Deep learning algorithm performs similarly to radiologists in the assessment of prostate volume on MRI.

OBJECTIVES: Prostate volume (PV) in combination with prostate specific antigen (PSA) yields PSA density which is an increasingly important biomarker. Calculating PV from MRI is a time-consuming, radiologist-dependent task. The aim of this study was to assess whether a deep learning algorithm can replace PI-RADS 2.1 based ellipsoid formula (EF) for calculating PV. METHODS: Eight different measures of PV were retrospectively collected for each of 124 patients who underwent radical prostatectomy and preoperative MRI of the prostate (multicenter and multi-scanner MRI's 1.5 and 3 T). Agreement between volumes obtained from the deep learning algorithm (PVDL) and ellipsoid formula by two radiologists (PVEF1 and PVEF2) was evaluated against the reference standard PV obtained by manual planimetry by an expert radiologist (PVMPE). A sensitivity analysis was performed using a prostatectomy specimen as the reference standard. Inter-reader agreement was evaluated between the radiologists using the ellipsoid formula and between the expert and inexperienced radiologists performing manual planimetry. RESULTS: PVDL showed better agreement and precision than PVEF1 and PVEF2 using the reference standard PVMPE (mean difference [95% limits of agreement] PVDL: -0.33 [-10.80; 10.14], PVEF1: -3.83 [-19.55; 11.89], PVEF2: -3.05 [-18.55; 12.45]) or the PV determined based on specimen weight (PVDL: -4.22 [-22.52; 14.07], PVEF1: -7.89 [-30.50; 14.73], PVEF2: -6.97 [-30.13; 16.18]). Inter-reader agreement was excellent between the two experienced radiologists using the ellipsoid formula and was good between expert and inexperienced radiologists performing manual planimetry. CONCLUSION: Deep learning algorithm performs similarly to radiologists in the assessment of prostate volume on MRI. KEY POINTS: • A commercially available deep learning algorithm performs similarly to radiologists in the assessment of prostate volume on MRI. • The deep-learning algorithm was previously untrained on this heterogenous multicenter day-to-day practice MRI data set.

Deposition of inhaled nanoparticles is reduced in subjects with COPD and correlates with the extent of emphysema: proof of concept for a novel diagnostic technique.

BACKGROUND: The diagnosis of chronic obstructive pulmonary disease (COPD) is often based on spirometry, which is not sensitive to early emphysema. We have recently described a method for assessing distal airspace dimensions by measuring recovery of nanoparticles in exhaled air after a single-breath inhalation followed by breath-hold. Recovery refers to the non-deposited particle fraction. The aim of this study was to explore differences in the recovery of exhaled nanoparticles in subjects with COPD and never-smoking controls. A secondary aim was to determine whether recovery correlates with the extent of emphysema. METHOD: A total of 19 patients with COPD and 19 controls underwent three repeats of single-breath nanoparticle inhalation followed by breath-hold. Particle concentrations in the inhaled aerosol, and in an alveolar sample exhaled after breath-hold, were measured to obtain recovery. FINDINGS: The patients with COPD had a significantly higher mean recovery than controls, 0·128 ± 0·063 versus 0·074 ± 0·058; P = 0·010. Also, recovery correlated significantly with computed tomography (CT) densitometry variables (P<0·01) and diffusing capacity for carbon monoxide (DL,CO ; P = 0·002). INTERPRETATION: Higher recovery for emphysema patients, relative to controls, is explained by larger diffusion distances in enlarged distal airspaces. The nanoparticle inhalation method shows potential to be developed towards a tool to diagnose emphysema.

14C BOMB-PULSE DATING AND STABLE ISOTOPE ANALYSIS FOR GROWTH RATE AND DIETARY INFORMATION IN BREAST CANCER?

The purpose of this study was to perform an initial investigation of the possibility to determine breast cancer growth rate with (14)C bomb-pulse dating. Tissues from 11 breast cancers, diagnosed in 1983, were retrieved from a regional biobank. The estimated average age of the majority of the samples overlapped the year of collection (1983) within 3σ Thus, this first study of tumour tissue has not yet demonstrated that (14)C bomb-pulse dating can obtain information on the growth of breast cancer. However, with further refinement, involving extraction of cell types and components, there is a possibility that fundamental knowledge of tumour biology might still be gained by the bomb-pulse technique. Additionally, δ (13)C and δ (15)N analyses were performed to obtain dietary and metabolic information, and to serve as a base for improvement of the age determination.

Breast cancer detection in digital breast tomosynthesis and digital mammography-a side-by-side review of discrepant cases.

OBJECTIVE: To analyse discrepant breast cancer detection in digital breast tomosynthesis (DBT) and digital mammography (DM). METHODS: From a previous detection study comparing DBT and DM, 26 discrepant cases were extracted, 19 detected by DBT only and 7 by DM only. An expert panel of three radiologists reviewed these cases and documented the level of discrepancy, lesion visibility, radiographic pattern and lesion conspicuity and assessed the reason for non-detection. Differences between groups were tested using the Wilcoxon rank sum test, the Kruskal-Wallis test and visual grading characteristics. RESULTS: The proportion of lesion periphery in fatty tissue was statistically significantly larger, and there were significantly more spiculated masses in DBT compared with DM in the DBT only group (p = 0.018; p = 0.015). The main reasons for missing a lesion were poor lesion visibility when using DM and interpretative error when using DBT. CONCLUSION: Lesion visualization is superior with DBT, particularly of spiculated tumours. A major reason for non-detection in DBT seems to be interpretative error, which may be due to lack of experience. ADVANCES IN KNOWLEDGE: Our findings suggest that DBT is better than DM in visualizing breast cancer and that non-detection when using DBT is related to interpretative error regarding clearly visible lesions.

Light in and sound out: emerging translational strategies for photoacoustic imaging.

Photoacoustic imaging (PAI) has the potential for real-time molecular imaging at high resolution and deep inside the tissue, using nonionizing radiation and not necessarily depending on exogenous imaging agents, making this technique very promising for a range of clinical applications. The fact that PAI systems can be made portable and compatible with existing imaging technologies favors clinical translation even more. The breadth of clinical applications in which photoacoustics could play a valuable role include: noninvasive imaging of the breast, sentinel lymph nodes, skin, thyroid, eye, prostate (transrectal), and ovaries (transvaginal); minimally invasive endoscopic imaging of gastrointestinal tract, bladder, and circulating tumor cells (in vivo flow cytometry); and intraoperative imaging for assessment of tumor margins and (lymph node) metastases. In this review, we describe the basics of PAI and its recent advances in biomedical research, followed by a discussion of strategies for clinical translation of the technique.

Breast tomosynthesis and digital mammography: a comparison of diagnostic accuracy.

OBJECTIVE: Our aim was to compare the ability of radiologists to detect breast cancers using one-view breast tomosynthesis (BT) and two-view digital mammography (DM) in an enriched population of diseased patients and benign and/or healthy patients. METHODS: All participants gave informed consent. The BT and DM examinations were performed with about the same average glandular dose to the breast. The study population comprised patients with subtle signs of malignancy seen on DM and/or ultrasonography. Ground truth was established by pathology, needle biopsy and/or by 1-year follow-up by mammography, which retrospectively resulted in 89 diseased breasts (1 breast per patient) with 95 malignant lesions and 96 healthy or benign breasts. Two experienced radiologists, who were not participants in the study, determined the locations of the malignant lesions. Five radiologists, experienced in mammography, interpreted the cases independently in a free-response study. The data were analysed by the receiver operating characteristic (ROC) and jackknife alternative free-response ROC (JAFROC) methods, regarding both readers and cases as random effects. RESULTS: The diagnostic accuracy of BT was significantly better than that of DM (JAFROC: p=0.0031, ROC: p=0.0415). The average sensitivity of BT was higher than that of DM (∼90% vs ∼79%; 95% confidence interval of difference: 0.036, 0.108) while the average false-positive fraction was not significantly different (95% confidence interval of difference: -0.117, 0.010). CONCLUSION: The diagnostic accuracy of BT was superior to DM in an enriched population.

Tumour-related factors and prognosis in breast cancer detected by screening.

BACKGROUND: Breast cancer detected by screening has an unexplained prognostic advantage beyond stage shift compared with cancers detected clinically. The aim was to investigate biological factors in invasive breast cancer, with reference to mode of detection and rate of death from breast cancer. METHODS: Histology, oestrogen receptor α and ß, progesterone receptor, human epidermal growth factor receptor (HER) 2, cyclin D1, p27, Ki-67 and perinodal growth were analysed in 466 tumours from a prospective cohort, the Malmö Diet and Cancer Study. Using logistic regression, odds ratios were calculated to investigate the relationship between tumour characteristics and mode of detection. The same tumour factors were analysed in relation to standard prognostic features. Death from breast cancer was analysed using Cox regression with adjustments for standard tumour factors; differences following adjustment were analysed by means of Freedman statistics. RESULTS: None of the biological tumour characteristics varied with mode of detection of breast cancer. After adjustment for age, tumour size, axillary lymph node involvement (ALNI) and grade, women with cancer detected clinically had an increased risk of death from breast cancer (hazard ratio 2·48, 95 per cent confidence interval 1·34 to 4·59), corresponding to a 37·2 per cent difference compared with the unadjusted model. Additional adjustment for biological tumour factors studied caused only minor changes. CONCLUSION: None of the biological tumour markers investigated explained the improved prognosis in breast cancer detected by screening. None of the factors was related to ALNI, suggesting that other mechanisms may be responsible for tumour spread.

Breast cancer screening with tomosynthesis--initial experiences.

Experiences gained so far using tomosynthesis for breast cancer screening will be reported. A short summary of results from preparatory studies will also be presented. The sensitivity and specificity of breast tomosynthesis (BT) will be compared with conventional two-dimensional digital mammography (DM) for breast cancer screening in a population-based study. Over 2000 women have been examined so far with BT and DM. The BT reading is significantly more time-consuming than the DM reading. Preparatory studies have shown that BT has a higher diagnostic precision and higher accuracy of size measurements and stage determination than DM. There is potential to use lower compression force with BT compared with DM, without decreasing the diagnostic accuracy. BT might play an important role in clinical as well as screening mammography. A large-scale population-based study to investigate BT as a screening modality is underway.

The diagnostic accuracy of dual-view digital mammography, single-view breast tomosynthesis and a dual-view combination of breast tomosynthesis and digital mammography in a free-response observer performance study.

The purpose of the present study was to compare the diagnostic accuracy of dual-view digital mammography (DM), single-view breast tomosynthesis (BT) and BT combined with the opposite DM view. Patients with subtle lesions were selected to undergo BT examinations. Two radiologists who are non-participants in the study and have experience in using DM and BT determined the locations and extents of lesions in the images. Five expert mammographers interpreted the cases using the free-response paradigm. The task was to mark and rate clinically reportable findings suspicious for malignancy and clinically relevant benign findings. The marks were scored with reference to the outlined regions into lesion localization or non-lesion localization, and analysed by the jackknife alternative free-response receiver operating characteristic method. The analysis yielded statistically significant differences between the combined modality and dual-view DM (p < 0.05). No differences were found between single-view BT and dual-view DM or between single-view BT and the combined modality.

The effect of reduced breast compression in breast tomosynthesis: human observer study using clinical cases.

The aim of this study was to investigate whether the compression force used with conventional mammography can be reduced with breast tomosynthesis (BT), without adversely affecting the visualisation of normal and pathological structures. Forty-five women were examined with BT using full (same as for 2D mammography) and half compression force. Both examinations were performed with the same acquisition parameters. A total of 103 paired structure images were evaluated according to specified image quality criteria. Three experienced radiologists participated in the study. They had to make a forced choice, i.e. choose the image they felt best fulfilled the image quality criteria. The results showed no evident difference in the image quality, indicating that BT may be performed with substantially less compression force compared with 2D mammography. A majority of the examined women felt that half compression was more comfortable than full compression.

Body mass index and breast cancer survival in relation to the introduction of mammographic screening.

AIMS: Mammographic screening reduces mortality in breast cancer. It is not known if this reduction is more pronounced in certain groups. Obesity has been associated with worse survival following breast cancer diagnosis. This study investigates BMI in relation to breast cancer mortality, and if this association is affected by invitation to mammographic screening. METHODS: In 1976, a randomised mammographic screening trial, inviting 50% of all women aged 45-69 years (n=42 283), was set up in Malmö, Sweden. BMI in relation to breast cancer mortality was examined separately in women invited or not invited to screening in the trial. The analyses also included a historical control-group diagnosed before the screening trial. The study included 2974 women diagnosed in 1961-1991. Relative risks (RR) with a 95% confidence interval was obtained from a Cox proportional hazard analysis and in the analysis of all women, follow-up was limited to 10 years. RESULTS: Obese women (BMI> or =30) not invited to mammographic screening had a higher adjusted RR of dying of breast cancer as compared to normal weight women (2.08:1.13-3.81) in the 10-year follow-up. In women invited to screening there was no association between BMI and breast cancer mortality. In the historical control group, mortality was increased in overweight women (BMI: 25-30), RR=1.27:0.99-1.62, and obese women, RR=1.32:0.94-1.84, but these associations totally disappeared in the multivariate analysis, following adjustment for tumour size and stage. CONCLUSIONS: Overweight and obese women may be a group that profit from mammographic screening to more than normal weight women.

Parity in relation to risk of axillary lymph node involvement in women with breast cancer. Results from Swedish population-based series of 3,472 consecutive cases.

OBJECTIVE: To investigate the association between parity and axillary lymph node involvement (ALNI) at breast cancer diagnosis. METHODS: One surgeon has reviewed all breast cancer cases in Malmo, Sweden, diagnosed 1961-1991. This study includes the 3,472 women who had a first-time diagnosis of unilateral invasive breast cancer, and who had undergone axillary dissection. Information was collected regarding date of birth, date of diagnosis, age at diagnosis, menopausal status, tumour size, histological type, tumour location, type of surgery, stage (ALNI), and parity. Parity was investigated in relation to ALNI using logistic regression analysis, adjusted for potential confounders, yielding odds ratios (OR) with 95% confidence intervals (CI). The analyses were repeated in different strata with regard to birth-years cohort, age at diagnosis, and period of diagnosis. RESULTS: High parity was associated with ALNI, the adjusted OR for ALNI among women with 4 or more children was 1.56 (1.13-2.15). This association was stronger in comparatively old women (> or = 67.45 years), OR 1.78 (1.10-2.88). Considering parity a continuous variable, the OR for ALNI among all women was 1.06 (1.01-1.12). CONCLUSIONS: We conclude that women with 4 or more children had an increased risk of ALNI at breast cancer diagnosis.