Eye-gaze tracking research offers significant promise in enhancing various healthcare-related tasks, above all in medical image analysis and interpretation. Eye tracking, a technology that monitors and records the movement of the eyes, provides valuable insights into human visual attention patterns. This technology can transform how healthcare professionals and medical specialists engage with and analyze diagnostic images, offering a more insightful and efficient approach to medical diagnostics. Hence, extracting meaningful features and insights from medical images by leveraging eye-gaze data improves our understanding of how radiologists and other medical experts monitor, interpret, and understand images for diagnostic purposes. Eye-tracking data, with intricate human visual attention patterns embedded, provides a bridge to integrating artificial intelligence (AI) development and human cognition. This integration allows novel methods to incorporate domain knowledge into machine learning (ML) and deep learning (DL) approaches to enhance their alignment with human-like perception and decision-making. Moreover, extensive collections of eye-tracking data have also enabled novel ML/DL methods to analyze human visual patterns, paving the way to a better understanding of human vision, attention, and cognition. This systematic review investigates eye-gaze tracking applications and methodologies for enhancing ML/DL algorithms for medical image analysis in depth.
Complete resection of malignant gliomas is hampered by the difficulty in distinguishing tumor cells at the infiltration zone. Fluorescence guidance with 5-ALA assists in reaching this goal. Using hyperspectral imaging, previous work characterized five fluorophores' emission spectra in most human brain tumors. In this paper, the effectiveness of these five spectra was explored for different tumor and tissue classification tasks in 184 patients (891 hyperspectral measurements) harboring low- (n=30) and high-grade gliomas (n=115), non-glial primary brain tumors (n=19), radiation necrosis (n=2), miscellaneous (n=10) and metastases (n=8). Four machine learning models were trained to classify tumor type, grade, glioma margins and IDH mutation. Using random forests and multi-layer perceptrons, the classifiers achieved average test accuracies of 84-87%, 96%, 86%, and 93% respectively. All five fluorophore abundances varied between tumor margin types and tumor grades (p < 0.01). For tissue type, at least four of the five fluorophore abundances were found to be significantly different (p < 0.01) between all classes. These results demonstrate the fluorophores' differing abundances in different tissue classes, as well as the value of the five fluorophores as potential optical biomarkers, opening new opportunities for intraoperative classification systems in fluorescence-guided neurosurgery.
Digital pathology based on whole slide images (WSIs) plays a key role in cancer diagnosis and clinical practice. Due to the high resolution of the WSI and the unavailability of patch-level annotations, WSI classification is usually formulated as a weakly supervised problem, which relies on multiple instance learning (MIL) based on patches of a WSI. In this paper, we aim to learn an optimal patch-level feature space by integrating prototype learning with MIL. To this end, we develop a Trainable Prototype enhanced deep MIL (TPMIL) framework for weakly supervised WSI classification. In contrast to the conventional methods which rely on a certain number of selected patches for feature space refinement, we softly cluster all the instances by allocating them to their corresponding prototypes. Additionally, our method is able to reveal the correlations between different tumor subtypes through distances between corresponding trained prototypes. More importantly, TPMIL also enables to provide a more accurate interpretability based on the distance of the instances from the trained prototypes which serves as an alternative to the conventional attention score-based interpretability. We test our method on two WSI datasets and it achieves a new SOTA. GitHub repository: https://github.com/LitaoYang-Jet/TPMIL
Whole Slide Images (WSIs) or histopathology images are used in digital pathology. WSIs pose great challenges to deep learning models for clinical diagnosis, owing to their size and lack of pixel-level annotations. With the recent advancements in computational pathology, newer multiple-instance learning-based models have been proposed. Multiple-instance learning for WSIs necessitates creating patches and uses the encoding of these patches for diagnosis. These models use generic pre-trained models (ResNet-50 pre-trained on ImageNet) for patch encoding. The recently proposed KimiaNet, a DenseNet121 model pre-trained on TCGA slides, is a domain-specific pre-trained model. This paper shows the effect of domain-specific pre-training on WSI classification. To investigate the impact of domain-specific pre-training, we considered the current state-of-the-art multiple-instance learning models, 1) CLAM, an attention-based model, and 2) TransMIL, a self-attention-based model, and evaluated the models' confidence and predictive performance in detecting primary brain tumors - gliomas. Domain-specific pre-training improves the confidence of the models and also achieves a new state-of-the-art performance of WSI-based glioma subtype classification, showing a high clinical applicability in assisting glioma diagnosis.
Pre-processing and Data Augmentation play an important role in Deep Convolutional Neural Networks (DCNN). Whereby several methods aim for standardization and augmentation of the dataset, we here propose a novel method aimed to feed DCNN with spherical space transformed input data that could better facilitate feature learning compared to standard Cartesian space images and volumes. In this work, the spherical coordinates transformation has been applied as a preprocessing method that, used in conjunction with normal MRI volumes, improves the accuracy of brain tumor segmentation and patient overall survival (OS) prediction on Brain Tumor Segmentation (BraTS) Challenge 2020 dataset. The LesionEncoder framework has been then applied to automatically extract features from DCNN models, achieving 0.586 accuracy of OS prediction on the validation data set, which is one of the best results according to BraTS 2020 leaderboard.
Magnetic Resonance Imaging (MRI) is used in everyday clinical practice to assess brain tumors. Several automatic or semi-automatic segmentation algorithms have been introduced to segment brain tumors and achieve an expert-like accuracy. Deep Convolutional Neural Networks (DCNN) have recently shown very promising results, however, DCNN models are still far from achieving clinically meaningful results mainly because of the lack of generalization of the models. DCNN models need large annotated datasets to achieve good performance. Models are often optimized on the domain dataset on which they have been trained, and then fail the task when the same model is applied to different datasets from different institutions. One of the reasons is due to the lack of data standardization to adjust for different models and MR machines. In this work, a 3D Spherical coordinates transform during the pre-processing phase has been hypothesized to improve DCNN models' accuracy and to allow more generalizable results even when the model is trained on small and heterogeneous datasets and translated into different domains. Indeed, the spherical coordinate system avoids several standardization issues since it works independently of resolution and imaging settings. Both Cartesian and spherical volumes were evaluated in two DCNN models with the same network structure using the BraTS 2019 dataset. The model trained on spherical transform pre-processed inputs resulted in superior performance over the Cartesian-input trained model on predicting gliomas' segmentation on tumor core and enhancing tumor classes (increase of 0.011 and 0.014 respectively on the validation dataset), achieving a further improvement in accuracy by merging the two models together. Furthermore, the spherical transform is not resolution-dependent and achieve same results on different input resolution.
Social media platforms now serve billions of users by providing convenient means of communication, content sharing and even payment between different users. Due to such convenient and anarchic nature, they have also been used rampantly to promote and conduct business activities between unregistered market participants without paying taxes. Tax authorities worldwide face difficulties in regulating these hidden economy activities by traditional regulatory means. This paper presents a machine learning based Regtech tool for international tax authorities to detect transaction-based tax evasion activities on social media platforms. To build such a tool, we collected a dataset of 58,660 Instagram posts and manually labelled 2,081 sampled posts with multiple properties related to transaction-based tax evasion activities. Based on the dataset, we developed a multi-modal deep neural network to automatically detect suspicious posts. The proposed model combines comments, hashtags and image modalities to produce the final output. As shown by our experiments, the combined model achieved an AUC of 0.808 and F1 score of 0.762, outperforming any single modality models. This tool could help tax authorities to identify audit targets in an efficient and effective manner, and combat social e-commerce tax evasion in scale.
We present a longitudinal MR simulation framework which simulates the future neurodegenerative progression by outputting the predicted follow-up MR image and the voxel-based morphometry (VBM) map. This framework expects the patients to have at least 2 historical MR images available. The longitudinal and cross-sectional VBM maps are extracted to measure the affinity between the target subject and the template subjects collected for simulation. Then the follow-up simulation is performed by resampling the latest available target MR image with a weighted sum of non-linear transformations derived from the best-matched templates. The leave-one-out strategy was used to compare different simulation methods. Compared to the state-of-the-art voxel-based method, our proposed morphometry-based simulation achieves better accuracy in most cases.