RESUMEN
BACKGROUND: Histopathology images of tumor biopsies present unique challenges for applying machine learning to the diagnosis and treatment of cancer. The pathology slides are high resolution, often exceeding 1GB, have non-uniform dimensions, and often contain multiple tissue slices of varying sizes surrounded by large empty regions. The locations of abnormal or cancerous cells, which may constitute a small portion of any given tissue sample, are not annotated. Cancer image datasets are also extremely imbalanced, with most slides being associated with relatively common cancers. Since deep representations trained on natural photographs are unlikely to be optimal for classifying pathology slide images, which have different spectral ranges and spatial structure, we here describe an approach for learning features and inferring representations of cancer pathology slides based on sparse coding. RESULTS: We show that conventional transfer learning using a state-of-the-art deep learning architecture pre-trained on ImageNet (RESNET) and fine tuned for a binary tumor/no-tumor classification task achieved between 85% and 86% accuracy. However, when all layers up to the last convolutional layer in RESNET are replaced with a single feature map inferred via a sparse coding using a dictionary optimized for sparse reconstruction of unlabeled pathology slides, classification performance improves to over 93%, corresponding to a 54% error reduction. CONCLUSIONS: We conclude that a feature dictionary optimized for biomedical imagery may in general support better classification performance than does conventional transfer learning using a dictionary pre-trained on natural images.
Asunto(s)
Aprendizaje Profundo/tendencias , Neoplasias/patología , Redes Neurales de la Computación , HumanosRESUMEN
Prurigo nodularis (PN) is an understudied inflammatory skin disease characterized by pruritic, hyperkeratotic nodules. Identifying the genetic factors underlying PN could help to better understand its etiology and guide the development of therapies. In this study, we developed a polygenic risk score that predicts a diagnosis of PN (OR = 1.41, P = 1.6 × 10-5) in two independent and continentally distinct populations. We also performed GWASs, which uncovered genetic variants associated with PN, including one near PLCB4 (rs6039266: OR = 3.15, P = 4.8 × 10-8) and others near TXNRD1 (rs34217906: OR = 1.71, P = 6.4 × 10-7; rs7134193: OR = 1.57, P = 1.1 × 10-6). Finally, we discovered that Black patients have over a two-times greater genetic risk of developing PN (OR = 2.63, P = 7.8 × 10-4). Combining the polygenic risk score and self-reported race together was significantly predictive of PN (OR = 1.32, P = 4.7 × 10-3). Strikingly, this association was more significant with race than after adjusting for genetic ancestry. Because race is a sociocultural construct and not a genetically bound category, our findings suggest that genetics, environmental influence, and social determinants of health likely affect the development of PN and may contribute to clinically observed racial disparities.
Asunto(s)
Dermatitis , Prurigo , Humanos , Población Negra , Dermatitis/etnología , Dermatitis/genética , Predisposición Genética a la Enfermedad , Prurigo/etnología , Prurigo/genética , Factores de RiesgoRESUMEN
Image segmentation is one of the main problems in image processing. In order to improve the accuracy of segmentation, one often creates a number of masks (annotations) for a same image and then uses some voting methods on these masks to obtain a more accurate mask. In this paper, we propose a voting method whose voting rule is not pixel-wise but takes into account the natural geometric-topological properties of the masks. On three concrete examples, we show that our voting method outperforms the usual arithmetical voting method.
RESUMEN
We present a new lossy compression algorithm for statistical floating-point data through a representation learning with binary variables. The algorithm finds a set of basis vectors and their binary coefficients that precisely reconstruct the original data. The optimization for the basis vectors is performed classically, while binary coefficients are retrieved through both simulated and quantum annealing for comparison. A bias correction procedure is also presented to estimate and eliminate the error and bias introduced from the inexact reconstruction of the lossy compression for statistical data analyses. The compression algorithm is demonstrated on two different datasets of lattice quantum chromodynamics simulations. The results obtained using simulated annealing show 3-3.5 times better compression performance than the algorithm based on neural-network autoencoder. Calculations using quantum annealing also show promising results, but performance is limited by the integrated control error of the quantum processing unit, which yields large uncertainties in the biases and coupling parameters. Hardware comparison is further studied between the previous generation D-Wave 2000Q and the current D-Wave Advantage system. Our study shows that the Advantage system is more likely to obtain low-energy solutions for the problems than the 2000Q.
RESUMEN
We propose a regression algorithm that utilizes a learned dictionary optimized for sparse inference on a D-Wave quantum annealer. In this regression algorithm, we concatenate the independent and dependent variables as a combined vector, and encode the high-order correlations between them into a dictionary optimized for sparse reconstruction. On a test dataset, the dependent variable is initialized to its average value and then a sparse reconstruction of the combined vector is obtained in which the dependent variable is typically shifted closer to its true value, as in a standard inpainting or denoising task. Here, a quantum annealer, which can presumably exploit a fully entangled initial state to better explore the complex energy landscape, is used to solve the highly non-convex sparse coding optimization problem. The regression algorithm is demonstrated for a lattice quantum chromodynamics simulation data using a D-Wave 2000Q quantum annealer and good prediction performance is achieved. The regression test is performed using six different values for the number of fully connected logical qubits, between 20 and 64. The scaling results indicate that a larger number of qubits gives better prediction accuracy.