Deep representation learning of tissue metabolome and computed tomography annotates NSCLC classification and prognosis

The rich chemical information from tissue metabolomics provides a powerful means to elaborate tissue physiology or tumor characteristics at cellular and tumor microenvironment levels. However, the process of obtaining such information requires invasive biopsies, is costly, and can delay clinical patient management. Conversely, computed tomography (CT) is a clinical standard of care but does not intuitively harbor histological or prognostic information. Furthermore, the ability to embed metabolome information into CT to subsequently use the learned representation for classification or prognosis has yet to be described. This study develops a deep learning-based framework -- tissue-metabolomic-radiomic-CT (TMR-CT) by combining 48 paired CT images and tumor/normal tissue metabolite intensities to generate ten image embeddings to infer metabolite-derived representation from CT alone. In clinical NSCLC settings, we ascertain whether TMR-CT results in an enhanced feature generation model solving histology classification/prognosis tasks in an unseen international CT dataset of 742 patients. TMR-CT non-invasively determines histological classes - adenocarcinoma/squamous cell carcinoma with an F1-score = 0.78 and further asserts patients' prognosis with a c-index = 0.72, surpassing the performance of radiomics models and deep learning on single modality CT feature extraction. Additionally, our work shows the potential to generate informative biology-inspired CT-led features to explore connections between hard-to-obtain tissue metabolic profiles and routine lesion-derived image data.

Interval cancer in the Córdoba Breast Tomosynthesis Screening Trial (CBTST): comparison of digital breast tomosynthesis plus digital mammography to digital mammography alone

PURPOSE

This work aims to compare the interval cancer rate and interval cancer characteristics between women screened with digital breast tomosynthesis (DBT) + digital mammography (DM) and those screened with DM alone.

METHODS

The interval cancer rate and interval cancer characteristics of the study population included in the Córdoba Breast Tomosynthesis Screening Trial (CBTST) were compared to a contemporary control population screened with DM. The tumour characteristics of screen-detected and interval cancers were also compared. Contingency tables were used to compare interval cancer rates. The chi-square test and Fisher's exact test were used to compare the qualitative characteristics of the cancers whereas Student's t test and the Mann-Whitney U test were used to analyse quantitative features.

RESULTS

A total of 16,068 screening exams with DBT + DM were conducted within the CBTST (mean age 57.59 ± 5.9 [SD]) between January 2015 and December 2016 (study population). In parallel, 23,787 women (mean age 58.89 ± 5.9 standard deviation [SD]) were screened with DM (control population). The interval cancer rate was lower in the study population than in the control population (15 [0.93‰; 95% confidence interval (CI): 0.73, 1.14] vs 43 [1.8‰; 95% CI: 1.58, 2.04] respectively; p = 0.045). The difference in rate was more marked in women with dense breasts (0.95‰ in the study population vs 3.17‰ in the control population; p = 0.031). Interval cancers were smaller in the study population than in the control population (p = 0.031).

CONCLUSIONS

The interval cancer rate was lower in women screened with DBT + DM compared to those screened with DM alone. These differences were more pronounced in women with dense breasts.

CLINICAL RELEVANCE STATEMENT

Women screened using tomosynthesis and digital mammography had a lower rate of interval cancer than women screened with digital mammography, with the greatest difference in the interval cancer rate observed in women with dense breasts.

KEY POINTS

• The interval cancer rate was lower in the study population (digital breast tomosynthesis [DBT] + digital mammography [DM]) than in the control population (DM). • The difference in interval cancer rates was more pronounced in women with dense breasts. • Interval cancers were smaller in the study population (DBT + DM) than in the control population (DM).

Impact of real-life use of artificial intelligence as support for human reading in a population-based breast cancer screening program with mammography and tomosynthesis

OBJECTIVES

To evaluate the impact of using an artificial intelligence (AI) system as support for human double reading in a real-life scenario of a breast cancer screening program with digital mammography (DM) or digital breast tomosynthesis (DBT).

MATERIAL AND METHODS

We analyzed the performance of double reading screening with mammography and tomosynthesis after implementarion of AI as decision support. The study group consisted of a consecutive cohort of 1 year screening between March 2021 and March 2022 where double reading was performed with concurrent AI support that automatically detects and highlights lesions suspicious of breast cancer in mammography and tomosynthesis. Screening performance was measured as cancer detection rate (CDR), recall rate (RR), and positive predictive value (PPV) of recalls. Performance in the study group was compared using a McNemar test to a control group that included a screening cohort of the same size, recorded just prior to the implementation of AI.

RESULTS

A total of 11,998 women (mean age 57.59 years ± 5.8 [sd]) were included in the study group (5049 DM and 6949 DBT). Comparing global results (including DM and DBT) of double reading with vs. without AI support, we observed an increase in CDR, PPV, and RR by 3.2/‰ (5.8 vs. 9; p < 0.001), 4% (10.6 vs. 14.6; p < 0.001), and 0.7% (5.4 vs. 6.1; p < 0.001) respectively.

CONCLUSION

AI used as support for human double reading in a real-life breast cancer screening program with DM and DBT increases CDR and PPV of the recalled women.

CLINICAL RELEVANCE STATEMENT

Artificial intelligence as support for human double reading improves accuracy in a real-life breast cancer screening program both in digital mammography and digital breast tomosynthesis.

KEY POINTS

• AI systems based on deep learning technology offer potential for improving breast cancer screening programs. • Using artificial intelligence as support for reading improves radiologists' performance in breast cancer screening programs with mammography or tomosynthesis. • Artificial intelligence used concurrently with human reading in clinical screening practice increases breast cancer detection rate and positive predictive value of the recalled women.

A cannabidiol aminoquinone derivative activates the PP2A/B55α/HIF pathway and shows protective effects in a murine model of traumatic brain injury

BACKGROUND

Traumatic brain injury (TBI) is characterized by a primary mechanical injury and a secondary injury associated with neuroinflammation, blood-brain barrier (BBB) disruption and neurodegeneration. We have developed a novel cannabidiol aminoquinone derivative, VCE-004.8, which is a dual PPARγ/CB₂ agonist that also activates the hypoxia inducible factor (HIF) pathway. VCE-004.8 shows potent antifibrotic, anti-inflammatory and neuroprotective activities and it is now in Phase II clinical trials for systemic sclerosis and multiple sclerosis. Herein, we investigated the mechanism of action of VCE-004.8 in the HIF pathway and explored its efficacy in a preclinical model of TBI.

METHODS

Using a phosphoproteomic approach, we investigated the effects of VCE-004.8 on prolyl hydroxylase domain-containing protein 2 (PHD2) posttranslational modifications. The potential role of PP2A/B55α in HIF activation was analyzed using siRNA for B55α. To evaluate the angiogenic response to the treatment with VCE-004.8 we performed a Matrigel plug in vivo assay. Transendothelial electrical resistance (TEER) as well as vascular cell adhesion molecule 1 (VCAM), and zonula occludens 1 (ZO-1) tight junction protein expression were studied in brain microvascular endothelial cells. The efficacy of VCE-004.8 in vivo was evaluated in a controlled cortical impact (CCI) murine model of TBI.

RESULTS

Herein we provide evidence that VCE-004.8 inhibits PHD2 Ser125 phosphorylation and activates HIF through a PP2A/B55α pathway. VCE-004.8 induces angiogenesis in vivo increasing the formation of functional vessel (CD31/α-SMA) and prevents in vitro blood-brain barrier (BBB) disruption ameliorating the loss of ZO-1 expression under proinflammatory conditions. In CCI model VCE-004.8 treatment ameliorates early motor deficits after TBI and attenuates cerebral edema preserving BBB integrity. Histopathological analysis revealed that VCE-004.8 treatment induces neovascularization in pericontusional area and prevented immune cell infiltration to the brain parenchyma. In addition, VCE-004.8 attenuates neuroinflammation and reduces neuronal death and apoptosis in the damaged area.

CONCLUSIONS

This study provides new insight about the mechanism of action of VCE-004.8 regulating the PP2A/B55α/PHD2/HIF pathway. Furthermore, we show the potential efficacy for TBI treatment by preventing BBB disruption, enhancing angiogenesis, and ameliorating neuroinflammation and neurodegeneration after brain injury.

Stand-Alone Use of Artificial Intelligence for Digital Mammography and Digital Breast Tomosynthesis Screening: A Retrospective Evaluation

Background Use of artificial intelligence (AI) as a stand-alone reader for digital mammography (DM) or digital breast tomosynthesis (DBT) breast screening could ease radiologists' workload while maintaining quality. Purpose To retrospectively evaluate the stand-alone performance of an AI system as an independent reader of DM and DBT screening examinations. Materials and Methods Consecutive screening-paired and independently read DM and DBT images acquired between January 2015 and December 2016 were retrospectively collected from the Tomosynthesis Cordoba Screening Trial. An AI system computed a cancer risk score (range, 1-100) for DM and DBT examinations independently. AI stand-alone performance was measured using the area under the receiver operating characteristic curve (AUC) and sensitivity and recall rate at different operating points selected to have noninferior sensitivity compared with the human readings (noninferiority margin, 5%). The recall rate of AI and the human readings were compared using a McNemar test. Results A total of 15 999 DM and DBT examinations (113 breast cancers, including 98 screen-detected and 15 interval cancers) from 15 998 women (mean age, 58 years ± 6 [standard deviation]) were evaluated. AI achieved an AUC of 0.93 (95% CI: 0.89, 0.96) for DM and 0.94 (95% CI: 0.91, 0.97) for DBT. For DM, AI achieved noninferior sensitivity as a single (58.4%; 66 of 113; 95% CI: 49.2, 67.1) or double (67.3%; 76 of 113; 95% CI: 58.2, 75.2) reader, with a reduction in recall rate (P < .001) of up to 2% (95% CI: -2.4, -1.6). For DBT, AI achieved noninferior sensitivity as a single (77%; 87 of 113; 95% CI: 68.4, 83.8) or double (81.4%; 92 of 113; 95% CI: 73.3, 87.5) reader, but with a higher recall rate (P < .001) of up to 12.3% (95% CI: 11.7, 12.9). Conclusion Artificial intelligence could replace radiologists' readings in breast screening, achieving a noninferior sensitivity, with a lower recall rate for digital mammography but a higher recall rate for digital breast tomosynthesis. © RSNA, 2021 See also the editorial by Fuchsjäger and Adelsmayr in this issue.

AI-based Strategies to Reduce Workload in Breast Cancer Screening with Mammography and Tomosynthesis: A Retrospective Evaluation

Background The workflow of breast cancer screening programs could be improved given the high workload and the high number of false-positive and false-negative assessments. Purpose To evaluate if using an artificial intelligence (AI) system could reduce workload without reducing cancer detection in breast cancer screening with digital mammography (DM) or digital breast tomosynthesis (DBT). Materials and Methods Consecutive screening-paired and independently read DM and DBT images acquired from January 2015 to December 2016 were retrospectively collected from the Córdoba Tomosynthesis Screening Trial. The original reading settings were single or double reading of DM or DBT images. An AI system computed a cancer risk score for DM and DBT examinations independently. Each original setting was compared with a simulated autonomous AI triaging strategy (the least suspicious examinations for AI are not human-read; the rest are read in the same setting as the original, and examinations not recalled by radiologists but graded as very suspicious by AI are recalled) in terms of workload, sensitivity, and recall rate. The McNemar test with Bonferroni correction was used for statistical analysis. Results A total of 15 987 DM and DBT examinations (which included 98 screening-detected and 15 interval cancers) from 15 986 women (mean age ± standard deviation, 58 years ± 6) were evaluated. In comparison with double reading of DBT images (568 hours needed, 92 of 113 cancers detected, 706 recalls in 15 987 examinations), AI with DBT would result in 72.5% less workload (P < .001, 156 hours needed), noninferior sensitivity (95 of 113 cancers detected, P = .38), and 16.7% lower recall rate (P < .001, 588 recalls in 15 987 examinations). Similar results were obtained for AI with DM. In comparison with the original double reading of DM images (222 hours needed, 76 of 113 cancers detected, 807 recalls in 15 987 examinations), AI with DBT would result in 29.7% less workload (P < .001), 25.0% higher sensitivity (P < .001), and 27.1% lower recall rate (P < .001). Conclusion Digital mammography and digital breast tomosynthesis screening strategies based on artificial intelligence systems could reduce workload up to 70%. Published under a CC BY 4.0 license.

The Reference Site Collaborative Network of the European Innovation Partnership on Active and Healthy Ageing

Seventy four Reference Sites of the European Innovation Partnership on Active and Healthy Ageing (EIP on AHA) have been recognised by the European Commission in 2016 for their commitment to excellence in investing and scaling up innovative solutions for active and healthy ageing. The Reference Site Collaborative Network (RSCN) brings together the EIP on AHA Reference Sites awarded by the European Commission, and Candidate Reference Sites into a single forum. The overarching goals are to promote cooperation, share and transfer good practice and solutions in the development and scaling up of health and care strategies, policies and service delivery models, while at the same time supporting the action groups in their work. The RSCN aspires to be recognized by the EU Commission as the principal forum and authority representing all EIP on AHA Reference Sites. The RSCN will contribute to achieve the goals of the EIP on AHA by improving health and care outcomes for citizens across Europe, and the development of sustainable economic growth and the creation of jobs.

Breast cancer is associated to impaired glucose/insulin homeostasis in premenopausal obese/overweight patients

The association between breast cancer (BCa) presence and altered glucose/insulin metabolism is controversial likely due to an inaccurate insulin resistance (IR) assessment and inappropriate stratification of patients by body-mass index (BMI) and menopausal state. 148 women with suspect of sporadic BCa were stratified by BMI and menopause. Fasting levels of glucose, insulin, glycohemoglobin and selected IR-related and tumor-derived markers were measured. Glucose/insulin levels during OGTT were used to calculate insulin resistance/sensitivity indexes. Analysis of 77 BCa-bearing patients and 71 controls showed an association between BCa and IR as demonstrated by impaired glucose/insulin homeostasis (increased fasting- and OGTT-induced glucose levels) and deteriorated IR indexes, which was especially patent in premenopausal women. The association between BCa presence and IR was markedly influenced by BMI, being obese BCa patients significantly more insulin resistant than controls. BCa presence was associated to elevated levels of IR (glucose, triglycerides) and tumor-derived (VEGF) markers, especially in overweight/obese patients. BCa presence is associated to IR in overweight/obese premenopausal but not in premenopausal normal weight or postmenopausal women. Our data support a bidirectional relationship between dysregulated/imbalanced glucose/insulin metabolism and BCa, as tumor- and IR-markers are correlated with the impairment of glucose/insulin metabolism in overweight/obese premenopausal BCa patients.

Factors Associated With Disease Recurrence in Breast Cancer Patients With Negative Sentinel Lymph Node Biopsy

INTRODUCTION

The objective of our study was to assess recurrence after negative sentinel lymph node biopsy (SLNB) and to determine the risk factors related to local and distant recurrence in this group of patients.

MATERIALS AND METHODS

We conducted a prospective observational study from 2006 to 2011. It included 607 patients with early-stage breast cancer and negative SLNB with a 5-year follow-up period.

RESULTS

The disease-free survival rate was 98.5% and 96.5% at 2 and 5 years, respectively. Multivariate analysis identified the following prognostic factors for disease recurrence: tumor necrosis (hazard ratio [HR], 4.89; 95% confidence interval [CI], 1.61-14.89; P = .005), lymphovascular invasion (HR, 3.46; 95% CI, 1.14-10.55; P = .029), T2 tumor size (HR, 4.35; 95% CI, 1.40-13.52; P = .011), and moderate to severe lymphoplasmacytic stromal infiltration (HR, 3.06; 95% CI, 1.18-7.96; P = .022).

CONCLUSION

Recurrence in patients with negative SLNB was satisfactorily low. Nevertheless, determining the prognostic factors related to a greater recurrence rate could help identify high-risk patients and influence systemic adjuvant therapy.

Obesity alters gene expression for GH/IGF-I axis in mouse mammary fat pads: differential role of cortistatin and somatostatin

Locally produced growth hormone (GH) and IGF-I are key factors in the regulation of mammary gland (MG) development and may be important in breast cancer development/progression. Somatostatin (SST) and cortistatin (CORT) regulate GH/IGF-I axis at various levels, but their role in regulating GH/IGF-I in MGs remains unknown. Since obesity alters the expression of these systems in different tissues and is associated to MG (patho) physiology, we sought to investigate the role of SST/CORT in regulating GH/IGF-I system in the MGs of lean and obese mice. Therefore, we analyzed GH/IGF-I as well as SST/CORT and ghrelin systems expression in the mammary fat pads (MFPs) of SST- or CORT-knockout (KO) mice and their respective littermate-controls fed a low-fat (LF) or a high-fat (HF) diet for 16 wks. Our results demonstrate that the majority of the components of GH/IGF-I, SST/CORT and ghrelin systems are locally expressed in mouse MFP. Expression of elements of the GH/IGF-I axis was significantly increased in MFPs of HF-fed control mice while lack of endogenous SST partially suppressed, and lack of CORT completely blunted, the up-regulation observed in obese WT-controls. Since SST/CORT are known to exert an inhibitory role on the GH/IGFI axis, the increase in SST/CORT-receptor sst2 expression in MFPs of HF-fed CORT- and SST-KOs together with an elevation on circulating SST in CORT-KOs could explain the differences observed. These results offer new information on the factors (GH/IGF-I axis) involved in the endocrine/metabolic dysregulation of MFPs in obesity, and suggest that CORT is not a mere SST sibling in regulating MG physiology.