Search

Abstract Deep learning has enabled breakthroughs in automated diagnosis from medical imaging, with many successful applications in ophthalmology. However, standard medical image classification approaches only assess disease presence at the time of acquisition, neglecting the common clinical setting of longitudinal imaging. For slow, progressive eye diseases like age-related macular degeneration (AMD) and primary open-angle glaucoma (POAG), patients undergo repeated imaging over time to track disease progression and forecasting the future risk of developing a disease is critical to properly plan treatment. Our proposed Longitudinal Transformer for Survival Analysis (LTSA) enables dynamic disease prognosis from longitudinal medical imaging, modeling the time to disease from sequences of fundus photography images captured over long, irregular time periods. Using longitudinal imaging data from the Age-Related Eye Disease Study (AREDS) and Ocular Hypertension Treatment Study (OHTS), LTSA significantly outperformed a single-image baseline in 19/20 head-to-head comparisons on late AMD prognosis and 18/20 comparisons on POAG prognosis. A temporal attention analysis also suggested that, while the most recent image is typically the most influential, prior imaging still provides additional prognostic value.

Abstract Background Advances in self-supervised learning (SSL) have enabled state-of-the-art automated medical image diagnosis from small, labeled datasets. This label efficiency is often desirable, given the difficulty of obtaining expert labels for medical image recognition tasks. However, most efforts toward SSL in medical imaging are not adapted to video-based modalities, such as echocardiography. Methods We developed a self-supervised contrastive learning approach, EchoCLR, for echocardiogram videos with the goal of learning strong representations for efficient fine-tuning on downstream cardiac disease diagnosis. EchoCLR pretraining involves (i) contrastive learning, where the model is trained to identify distinct videos of the same patient, and (ii) frame reordering, where the model is trained to predict the correct of video frames after being randomly shuffled. Results When fine-tuned on small portions of labeled data, EchoCLR pretraining significantly improves classification performance for left ventricular hypertrophy (LVH) and aortic stenosis (AS) over other transfer learning and SSL approaches across internal and external test sets. When fine-tuning on 10% of available training data (519 studies), an EchoCLR-pretrained model achieves 0.72 AUROC (95% CI: [0.69, 0.75]) on LVH classification, compared to 0.61 AUROC (95% CI: [0.57, 0.64]) with a standard transfer learning approach. Similarly, using 1% of available training data (53 studies), EchoCLR pretraining achieves 0.82 AUROC (95% CI: [0.79, 0.84]) on severe AS classification, compared to 0.61 AUROC (95% CI: [0.58, 0.65]) with transfer learning. Conclusions EchoCLR is unique in its ability to learn representations of echocardiogram videos and demonstrates that SSL can enable label-efficient disease classification from small amounts of labeled data.

Abstract Deep learning has become a popular tool for computer-aided diagnosis using medical images, sometimes matching or exceeding the performance of clinicians. However, these models can also reflect and amplify human bias, potentially resulting inaccurate missed diagnoses. Despite this concern, the problem of improving model fairness in medical image classification by deep learning has yet to be fully studied. To address this issue, we propose an algorithm that leverages the marginal pairwise equal opportunity to reduce bias in medical image classification. Our evaluations across four tasks using four independent large-scale cohorts demonstrate that our proposed algorithm not only improves fairness in individual and intersectional subgroups but also maintains overall performance. Specifically, the relative change in pairwise fairness difference between our proposed model and the baseline model was reduced by over 35%, while the relative change in AUC value was typically within 1%. By reducing the bias generated by deep learning models, our proposed approach can potentially alleviate concerns about the fairness and reliability of image-based computer-aided diagnosis.

Abstract Background Apoptosis signal-regulating kinase 1 (ASK1) not only causes neuronal programmed cell death via the mitochondrial pathway but also is an essential component of the signalling cascade during microglial activation. We hypothesize that ASK1 selective deletion modulates inflammatory responses in microglia/macrophages(Mi/Mϕ) and attenuates seizure severity and long-term cognitive impairments in an epileptic mouse model. Methods Mi/Mϕ-specific ASK1 conditional knockout (ASK1 cKO) mice were obtained for experiments by mating ASK1flox/flox mice with CX3CR1creER mice with tamoxifen induction. Epileptic seizures were induced by intrahippocampal injection of kainic acid (KA). ASK1 expression and distribution were detected by western blotting and immunofluorescence staining. Seizures were monitored for 24 h per day with video recordings. Cognition, social and stress related activities were assessed with the Y maze test and the three-chamber social novelty preference test. The heterogeneous Mi/Mϕ status and inflammatory profiles were assessed with immunofluorescence staining and real-time polymerase chain reaction (q-PCR). Immunofluorescence staining was used to detect the proportion of Mi/Mϕ in contact with apoptotic neurons, as well as neuronal damage. Results ASK1 was highly expressed in Mi/Mϕ during the acute phase of epilepsy. Conditional knockout of ASK1 in Mi/Mϕ markedly reduced the frequency of seizures in the acute phase and the frequency of spontaneous recurrent seizures (SRSs) in the chronic phase. In addition, ASK1 conditional knockout mice displayed long-term neurobehavioral improvements during the Y maze test and the three-chamber social novelty preference test. ASK1 selective knockout mitigated neuroinflammation, as evidenced by lower levels of Iba1+/CD16+ proinflammatory Mi/Mϕ. Conditional knockout of ASK1 increased Mi/Mϕ proportion in contact with apoptotic neurons. Neuronal loss was partially restored by ASK1 selective knockout. Conclusion Conditional knockout of ASK1 in Mi/Mϕ reduced seizure severity, neurobehavioral impairments, and histological damage, at least via inhibiting proinflammatory microglia/macrophages responses. ASK1 in microglia/macrophages is a potential therapeutic target for inflammatory responses in epilepsy.

Recent advances in machine learning, from large-scale optimization to building deep neural networks, are increasingly being applied in the emerging field of computational sensing and imaging [...]

Classification is a common objective when analyzing hyperspectral images, where each pixel is assigned to a predefined label. Deep learning-based algorithms have been introduced in the remote-sensing community successfully in the past decade and have achieved significant performance improvements compared with conventional models. However, research on the extraction of sequential features utilizing a single image, instead of multi-temporal images still needs to be further investigated. In this paper, a novel strategy for constructing sequential features from a single image in long short-term memory (LSTM) is proposed. Two pixel-wise-based similarity measurements, including pixel-matching (PM) and block-matching (BM), are employed for the selection of sequence candidates from the whole image. Then, the sequential structure of a given pixel can be constructed as the input of LSTM by utilizing the first several matching pixels with high similarities. The resulting PM-based LSTM and BM-based LSTM are appealing, as all pixels in the whole image are taken into consideration when calculating the similarity. In addition, BM-based LSTM also utilizes local spectral-spatial information that has already shown its effectiveness in hyperspectral image classification. Two common distance measures, Euclidean distance and spectral angle mapping, are also investigated in this paper. Experiments with two benchmark hyperspectral images demonstrate that the proposed methods achieve marked improvements in classification performance relative to the other state-of-the-art methods considered. For instance, the highest overall accuracy achieved on the Pavia University image is 96.20% (using both BM-based LSTM and spectral angle mapping), which is an improvement compared with 84.45% overall accuracy generated by 1D convolutional neural networks.