Dataset Information

Deep convolutional models improve predictions of macaque V1 responses to natural images.

ABSTRACT: Despite great efforts over several decades, our best models of primary visual cortex (V1) still predict spiking activity quite poorly when probed with natural stimuli, highlighting our limited understanding of the nonlinear computations in V1. Recently, two approaches based on deep learning have emerged for modeling these nonlinear computations: transfer learning from artificial neural networks trained on object recognition and data-driven convolutional neural network models trained end-to-end on large populations of neurons. Here, we test the ability of both approaches to predict spiking activity in response to natural images in V1 of awake monkeys. We found that the transfer learning approach performed similarly well to the data-driven approach and both outperformed classical linear-nonlinear and wavelet-based feature representations that build on existing theories of V1. Notably, transfer learning using a pre-trained feature space required substantially less experimental time to achieve the same performance. In conclusion, multi-layer convolutional neural networks (CNNs) set the new state of the art for predicting neural responses to natural images in primate V1 and deep features learned for object recognition are better explanations for V1 computation than all previous filter bank theories. This finding strengthens the necessity of V1 models that are multiple nonlinearities away from the image domain and it supports the idea of explaining early visual cortex based on high-level functional goals.

SUBMITTER: Cadena SA

PROVIDER: S-EPMC6499433 | biostudies-literature | 2019 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep convolutional models improve predictions of macaque V1 responses to natural images.

Cadena Santiago A SA Denfield George H GH Walker Edgar Y EY Gatys Leon A LA Tolias Andreas S AS Bethge Matthias M Ecker Alexander S AS

PLoS computational biology 20190423 4

Despite great efforts over several decades, our best models of primary visual cortex (V1) still predict spiking activity quite poorly when probed with natural stimuli, highlighting our limited understanding of the nonlinear computations in V1. Recently, two approaches based on deep learning have emerged for modeling these nonlinear computations: transfer learning from artificial neural networks trained on object recognition and data-driven convolutional neural network models trained end-to-end o ...[more]

PMID: 31013278

Similar Datasets

Project description:BackgroundThe incidence of thyroid cancer is rising steadily because of overdiagnosis and overtreatment conferred by widespread use of sensitive imaging techniques for screening. This overall incidence growth is especially driven by increased diagnosis of indolent and well-differentiated papillary subtype and early-stage thyroid cancer, whereas the incidence of advanced-stage thyroid cancer has increased marginally. Thyroid ultrasound is frequently used to diagnose thyroid cancer. The aim of this study was to use deep convolutional neural network (DCNN) models to improve the diagnostic accuracy of thyroid cancer by analysing sonographic imaging data from clinical ultrasounds.MethodsWe did a retrospective, multicohort, diagnostic study using ultrasound images sets from three hospitals in China. We developed and trained the DCNN model on the training set, 131 731 ultrasound images from 17 627 patients with thyroid cancer and 180 668 images from 25 325 controls from the thyroid imaging database at Tianjin Cancer Hospital. Clinical diagnosis of the training set was made by 16 radiologists from Tianjin Cancer Hospital. Images from anatomical sites that were judged as not having cancer were excluded from the training set and only individuals with suspected thyroid cancer underwent pathological examination to confirm diagnosis. The model's diagnostic performance was validated in an internal validation set from Tianjin Cancer Hospital (8606 images from 1118 patients) and two external datasets in China (the Integrated Traditional Chinese and Western Medicine Hospital, Jilin, 741 images from 154 patients; and the Weihai Municipal Hospital, Shandong, 11 039 images from 1420 patients). All individuals with suspected thyroid cancer after clinical examination in the validation sets had pathological examination. We also compared the specificity and sensitivity of the DCNN model with the performance of six skilled thyroid ultrasound radiologists on the three validation sets.FindingsBetween Jan 1, 2012, and March 28, 2018, ultrasound images for the four study cohorts were obtained. The model achieved high performance in identifying thyroid cancer patients in the validation sets tested, with area under the curve values of 0·947 (95% CI 0·935-0·959) for the Tianjin internal validation set, 0·912 (95% CI 0·865-0·958) for the Jilin external validation set, and 0·908 (95% CI 0·891-0·925) for the Weihai external validation set. The DCNN model also showed improved performance in identifying thyroid cancer patients versus skilled radiologists. For the Tianjin internal validation set, sensitivity was 93·4% (95% CI 89·6-96·1) versus 96·9% (93·9-98·6; p=0·003) and specificity was 86·1% (81·1-90·2) versus 59·4% (53·0-65·6; p<0·0001). For the Jilin external validation set, sensitivity was 84·3% (95% CI 73·6-91·9) versus 92·9% (84·1-97·6; p=0·048) and specificity was 86·9% (95% CI 77·8-93·3) versus 57·1% (45·9-67·9; p<0·0001). For the Weihai external validation set, sensitivity was 84·7% (95% CI 77·0-90·7) versus 89·0% (81·9-94·0; p=0·25) and specificity was 87·8% (95% CI 81·6-92·5) versus 68·6% (60·7-75·8; p<0·0001).InterpretationThe DCNN model showed similar sensitivity and improved specificity in identifying patients with thyroid cancer compared with a group of skilled radiologists. The improved technical performance of the DCNN model warrants further investigation as part of randomised clinical trials.FundingThe Program for Changjiang Scholars and Innovative Research Team in University in China, and National Natural Science Foundation of China.

Project description:PURPOSE:Convolutional neural networks have become rapidly popular for image recognition and image analysis because of its powerful potential. In this paper, we developed a method for classifying subtypes of lung adenocarcinoma from pathological images using neural network whose that can evaluate phenotypic features from wider area to consider cellular distributions. METHODS:In order to recognize the types of tumors, we need not only to detail features of cells, but also to incorporate statistical distribution of the different types of cells. Variants of autoencoders as building blocks of pre-trained convolutional layers of neural networks are implemented. A sparse deep autoencoder which minimizes local information entropy on the encoding layer is then proposed and applied to images of size [Formula: see text]. We applied this model for feature extraction from pathological images of lung adenocarcinoma, which is comprised of three transcriptome subtypes previously defined by the Cancer Genome Atlas network. Since the tumor tissue is composed of heterogeneous cell populations, recognition of tumor transcriptome subtypes requires more information than local pattern of cells. The parameters extracted using this approach will then be used in multiple reduction stages to perform classification on larger images. RESULTS:We were able to demonstrate that these networks successfully recognize morphological features of lung adenocarcinoma. We also performed classification and reconstruction experiments to compare the outputs of the variants. The results showed that the larger input image that covers a certain area of the tissue is required to recognize transcriptome subtypes. The sparse autoencoder network with [Formula: see text] input provides a 98.9% classification accuracy. CONCLUSION:This study shows the potential of autoencoders as a feature extraction paradigm and paves the way for a whole slide image analysis tool to predict molecular subtypes of tumors from pathological features.

Dataset Information

Deep convolutional models improve predictions of macaque V1 responses to natural images.

Publications

Deep convolutional models improve predictions of macaque V1 responses to natural images.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets