'Artiphysiology' reveals V4-like shape tuning in a deep network trained for image classification.
Ontology highlight
ABSTRACT:
SUBMITTER: Pospisil DA
PROVIDER: S-EPMC6335056 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Previous studies have shown that neurons in area V4 are involved in the processing of shapes of intermediate complexity and are sensitive to curvature. These studies also suggest that curvature-tuned neurons are position invariant. We sought to examine the mechanisms that endow V4 neurons with these properties. Consistent with previous studies, we found that response rank order to the most- and least-preferred stimuli was preserved throughout the receptive field. However, a fine-grained analysis of shape tuning revealed a surprising result: V4 neurons tuned to highly curved shapes exhibit very limited translation invariance. At a fine spatial scale, these neurons exhibit local variation in orientation. In contrast, neurons that prefer straight contours exhibit spatially invariant orientation-tuning and homogenous fine-scale orientation maps. Both of these patterns are consistent with a simple orientation-pooling model, with tuning for straight or curved shapes resulting, respectively, from pooling of homogenous or heterogeneous orientation signals inherited from early visual areas.
| S-EPMC3694358 | biostudies-literature
Project description:With many thyroid nodules being incidentally detected, it is important to identify as many malignant nodules as possible while excluding those that are highly likely to be benign from fine needle aspiration (FNA) biopsies or surgeries. This paper presents a computer-aided diagnosis (CAD) system for classifying thyroid nodules in ultrasound images. We use deep learning approach to extract features from thyroid ultrasound images. Ultrasound images are pre-processed to calibrate their scale and remove the artifacts. A pre-trained GoogLeNet model is then fine-tuned using the pre-processed image samples which leads to superior feature extraction. The extracted features of the thyroid ultrasound images are sent to a Cost-sensitive Random Forest classifier to classify the images into "malignant" and "benign" cases. The experimental results show the proposed fine-tuned GoogLeNet model achieves excellent classification performance, attaining 98.29% classification accuracy, 99.10% sensitivity and 93.90% specificity for the images in an open access database (Pedraza et al. 16), while 96.34% classification accuracy, 86% sensitivity and 99% specificity for the images in our local health region database.
| S-EPMC5537102 | biostudies-other
Project description:This study aimed to investigate deep convolutional neural network- (DCNN-) based artificial intelligence (AI) model using cephalometric images for the classification of sagittal skeletal relationships and compare the performance of the newly developed DCNN-based AI model with that of the automated-tracing AI software. A total of 1574 cephalometric images were included and classified based on the A-point-Nasion- (N-) point-B-point (ANB) angle (Class I being 0-4°, Class II > 4°, and Class III < 0°). The DCNN-based AI model was developed using training (1334 images) and validation (120 images) sets with a standard classification label for the individual images. A test set of 120 images was used to compare the AI models. The agreement of the DCNN-based AI model or the automated-tracing AI software with a standard classification label was measured using Cohen's kappa coefficient (0.913 for the DCNN-based AI model; 0.775 for the automated-tracing AI software). In terms of their performances, the micro-average values of the DCNN-based AI model (sensitivity, 0.94; specificity, 0.97; precision, 0.94; accuracy, 0.96) were higher than those of the automated-tracing AI software (sensitivity, 0.85; specificity, 0.93; precision, 0.85; accuracy, 0.90). With regard to the sagittal skeletal classification using cephalometric images, the DCNN-based AI model outperformed the automated-tracing AI software.
| S-EPMC9270345 | biostudies-literature
Project description:BackgroundAutomatic cancer diagnostic systems based on histological image classification are important for improving therapeutic decisions. Previous studies propose textural and morphological features for such systems. These features capture patterns in histological images that are useful for both cancer grading and subtyping. However, because many of these features lack a clear biological interpretation, pathologists may be reluctant to adopt these features for clinical diagnosis.MethodsWe examine the utility of biologically interpretable shape-based features for classification of histological renal tumor images. Using Fourier shape descriptors, we extract shape-based features that capture the distribution of stain-enhanced cellular and tissue structures in each image and evaluate these features using a multi-class prediction model. We compare the predictive performance of the shape-based diagnostic model to that of traditional models, i.e., using textural, morphological and topological features.ResultsThe shape-based model, with an average accuracy of 77%, outperforms or complements traditional models. We identify the most informative shapes for each renal tumor subtype from the top-selected features. Results suggest that these shapes are not only accurate diagnostic features, but also correlate with known biological characteristics of renal tumors.ConclusionsShape-based analysis of histological renal tumor images accurately classifies disease subtypes and reveals biologically insightful discriminatory features. This method for shape-based analysis can be extended to other histological datasets to aid pathologists in diagnostic and therapeutic decisions.
| S-EPMC3623732 | biostudies-literature
Project description:BACKGROUND:Modern plant taxonomy reflects phylogenetic relationships among taxa based on proposed morphological and genetic similarities. However, taxonomical relation is not necessarily reflected by close overall resemblance, but rather by commonality of very specific morphological characters or similarity on the molecular level. It is an open research question to which extent phylogenetic relations within higher taxonomic levels such as genera and families are reflected by shared visual characters of the constituting species. As a consequence, it is even more questionable whether the taxonomy of plants at these levels can be identified from images using machine learning techniques. RESULTS:Whereas previous studies on automated plant identification from images focused on the species level, we investigated classification at higher taxonomic levels such as genera and families. We used images of 1000 plant species that are representative for the flora of Western Europe. We tested how accurate a visual representation of genera and families can be learned from images of their species in order to identify the taxonomy of species included in and excluded from learning. Using natural images with random content, roughly 500 images per species are required for accurate classification. The classification accuracy for 1000 species amounts to 82.2% and increases to 85.9% and 88.4% on genus and family level. Classifying species excluded from training, the accuracy significantly reduces to 38.3% and 38.7% on genus and family level. Excluded species of well represented genera and families can be classified with 67.8% and 52.8% accuracy. CONCLUSION:Our results show that shared visual characters are indeed present at higher taxonomic levels. Most dominantly they are preserved in flowers and leaves, and enable state-of-the-art classification algorithms to learn accurate visual representations of plant genera and families. Given a sufficient amount and composition of training data, we show that this allows for high classification accuracy increasing with the taxonomic level and even facilitating the taxonomic identification of species excluded from the training process.
| S-EPMC6318858 | biostudies-other
Project description:Accurate cancer type classification based on genetic mutation can significantly facilitate cancer-related diagnosis. However, existing methods usually use feature selection combined with simple classifiers to quantify key mutated genes, resulting in poor classification performance. To circumvent this problem, a novel image-based deep learning strategy is employed to distinguish different types of cancer. Unlike conventional methods, we first convert gene mutation data containing single nucleotide polymorphisms, insertions and deletions into a genetic mutation map, and then apply the deep learning networks to classify different cancer types based on the mutation map. We outline these methods and present results obtained in training VGG-16, Inception-v3, ResNet-50 and Inception-ResNet-v2 neural networks to classify 36 types of cancer from 9047 patient samples. Our approach achieves overall higher accuracy (over 95%) compared with other widely adopted classification methods. Furthermore, we demonstrate the application of a Guided Grad-CAM visualization to generate heatmaps and identify the top-ranked tumor-type-specific genes and pathways. Experimental results on prostate and breast cancer demonstrate our method can be applied to various types of cancer. Powered by the deep learning, this approach can potentially provide a new solution for pan-cancer classification and cancer driver gene discovery. The source code and datasets supporting the study is available at https://github.com/yetaoyu/Genomic-pan-cancer-classification.
| S-EPMC7848437 | biostudies-literature
Project description:Medical image classification is a novel technology that presents a new challenge. It is essential that pathological images are automatically and correctly classified to enable doctors to provide precise treatment. Convolutional neural networks have demonstrated their effectiveness in classifying images in deep learning, which may have dozens or hundreds of layers, to illustrate the relationship between them in terms of their different neural network features. Convolutional layers consisting of small kernels take weights as input and guide them through an activation function as output. The main advantage of using convolutional neural networks (CNNs) instead of traditional neural networks is that they reduce the model parameters for greater accuracy. However, many studies have simply been focused on finding the best CNN model and classification results from a single medical image classification. Therefore, we applied a common deep learning network model in an attempt to identify the best model framework by training and validating different model parameters to classify medical images. After conducting experiments on six publicly available databases of pathological images, including colorectal cancer tissue, chest X-rays, common skin lesions, diabetic retinopathy, pediatric chest X-ray, and breast ultrasound image datasets, we were able to confirm that the recognition accuracy of the Inception V3 method was significantly better than that of other existing deep learning models.
| S-EPMC9600639 | biostudies-literature
Project description:In the absence of sensory input, neuronal networks are far from being silent. Whether spontaneous changes in ongoing activity reflect previous sensory experience or stochastic fluctuations in brain activity is not well understood. Here we describe reactivation of stimulus-evoked activity in awake visual cortical networks. We found that continuous exposure to randomly flashed image sequences induces reactivation in macaque V4 cortical networks in the absence of visual stimulation. This reactivation of previously evoked activity is stimulus-specific, occurs only in the same temporal order as the original response, and strengthens with increased stimulus exposures. Importantly, cells exhibiting significant reactivation carry more information about the stimulus than cells that do not reactivate. These results demonstrate a surprising degree of experience-dependent plasticity in visual cortical networks as a result of repeated exposure to unattended information. We suggest that awake reactivation in visual cortex may underlie perceptual learning by passive stimulus exposure.
| S-EPMC3511092 | biostudies-literature
Project description:We have developed a novel photoacoustic microscopy/ultrasound (PAM/US) endoscope to image post-treatment rectal cancer for surgical management of residual tumor after radiation and chemotherapy. Paired with a deep-learning convolutional neural network (CNN), the PAM images accurately differentiated pathological complete responders (pCR) from incomplete responders. However, the role of CNNs compared with traditional histogram-feature based classifiers needs further exploration. In this work, we compare the performance of the CNN models to generalized linear models (GLM) across 24 ex vivo specimens and 10 in vivo patient examinations. First order statistical features were extracted from histograms of PAM and US images to train, validate and test GLM models, while PAM and US images were directly used to train, validate, and test CNN models. The PAM-CNN model performed superiorly with an AUC of 0.96 (95% CI: 0.95-0.98) compared to the best PAM-GLM model using kurtosis with an AUC of 0.82 (95% CI: 0.82-0.83). We also found that both CNN and GLMs derived from photoacoustic data outperformed those utilizing ultrasound alone. We conclude that deep-learning neural networks paired with photoacoustic images is the optimal analysis framework for determining presence of residual cancer in the treated human rectum.
| S-EPMC8495416 | biostudies-literature
Project description:The examination of urinary sediment crystals, the sedimentary components of urine, is useful in screening tests, and is always performed in medical examinations. The examination of urinary sediment crystals is typically done by classifying them under a microscope. Although automated analyzers are commercially available, manual classification is required, which is time-consuming and varies depending on the technologist performing the test and the laboratory. A set of test images was created, consisting of training, validation, and test images. The training images were transformed and augmented using various methods. The test images were classified to determine the patterns that could be correctly classified. Convolutional neural networks were used for training. Furthermore, we also considered the case where the crystal subcategories were not treated as separate. Learning with all parameters except the random cropping parameter showed the highest accuracy value. Treating the subcategories together or separately did not seem to affect the accuracy value. The accuracy of the best pattern was 0.918. When matched to a real-world case, the percentage of correct answers was 88%. Although the number of images was limited, good results were obtained in the classification of crystal images with optimal parameter tuning. The parameter optimization performed in this study can be used as a reference for future studies, with the goal of image classification by deep learning in clinical practice.
| S-EPMC9729224 | biostudies-literature