Radiomics in the evaluation of ovarian masses - a systematic review.

OBJECTIVES: The study aim was to conduct a systematic review of the literature reporting the application of radiomics to imaging techniques in patients with ovarian lesions. METHODS: MEDLINE/PubMed, Web of Science, Scopus, EMBASE, Ovid and ClinicalTrials.gov were searched for relevant articles. Using PRISMA criteria, data were extracted from short-listed studies. Validity and bias were assessed independently by 2 researchers in consensus using the Quality in Prognosis Studies (QUIPS) tool. Radiomic Quality Score (RQS) was utilised to assess radiomic methodology. RESULTS: After duplicate removal, 63 articles were identified, of which 33 were eligible. Fifteen assessed lesion classifications, 10 treatment outcomes, 5 outcome predictions, 2 metastatic disease predictions and 1 classification/outcome prediction. The sample size ranged from 28 to 501 patients. Twelve studies investigated CT, 11 MRI, 4 ultrasound and 1 FDG PET-CT. Twenty-three studies (70%) incorporated 3D segmentation. Various modelling methods were used, most commonly LASSO (least absolute shrinkage and selection operator) (10/33). Five studies (15%) compared radiomic models to radiologist interpretation, all demonstrating superior performance. Only 6 studies (18%) included external validation. Five studies (15%) had a low overall risk of bias, 9 (27%) moderate, and 19 (58%) high risk of bias. The highest RQS achieved was 61.1%, and the lowest was - 16.7%. CONCLUSION: Radiomics has the potential as a clinical diagnostic tool in patients with ovarian masses and may allow better lesion stratification, guiding more personalised patient care in the future. Standardisation of the feature extraction methodology, larger and more diverse patient cohorts and real-world evaluation is required before clinical translation. CLINICAL RELEVANCE STATEMENT: Radiomics shows promising results in improving lesion stratification, treatment selection and outcome prediction. Modelling with larger cohorts and real-world evaluation is required before clinical translation. KEY POINTS: • Radiomics is emerging as a tool for enhancing clinical decisions in patients with ovarian masses. • Radiomics shows promising results in improving lesion stratification, treatment selection and outcome prediction. • Modelling with larger cohorts and real-world evaluation is required before clinical translation.

Artificial intelligence in ovarian cancer histopathology: a systematic review.

This study evaluates the quality of published research using artificial intelligence (AI) for ovarian cancer diagnosis or prognosis using histopathology data. A systematic search of PubMed, Scopus, Web of Science, Cochrane CENTRAL, and WHO-ICTRP was conducted up to May 19, 2023. Inclusion criteria required that AI was used for prognostic or diagnostic inferences in human ovarian cancer histopathology images. Risk of bias was assessed using PROBAST. Information about each model was tabulated and summary statistics were reported. The study was registered on PROSPERO (CRD42022334730) and PRISMA 2020 reporting guidelines were followed. Searches identified 1573 records, of which 45 were eligible for inclusion. These studies contained 80 models of interest, including 37 diagnostic models, 22 prognostic models, and 21 other diagnostically relevant models. Common tasks included treatment response prediction (11/80), malignancy status classification (10/80), stain quantification (9/80), and histological subtyping (7/80). Models were developed using 1-1375 histopathology slides from 1-776 ovarian cancer patients. A high or unclear risk of bias was found in all studies, most frequently due to limited analysis and incomplete reporting regarding participant recruitment. Limited research has been conducted on the application of AI to histopathology images for diagnostic or prognostic purposes in ovarian cancer, and none of the models have been demonstrated to be ready for real-world implementation. Key aspects to accelerate clinical translation include transparent and comprehensive reporting of data provenance and modelling approaches, and improved quantitative evaluation using cross-validation and external validations. This work was funded by the Engineering and Physical Sciences Research Council.

Combined PET-CT and MRI for response evaluation in patients with squamous cell anal carcinoma treated with curative-intent chemoradiotherapy.

OBJECTIVES: To assess the effectiveness of fluorine-18 fluorodeoxyglucose (FDG) positron-emission tomography-computed tomography (PET-CT) and magnetic resonance imaging (MRI) for response assessment post curative-intent chemoradiotherapy (CRT) in anal squamous cell carcinoma (ASCC). METHODS: Consecutive ASCC patients treated with curative-intent CRT at a single centre between January 2018 and April 2020 were retrospectively identified. Clinical meta-data including progression-free survival (PFS) and overall survival (OS) outcomes were collated. Three radiologists evaluated PET-CT and MRI using qualitative response assessment criteria and agreed in consensus. Two-proportion z test was used to compare diagnostic performance metrics (sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy). Kaplan-Meier analysis (Mantel-Cox log-rank) was performed. RESULTS: MRI (accuracy 76%, PPV 44.8%, NPV 95.7%) and PET-CT (accuracy 69.3%, PPV 36.7%, NPV 91.1%) performance metrics were similar; when combined, there were statistically significant improvements (accuracy 94.7%, PPV 78.9%, NPV 100%). Kaplan-Meier analysis demonstrated significant differences in PFS between responders and non-responders at PET-CT (p = 0.007), MRI (p = 0.005), and consensus evaluation (p < 0.001). Cox regression analysis of PFS demonstrated a lower hazard ratio (HR) and narrower 95% confidence intervals for consensus findings (HR = 0.093, p < 0.001). Seventy-five patients, of which 52 (69.3%) were females, with median follow-up of 17.8 months (range 5-32.6) were included. Fifteen of the 75 (20%) had persistent anorectal and/or nodal disease after CRT. Three patients died, median time to death 6.2 months (range 5-18.3). CONCLUSION: Combined PET-CT and MRI response assessment post-CRT better predicts subsequent outcome than either modality alone. This could have valuable clinical benefits by guiding personalised risk-adapted patient follow-up. KEY POINTS: • MRI and PET-CT performance metrics for assessing response following chemoradiotherapy (CRT) in patients with anal squamous cell carcinoma (ASCC) were similar. • Combined MRI and PET-CT treatment response assessment 3 months after CRT in patients with ASCC was demonstrated to be superior to either modality alone. • A combined MRI and PET-CT assessment 3 months after CRT in patients with ASCC has the potential to improve accuracy and guide optimal patient management with a greater ability to predict outcome than either modality alone.

The Impact of COVID-19 on Interventional Radiology Services in the UK.

INTRODUCTION: The coronavirus disease 2019 (COVID-19) has created unprecedented challenges on the healthcare system. The aim of this multi-centre study was to measure the impact of COVID-19 on IR services in the UK. MATERIAL AND METHODS: Retrospective cross-sectional study of IR practice in six UK centres during the COVID-19 pandemic was carried out. All therapeutic IR procedures were identified using the respective hospital radiology information systems and COVID-19 status found on the hospital patient record systems. The total number of therapeutic IR procedures was recorded over two time periods, 25/03/2019-21/04/2019 (control group) and 30/03/2020-26/04/2020 (COVID-19 group). The data points collected were: procedure type, aerosol-generating nature, acute or elective case, modality used, in- or out-of-hours case and whether the procedure was done at the bedside (portable). RESULTS: A 31% decrease in overall number of IR procedures was observed during COVID-19 compared to the control group (1363 cases vs 942 cases); however, the acute work decreased by only 0.5%. An increase in out-of-hours work by 10% was observed. COVID-19 was suspected or laboratory proved in 9.9% of cases (n = 93), and 15% of total cases (n = 141) were classed as aerosol-generating procedures. A 66% rise in cholecystostomy was noted during COVID-19. Image-guided ablation, IVC filters, aortic stent grafting and visceral vascular stenting had the greatest % decreases in practice during COVID-19, with 91.7%, 83.3%, 80.8% and 80.2% decreases, respectively. CONCLUSION: During the global pandemic, IR has continued to provide emergency and elective treatment highlighting the adaptability of IR in supporting other specialties.

Comparison of quantity and quality of muscle as clinical prognostic markers in patients undergoing carotid endarterectomy.

OBJECTIVE: The measurement of muscle area is routinely utilised in determining sarcopaenia in clinical research. However, this simple measure fails to factor in age-related morphometric changes in muscle quality such as myosteatosis. The aims of this study were to: firstly investigate the relationship between the masseter area (quantity) and density (quality), and secondly compare the prognostic clinical relevance of each parameter. METHODS: Cross-sectional CT head scans were reviewed for patients undergoing carotid endarterectomy. The masseter was manually delineated and the total masseter area (TMA) and the total masseter density (TMD) calculated. Measurements of the TMA were standardised against the cranial circumference. Observer variability in measurements were assessed using Bland-Altman plots. The relationship between TMA and TMD were evaluated using Pearson's correlation and linear regression analyses. The prognostic value of TMA and TMD were assessed using receiver operator curves and cox-regression analyses. RESULTS: In total, 149 patients who had undergone routine CT scans prior to a carotid endarterectomy were included in this study. No significant observer variations were observed in measuring the TMA, TMD and cranium circumference. There was a significant positive correlation between standardised TMA and TMD (Pearson's correlation 0.426, p < 0.001, adjusted R-squared 17.6%). The area under the curve for standardised TMA in predicting all-cause mortality at 30 days, 1 year and 4 years were higher when compared to TMD. Standardised TMA was only predictive of post-operative overall all-cause mortality (adjusted hazard ratio 0.38, 95% confidence interval 0.15-0.97, p = 0.043). CONCLUSION: We demonstrate a strong relationship between muscle size and density. However, the utilisation of muscle area is likely to be limited in routine clinical care. ADVANCES IN KNOWLEDGE: Our study supports the utilisation of muscle area in clinical sarcopaenia research. We did not observe any additional prognostic advantage in quantifying muscle density.

Volumetric versus single slice measurements of core abdominal muscle for sarcopenia.

OBJECTIVE: We investigated whether total psoas muscle area (TPMA) was representative of the total psoas muscle volume (TPMV). Secondly, we assessed whether there was a relationship between the two commonly used single slice measurements of sarcopenia, TPMA and total abdominal muscle area (TAMA). METHODS: Pre-operative CT imaging of 110 patients undergoing elective endovascular aneurysm repair were analyzed by two trained independent observers. TPMA was measured at individual vertebral levels between the second lumbar vertebrae and sacrum. TPMV was also estimated between the second lumbar vertebrae and sacrum. TAMA was measured at the third lumbar vertebrae (L3). Observer differences were assessed using Bland-Altman plots. Associations between the different measures were assessed using linear regression and Pearson's correlation. RESULTS: We found single slice measurements of the TPMA to be representative of the TPMV at individual levels between L2 to the sacrum. The strongest association was seen at L3 [adjusted regression coefficient 16.7, 95% confidence interval (12.1 to 21.4), p < 0.001]. There was no association between TPMA and TAMA [adjusted regression coefficient -0.7, 95% confidence interval (-4.1 to 2.8), p = 0.710]. CONCLUSION: We demonstrate that measurements of the TPMA between L2 to the sacrum are representative of the TPMV, with the greatest association at the third lumbar vertebrae. There was no association between the TPMA and TAMA. ADVANCES IN KNOWLEDGE: We demonstrate that a single slice measurement of TPMA at L3 is representative of the muscle volume, contrary to previous criticism. Future sarcopenia studies can continue to measure TPMA which is representative of the TPMV.

Development of an anthropomorphic shoulder phantom model that simulates bony anatomy for sonographic measurement of the acromiohumeral distance.

The purpose of this project was to create a sonographic phantom model of the shoulder that was accurate in bone configuration. Its main purpose was for operator training to measure the acromiohumeral distance. A computerized 3-dimensional model of the superior half of the humerus and scapula was rendered and 3-dimensionally printed. The bone model was embedded in a gelatin compound and set in a shoulder-shaped mold. The materials used had speeds of sound that were well matched to soft tissue and epiphyseal bone. The model was specifically effective in simulating the acromiohumeral distance because of its accurate bone geometry.

Validation of ultrasound measurement of the subacromial space using a novel shoulder phantom model.

Ultrasound has a high degree of diagnostic accuracy in the assessment of rotator cuff tendons. Increasingly, ultrasound is being used to measure other parameters of rotator cuff pathology, including the size of the subacromial space, or acromiohumeral distance (AHD). Although this measure has been found to be clinically reliable, no assessment of its validity has been carried out. This technical study reports on the development of a novel ultrasound phantom of the shoulder and its use in validation of ultrasound measurement of AHD. There was a close agreement between AHD measures using ultrasound and the true subacromial space of the phantom model, providing support for the construct validity of this measurement. The phantom model has good potential for further development as a training tool for shoulder ultrasound and guided injections.