Pancreatic cysts: can surveillance interval for small low-risk lesions be lengthened?

BACKGROUND: Surveillance of pancreatic cysts are necessary due to risk of malignant transformation. However, reported progression rates to advanced neoplasia are variable and the high frequency of surveillance scans may pose a considerable burden on healthcare resources. PURPOSE: To validate the effectiveness of the Fukuoka Guidelines surveillance regime and determine if a longer surveillance interval can be established. MATERIAL AND METHODS: All magnetic resonance imaging (MRI) studies of the pancreas performed at our institution between January 2014 and December 2016 with at least one pancreatic cystic lesion and follow-up MRI or computed tomography (CT) over at least two years were reviewed for size, worrisome feature (WF), and high-risk stigmata (HRS) at diagnosis and follow-up imaging (up to year 6). Reference standards for advanced neoplasia were based on endoscopic ultrasound, fine needle aspiration cytology, or the presence of ≥2 WF or ≥1 HRS on imaging. Comparison of MRI features of progression and outcomes of diagnostic endpoints between lesions <20 mm and ≥20 mm was performed. RESULTS: A total of 270 patients were included (201 cysts <20 mm, 69 cysts ≥20 mm). Compared with cysts <20 mm, cysts ≥20 mm were more likely to be associated with WF or HRS (40.6% vs. 12.4%; P ≤0.00001), demonstrate increase in size of ≥5 mm in two years (20.3% vs. 10.9%; P = 0.049), and develop advanced neoplasia (24.6% vs. 0.5%; P <0.00001). CONCLUSION: Pancreatic cysts <20 mm have a low risk of developing WF and HRS and surveillance interval may be lengthened.

Harnessing artificial intelligence in radiology to augment population health.

This review article serves to highlight radiological services as a major cost driver for the healthcare sector, and the potential improvements in productivity and cost savings that can be generated by incorporating artificial intelligence (AI) into the radiology workflow, referencing Singapore healthcare as an example. More specifically, we will discuss the opportunities for AI in lowering healthcare costs and supporting transformational shifts in our care model in the following domains: predictive analytics for optimising throughput and appropriate referrals, computer vision for image enhancement (to increase scanner efficiency and decrease radiation exposure) and pattern recognition (to aid human interpretation and worklist prioritisation), natural language processing and large language models for optimising reports and text data-mining. In the context of preventive health, we will discuss how AI can support population level screening for major disease burdens through opportunistic screening and democratise expertise to increase access to radiological services in primary and community care.

Use of Imaging and Biopsy in Prostate Cancer Diagnosis: A Survey From the Asian Prostate Imaging Working Group.

OBJECTIVE: To elucidate the use of radiological studies, including nuclear medicine, and biopsy for the diagnosis and staging of prostate cancer (PCA) in clinical practice and understand the current status of PCA in Asian countries via an international survey. MATERIALS AND METHODS: The Asian Prostate Imaging Working Group designed a survey questionnaire with four domains focused on prostate magnetic resonance imaging (MRI), other prostate imaging, prostate biopsy, and PCA backgrounds. The questionnaire was sent to 111 members of professional affiliations in Korea, Japan, Singapore, and Taiwan who were representatives of their working hospitals, and their responses were analyzed. RESULTS: This survey had a response rate of 97.3% (108/111). The rates of using 3T scanners, antispasmodic agents, laxative drugs, and prostate imaging-reporting and data system reporting for prostate MRI were 21.6%-78.9%, 22.2%-84.2%, 2.3%-26.3%, and 59.5%-100%, respectively. Respondents reported using the highest b-values of 800-2000 sec/mm² and fields of view of 9-30 cm. The prostate MRI examinations per month ranged from 1 to 600, and they were most commonly indicated for biopsy-naïve patients suspected of PCA in Japan and Singapore and staging of proven PCA in Korea and Taiwan. The most commonly used radiotracers for prostate positron emission tomography are prostate-specific membrane antigen in Singapore and fluorodeoxyglucose in three other countries. The most common timing for prostate MRI was before biopsy (29.9%). Prostate-targeted biopsies were performed in 63.8% of hospitals, usually by MRI-ultrasound fusion approach. The most common presentation was localized PCA in all four countries, and it was usually treated with radical prostatectomy. CONCLUSION: This survey showed the diverse technical details and the availability of imaging and biopsy in the evaluation of PCA. This suggests the need for an educational program for Asian radiologists to promote standardized evidence-based imaging approaches for the diagnosis and staging of PCA.

The effects of community-based exercise modalities and volume on musculoskeletal health and functions in elderly people.

The effects of different muscle loading exercise (MLEX) modes and volume on musculoskeletal health is not well-studied in older populations. Aim: Therefore, this study aimed to compare the effects of community-based MLEX modalities and volume on musculoskeletal health in elderly people. Methods: Elderly men (n = 86) and women (n = 170), age 50-82 years old, were assigned to the sedentary (SE, n = 60), muscle strengthening exercise (MSE, n = 71), aerobic exercise (AE, n = 62) and Tai Chi exercise (TCE, n = 63) groups, based on > 2 years of exercise history. Exercise volume was compared between "Minimum" ("Min" < 60 min/week), "Low" (60-120 min/week). "Moderate" (121-239 min/week) and "High" (240-720 min/week) volumes. Results: All three modes of MLEX were associated with lower percentage of body fat (BF%) and higher percentage of lean body mass (LBM%, p = 0.003 main effect of group, and p = 0.002 main effect of volume for both BF% and LBM%), but not with higher bone mineral density (BMD, total body, lumbar spine, total hip and neck of femur), than SE. TCE had a distinct advantage in trunk flexibility (p = 0.007 with MSE, p = 0.02 with AE, and p = 0.01 with SE), and both TCE (p = 0.03) and AE (p = 0.03) performed better than SE in the one-leg stand balance test. Isometric strength and throwing speed and peak power with a 2 kg power ball were higher in the MLEX than SE groups (p = 0.01), in the ranking order of MSE, AE and TCE. However, there was no difference in handgrip strength performance between the MLEX groups, which performed better than the SE participants. Accumulating >120 min/week of MLEX can promote body composition health and muscle functions, but 60 min/week of MSE alone may have equal or better outcomes in these parameters. Conclusion: Community-based MLEX classes may be used to mitigate age-related chronic disease that are associated with body composition and muscular functions.

Deep Neural Network Augments Performance of Junior Residents in Diagnosing COVID-19 Pneumonia on Chest Radiographs.

Chest X-rays (CXRs) are essential in the preliminary radiographic assessment of patients affected by COVID-19. Junior residents, as the first point-of-contact in the diagnostic process, are expected to interpret these CXRs accurately. We aimed to assess the effectiveness of a deep neural network in distinguishing COVID-19 from other types of pneumonia, and to determine its potential contribution to improving the diagnostic precision of less experienced residents. A total of 5051 CXRs were utilized to develop and assess an artificial intelligence (AI) model capable of performing three-class classification, namely non-pneumonia, non-COVID-19 pneumonia, and COVID-19 pneumonia. Additionally, an external dataset comprising 500 distinct CXRs was examined by three junior residents with differing levels of training. The CXRs were evaluated both with and without AI assistance. The AI model demonstrated impressive performance, with an Area under the ROC Curve (AUC) of 0.9518 on the internal test set and 0.8594 on the external test set, which improves the AUC score of the current state-of-the-art algorithms by 1.25% and 4.26%, respectively. When assisted by the AI model, the performance of the junior residents improved in a manner that was inversely proportional to their level of training. Among the three junior residents, two showed significant improvement with the assistance of AI. This research highlights the novel development of an AI model for three-class CXR classification and its potential to augment junior residents' diagnostic accuracy, with validation on external data to demonstrate real-world applicability. In practical use, the AI model effectively supported junior residents in interpreting CXRs, boosting their confidence in diagnosis. While the AI model improved junior residents' performance, a decline in performance was observed on the external test compared to the internal test set. This suggests a domain shift between the patient dataset and the external dataset, highlighting the need for future research on test-time training domain adaptation to address this issue.

Can we omit systematic biopsies in patients undergoing MRI fusion-targeted prostate biopsies?

Magnetic resonance imaging (MRI)-targeted prostate biopsy is the recommended investigation in men with suspicious lesion(s) on MRI. The role of concurrent systematic in addition to targeted biopsies is currently unclear. Using our prospectively maintained database, we identified men with at least one Prostate Imaging-Reporting and Data System (PI-RADS) ≥3 lesion who underwent targeted and/or systematic biopsies from May 2016 to May 2020. Clinically significant prostate cancer (csPCa) was defined as any Gleason grade group ≥2 cancer. Of 545 patients who underwent MRI fusion-targeted biopsy, 222 (40.7%) were biopsy naïve, 247 (45.3%) had previous prostate biopsy(s), and 76 (13.9%) had known prostate cancer undergoing active surveillance. Prostate cancer was more commonly found in biopsy-naïve men (63.5%) and those on active surveillance (68.4%) compared to those who had previous biopsies (35.2%; both P < 0.001). Systematic biopsies provided an incremental 10.4% detection of csPCa among biopsy-naïve patients, versus an incremental 2.4% among those who had prior negative biopsies. Multivariable regression found age (odds ratio [OR] = 1.03, P = 0.03), prostate-specific antigen (PSA) density ≥0.15 ng ml-2 (OR = 3.24, P < 0.001), prostate health index (PHI) ≥35 (OR = 2.43, P = 0.006), higher PI-RADS score (vs PI-RADS 3; OR = 4.59 for PI-RADS 4, and OR = 9.91 for PI-RADS 5; both P < 0.001) and target lesion volume-to-prostate volume ratio ≥0.10 (OR = 5.26, P = 0.013) were significantly associated with csPCa detection on targeted biopsy. In conclusion, for men undergoing MRI fusion-targeted prostate biopsies, systematic biopsies should not be omitted given its incremental value to targeted biopsies alone. The factors such as PSA density ≥0.15 ng ml-2, PHI ≥35, higher PI-RADS score, and target lesion volume-to-prostate volume ratio ≥0.10 can help identify men at higher risk of csPCa.

Machine learning in medicine: what clinicians should know.

With the advent of artificial intelligence (AI), machines are increasingly being used to complete complicated tasks, yielding remarkable results. Machine learning (ML) is the most relevant subset of AI in medicine, which will soon become an integral part of our everyday practice. Therefore, physicians should acquaint themselves with ML and AI, and their role as an enabler rather than a competitor. Herein, we introduce basic concepts and terms used in AI and ML, and aim to demystify commonly used AI/ML algorithms such as learning methods including neural networks/deep learning, decision tree and application domain in computer vision and natural language processing through specific examples. We discuss how machines are already being used to augment the physician's decision-making process, and postulate the potential impact of ML on medical practice and medical research based on its current capabilities and known limitations. Moreover, we discuss the feasibility of full machine autonomy in medicine.

Efficacy of texture analysis of pre-operative magnetic resonance imaging in predicting microvascular invasion in hepatocellular carcinoma.

BACKGROUND: Presence of microvascular invasion (MVI) indicates poorer prognosis post-curative resection of hepatocellular carcinoma (HCC), with an increased chance of tumour recurrence. By present standards, MVI can only be diagnosed post-operatively on histopathology. Texture analysis potentially allows identification of patients who are considered 'high risk' through analysis of pre-operative magnetic resonance imaging (MRI) studies. This will allow for better patient selection, improved individualised therapy (such as extended surgical margins or adjuvant therapy) and pre-operative prognostication. AIM: This study aims to evaluate the accuracy of texture analysis on pre-operative MRI in predicting MVI in HCC. METHODS: Retrospective review of patients with new cases of HCC who underwent hepatectomy between 2007 and 2015 was performed. Exclusion criteria: No pre-operative MRI, significant movement artefacts, loss-to-follow-up, ruptured HCCs, previous hepatectomy and adjuvant therapy. Fifty patients were divided into MVI (n = 15) and non-MVI (n = 35) groups based on tumour histology. Selected images of the tumour on post-contrast-enhanced T1-weighted MRI were analysed. Both qualitative (performed by radiologists) and quantitative data (performed by software) were obtained. Radiomics texture parameters were extracted based on the largest cross-sectional area of each tumor and analysed using MaZda software. Five separate methods were performed. Methods 1, 2 and 3 exclusively made use of features derived from arterial, portovenous and equilibrium phases respectively. Methods 4 and 5 made use of the comparatively significant features to attain optimal performance. RESULTS: Method 5 achieved the highest accuracy of 87.8% with sensitivity of 73% and specificity of 94%. CONCLUSION: Texture analysis of tumours on pre-operative MRI can predict presence of MVI in HCC with accuracies of up to 87.8% and can potentially impact clinical management.

Algorithm-based approach to focal liver lesions in contrast-enhanced ultrasound.

Focal liver lesions are commonly encountered. Grey-scale and Doppler sonographic characteristics of focal liver lesions are often non-specific and insufficient to conclusively characterise lesions as benign or malignant. Contrast-enhanced ultrasound is useful for the characterisation of FLLs in patients who are unable to undergo contrast-enhanced computed tomography or magnetic resonance imaging. It is also easily available and relatively cheap. However, interpretation of contrast-enhanced ultrasound can be challenging without a systematic approach. In this pictorial essay, we highlight an algorithm-based approach to FLLs and discuss the characteristic contrast-enhanced ultrasound features of commonly encountered and clinically significant focal liver lesions.

Gadoxetate-Enhanced MRI as a Diagnostic Tool in the Management of Hepatocellular Carcinoma: Report from a 2020 Asia-Pacific Multidisciplinary Expert Meeting.

Gadoxetate magnetic resonance imaging (MRI) is widely used in clinical practice for liver imaging. For optimal use, we must understand both its advantages and limitations. This article is the outcome of an online advisory board meeting and subsequent discussions by a multidisciplinary group of experts on liver diseases across the Asia-Pacific region, first held on September 28, 2020. Here, we review the technical considerations for the use of gadoxetate, its current role in the management of patients with hepatocellular carcinoma (HCC), and its relevance in consensus guidelines for HCC imaging diagnosis. In the latter part of this review, we examine recent evidence evaluating the impact of gadoxetate on clinical outcomes on a continuum from diagnosis to treatment decision-making and follow-up. In conclusion, we outline the potential future roles of gadoxetate MRI based on an evolving understanding of the clinical utility of this contrast agent in the management of patients at risk of, or with, HCC.

Variant Hepatocellular Carcinoma Subtypes According to the 2019 WHO Classification: An Imaging-Focused Review.

The 2019 5th edition of the WHO classification of digestive system tumors estimates that up to 35% of hepatocellular carcinomas (HCCs) can be classified as one of eight subtypes defined by molecular characteristics: steatohepatitic, clear cell, macrotrabecular-massive, scirrhous, chromophobe, fibrolamellar, neutrophil-rich, and lymphocyte-rich HCCs. Due to their distinct cellular and architectural characteristics, these subtypes may not display arterial phase hyperenhancement and washout appearance, which are the classic MRI features of HCC, creating challenges in noninvasively diagnosing such lesions as HCC. Moreover, certain subtypes with atypical imaging features have a worse prognosis than other HCCs. A range of distinguishing imaging features may help raise suspicion that a liver lesion represents one of these HCC subtypes. In this review, we describe the MRI features that have been reported in association with various HCC subtypes according to the 2019 WHO classification, with attention given to the current understanding of these subtypes' pathologic and molecular bases and relevance to clinical practice. Imaging findings that differentiate the subtypes from benign liver lesions and non-HCC malignancies are highlighted. Familiarity with these sub-types and their imaging features may allow the radiologist to suggest their presence, though histologic analysis remains needed to establish the diagnosis.

Machine Learning in Prostate MRI for Prostate Cancer: Current Status and Future Opportunities.

Advances in our understanding of the role of magnetic resonance imaging (MRI) for the detection of prostate cancer have enabled its integration into clinical routines in the past two decades. The Prostate Imaging Reporting and Data System (PI-RADS) is an established imaging-based scoring system that scores the probability of clinically significant prostate cancer on MRI to guide management. Image fusion technology allows one to combine the superior soft tissue contrast resolution of MRI, with real-time anatomical depiction using ultrasound or computed tomography. This allows the accurate mapping of prostate cancer for targeted biopsy and treatment. Machine learning provides vast opportunities for automated organ and lesion depiction that could increase the reproducibility of PI-RADS categorisation, and improve co-registration across imaging modalities to enhance diagnostic and treatment methods that can then be individualised based on clinical risk of malignancy. In this article, we provide a comprehensive and contemporary review of advancements, and share insights into new opportunities in this field.

Diagnostic Performance of a Deep Learning Model Deployed at a National COVID-19 Screening Facility for Detection of Pneumonia on Frontal Chest Radiographs.

(1) Background: Chest radiographs are the mainstay of initial radiological investigation in this COVID-19 pandemic. A reliable and readily deployable artificial intelligence (AI) algorithm that detects pneumonia in COVID-19 suspects can be useful for screening or triage in a hospital setting. This study has a few objectives: first, to develop a model that accurately detects pneumonia in COVID-19 suspects; second, to assess its performance in a real-world clinical setting; and third, by integrating the model with the daily clinical workflow, to measure its impact on report turn-around time. (2) Methods: The model was developed from the NIH Chest-14 open-source dataset and fine-tuned using an internal dataset comprising more than 4000 CXRs acquired in our institution. Input from two senior radiologists provided the reference standard. The model was integrated into daily clinical workflow, prioritising abnormal CXRs for expedited reporting. Area under the receiver operating characteristic curve (AUC), F1 score, sensitivity, and specificity were calculated to characterise diagnostic performance. The average time taken by radiologists in reporting the CXRs was compared against the mean baseline time taken prior to implementation of the AI model. (3) Results: 9431 unique CXRs were included in the datasets, of which 1232 were ground truth-labelled positive for pneumonia. On the "live" dataset, the model achieved an AUC of 0.95 (95% confidence interval (CI): 0.92, 0.96) corresponding to a specificity of 97% (95% CI: 0.97, 0.98) and sensitivity of 79% (95% CI: 0.72, 0.84). No statistically significant degradation of diagnostic performance was encountered during clinical deployment, and report turn-around time was reduced by 22%. (4) Conclusion: In real-world clinical deployment, our model expedites reporting of pneumonia in COVID-19 suspects while preserving diagnostic performance without significant model drift.

Imaging patterns in non-traumatic spleen lesions in adults-a review.

The spleen is a complex organ involved in multiple physiological processes in the human body. Elective splenectomy is an uncommon operation, and the precise characterization of the lesion should be achieved to determine the risks and benefits of this operation accurately. Given the significant role of the spleen in homeostasis and the potential risks of the surgery itself and following sequelae such as infection susceptibility, accurate recognition, and classification of splenic lesions is required before surgery. This review provides an overview of malignant (e.g., lymphoma, angiosarcoma) and benign (e.g., cysts, hemangioma, hamartoma) splenic lesions that may warrant an elective splenectomy. Images from a cohort of adult patients undergoing isolated splenectomy for non-traumatic indications in a single center are provided. This review highlights the considerable overlap in imaging patterns between splenic lesions, splenic lesions masquerading as lesions in other organs, increased detection of asymptomatic splenic incidentalomas due to improvements in imaging modalities. This review also provides clinical correlations for each lesion, providing additional information to help clinicians differentiate between lesions and accurately identify diseases amenable to surgical management.