been applied to prostate cancer MR imaging to improve its diagnostic accuracy and reproducibility of interpretation. Multiple models have been tested for gland segmentation and volume calculation, automated lesion detection, localization, and characterization, as well as prediction of tumor aggressiveness and tumor recurrence. Studies show, for example, that very robust automated gland segmentation and volume calculations can be achieved and that lesions can be detected and accurately characterized. Although results are promising, we should view these with caution. Most studies included a small sample of patients from a single institution and most models did not undergo proper external validation. More research is needed with larger and well-design studies for the development of reliable artificial intelligence tools.

Malignant bowel obstruction: effectiveness and safety of systemic chemotherapy.

OBJECTIVES: Although systemic chemotherapy is often administered to patients with malignant bowel obstruction (MBO), its benefit remains unknown. This study assessed the outcomes of patients who received systemic chemotherapy as part of MBO treatment. METHODS: For this retrospective cohort study, data were extracted from records of patients hospitalised due to MBO in a tertiary cancer centre from 2008 to 2020. Eligible patients were not candidates for surgery and received systemic chemotherapy targeting the underlying malignancy causing MBO. Primary objective was to assess patient outcomes after chemotherapy; secondary objectives were rates of intestinal function recovery, hospital discharge and grade ≥3 toxicities. The primary endpoint was overall survival (OS). RESULTS: A total of 167 patients were included: median age was 55 (18-81) years, 91% had an Eastern Cooperative Oncology Group (ECOG) performance status ≥2, 75.5% had gastrointestinal tumours and 70% were treatment-naive. The median OS after chemotherapy was 4.4 weeks (95% CI 3.4 to 5.5) in the overall population. No OS difference was observed according to treatment line (p=0.24) or primary tumour (p=0.13). Intestinal function recovery occurred in 87 patients (52%), out of whom 21 (24.1%) had a reobstruction. Hospital discharge was possible in 74 patients (44.3%). Grade≥3 adverse events occurred in 26.9% of the patients, and a total of 12 deaths (7%) attributed to toxicities were observed after chemotherapy. CONCLUSIONS: MBO was associated with a dismal prognosis in this mostly treatment-naive population. The administration of chemotherapy yielded a significant risk of toxicities, whereas it did not appear to provide any relevant survival benefit in this scenario.

Lesion detection performance of an abbreviated gadoxetic acid-enhanced MRI protocol for colorectal liver metastasis surveillance.

OBJECTIVE: To assess the lesion detection performance of an abbreviated MRI (AMRI-M) protocol consisting of ultrafast SE T2W, DWI, and T1W-HBP at 20 min for colorectal liver metastasis (CRLM) surveillance. METHODS: In this Institutional Review Board (IRB)-approved retrospective study, gadoxetic acid-enhanced MRI scans of 57 patients (43 with pathologically proven CRLMs) were assessed. Two readers independently evaluated two sets of images per patient and commented on the number, location, and size of liver lesions. Set 1 included ultrafast spin-echo (SE) T2-weighted (T2W) + T1-weighted (T1W) hepatobiliary phase (HBP) at 20 min sequences + diffusion-weighted imaging (DWI), and set 2 consisted of the standard MRI protocol. A maximum of 10 lesions per patient were recorded. Cohen's kappa analysis, sensitivity, areas under the curve (AUCs), and the MRI cost analysis of the AMRI-M protocol were assessed. RESULTS: Between 198 and 209 lesions were assessed with each set of images. The inter-observer agreement for the abbreviated protocol was reported excellent (κ = 0.91). The sensitivity and AUCs for the lesion characterization of AMRI-M protocol were very high (over 90%) for both readers. No statistically significant differences in sensitivity (assessed by mixed-effects logistic regression) and AUCs for lesion characterization (by ROC regression) were found between both protocols. The AMRI-M acquisition time was estimated to be less than 10 min, which translated into 59% cost of standard MRI. CONCLUSION: Our proposed AMRI-M protocol (ultrafast SE T2W, DWI, and T1W-HBP at 20 min) is fast, low-cost alternative to the standard MRI protocol and has a high lesion detection performance. KEY POINTS: • Gadoxetic acid-enhanced protocol has increased the accuracy, sensitivity, and specificity of MRI for detecting colorectal liver metastases. • Our proposed abbreviated MRI protocol is fast, low-cost alternative compared with the standard MRI protocol and has a high lesion detection performance. • Adoption of our protocol may translate to substantial savings for patients and payers.

Abbreviated MRI Protocols for the Abdomen.

Technical advances in MRI have improved image quality and have led to expanding clinical indications for its use. However, long examination and interpretation times, as well as higher costs, still represent barriers to use of MRI. Abbreviated MRI protocols have emerged as an alternative to standard MRI protocols. These abbreviated MRI protocols seek to reduce longer MRI protocols by eliminating unnecessary or redundant sequences that negatively affect cost, MRI table time, patient comfort, image quality, and image interpretation time. However, the diagnostic information is generally not compromised. Abbreviated MRI protocols have already been used successfully for hepatocellular carcinoma screening, for prostate cancer detection, and for screening for nonalcoholic fatty liver disease as well as monitoring patients with this disease. It has been reported that image acquisition time and costs can be considerably reduced with abbreviated MRI protocols, compared with standard MRI protocols, while maintaining a similar sensitivity and accuracy. Nevertheless, multiple applications still need to be explored in the abdomen and pelvis (eg, surveillance of metastases to the liver; follow-up of cystic pancreatic lesions, adrenal incidentalomas, and small renal masses; evaluation of ovarian cysts in postmenopausal women; staging of cervical and uterine corpus neoplasms; evaluation of müllerian duct anomalies). This article describes some successful applications of abbreviated MRI protocols, demonstrates how they can help in improving the MRI workflow, and explores potential future directions. ©RSNA, 2019.

Radiation dose reduction in chest dual-energy computed tomography: effect on image quality and diagnostic information.

OBJECTIVE: To determine whether dual-energy computed tomography (DECT) of the chest can be performed at a reduced radiation dose, with an emphasis on images generated with post-processing techniques. MATERIALS AND METHODS: In 21 patients undergoing DECT of the chest in a dual-source scanner, an additional image series was acquired at a reduced radiation dose. Four thoracic radiologists assessed both image series for image quality, normal thoracic structures, as well as pulmonary and mediastinal abnormalities, on virtual monochromatic images at 40 keV and 60 keV. Data were analyzed with Student's t-test, kappa statistics, analysis of variance, and the Wilcoxon signed-rank test. RESULTS: The overall image quality of 60 keV virtual monochromatic images at a reduced radiation dose was considered optimal in all patients, and no abnormalities were missed. Contrast enhancement and lesion detection performance were comparable between reduced-dose images at 40 keV and standard-of-care images at 60 keV. The intraobserver and interobserver agreement were both good. The mean volumetric CT dose index (CTDIvol), size-specific dose estimate (SSDE), dose-length product (DLP), and effective dose (ED) for reduced-dose DECT were 3.0 ± 0.6 mGy, 4.0 ± 0.6 mGy, 107 ± 30 mGy.cm, and 1.5 ± 0.4 mSv, respectively. CONCLUSION: DECT of the chest can be performed at a reduced radiation dose (CTDIvol < 3 mGy) without loss of diagnostic information.

Radiation dose reduction in chest dual-energy computed tomography: effect on image quality and diagnostic information / Redução da dose de radiação na tomografia computadorizada de dupla energia do tórax: efeito na qualidade das imagens e na informação diagnóstica

Abstract Objective: To determine whether dual-energy computed tomography (DECT) of the chest can be performed at a reduced radiation dose, with an emphasis on images generated with post-processing techniques. Materials and Methods: In 21 patients undergoing DECT of the chest in a dual-source scanner, an additional image series was acquired at a reduced radiation dose. Four thoracic radiologists assessed both image series for image quality, normal thoracic structures, as well as pulmonary and mediastinal abnormalities, on virtual monochromatic images at 40 keV and 60 keV. Data were analyzed with Student's t-test, kappa statistics, analysis of variance, and the Wilcoxon signed-rank test. Results: The overall image quality of 60 keV virtual monochromatic images at a reduced radiation dose was considered optimal in all patients, and no abnormalities were missed. Contrast enhancement and lesion detection performance were comparable between reduced-dose images at 40 keV and standard-of-care images at 60 keV. The intraobserver and interobserver agreement were both good. The mean volumetric CT dose index (CTDIvol), size-specific dose estimate (SSDE), dose-length product (DLP), and effective dose (ED) for reduced-dose DECT were 3.0 ± 0.6 mGy, 4.0 ± 0.6 mGy, 107 ± 30 mGy.cm, and 1.5 ± 0.4 mSv, respectively. Conclusion: DECT of the chest can be performed at a reduced radiation dose (CTDIvol < 3 mGy) without loss of diagnostic information.

Resumo Objetivo: Verificar se a tomografia computadorizada de dupla energia (TCDE) do tórax pode ser realizada com baixas doses de radiação, com ênfase em imagens pós-processadas. Materiais e Métodos: Em 21 pacientes submetidos a DECT do tórax foi adicionada uma série de imagens adquiridas com baixas doses de radiação. Quatro radiologistas com especialidade em tórax avaliaram a qualidade, visualização de estruturas torácicas normais e também anormalidades pulmonares e mediastinais das imagens monocromáticas de baixa energia (40 e 60 keV). Os dados foram analisados utilizando t-test, estatística kappa, análise de variância e teste Wilcoxon. Resultados: A qualidade das imagens monocromáticas de baixa energia (60 keV) com doses reduzidas foi considerada ótima para todos os pacientes e nenhuma anormalidade no tórax foi perdida. O realce pelo contraste e a performance de detecção de lesões foram similares nas imagens com radiação reduzida e com radiação padrão. Boa concordância intra-avaliadores e interavaliadores foi observada. A média dos parâmetros CTDIvol, SSDE, DLP e ED para TCDE de baixa dose foram 3,0 ± 0,6 mGy, 4,0 ± 0,6 mGy, 107 ± 30 mGy.cm e 1,5 ± 0,4 mSv, respectivamente. Conclusão: TCDE do tórax pode ser realizada com baixas doses de radiação (CTDIvol < 3 mGy), sem perder informações diagnósticas.

Multifactorial Analysis of Mortality in Screening Detected Lung Cancer.

We hypothesized that severity of coronary artery calcification (CAC), emphysema, muscle mass, and fat attenuation can help predict mortality in patients with lung cancer participating in the National Lung Screening Trial (NLST). Following regulatory approval from the Cancer Data Access System (CDAS), all patients diagnosed with lung cancer at the time of the screening study were identified. These subjects were classified into two groups: survivors and nonsurvivors at the conclusion of the NLST trial. These groups were matched based on their age, gender, body mass index (BMI), smoking history, lung cancer stage, and survival time. CAC, emphysema, muscle mass, and subcutaneous fat attenuation were quantified on baseline low-dose chest CT (LDCT) for all patients in both groups. Nonsurvivor group had significantly greater CAC, decreased muscle mass, and higher fat attenuation compared to the survivor group (p < 0.01). No significant difference in severity of emphysema was noted between the two groups (p > 0.1). We thus conclude that it is possible to create a quantitative prediction model for lung cancer mortality for subjects with lung cancer detected on screening low-dose CT (LDCT).

Advances in Pancreatic CT Imaging.

OBJECTIVE: The purpose of this article is to discuss the advances in CT acquisition and image postprocessing as they apply to imaging the pancreas and to conceptualize the role of radiogenomics and machine learning in pancreatic imaging. CONCLUSION: CT is the preferred imaging modality for assessment of pancreatic diseases. Recent advances in CT (dual-energy CT, CT perfusion, CT volumetry, and radiogenomics) and emerging computational algorithms (machine learning) have the potential to further increase the value of CT in pancreatic imaging.

Pancreatic neuroendocrine tumor: Correlations between MRI features, tumor biology, and clinical outcome after surgery.

PURPOSE: To assess which magnetic resonance imaging (MRI) features are associated with pNETs (pancreatic neuroendocrine tumors) grade based on the WHO classification, as well as identify MRI features related to disease progression after surgery. MATERIALS AND METHODS: In this Institutional Review Board (IRB)-approved study, 1.5T and 3.0T MRI scans of 80 patients with surgically verified pNETs were assessed. The images were evaluated for tumor location; size; pattern; predominant signal intensity on precontrast T1 - and T2 -weighted images, as well as on postcontrast arterial and portal venous phase T1 -weighted sequences; presence of pancreatic duct dilatation; pancreatic atrophy; restricted diffusion; vascular involvement by the tumor; extrapancreatic tumor spread; and synchronous liver metastases. Tumors were graded based on the WHO classification and patients were followed-up with computed tomography (CT) or MRI after surgical resection. Data were analyzed with Student's t and chi-square tests, logistic regression, and Kaplan-Meier curves. RESULTS: The MRI features that were associated with aggressive tumors were: size >2.0 cm (odds ratio [OR] = 4.8, P = 0.002), "T2 nonbright lesions" on T2 -weighted images (OR = 4.6, P = 0.008), presence of pancreatic ductal dilatation (OR = 4.9, P = 0.024), and restricted diffusion within the lesion (OR = 4.9, P = 0.013). Differences in progression-free survival distribution were found for patients whose pNETs were associated with the following MRI features: size >2.0 cm (χ2 (1) = 6.0, P = 0.014), "nonbright lesions" on T2 -weighted images (χ2 (1) = 6.8, P = 0.009), and presence of pancreatic duct dilatation (χ2 (1) = 10.9, P = 0.001). CONCLUSION: MRI features can be used to assess pNETs aggressiveness and identify patients at risk for early disease progression after surgical resection. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2018;47:425-432.

Submillisievert chest dual energy computed tomography: a pilot study.

OBJECTIVE: To assess if diagnostic dual energy CT (DECT) of the chest can be achieved at submillisievert (sub-mSv) doses. METHODS: Our IRB-approved prospective study included 20 patients who were scanned on dual-source multidector CT(MDCT). All patients gave written informed consent for acquisition of additional image series at reduced radiation dose on a dual-source MDCT (80/140 kV) within 10 s after the standard of care acquisition. Dose reduction was achieved by reducing the quality reference milliampere-second, with combined angular exposure control. Four readers, blinded to all clinical data, evaluated the image sets. Image noise, signal-to-noise and contrast-to-noise ratio were assessed. Volumetric CT dose index (CTDIvol), doselength product (DLP), size specific dose estimate, and effective dose were also recorded. RESULTS: The mean age and body mass index of the patients were 71 years ± 9 and 24 kg m-2 ± 3, respectively. Although images became noisier, overall image quality and image sharpness on blended images were considered good or excellent in all cases (20/20). All findings made on the reduced dose images presented with good demarcation. The intraobserver and interobserver agreements were κ = 0.83 and 0.73, respectively. Mean CTDIvol, size specific dose estimate, DLP and effective dose for reduced dose DECT were: 1.3 ± 0.2 mGy, 1.8 ± 0.2 mGy, 51 ± 9.9 mGy.cm and 0.7 ± 0.1 mSv, respectively. CONCLUSION: Routine chest DECT can be performed at sub-mSv doses with good image quality and without loss of relevant diagnostic information. Advances in knowledge: (1) Contrast-enhanced DECT of the chest can be performed at sub-mSv doses, down to mean CTDIvol 1.3 mGy and DLP 51 mGy.cm in patients with body mass index <31 kg m-2. (2) To our knowledge, this is the first time that sub-mSv doses have been successfully applied in a patient study using a dual source DECT scanner.

Prediction of Pancreatic Neuroendocrine Tumor Grade Based on CT Features and Texture Analysis.

OBJECTIVE: The purposes of this study were to assess whether CT texture analysis and CT features are predictive of pancreatic neuroendocrine tumor (PNET) grade based on the World Health Organization (WHO) classification and to identify features related to disease progression after surgery. MATERIALS AND METHODS: Preoperative contrast-enhanced CT images of 101 patients with PNETs were assessed. The images were evaluated for tumor location, tumor size, tumor pattern, predominantly solid or cystic composition, presence of calcification, presence of heterogeneous enhancement on contrast-enhanced images, presence of pancreatic duct dilatation, presence of pancreatic atrophy, presence of vascular involvement by the tumor, and presence of lymphadenopathy. Texture features were also extracted from CT images. Surgically verified tumors were graded according to the WHO classification, and patients underwent CT or MRI follow-up after surgical resection. Data were analyzed with chi-square tests, kappa statistics, logistic regression analysis, and Kaplan-Meier curves. RESULTS: The CT features predictive of a more aggressive tumor (grades 2 and 3) were size larger than 2.0 cm (odds ratio [OR], 3.3; p = 0.014), presence of vascular involvement (OR, 25.2; p = 0.003), presence of pancreatic ductal dilatation (OR, 6.0; p = 0.002), and presence of lymphadenopathy (OR, 6.8; p = 0.002). The texture parameter entropy (OR, 3.7; p = 0.008) was also predictive of more aggressive tumors. Differences in progression-free survival distribution were found for grade 1 versus grades 2 and 3 tumors (χ2 [df, 1] = 21.6; p < 0.001); for PNETs with vascular involvement (χ2 [df, 1] = 20.8; p < 0.001); and for tumors with entropy (spatial scale filter 2) values greater than 4.65 (χ2 (df, 1) = 4.4; p = 0.037). CONCLUSION: CT texture analysis and CT features are predictive of PNET aggressiveness and can be used to identify patients at risk of early disease progression after surgical resection.

Characterization of Portal Vein Thrombosis (Neoplastic Versus Bland) on CT Images Using Software-Based Texture Analysis and Thrombus Density (Hounsfield Units).

OBJECTIVE: The purpose of this study was to investigate the role of CT texture analysis and thrombus density (measured in Hounsfield units) in distinguishing between neoplastic and bland portal vein thrombosis (PVT) on portal venous phase CT. MATERIALS AND METHODS: In this retrospective study, 117 contrast-enhanced CT studies of 109 patients were included for characterization of PVT. Assessment of PVT was performed by estimation of CT textural features using CT texture analysis software and measurement of attenuation values. For CT texture analysis, filtered and unfiltered images were assessed to quantify heterogeneity using a set of predefined histogram-based texture parameters. The Mann-Whitney U test and binary logistic regression were applied for statistical significance. ROC curves were used to identify accuracy and optimal cutoff values. RESULTS: Of the 117 CT studies, 63 neoplastic thrombi and 54 bland thrombi were identified on the images. The two most discriminative CT texture analysis parameters to differentiate neoplastic from bland thrombus were mean value of positive pixels (without filtration, p < 0.001) and entropy (with fine filtration, p < 0.001). Mean thrombus density values could also reliably distinguish neoplastic (81.39 HU) and bland (32.88 HU) thrombi (p < 0.001). The AUCs were 0.97 for mean value of positive pixels (p < 0.001), 0.93 for entropy (p < 0.001), 0.99 for the model combining mean value of positive pixels and entropy (p < 0.001), 0.91 for thrombus density (p < 0.001), and 0.61 for the radiologist's subjective evaluation (p = 0.037). The optimal cutoffs values were 56.9 for mean value of positive pixels, 4.50 for entropy, and 54.0 HU for thrombus density. CONCLUSION: CT texture analysis and CT attenuation values allow reliable differentiation between neoplastic and bland thrombi on a single portal venous phase CT examination.

Cavitated conglomerate mass in silicosis indicating associated tuberculosis.

Silicosis is the most common occupational lung disease worldwide. It leads to respiratory impairment and may have associated infections that decrease pulmonary function. We describe the case of a 55-year-old man with chronic silicosis who presented with hemoptysis and a cavitated conglomerate mass. The final diagnosis was silicotuberculosis.

Pulmonary alveolar microlithiasis: a case report with emphasis on imaging findings.

Pulmonary alveolar microlithiasis (PAM) is a rare disease characterized by the presence of small calculi in the alveolar space. The authors report a case of a 21-year-old man with a 2-year history of shortness of breath on exertion and dry cough. Physical examination was altered only for crackles at auscultation. Pulmonary function revealed a mild restrictive ventilatory defect and the chest radiograph demonstrated paracardiac confluence of dense micronodular infiltrate. High-resolution CT scan revealed diffuse ground glass attenuation and septal thickening, more pronounced in lower pulmonary regions, with calcifications along the interlobar septa and subpleural regions. A transbronchial lung biopsy confirmed the diagnosis of PAM.

Sclerosing variant of the bronchioloalveolar carcinoma: imaging findings in an atypical case.

Bronchioloalveolar carcinoma remains one of the most enigmatic lung cancers, demonstrating varied growth patterns, mixed histological features, and confusing clinical manifestations. This paper reports a case of an unusual form of presentation: a sclerosing type associated with desmoplastic reaction and cicatrization. A 75-year-old woman was admitted with persistent dry cough and progressive dyspnea. Physical examination showed bilateral inspiratory crackles. A chest radiograph and high-resolution computed tomography demonstrated confluent airspace nodules, forming areas of consolidation in both lungs, with signs of architectural distortion. The lung biopsy revealed a nonmucinous sclerosing bronchioloalveolar carcinoma.

Spontaneous pneumothorax as an atypical presentation of pulmonary paracoccidioidomycosis: a case report with emphasis on the imaging findings.

We describe the case of a 45-year-old male with pulmonary paracoccidioidomycosis and spontaneous pneumothorax. The patient presented to the hospital with sudden and intense chest pain accompanied by dyspnea and had a six-month history of dry cough, weight loss, and progressive dyspnea on exertion. Chest X-ray showed a small right pneumothorax, bilateral nonhomogeneous opacities, and emphysematous areas in the lung base. Chest computed tomography showed consolidation in both lungs, with architectural distortion, nodules, interlobular septal thickening, and emphysema, in addition to the right pneumothorax. A lung biopsy revealed yeast consistent with Paracoccidioides brasiliensis. No drainage was needed, and the lung was re-expanded. The patient was treated with antifungal drugs, showed mild improvement, and was referred to outpatient care.

Hyalinizing granuloma: an unusual case of a pulmonary mass.

We describe the case of pulmonary hyalinizing granuloma in a 34-year-old asymptomatic man who presented with a pulmonary nodule apparent by chest radiography and computed tomography (CT). He had a history of previous treatment for tuberculosis. His laboratory data were normal. Bronchoscopy and CT-guided percutaneous transthoracic fine needle aspiration cytology were inconclusive. The diagnosis was revealed after the histopathological examination of an open lung biopsy.

Medullary thyroid carcinoma with micronodular lung metastases: a case report with an emphasis on the imaging findings.

Medullary thyroid carcinoma is a rare malignancy that arises from calcitonin-producing C-cells and frequently metastasizes to lymph nodes in the neck. Distant metastases may involve bone, lung, and liver. The infrequent number of cases limits the clinical nature and ability to optimize diagnostic tools. Here, we present a case of a micronodular radiographic pattern in metastatic medullary thyroid cancer in order to enhance awareness of the disease process. A case discussion and relevant review of the literature are provided.

Colon mucinous adenocarcinoma in childhood: a case report with emphasis on image findings.

Colorectal cancer is extremely rare in children. We report a case of a 12-year-old boy who presented with a five-month history of weight loss and anorexia, associated with vomiting episodes, dizziness, fatigue, and dyspnea. On physical examination, a palpable abdominal mass was noticed on the right hypochondrium and flank. An imaging study was performed, which showed a solid mass on the right colon. The patient underwent incisional surgical biopsy, and subsequent histopathologic analysis revealed a colon mucinous adenocarcinoma.