Deep learning-based melanoma classification with dermoscopic images has recently shown great potential in automatic early-stage melanoma diagnosis. However, limited by the significant data imbalance and obvious extraneous artifacts, i.e., the hair and ruler markings, discriminative feature extraction from dermoscopic images is very challenging. In this study, we seek to resolve these problems respectively towards better representation learning for lesion features. Specifically, a GAN-based data augmentation (GDA) strategy is adapted to generate synthetic melanoma-positive images, in conjunction with the proposed implicit hair denoising (IHD) strategy. Wherein the hair-related representations are implicitly disentangled via an auxiliary classifier network and reversely sent to the melanoma-feature extraction backbone for better melanoma-specific representation learning. Furthermore, to train the IHD module, the hair noises are additionally labeled on the ISIC2020 dataset, making it the first large-scale dermoscopic dataset with annotation of hair-like artifacts. Extensive experiments demonstrate the superiority of the proposed framework as well as the effectiveness of each component. The improved dataset publicly avaliable at https://github.com/kirtsy/DermoscopicDataset.

Bacterial infections are responsible for high mortality worldwide. Antimicrobial resistance underlying the infection, and multifaceted patient's clinical status can hamper the correct choice of antibiotic treatment. Randomized clinical trials provide average treatment effect estimates but are not ideal for risk stratification and optimization of therapeutic choice, i.e., individualized treatment effects (ITE). Here, we leverage large-scale electronic health record data, collected from Southern US academic clinics, to emulate a clinical trial, i.e., 'target trial', and develop a machine learning model of mortality prediction and ITE estimation for patients diagnosed with acute bacterial skin and skin structure infection (ABSSSI) due to methicillin-resistant Staphylococcus aureus (MRSA). ABSSSI-MRSA is a challenging condition with reduced treatment options - vancomycin is the preferred choice, but it has non-negligible side effects. First, we use propensity score matching to emulate the trial and create a treatment randomized (vancomycin vs. other antibiotics) dataset. Next, we use this data to train various machine learning methods (including boosted/LASSO logistic regression, support vector machines, and random forest) and choose the best model in terms of area under the receiver characteristic (AUC) through bootstrap validation. Lastly, we use the models to calculate ITE and identify possible averted deaths by therapy change. The out-of-bag tests indicate that SVM and RF are the most accurate, with AUC of 81% and 78%, respectively, but BLR/LASSO is not far behind (76%). By calculating the counterfactuals using the BLR/LASSO, vancomycin increases the risk of death, but it shows a large variation (odds ratio 1.2, 95% range 0.4-3.8) and the contribution to outcome probability is modest. Instead, the RF exhibits stronger changes in ITE, suggesting more complex treatment heterogeneity.

A recent trend in artificial intelligence is the use of pretrained models for language and vision tasks, which have achieved extraordinary performance but also puzzling failures. Probing these models' abilities in diverse ways is therefore critical to the field. In this paper, we explore the reliability of models, where we define a reliable model as one that not only achieves strong predictive performance but also performs well consistently over many decision-making tasks involving uncertainty (e.g., selective prediction, open set recognition), robust generalization (e.g., accuracy and proper scoring rules such as log-likelihood on in- and out-of-distribution datasets), and adaptation (e.g., active learning, few-shot uncertainty). We devise 10 types of tasks over 40 datasets in order to evaluate different aspects of reliability on both vision and language domains. To improve reliability, we developed ViT-Plex and T5-Plex, pretrained large model extensions for vision and language modalities, respectively. Plex greatly improves the state-of-the-art across reliability tasks, and simplifies the traditional protocol as it improves the out-of-the-box performance and does not require designing scores or tuning the model for each task. We demonstrate scaling effects over model sizes up to 1B parameters and pretraining dataset sizes up to 4B examples. We also demonstrate Plex's capabilities on challenging tasks including zero-shot open set recognition, active learning, and uncertainty in conversational language understanding.

To control boll weevil (Anthonomus grandis L.) pest re-infestation in cotton fields, the current practices of volunteer cotton (VC) (Gossypium hirsutum L.) plant detection in fields of rotation crops like corn (Zea mays L.) and sorghum (Sorghum bicolor L.) involve manual field scouting at the edges of fields. This leads to many VC plants growing in the middle of fields remain undetected that continue to grow side by side along with corn and sorghum. When they reach pinhead squaring stage (5-6 leaves), they can serve as hosts for the boll weevil pests. Therefore, it is required to detect, locate and then precisely spot-spray them with chemicals. In this paper, we present the application of YOLOv5m on radiometrically and gamma-corrected low resolution (1.2 Megapixel) multispectral imagery for detecting and locating VC plants growing in the middle of tasseling (VT) growth stage of cornfield. Our results show that VC plants can be detected with a mean average precision (mAP) of 79% and classification accuracy of 78% on images of size 1207 x 923 pixels at an average inference speed of nearly 47 frames per second (FPS) on NVIDIA Tesla P100 GPU-16GB and 0.4 FPS on NVIDIA Jetson TX2 GPU. We also demonstrate the application of a customized unmanned aircraft systems (UAS) for spot-spray applications based on the developed computer vision (CV) algorithm and how it can be used for near real-time detection and mitigation of VC plants growing in corn fields for efficient management of the boll weevil pests.

Maintaining an up-to-date map to reflect recent changes in the scene is very important, particularly in situations involving repeated traversals by a robot operating in an environment over an extended period. Undetected changes may cause a deterioration in map quality, leading to poor localization, inefficient operations, and lost robots. Volumetric methods, such as truncated signed distance functions (TSDFs), have quickly gained traction due to their real-time production of a dense and detailed map, though map updating in scenes that change over time remains a challenge. We propose a framework that introduces a novel probabilistic object state representation to track object pose changes in semi-static scenes. The representation jointly models a stationarity score and a TSDF change measure for each object. A Bayesian update rule that incorporates both geometric and semantic information is derived to achieve consistent online map maintenance. To extensively evaluate our approach alongside the state-of-the-art, we release a novel real-world dataset in a warehouse environment. We also evaluate on the public ToyCar dataset. Our method outperforms state-of-the-art methods on the reconstruction quality of semi-static environments.

Contrastive learning is a representation learning method performed by contrasting a sample to other similar samples so that they are brought closely together, forming clusters in the feature space. The learning process is typically conducted using a two-stage training architecture, and it utilizes the contrastive loss (CL) for its feature learning. Contrastive learning has been shown to be quite successful in handling imbalanced datasets, in which some classes are overrepresented while some others are underrepresented. However, previous studies have not specifically modified CL for imbalanced datasets. In this work, we introduce an asymmetric version of CL, referred to as ACL, in order to directly address the problem of class imbalance. In addition, we propose the asymmetric focal contrastive loss (AFCL) as a further generalization of both ACL and focal contrastive loss (FCL). Results on the FMNIST and ISIC 2018 imbalanced datasets show that AFCL is capable of outperforming CL and FCL in terms of both weighted and unweighted classification accuracies. In the appendix, we provide a full axiomatic treatment on entropy, along with complete proofs.

The use of machine learning (ML) methods for prediction and forecasting has become widespread across the quantitative sciences. However, there are many known methodological pitfalls, including data leakage, in ML-based science. In this paper, we systematically investigate reproducibility issues in ML-based science. We show that data leakage is indeed a widespread problem and has led to severe reproducibility failures. Specifically, through a survey of literature in research communities that adopted ML methods, we find 17 fields where errors have been found, collectively affecting 329 papers and in some cases leading to wildly overoptimistic conclusions. Based on our survey, we present a fine-grained taxonomy of 8 types of leakage that range from textbook errors to open research problems. We argue for fundamental methodological changes to ML-based science so that cases of leakage can be caught before publication. To that end, we propose model info sheets for reporting scientific claims based on ML models that would address all types of leakage identified in our survey. To investigate the impact of reproducibility errors and the efficacy of model info sheets, we undertake a reproducibility study in a field where complex ML models are believed to vastly outperform older statistical models such as Logistic Regression (LR): civil war prediction. We find that all papers claiming the superior performance of complex ML models compared to LR models fail to reproduce due to data leakage, and complex ML models don't perform substantively better than decades-old LR models. While none of these errors could have been caught by reading the papers, model info sheets would enable the detection of leakage in each case.

The cotton boll weevil, Anthonomus grandis Boheman is a serious pest to the U.S. cotton industry that has cost more than 16 billion USD in damages since it entered the United States from Mexico in the late 1800s. This pest has been nearly eradicated; however, southern part of Texas still faces this issue and is always prone to the pest reinfestation each year due to its sub-tropical climate where cotton plants can grow year-round. Volunteer cotton (VC) plants growing in the fields of inter-seasonal crops, like corn, can serve as hosts to these pests once they reach pin-head square stage (5-6 leaf stage) and therefore need to be detected, located, and destroyed or sprayed . In this paper, we present a study to detect VC plants in a corn field using YOLOv3 on three band aerial images collected by unmanned aircraft system (UAS). The two-fold objectives of this paper were : (i) to determine whether YOLOv3 can be used for VC detection in a corn field using RGB (red, green, and blue) aerial images collected by UAS and (ii) to investigate the behavior of YOLOv3 on images at three different scales (320 x 320, S1; 416 x 416, S2; and 512 x 512, S3 pixels) based on average precision (AP), mean average precision (mAP) and F1-score at 95% confidence level. No significant differences existed for mAP among the three scales, while a significant difference was found for AP between S1 and S3 (p = 0.04) and S2 and S3 (p = 0.02). A significant difference was also found for F1-score between S2 and S3 (p = 0.02). The lack of significant differences of mAP at all the three scales indicated that the trained YOLOv3 model can be used on a computer vision-based remotely piloted aerial application system (RPAAS) for VC detection and spray application in near real-time.

This paper proposes a low-cost and highly accurate ECG-monitoring system intended for personalized early arrhythmia detection for wearable mobile sensors. Earlier supervised approaches for personalized ECG monitoring require both abnormal and normal heartbeats for the training of the dedicated classifier. However, in a real-world scenario where the personalized algorithm is embedded in a wearable device, such training data is not available for healthy people with no cardiac disorder history. In this study, (i) we propose a null space analysis on the healthy signal space obtained via sparse dictionary learning, and investigate how a simple null space projection or alternatively regularized least squares-based classification methods can reduce the computational complexity, without sacrificing the detection accuracy, when compared to sparse representation-based classification. (ii) Then we introduce a sparse representation-based domain adaptation technique in order to project other existing users' abnormal and normal signals onto the new user's signal space, enabling us to train the dedicated classifier without having any abnormal heartbeat of the new user. Therefore, zero-shot learning can be achieved without the need for synthetic abnormal heartbeat generation. An extensive set of experiments performed on the benchmark MIT-BIH ECG dataset shows that when this domain adaptation-based training data generator is used with a simple 1-D CNN classifier, the method outperforms the prior work by a significant margin. (iii) Then, by combining (i) and (ii), we propose an ensemble classifier that further improves the performance. This approach for zero-shot arrhythmia detection achieves an average accuracy level of 98.2% and an F1-Score of 92.8%. Finally, a personalized energy-efficient ECG monitoring scheme is proposed using the above-mentioned innovations.

Accurate and efficient detection of ovarian cancer at early stages is critical to ensure proper treatments for patients. Among the first-line modalities investigated in studies of early diagnosis are features distilled from protein mass spectra. This method, however, considers only a specific subset of spectral responses and ignores the interplay among protein expression levels, which can also contain diagnostic information. We propose a new modality that automatically searches protein mass spectra for discriminatory features by considering the self-similar nature of the spectra. Self-similarity is assessed by taking a wavelet decomposition of protein mass spectra and estimating the rate of level-wise decay in the energies of the resulting wavelet coefficients. Level-wise energies are estimated in a robust manner using distance variance, and rates are estimated locally via a rolling window approach. This results in a collection of rates that can be used to characterize the interplay among proteins, which can be indicative of cancer presence. Discriminatory descriptors are then selected from these evolutionary rates and used as classifying features. The proposed wavelet-based features are used in conjunction with features proposed in the existing literature for early stage diagnosis of ovarian cancer using two datasets published by the American National Cancer Institute. Including the wavelet-based features from the new modality results in improvements in diagnostic performance for early-stage ovarian cancer detection. This demonstrates the ability of the proposed modality to characterize new ovarian cancer diagnostic information.