Familiarity, confidence and preference of artificial intelligence feedback and prompts by Australian breast cancer screening readers.

Objectives This study explored the familiarity, perceptions and confidence of Australian radiology clinicians involved in reading screening mammograms, regarding artificial intelligence (AI) applications in breast cancer detection. Methods Sixty-five radiologists, breast physicians and radiology trainees participated in an online survey that consisted of 23 multiple choice questions asking about their experience and familiarity with AI products. Furthermore, the survey asked about their confidence in using AI outputs and their preference for AI modes applied in a breast screening context. Participants' responses to questions were compared using Pearson's χ 2 test. Bonferroni-adjusted significance tests were used for pairwise comparisons. Results Fifty-five percent of respondents had experience with AI in their workplaces, with automatic density measurement powered by machine learning being the most familiar AI product (69.4%). The top AI outputs with the highest ranks of perceived confidence were 'Displaying suspicious areas on mammograms with the percentage of cancer possibility' (67.8%) and 'Automatic mammogram classification (normal, benign, cancer, uncertain)' (64.6%). Radiology and breast physicians preferred using AI as second-reader mode (75.4% saying 'somewhat happy' to 'extremely happy') over triage (47.7%), pre-screening and first-reader modes (both with 26.2%) (P < 0.001). Conclusion The majority of screen readers expressed increased confidence in utilising AI for highlighting suspicious areas on mammograms and for automatically classifying mammograms. They considered AI as an optimal second-reader mode being the most ideal use in a screening program. The findings provide valuable insights into the familiarities and expectations of radiologists and breast clinicians for the AI products that can enhance the effectiveness of the breast cancer screening programs, benefitting both healthcare professionals and patients alike.

AI for interpreting screening mammograms: implications for missed cancer in double reading practices and challenging-to-locate lesions.

Although the value of adding AI as a surrogate second reader in various scenarios has been investigated, it is unknown whether implementing an AI tool within double reading practice would capture additional subtle cancers missed by both radiologists who independently assessed the mammograms. This paper assesses the effectiveness of two state-of-the-art Artificial Intelligence (AI) models in detecting retrospectively-identified missed cancers within a screening program employing double reading practices. The study also explores the agreement between AI and radiologists in locating the lesions, considering various levels of concordance among the radiologists in locating the lesions. The Globally-aware Multiple Instance Classifier (GMIC) and Global-Local Activation Maps (GLAM) models were fine-tuned for our dataset. We evaluated the sensitivity of both models on missed cancers retrospectively identified by a panel of three radiologists who reviewed prior examinations of 729 cancer cases detected in a screening program with double reading practice. Two of these experts annotated the lesions, and based on their concordance levels, cases were categorized as 'almost perfect,' 'substantial,' 'moderate,' and 'poor.' We employed Similarity or Histogram Intersection (SIM) and Kullback-Leibler Divergence (KLD) metrics to compare saliency maps of malignant cases from the AI model with annotations from radiologists in each category. In total, 24.82% of cancers were labeled as "missed." The performance of GMIC and GLAM on the missed cancer cases was 82.98% and 79.79%, respectively, while for the true screen-detected cancers, the performances were 89.54% and 87.25%, respectively (p-values for the difference in sensitivity < 0.05). As anticipated, SIM and KLD from saliency maps were best in 'almost perfect,' followed by 'substantial,' 'moderate,' and 'poor.' Both GMIC and GLAM (p-values < 0.05) exhibited greater sensitivity at higher concordance. Even in a screening program with independent double reading, adding AI could potentially identify missed cancers. However, the challenging-to-locate lesions for radiologists impose a similar challenge for AI.

Evaluating Recalibrating AI Models for Breast Cancer Diagnosis in a New Context: Insights from Transfer Learning, Image Enhancement and High-Quality Training Data Integration.

This paper investigates the adaptability of four state-of-the-art artificial intelligence (AI) models to the Australian mammographic context through transfer learning, explores the impact of image enhancement on model performance and analyses the relationship between AI outputs and histopathological features for clinical relevance and accuracy assessment. A total of 1712 screening mammograms (n = 856 cancer cases and n = 856 matched normal cases) were used in this study. The 856 cases with cancer lesions were annotated by two expert radiologists and the level of concordance between their annotations was used to establish two sets: a 'high-concordances subset' with 99% agreement of cancer location and an 'entire dataset' with all cases included. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of Globally aware Multiple Instance Classifier (GMIC), Global-Local Activation Maps (GLAM), I&H and End2End AI models, both in the pretrained and transfer learning modes, with and without applying the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm. The four AI models with and without transfer learning in the high-concordance subset outperformed those in the entire dataset. Applying the CLAHE algorithm to mammograms improved the performance of the AI models. In the high-concordance subset with the transfer learning and CLAHE algorithm applied, the AUC of the GMIC model was highest (0.912), followed by the GLAM model (0.909), I&H (0.893) and End2End (0.875). There were significant differences (p < 0.05) in the performances of the four AI models between the high-concordance subset and the entire dataset. The AI models demonstrated significant differences in malignancy probability concerning different tumour size categories in mammograms. The performance of AI models was affected by several factors such as concordance classification, image enhancement and transfer learning. Mammograms with a strong concordance with radiologists' annotations, applying image enhancement and transfer learning could enhance the accuracy of AI models.

Variations of image interpretations of radiologists from different populations in mammography and tomosynthesis with different levels of breast density.

Purpose: This study aims to investigate the diagnostic performances of Australian and Shanghai-based Chinese radiologists in reading full-field digital mammogram (FFDM) and digital breast tomosynthesis (DBT) with different levels of breast density. Approach: Eighty-two Australian radiologists interpreted a 60-case FFDM set, and 29 radiologists also reported a 35-case DBT set. Sixty Shanghai radiologists read the same FFDM set, and 32 radiologists read the DBT set. The diagnostic performances of Australian and Shanghai radiologists were assessed using truth data (cancer cases were biopsy proven) and compared overall in specificity, case sensitivity, lesion sensitivity, receiver operating characteristics (ROC) area under the curve, and jack-knife free-response receiver operating characteristics (JAFROC) figure of merit, and they were stratified by case characteristics using the Mann-Whitney U test. The Spearman rank test was used to explore the association between radiologists' performances and their work experience in mammogram interpretation. Results: There were significantly higher performances of Australian radiologists compared with Shanghai radiologists in low breast density for case sensitivity, lesion sensitivity, ROC, and JAFROC in the FFDM set ( P < 0.0001 ); in high breast density, Shanghai radiologists' performances in lesion sensitivity and JAFROC were also lower than Australian radiologists ( P < 0.0001 ). In the DBT test set, Australian radiologists performed better than Shanghai radiologists in cancer detection in both low and high breast density. The work experience of Australian radiologists was positively linked to their diagnostic performances, whereas this association was not statistically significant in Shanghai radiologists. Conclusion: There were significant variations in reading performances between Australian and Shanghai radiologists in FFDM and DBT across different levels of breast density, lesion types, and lesion sizes. An effective training initiative tailored to suit local readers is essential to enhancing the diagnostic accuracy of Shanghai radiologists.

The Impact of Prior Mammograms on the Diagnostic Performance of Radiologists in Early Breast Cancer Detection: A Focus on Breast Density, Lesion Features and Vendors Using Wholly Digital Screening Cases.

BACKGROUND: This study aims to investigate the diagnostic efficacy of radiologists when reading screening mammograms in the absence of previous images, and with the presence of prior images from the same and different vendors. METHODS: 612 radiologists' readings across 9 test sets, consisting of 540 screening mammograms (361-normal and 179-cancer) with 245 cases having prior images obtained from same vendor as current images, 129 from a different vendor and 166 cases having no prior images, were retrospectively analysed. True positive (sensitivity), true negative (specificity) and area under ROC curve (AUC) values of radiologists were calculated for three groups of cases (without prior images (NP), with prior images from same vendor (SP), and with prior images from different vendor (DP)). Logistic regression was used to estimate the odds ratio (OR) of true positive, true negative and true cancer localization among case groups with different levels of breast density and lesion characteristics. RESULTS: Radiologists obtained 12.8% and 10.3% higher sensitivity in NP and DP than SP (0.803-and-0.785 vs. 0.712; p < 0.0001). Specificity in NP and DP cases were 4.8% and 2.0% lower than SP cases (0.749 and 0.771 vs. 0.787). The AUC values for NP and DP were significantly higher than SP cases across different levels of breast density (0.814-and-0.820 vs. 0.782; p < 0.0001). The odds ratio (OR) of true positive for NP relative to SP was 1.6 (p < 0.0001) and DP relative to SP was 1.5 (p < 0.0001). Radiologists were more like to detect architectural distortion in DP than SP cases (OR = 3.2; p < 0.0001), whilst the OR for abnormal calcifications was 2.85 (p < 0.0001). CONCLUSIONS: Cases without previous mammograms or with prior mammograms obtained from different vendors were more likely to benefit radiologists in cancer detection, whilst prior mammograms undertaken from the same vendor were more useful for radiologists in evaluating normal cases.

Radiologists' performance in reading digital breast tomosynthesis with and without synthesized views for cancer detection.

OBJECTIVE: The study aims to evaluate the diagnostic efficacy of radiologists and radiology trainees in digital breast tomosynthesis (DBT) alone vs DBT plus synthesized view (SV) for an understanding of the adequacy of DBT images to identify cancer lesions. METHODS: Fifty-five observers (30 radiologists and 25 radiology trainees) participated in reading a set of 35 cases (15 cancer) with 28 readers reading DBT and 27 readers reading DBT plus SV. Two groups of readers had similar experience in interpreting mammograms. The performances of participants in each reading mode were compared with the ground truth and calculated in term of specificity, sensitivity, and ROC AUC. The cancer detection rate in various levels of breast density, lesion types and lesion sizes between 'DBT' and 'DBT + SV' were also analyzed. The difference in diagnostic accuracy of readers between two reading modes was assessed using Man-Whitney U test. p < 0.05 indicated a significant result. RESULTS: There was no significant difference in specificity (0.67-vs-0.65; p = 0.69), sensitivity (0.77-vs-0.71; p = 0.09), ROC AUC (0.77-vs-0.73; p = 0.19) of radiologists reading DBT plus SV compared with radiologists reading DBT. Similar result was found in radiology trainees with no significant difference in specificity (0.70-vs-0.63; p = 0.29), sensitivity (0.44-vs-0.55; p = 0.19), ROC AUC (0.59-vs-0.62; p = 0.60) between two reading modes. Radiologists and trainees obtained similar results in two reading modes for cancer detection rate with different levels of breast density, cancer types and sizes of lesions (p > 0.05). CONCLUSION: Findings show that the diagnostic performances of radiologists and radiology trainees in DBT alone and DBT plus SV were equivalent in identifying cancer and normal cases. ADVANCES IN KNOWLEDGE: DBT alone had equivalent diagnostic accuracy as DBT plus SV which could imply the consideration of using DBT as a sole modality without SV.

Radiologist Self-training: a Study of Cancer Detection when Reading Mammograms at Work Clinics or Workshops.

Provision of online and remote specialist education and general continued professional education in medicine is a growing field. For radiology specifically, the ability to access web-based platforms that house high resolution medical images, and the high fidelity of simulated activities is increasingly growing due to positive changes in technology. This study investigates the differences in providing a self-directed specialist radiology education system in two modes: at clinics and in-person workshops. 335 Australian radiologists completed 562 readings of mammogram test sets through the web-based interactive BREAST platform with 325 at conference workshops and 237 at their workplaces. They engaged with test sets with each comprising of 60 mammogram cases (20 cancer and 40 normal). Radiologists marked the location of any cancers and had their performance measured via 5 metrics of diagnostic accuracy. Results show that the location of engagement with BREAST did not yield any significant difference in the performances of all radiologists and the same radiologists between two reading modes (P > 0.05). Radiologists who read screening mammograms for BreastScreen Australia performed better when they completed the test sets at designated workshops (P < 0.05), as was also the case for radiologists who read > 100 cases per week (P < 0.05). In contrast, radiologists who read less mammograms frequently recorded better performances in specificity and JAFROC at clinics (P < 0.05). Findings show that remotely accessed online education for specialised training and core skills building in radiology can provide a similar learning opportunity for breast radiologists when compared to on-site dedicated workshops at scientific meetings. For readers with high volumes of mammograms, a workshop setting may provide a superior experience while clinic setting is more helpful to less experienced readers.

Look how far we have come: BREAST cancer detection education on the international stage.

The development of screening mammography over 30 years has remarkedly reduced breast cancer-associated mortality by 20%-30% through detection of small cancer lesions at early stages. Yet breast screening programmes may function differently in each nation depending on the incidence rate, national legislation, local health infrastructure and training opportunities including feedback on performance. Mammography has been the frontline breast cancer screening tool for several decades; however, it is estimated that there are 15% to 35% of cancers missed on screening which are owing to perceptual and decision-making errors by radiologists and other readers. Furthermore, mammography screening is not available in all countries and the increased speed in the number of new breast cancer cases among less developed countries exceeds that of the developed world in recent decades. Studies conducted through the BreastScreen Reader Assessment Strategy (BREAST) training tools for breast screening readers have documented benchmarking and significant variation in diagnostic performances in screening mammogram test sets in different countries. The performance of the radiologists from less well-established breast screening countries such as China, Mongolia and Vietnam were significant lower in detecting early-stage cancers than radiologists from developed countries such as Australia, USA, Singapore, Italy. Differences in breast features and cancer presentations, discrepancies in the level of experiences in reading screening mammograms, the availability of high-quality national breast screening program and breast image interpretation training courses between developed and less developed countries are likely to have impact on the variation of readers' performances. Hence dedicated education training programs with the ability to tailor to different reader cohorts and different population presentations are suggested to ameliorate challenges in exposure to a range of cancer cases and improve the interpretation skills of local radiologists. Findings from this review provide a good understanding of the radiologist' performances and their improvement using the education interventions, primarily the BREAST program, which has been deployed in a large range of developing and developed countries in the last decade. Self-testing and immediate feedback loops have been shown to have important implications for benchmarking and improving the diagnostic accuracy in radiology worldwide for better breast cancer control.

MicroRNAs in toxic acute kidney injury: Systematic scoping review of the current status.

Acute kidney injury induced by nephrotoxic agents is common, increasing in incidence and associated with considerable morbidity and mortality in developing countries. MicroRNAs are stable biomarkers that can be detected in extracellular fluids. This systematic scoping review aims to describe published research on urinary and circulating microRNAs in toxic acute kidney injury in both animal and human studies. We conducted a literature search, using EMBASE and Medline, for articles on urinary and circulating microRNA in nephrotoxic injuries to February 2020. A total of 21 publications studied acute kidney injury from 12 different toxic agents. Cisplatin was the most common nephrotoxic agent (n = 10), followed by antibiotics (n = 4). There were no randomized controlled trials. An increase in urinary miR-218 predicted acute kidney injury in six different studies, suggesting it is a promising biomarker for nephrotoxin-induced acute kidney injury. There were many factors that prevented a more comprehensive synthesis of microRNA performance including highly variable models, no consistent protocols for RNA isolation, cDNA synthesis and PCR amplification, and variability in normalization methods using reference controls. In conclusion, while microRNAs are promising biomarkers to study nephrotoxic acute kidney injury, the replication of most positive findings is not assessable due to deficient reporting of negative outcomes. A very narrow range of poisons have been studied, and more human data are required. In particular, further studies are needed on the most important causes of nephrotoxic injury, such as pesticides, chemicals, snake envenoming, and medicines other than aminoglycosides and cisplatin.

Pharmacological Evaluation of Novel Bioisosteres of an Adamantanyl Benzamide P2X7 Receptor Antagonist.

Adamantanyl benzamide 1 was identified as a potent P2X7R antagonist but failed to progress further due to poor metabolic stability. We describe the synthesis and SAR of a series of bioisosteres of benzamide 1 to explore improvements in the pharmacological properties of this lead. Initial efforts investigated a series of heteroaromatic bioisosteres, which demonstrated improved physicochemical properties but reduced P2X7R antagonism. Installation of bioisosteric fluorine on the adamantane bridgeheads was well tolerated and led to a series of bioisosteres with improved physicochemical properties and metabolic stability. Trifluorinated benzamide 34 demonstrated optimal physicochemical parameters, superior metabolic stability (ten times longer than lead benzamide 1), and an improved physicokinetic profile and proved effective in the presence of several known P2X7R polymorphisms.

Clinical, cellular, microscopic, and ultrastructural studies of a case of fibrogenesis imperfecta ossium.

Fibrogenesis imperfecta ossium is a rare disorder of bone usually characterized by marked osteopenia and associated with variable osteoporosis and osteosclerosis, changing over time. Histological examination shows that newly formed collagen is abnormal, lacking birefringence when examined by polarized light. The case presented demonstrates these features and, in addition, a previously undocumented finding of a persistent marked reduction of the serum C3 and C4. Osteoblasts established in culture from a bone biopsy showed abnormal morphology on electron microscopy and increased proliferation when cultured with benzoylbenzoyl-ATP and 1,25-dihydroxyvitamin D, contrasting with findings in normal osteoblasts in culture. A gene microarray study showed marked upregulation of the messenger RNA (mRNA) for G-protein-coupled receptor 128 (GPR 128), an orphan receptor of unknown function and also of osteoprotegerin in the patient's osteoblasts in culture. When normal osteoblasts were cultured with the patient's serum, there was marked upregulation of the mRNA for aquaporin 1. A single pathogenetic factor to account for the features of this disorder has not been defined, but the unique findings described here may facilitate more definitive investigation of the abnormal bone cell function.

Discovery and pharmacological evaluation of a novel series of adamantyl cyanoguanidines as P2X7 receptor antagonists.

Here we report adamantyl cyanoguanidine compounds based on hybrids of the adamantyl amide scaffold reported by AstraZeneca and cyanoguanidine scaffold reported by Abbott Laboratories. Compound 27 displayed five-fold greater inhibitory potency than the lead compound 2 in both pore-formation and interleukin-1ß release assays, while 35-treated mice displayed an antidepressant phenotype in behavioral studies. This SAR study provides a proof of concept for hybrid compounds, which will help in the further development of P2X7R antagonists.

Derivatives of the pyrazolo[1,5-a]pyrimidine acetamide DPA-713 as translocator protein (TSPO) ligands and pro-apoptotic agents in human glioblastoma.

The 18kDa translocator protein (TSPO) is a target for novel glioblastoma therapies due to its upregulation in this cancer and relatively low levels of expression in the healthy cortex. The pyrazolo[1,5-a]pyrimidine acetamides, exemplified by DPA-713 and DPA-714, are a class of high affinity TSPO ligands with selectivity over the central benzodiazepine receptor. In this study we have explored the potential anti-glioblastoma activity of a library of DPA-713 and DPA-714 analogues, and investigated the effect of amending the alkyl ether chain on TSPO affinity and functional potential. All ligands demonstrated nanomolar affinity for TSPO, but showed diverse functional activity, for example DPA-713 and DPA-714 did not affect the proliferation or viability of human T98G glioblastoma cells, while the hexyl ether and benzyl ether derivatives decreased proliferation of T98G cells without affecting proliferation in human fetal glial SVGp12 cells. These ligands also induced apoptosis and dissipated T98G mitochondrial membrane potential. This suggests that the nature of the alkyl ether chain of pyrazolo[1,5-a]pyrimidine acetamides has little influence on TSPO affinity but is important for functional activity of this class of TSPO ligands.

TSPO as a target for glioblastoma therapeutics.

The translocator protein (TSPO) is an 18-kDa five-transmembrane protein, which is primarily found in the outer mitochondrial membrane. Levels of this protein are up-regulated in the most aggressive and common glioma, glioblastoma multiforme (GM). Levels of TSPO also correlate with GM clinical outcome, suggesting that TSPO may be a novel GM diagnostic imaging agent. Therapeutically, targeting the TSPO may provide a mechanism to abrogate the apoptotic-resistant, invasive and aggressive nature of GM and may also provide a way of targeting other anti-cancer treatments to GM sites. This review highlights recent progress in research on TSPO-based diagnostic imaging and therapeutics for GM.

First Demonstration of Positive Allosteric-like Modulation at the Human Wild Type Translocator Protein (TSPO).

We show that changing the number and position of nitrogen atoms in the heteroatomic core of a pyrazolopyrimidine acetamide is sufficient to induce complex binding to wild type human TSPO. Only compounds with this complex binding profile lacked intrinsic effect on glioblastoma proliferation but positively modulated the antiproliferative effects of a synthetic TSPO ligand. To the best of our knowledge this is the first demonstration of allosteric-like interaction at the wild type human TSPO.

The first CNS-active carborane: A novel P2X7 receptor antagonist with antidepressant activity.

Relative to other polycyclic frameworks (1-3), a carborane cage (4 and Cs·5) exerts a significant biological effect as an inhibitor of the purinergic P2X7 receptor (P2X7R) which allows one to target depression in vivo and thus demonstrate, for the first time, that a carborane has the capacity to modify CNS activity.

N-substituted 8-aminopentacyclo[5.4.0.0(2,6).0(3,10).0(5,9)]undecanes as σ receptor ligands with potential neuroprotective effects.

Several libraries of similarly N-substituted 8-aminopentacyclo[5.4.0.0(2,6).0(3,10).0(5,9)]undecanes (9), N-methyl-8-aminopentacyclo[5.4.0.0(2,6).0(3,10).0(5,9)]undecanes (14), and N-methyl-11-aminopentacyclo[5.4.0.0(2,6).0(3,10).0(5,9)]undecan-8-ones (13) were synthesised and screened against a panel of CNS targets in order to develop structure-affinity relationships for cage-modified trishomocubane σ receptor ligands based on the N-substituted 4-azahexacyclo[5.4.1.0(2,6).0(3,10).0(5,9).0(8,11)]dodecan-3-ol (8) scaffold. In general, compared to the corresponding 4-azahexacyclo[5.4.1.0(2,6).0(3,10).0(5,9).0(8,11)]dodecan-3-ols, compounds of type 9 were potent σ receptor ligands with low levels of subtype selectivity, while the corresponding N-methyl-8-aminopentacyclo[5.4.0.0(2,6).0(3,10).0(5,9)]undecanes showed reduced affinity but greater selectivity for σ2 receptors. The N-methyl-11-aminopentacyclo[5.4.0.0(2,6).0(3,10).0(5,9)]undecan-8-ones demonstrated the poorest σ receptor affinities, suggesting that 4-azahexacyclo[5.4.1.0(2,6).0(3,10).0(5,9).0(8,11)]dodecan-3-ols interact with σ receptors in the bridged hemiaminal form rather than as the non-transannular, aminoketone tautomers. Several compounds of type 8, 9, and 14 were assessed for their ability to inhibit nitric oxide release in vitro, and demonstrated comparable or greater efficacy than 4-phenyl-1-(4-phenylbutyl)piperidine (PPBP), an established neuroprotective σ ligand with NOS inhibitory activity.