Nima Hatami

Nima Hatami

Computational pathology tasks have some unique characterises such as multi-gigapixel images, tedious and frequently uncertain annotations, and unavailability of large number of cases [13]. To address some of these issues, we present Deep Fastfood Ensembles - a simple, fast and yet effective method for combining deep features pooled from popular CNN models pre-trained on totally different source domains (e.g., natural image objects) and projected onto diverse dimensions using random projections, the so-called Fastfood [11]. The final ensemble output is obtained by a consensus of simple individual classifiers, each of which is trained on a different collection of random basis vectors. This offers extremely fast and yet effective solution, especially when training times and domain labels are of the essence. We demonstrate the effectiveness of the proposed deep fastfood ensemble learning as compared to the state-of-the-art methods for three different tasks in histopathology image analysis.

Ezequiel de la Rosa, Mauricio Reyes, Sook-Lei Liew et al.

Diffusion-weighted MRI (DWI) is essential for stroke diagnosis, treatment decisions, and prognosis. However, image and disease variability hinder the development of generalizable AI algorithms with clinical value. We address this gap by presenting a novel ensemble algorithm derived from the 2022 Ischemic Stroke Lesion Segmentation (ISLES) challenge. ISLES'22 provided 400 patient scans with ischemic stroke from various medical centers, facilitating the development of a wide range of cutting-edge segmentation algorithms by the research community. Through collaboration with leading teams, we combined top-performing algorithms into an ensemble model that overcomes the limitations of individual solutions. Our ensemble model achieved superior ischemic lesion detection and segmentation accuracy on our internal test set compared to individual algorithms. This accuracy generalized well across diverse image and disease variables. Furthermore, the model excelled in extracting clinical biomarkers. Notably, in a Turing-like test, neuroradiologists consistently preferred the algorithm's segmentations over manual expert efforts, highlighting increased comprehensiveness and precision. Validation using a real-world external dataset (N=1686) confirmed the model's generalizability. The algorithm's outputs also demonstrated strong correlations with clinical scores (admission NIHSS and 90-day mRS) on par with or exceeding expert-derived results, underlining its clinical relevance. This study offers two key findings. First, we present an ensemble algorithm (https://github.com/Tabrisrei/ISLES22_Ensemble) that detects and segments ischemic stroke lesions on DWI across diverse scenarios on par with expert (neuro)radiologists. Second, we show the potential for biomedical challenge outputs to extend beyond the challenge's initial objectives, demonstrating their real-world clinical applicability.

Nima Hatami, Mohsin Bilal, Nasir Rajpoot

The problem of recognizing various types of tissues present in multi-gigapixel histology images is an important fundamental pre-requisite for downstream analysis of the tumor microenvironment in a bottom-up analysis paradigm for computational pathology. In this paper, we propose a deep dictionary learning approach to solve the problem of tissue phenotyping in histology images. We propose deep Multi-Resolution Dictionary Learning (deepMRDL) in order to benefit from deep texture descriptors at multiple different spatial resolutions. We show the efficacy of the proposed approach through extensive experiments on four benchmark histology image datasets from different organs (colorectal cancer, breast cancer and breast lymphnodes) and tasks (namely, cancer grading, tissue phenotyping, tumor detection and tissue type classification). We also show that the proposed framework can employ most off-the-shelf CNNs models to generate effective deep texture descriptors.

Nima Hatami, Michaël Sdika, Hélène Ratiney

Magnetic resonance spectroscopy (MRS) is an important technique in biomedical research and it has the unique capability to give a non-invasive access to the biochemical content (metabolites) of scanned organs. In the literature, the quantification (the extraction of the potential biomarkers from the MRS signals) involves the resolution of an inverse problem based on a parametric model of the metabolite signal. However, poor signal-to-noise ratio (SNR), presence of the macromolecule signal or high correlation between metabolite spectral patterns can cause high uncertainties for most of the metabolites, which is one of the main reasons that prevents use of MRS in clinical routine. In this paper, quantification of metabolites in MR Spectroscopic imaging using deep learning is proposed. A regression framework based on the Convolutional Neural Networks (CNN) is introduced for an accurate estimation of spectral parameters. The proposed model learns the spectral features from a large-scale simulated data set with different variations of human brain spectra and SNRs. Experimental results demonstrate the accuracy of the proposed method, compared to state of the art standard quantification method (QUEST), on concentration of 20 metabolites and the macromolecule.

Nima Hatami, Michael Goldbaum

Artery and vein (AV) classification of retinal images is a key to necessary tasks, such as automated measurement of arteriolar-to-venular diameter ratio (AVR). This paper comprehensively reviews the state-of-the art in AV classification methods. To improve on previous methods, a new Local Bi- nary Pattern-based method (LBP) is proposed. Beside its simplicity, LBP is robust against low contrast and low quality fundus images; and it helps the process by including additional AV texture and shape information. Experimental results compare the performance of the new method with the state-of-the art; and also methods with different feature extraction and classification schemas.

Nima Hatami, Camelia Chira

Early classification of time-series data in a dynamic environment is a challenging problem of great importance in signal processing. This paper proposes a classifier architecture with a reject option capable of online decision making without the need to wait for the entire time series signal to be present. The main idea is to classify an odor/gas signal with an acceptable accuracy as early as possible. Instead of using posterior probability of a classifier, the proposed method uses the "agreement" of an ensemble to decide whether to accept or reject the candidate label. The introduced algorithm is applied to the bio-chemistry problem of odor classification to build a novel Electronic-Nose called Forefront-Nose. Experimental results on wind tunnel test-bed facility confirms the robustness of the forefront-nose compared to the standard classifiers from both earliness and recognition perspectives.

Nima Hatami, Camelia Chira, Giuliano Armano

Hierarchical Text Categorization (HTC) is becoming increasingly important with the rapidly growing amount of text data available in the World Wide Web. Among the different strategies proposed to cope with HTC, the Local Classifier per Node (LCN) approach attains good performance by mirroring the underlying class hierarchy while enforcing a top-down strategy in the testing step. However, the problem of embedding hierarchical information (parent-child relationship) to improve the performance of HTC systems still remains open. A confidence evaluation method for a selected route in the hierarchy is proposed to evaluate the reliability of the final candidate labels in an HTC system. In order to take into account the information embedded in the hierarchy, weight factors are used to take into account the importance of each level. An acceptance/rejection strategy in the top-down decision making process is proposed, which improves the overall categorization accuracy by rejecting a few percentage of samples, i.e., those with low reliability score. Experimental results on the Reuters benchmark dataset (RCV1- v2) confirm the effectiveness of the proposed method, compared to other state-of-the art HTC methods.