Objectives
To evaluate the potential of artificial intelligence (AI) to identify normal mammograms in a screening population.
Methods
In this retrospective study, 9581 double-read mammography ...screening exams including 68 screen-detected cancers and 187 false positives, a subcohort of the prospective population-based Malmö Breast Tomosynthesis Screening Trial, were analysed with a deep learning–based AI system. The AI system categorises mammograms with a cancer risk score increasing from 1 to 10. The effect on cancer detection and false positives of excluding mammograms below different AI risk thresholds from reading by radiologists was investigated. A panel of three breast radiologists assessed the radiographic appearance, type, and visibility of screen-detected cancers assigned low-risk scores (≤ 5). The reduction of normal exams, cancers, and false positives for the different thresholds was presented with 95% confidence intervals (CI).
Results
If mammograms scored 1 and 2 were excluded from screen-reading, 1829 (19.1%; 95% CI 18.3–19.9) exams could be removed, including 10 (5.3%; 95% CI 2.1–8.6) false positives but no cancers. In total, 5082 (53.0%; 95% CI 52.0–54.0) exams, including 7 (10.3%; 95% CI 3.1–17.5) cancers and 52 (27.8%; 95% CI 21.4–34.2) false positives, had low-risk scores. All, except one, of the seven screen-detected cancers with low-risk scores were judged to be clearly visible.
Conclusions
The evaluated AI system can correctly identify a proportion of a screening population as cancer-free and also reduce false positives. Thus, AI has the potential to improve mammography screening efficiency.
Key Points
• Retrospective study showed that AI can identify a proportion of mammograms as normal in a screening population.
• Excluding normal exams from screening using AI can reduce false positives.
Objective
To assess the performance of one-view digital breast tomosynthesis (DBT) in breast cancer screening.
Methods
The Malmö Breast Tomosynthesis Screening Trial is a prospective population-based ...one-arm study with a planned inclusion of 15000 participants; a random sample of women aged 40–74 years eligible for the screening programme. This is an explorative analysis of the first half of the study population (n = 7500). Participants underwent one-view DBT and two-view digital mammography (DM), with independent double reading and scoring. Primary outcome measures were detection rate, recall rate and positive predictive value (PPV). McNemar's test with 95 % confidence intervals was used.
Results
Breast cancer was found in sixty-eight women. Of these, 46 cases were detected by both modalities, 21 by DBT alone and one by DM alone. The detection rate for one-view DBT was 8.9/1000 screens (95 % CI 6.9 to 11.3) and 6.3/1000 screens (4.6 to 8.3) for two-view DM (p < 0.0001). The recall rate after arbitration was 3.8 % (3.3 to 4.2) for DBT and 2.6 % (2.3 to 3.0) for DM (p < 0.0001). The PPV was 24 % for both DBT and DM.
Conclusion
Our results suggest that one-view DBT might be feasible as a stand-alone screening modality.
Key Points
•
One-view DBT as a stand-alone breast cancer screening modality has not been investigated.
•
One-view DBT increased the cancer detection rate significantly.
•
The recall rate increased significantly but was still low.
•
Breast cancer screening with one-view DBT as a stand-alone modality seems feasible.
Objectives
To investigate whether artificial intelligence (AI) can reduce interval cancer in mammography screening.
Materials and methods
Preceding screening mammograms of 429 consecutive women ...diagnosed with interval cancer in Southern Sweden between 2013 and 2017 were analysed with a deep learning–based AI system. The system assigns a risk score from 1 to 10. Two experienced breast radiologists reviewed and classified the cases in consensus as true negative, minimal signs or false negative and assessed whether the AI system correctly localised the cancer. The potential reduction of interval cancer was calculated at different risk score thresholds corresponding to approximately 10%, 4% and 1% recall rates.
Results
A statistically significant correlation between interval cancer classification groups and AI risk score was observed (
p
< .0001). AI scored one in three (143/429) interval cancer with risk score 10, of which 67% (96/143) were either classified as minimal signs or false negative. Of these, 58% (83/143) were correctly located by AI, and could therefore potentially be detected at screening with the aid of AI, resulting in a 19.3% (95% CI 15.9–23.4) reduction of interval cancer. At 4% and 1% recall thresholds, the reduction of interval cancer was 11.2% (95% CI 8.5–14.5) and 4.7% (95% CI 3.0–7.1). The corresponding reduction of interval cancer with grave outcome (women who died or with stage IV disease) at risk score 10 was 23% (8/35; 95% CI 12–39).
Conclusion
The use of AI in screen reading has the potential to reduce the rate of interval cancer without supplementary screening modalities.
Key Points
• Retrospective study showed that AI detected 19% of interval cancer at the preceding screening exam that in addition showed at least minimal signs of malignancy. Importantly, these were correctly localised by AI, thus obviating supplementary screening modalities
.
•
AI could potentially reduce a proportion of particularly aggressive interval cancers
.
•
There was a correlation between AI risk score and interval cancer classified as true negative, minimal signs or false negative.
Digital breast tomosynthesis is an advancement of the mammographic technique, with the potential to increase detection of lesions during breast cancer screening. The main aim of the Malmö Breast ...Tomosynthesis Screening Trial (MBTST) was to investigate the accuracy of one-view digital breast tomosynthesis in population screening compared with standard two-view digital mammography.
In this prospective, population-based screening study, of women aged 40–74 years invited to attend national breast cancer screening at Skåne University Hospital, Malmö, Sweden, a random sample was asked to participate in the trial (every third woman who was invited to attend regular screening was invited to participate). Participants had to be able to speak English or Swedish and were excluded from the study if they were pregnant. Participants underwent screening with two-view digital mammography (ie, craniocaudal and mediolateral oblique views) followed by one-view digital breast tomosynthesis with reduced compression in the mediolateral oblique view (with a wide tomosynthesis angle of 50°) at one screening visit. Images were read with masked double reading and scoring by two separate reading groups, one for each method, made up of seven radiologists. Any cancer detected with a malignancy probability score of three or higher by any reader in either group was discussed in a consensus meeting of at least two readers, from which the decision of whether or not to recall the woman for further investigation was made. The primary outcome measures were sensitivity and specificity of breast cancer detection. Secondary outcome measures were screening performance measures of cancer detection, recall, and interval cancers (cancers clinically detected between screenings), and positive predictive value for screen recalls and negative predictive value of each method. Outcomes were analysed in the per-protocol population. Follow-up of the participants for at least 2 years allowed for identification of interval cancers. This trial is registered with ClinicalTrials.gov, number NCT01091545.
Between Jan 27, 2010, and Feb 13, 2015, of 21 691 women invited, 14 851 (68%) agreed to participate. Three women withdrew consent during follow-up and were excluded from the analyses. 139 breast cancers were detected in 137 (<1%) of 14 848 women. Sensitivity was higher for digital breast tomosynthesis than for digital mammography (81·1%, 95% CI 74·2–86·9, vs 60·4%, 52·3–68·0) and specificity was slightly lower for digital breast tomosynthesis than was for digital mammography (97·2%, 95% CI 97·0–97·5, vs 98·1%, 97·9–98·3). The proportion of cancers detected was significantly higher with digital breast tomosynthesis than with digital mammography (8·7 cancers per 1000 women screened, 95% CI 7·3–10·3 vs 6·5 cancers per 1000 screened, 5·2–7·9; p<0·0001). The proportion of women recalled after discussion was higher among cancers detected by digital breast tomosynthesis than for those detected by digital mammography after consensus (3·6%, 95% CI 3·3–3·9 vs 2·5%, 2·2–2·8; p<0·0001). The positive predictive value for screen recalls was 24·1% (95% CI 20·5–28·0) for digital breast tomosynthesis and 25·9% (21·6–30·7) for digital mammography, and the negative predictive value was 99·8% (99·7–99·9) and 99·6% (99·4–99·7), respectively. The proportion of women who developed interval cancers after trial screening was 1·48 cancers per 1000 women screened (95% CI 0·93–2·24).
Breast cancer screening by use of one-view digital breast tomosynthesis with a reduced compression force has higher sensitivity at a slightly lower specificity for breast cancer detection compared with two-view digital mammography and has the potential to reduce the radiation dose and screen-reading burden required by two-view digital breast tomosynthesis with two-view digital mammography.
The Swedish Cancer Society, The Swedish Research Council, The Breast Cancer Foundation, The Swedish Medical Society, The Crafoord Foundation, The Gunnar Nilsson Cancer Foundation, The Skåne University Hospital Foundation, Governmental funding for clinical research, The South Swedish Health Care Region, The Malmö Hospital Cancer Foundation and The Cancer Foundation at the Department of Oncology, Skåne University Hospital.
The depolymerization of LignoBoost Kraft lignin in subcritical water, i.e. hydrothermal liquefaction (HTL), was investigated using ZrO2, K2CO3, and KOH as catalysts in a fixed-bed reactor with ...recirculation. Focus was placed on the effect exerted by the concentration of the phenol in suppressing repolymerization, which is responsible for forming char. Feeds with various concentrations of phenol (2–10%) were investigated, and the results showed that phenol partially prevents repolymerization even at low concentrations. The bio-oil yield of (61.0 ± 2.7) % was fairly stable when the concentration of phenol was varied. In the case of the formation of char on the catalyst, the char yield revealed a weakly decreasing trend (14.6–12.3%) when the amount of phenol in the feed was increased. The results also showed that the phenolic monomers that are alkylated, such as o-/p-cresols, increased significantly with increasing concentrations of phenol, while aromatic compounds, based on a guaiacol ring structure, showed decreasing trends.
•The conversion of lignin in near-critical water was investigated at 290–370°C.•ZrO2/K2CO3 was used as catalytic system and phenol as char suppressing agent.•The lignin-oil has higher HHV and lower ...contents of oxygen and sulphur than lignin.•The main 1-ring aromatics are anisoles, alkylphenols, guaiacols and catechols.•The yield of 1-ring aromatics increases remarkably with an increase in temperature.
The catalytic conversion of suspended LignoBoost Kraft lignin was performed in near-critical water using ZrO2/K2CO3 as the catalytic system and phenol as the co-solvent and char suppressing agent. The reaction temperature was varied from 290 to 370°C and its effect on the process was investigated in a continuous flow (1kg/h). The yields of water-soluble organics (WSO), bio-oil and char (dry lignin basis) were in the ranges of 5–11%, 69–87% and 16–22%, respectively. The bio-oil, being partially deoxygenated, exhibited higher carbon content and heat value, but lower sulphur content than lignin. The main 1-ring aromatics (in WSO and diethylether-soluble bio-oil) were anisoles, alkylphenols, catechols and guaiacols. The results show that increasing temperature increases the yield of 1-ring aromatics remarkably, while it increases the formation of char moderately. An increase in the yields of anisoles, alkylphenols and catechols, together with a decrease in the yield of guaiacols, was also observed.
Abstract Objective To evaluate the rate of over-diagnosis of breast cancer 15 years after the end of the Malmö mammographic screening trial. Design Follow-up study. Setting Malmö, Sweden. Subjects 42 ...283 women aged 45-69 years at randomisation. Interventions Screening for breast cancer with mammography or not (controls). Screening was offered at the end of the randomisation design to both groups aged 45-54 at randomisation but not to groups aged 55-69 at randomisation. Main outcome measures Rate of over-diagnosis of breast cancer (in situ and invasive), calculated as incidence in the invited and control groups, during period of randomised design (period 1), during period after randomised design ended (period 2), and at end of follow-up. Results In women aged 55-69 years at randomisation the relative rates of over-diagnosis of breast cancer (95% confidence intervals) were 1.32 (1.14 to 1.53) for period 1, 0.92 (0.79 to 1.06) for period 2, and 1.10 (0.99 to 1.22) at the end of follow-up. Conclusion Conclusions on over-diagnosis of breast cancer in the Malmö mammographic screening trial can be drawn mainly for women aged 55-69 years at randomisation whose control groups were never screened. Fifteen years after the trial ended the rate of over-diagnosis of breast cancer was 10% in this age group.
The thermal stability of bio-oil influences its application in industry and is, therefore, a very important factor that must be taken into consideration. In this study, the stability of low and high ...molecular weight (Mw) fractions of bio-oil obtained from the hydrothermal liquefaction (HTL) of lignin in subcritical water was studied at an elevated temperature (80 °C) for a period of 1 h, 1 day and 1 week. The changes in molecular weight (gel permeation chromatography (GPC)) and chemical composition (gas chromatography–mass spectrometry (GC–MS) and 2D heteronuclear single quantum correlation (HSQC) NMR (18.8 T, DMSO-d
6
)) of low and high Mw fractions of the HTL bio-oil (i.e. light oil (LO) and heavy oil (HO)) were evaluated before and after ageing. It was found that only a slight formation of high Mw insoluble structures was obtained during ageing at elevated temperature for 1 week: 0.5% for the LO and 3.1% for the HO. These higher Mw moieties might be formed from different polymerisation/condensation reactions of the reactive compounds (i.e. anisoles, guaiacols, phenols, methylene (–CH
2
–) groups in phenolic dimers and xanthene). The high Mw insolubles in both the LO and the HO were analysed for structural composition using 2D HSQC NMR to obtain a better understanding of the changes in the composition of bio-oil fractions during the accelerated ageing process. In addition, a chemical shift database in DMSO-d
6
was analysed for a subset of phenolic model compounds to simplify the interpretation of the 2D HSQC NMR spectra.
In this work a multilevel analysis approach have been used for characterization of LignoBoost™ kraft lignin and bio-oil produced from LignoBoost™ kraft lignin using a process based on subcritical ...water (350 °C, 25 MPa). LignoBoost™ kraft lignin and the different fractions of the bio-oil (light oil, heavy oil and suspended solids) was characterized with high field NMR (18.8 T, 2D13C, 1H-HSQC NMR and 13C-NMR), GPC, GC-MS and elemental composition to improve understanding of the subcritical process. By using high resolution 2D HSQC NMR it was possible determine the chemical structures both on low and high molecular weight fractions of the bio-oil. It was confirmed that the signals from the aliphatic lignin inter-unit linkages, i.e. β-O-4′, β-β′, β-1′ and β-5′, had disappeared from all of the bio-oil fractions studied. This means that both the aliphatic carbon-oxygen (CO) and to some extent carbon-carbon (CC) bonds in LignoBoost™ kraft lignin have been cleaved and an effective depolymerization has occurred. However, re-polymerization into higher molecular weight (Mw) fractions takes place simultaneously. These higher Mw fractions (heavy oil and suspended solids) were found to be re-polymerized macromolecules, with new structural networks based on guaiacol/disubstituted aromatic ethers and polyaromatic hydrocarbon structures bound tightly together.
Display omitted
•The effective de-oxygenation of lignin into bio-oil was performed (Oxygen 15%).•Aliphatic lignin inter-unit bonds were depolymerized in all bio-oil fractions.•The main oxygen content in the bio-oil was connected to aromatic rings.•High Mw fractions were new repolymerized macromolecules.•2D NMR structural characterization of the fractionated bio-oil.
PDF
