Independent evaluation of a multi-view multi-task convolutional neural network breast cancer classification model using Finnish mammography screening data.

BACKGROUND: Development of deep convolutional neural networks for breast cancer classification has taken significant steps towards clinical adoption. It is though unclear how the models perform for unseen data, and what is required to adapt them to different demographic populations. In this retrospective study, we adopt an openly available pre-trained mammography breast cancer multi-view classification model and evaluate it by utilizing an independent Finnish dataset. METHODS: Transfer learning was used, and the pre-trained model was finetuned with 8,829 examinations from the Finnish dataset (4,321 normal, 362 malignant and 4,146 benign examinations). Holdout dataset with 2,208 examinations from the Finnish dataset (1,082 normal, 70 malignant and 1,056 benign examinations) was used in the evaluation. The performance was also evaluated on a manually annotated malignant suspect subset. Receiver Operating Characteristic (ROC) and Precision-Recall curves were used to performance measures. RESULTS: The Area Under ROC [95%CI] values for malignancy classification obtained with the finetuned model for the entire holdout set were 0.82 [0.76, 0.87], 0.84 [0.77, 0.89], 0.85 [0.79, 0.90], and 0.83 [0.76, 0.89] for R-MLO, L-MLO, R-CC and L-CC views respectively. Performance on the malignant suspect subset was slightly better. On the auxiliary benign classification task performance remained low. CONCLUSIONS: The results indicate that the model performs well also in an out-of-distribution setting. Finetuning allowed the model to adapt to some of the underlying local demographics. Future research should concentrate to identify breast cancer subgroups adversely affecting performance, as it is a requirement for increasing the model's readiness level for a clinical setting.

Chemical-bond effect on epitaxial strain in perovskite sodium niobate.

Epitaxial films and heterostructures of perovskite oxides attract tremendous scientific interest because of the unique phenomena therein. Especially important is the epitaxial growth of films subjected to substrate-induced misfit strain. We show here that in contrast to conventional misfit-controlled epitaxy, chemical bonds determine the crystal stability and strain in epitaxial films of sodium niobate on different cubic substrates. Strain relaxation in sodium niobate is independent of misfit magnitude and proceeds through perovskite-specific tilting of oxygen octahedra in addition to common defect formation. The observed structural relaxation evidences a major role of a large internal strain that originates from chemical bonds in the perovskite cell. The effect of chemical bonds on film strain is anticipated to also control the epitaxy of other perovskite oxides and related compounds.

Multimodality scoring of chondral injuries in the equine fetlock joint ex vivo.

OBJECTIVE: We investigate the potential of a prototype multimodality arthroscope, combining ultrasound, optical coherence tomography (OCT) and arthroscopic indentation device, for assessing cartilage lesions, and compare the reliability of this approach with conventional arthroscopic scoring ex vivo. DESIGN: Areas of interest (AIs, N = 43) were selected from equine fetlock joints (N = 5). Blind-coded AIs were independently scored by two equine surgeons employing International Cartilage Repair Society (ICRS) scoring system via conventional arthroscope and multimodality arthroscope, in which high-frequency ultrasound and OCT catheters were attached to an arthroscopic indentation device. In addition, cartilage stiffness was measured with the indentation device, and lesions in OCT images scored using custom-made automated software. Measurements and scorings were performed twice in two separate rounds. Finally, the scores were compared to histological ICRS scores. RESULTS: OCT and arthroscopic examinations showed the highest average agreements (55.2%) between the scoring by surgeons and histology scores, whereas ultrasound had the lowest (50.6%). Average intraobserver agreements of surgeons and interobserver agreements between rounds were, respectively, for conventional arthroscope (68.6%, 69.8%), ultrasound (68.6%, 68.6%), OCT (65.1%, 61.7%) and automated software (65.1%, 59.3%). CONCLUSIONS: OCT imaging supplemented with the automated software provided the most reliable lesion scoring. However, limited penetration depth of light limits the clinical potential of OCT in assessing human cartilage thickness; thus, the combination of OCT and ultrasound could be optimal for reliable diagnostics. Present findings suggest imaging and quantitatively analyzing the entire articular surface to eliminate surgeon-related variation in the selection of the most severe lesion to be scored.

Dirty limit scattering behind the decreased anisotropy of doped YBa2Cu3O7-δ thin films.

We measured the resistivity of pulsed-laser-deposited BaCeO3 (BCO)-doped YBCO thin films containing spherical BCO particles in fields up to 30 T. The average diameter of the particles depends on the dopant concentration being below 4 nm in all the samples. Raised values of the upper critical field, Bc2, were observed in all the samples. Additionally, the parameter γ, describing the electron mass anisotropy, decreased from 6.2 in the undoped sample to 3.1 in the 8 wt.% BCO-doped sample. These results can be explained by the increased number of defects decreasing the mean free path of electrons and thus lowering the coherence length, which in turn increases Bc2.

Collagen and chondrocyte concentrations control ultrasound scattering in agarose scaffolds.

Ultrasound imaging has been proposed for diagnostics of osteoarthritis and cartilage injuries in vivo. However, the specific contribution of chondrocytes and collagen to ultrasound scattering in articular cartilage has not been systematically studied. We investigated the role of these tissue structures by measuring ultrasound scattering in agarose scaffolds with varying collagen and chondrocyte concentrations. Ultrasound catheters with center frequencies of 9 MHz (7.1-11.0 MHz, -6 dB) and 40 MHz (30.1-45.3 MHz, -6 dB) were applied using an intravascular ultrasound device. Ultrasound backscattering quantified in a region of interest starting right below sample surface differed significantly (p < 0.05) with the concentrations of collagen and chondrocytes. An ultrasound frequency of 40 MHz, as compared with 9 MHz, was more sensitive to variations in collagen and chondrocyte concentrations. The present findings may improve diagnostic interpretation of arthroscopic ultrasound imaging and provide information necessary for development of models describing ultrasound propagation within cartilage.