arXiv subjects

Hamid R. Tizhoosh

Publications and source records attributed to Hamid R. Tizhoosh.

At least 19 recordsLinked to original sources

arXiv2026

Beyond the Failures: Rethinking Foundation Models in Pathology

Despite their successes in vision and language, foundation models have stumbled in pathology, revealing low accuracy, instability, and heavy computational demands. These shortcomings stem not from tuning problems but from deeper conceptual mismatches: dense embeddings cannot represent the combinatorial richness of tissue, and current architectures inherit flaws in self-supervision, patch design, and noise-fragile pretraining. Biological complexity and limited domain innovation further widen the gap. The evidence is clear-pathology requires models explicitly designed for biological images rather than adaptations of large-scale natural-image methods whose assumptions do not hold for tissue.

cs.AI↗

arXiv2023

A Preliminary Investigation into Search and Matching for Tumour Discrimination in WHO Breast Taxonomy Using Deep Networks

Breast cancer is one of the most common cancers affecting women worldwide. They include a group of malignant neoplasms with a variety of biological, clinical, and histopathological characteristics. There are more than 35 different histological forms of breast lesions that can be classified and diagnosed histologically according to cell morphology, growth, and architecture patterns. Recently, deep learning, in the field of artificial intelligence, has drawn a lot of attention for the computerized representation of medical images. Searchable digital atlases can provide pathologists with patch matching tools allowing them to search among evidently diagnosed and treated archival cases, a technology that may be regarded as computational second opinion. In this study, we indexed and analyzed the WHO breast taxonomy (Classification of Tumours 5th Ed.) spanning 35 tumour types. We visualized all tumour types using deep features extracted from a state-of-the-art deep learning model, pre-trained on millions of diagnostic histopathology images from the TCGA repository. Furthermore, we test the concept of a digital "atlas" as a reference for search and matching with rare test cases. The patch similarity search within the WHO breast taxonomy data reached over 88% accuracy when validating through "majority vote" and more than 91% accuracy when validating using top-n tumour types. These results show for the first time that complex relationships among common and rare breast lesions can be investigated using an indexed digital archive.

eess.IV↗

arXiv2023

Decentralized Federated Learning through Proxy Model Sharing

Institutions in highly regulated domains such as finance and healthcare often have restrictive rules around data sharing. Federated learning is a distributed learning framework that enables multi-institutional collaborations on decentralized data with improved protection for each collaborator's data privacy. In this paper, we propose a communication-efficient scheme for decentralized federated learning called ProxyFL, or proxy-based federated learning. Each participant in ProxyFL maintains two models, a private model, and a publicly shared proxy model designed to protect the participant's privacy. Proxy models allow efficient information exchange among participants without the need of a centralized server. The proposed method eliminates a significant limitation of canonical federated learning by allowing model heterogeneity; each participant can have a private model with any architecture. Furthermore, our protocol for communication by proxy leads to stronger privacy guarantees using differential privacy analysis. Experiments on popular image datasets, and a cancer diagnostic problem using high-quality gigapixel histology whole slide images, show that ProxyFL can outperform existing alternatives with much less communication overhead and stronger privacy.

cs.LG↗

arXiv2021

Histogram of Cell Types: Deep Learning for Automated Bone Marrow Cytology

Bone marrow cytology is required to make a hematological diagnosis, influencing critical clinical decision points in hematology. However, bone marrow cytology is tedious, limited to experienced reference centers and associated with high inter-observer variability. This may lead to a delayed or incorrect diagnosis, leaving an unmet need for innovative supporting technologies. We have developed the first ever end-to-end deep learning-based technology for automated bone marrow cytology. Starting with a bone marrow aspirate digital whole slide image, our technology rapidly and automatically detects suitable regions for cytology, and subsequently identifies and classifies all bone marrow cells in each region. This collective cytomorphological information is captured in a novel representation called Histogram of Cell Types (HCT) quantifying bone marrow cell class probability distribution and acting as a cytological "patient fingerprint". The approach achieves high accuracy in region detection (0.97 accuracy and 0.99 ROC AUC), and cell detection and cell classification (0.75 mAP, 0.78 F1-score, Log-average miss rate of 0.31). HCT has potential to revolutionize hematopathology diagnostic workflows, leading to more cost-effective, accurate diagnosis and opening the door to precision medicine.

eess.IV↗

arXiv2021

Searching for Pneumothorax in X-Ray Images Using Autoencoded Deep Features

Fast diagnosis and treatment of pneumothorax, a collapsed or dropped lung, is crucial to avoid fatalities. Pneumothorax is typically detected on a chest X-ray image through visual inspection by experienced radiologists. However, the detection rate is quite low. Therefore, there is a strong need for automated detection systems to assist radiologists. Despite the high accuracy levels generally reported for deep learning classifiers in many applications, they may not be useful in clinical practice due to the lack of large number of high-quality labelled images as well as a lack of interpretation possibility. Alternatively, searching in the archive of past cases to find matching images may serve as a 'virtual second opinion' through accessing the metadata of matched evidently diagnosed cases. To use image search as a triaging/diagnosis tool, all chest X-ray images must first be tagged with identifiers, i.e., deep features. Then, given a query chest X-ray image, the majority vote among the top k retrieved images can provide a more explainable output. While image search can be clinically more viable, its detection performance needs to be investigated at a scale closer to real-world practice. We combined 3 public datasets to assemble a repository with more than 550,000 chest X-ray images. We developed the Autoencoding Thorax Net (short AutoThorax-Net) for image search in chest radiographs compressing three inputs: the left chest side, the flipped right side, and the entire chest image. Experimental results show that image search based on AutoThorax-Net features can achieve high identification rates providing a path towards real-world deployment. We achieved 92% AUC accuracy for a semi-automated search in 194,608 images (pneumothorax and normal) and 82% AUC accuracy for fully automated search in 551,383 images (normal, pneumothorax and many other chest diseases).

eess.IV↗

arXiv2020

Forming Local Intersections of Projections for Classifying and Searching Histopathology Images

In this paper, we propose a novel image descriptor called Forming Local Intersections of Projections (FLIP) and its multi-resolution version (mFLIP) for representing histopathology images. The descriptor is based on the Radon transform wherein we apply parallel projections in small local neighborhoods of gray-level images. Using equidistant projection directions in each window, we extract unique and invariant characteristics of the neighborhood by taking the intersection of adjacent projections. Thereafter, we construct a histogram for each image, which we call the FLIP histogram. Various resolutions provide different FLIP histograms which are then concatenated to form the mFLIP descriptor. Our experiments included training common networks from scratch and fine-tuning pre-trained networks to benchmark our proposed descriptor. Experiments are conducted on the publicly available dataset KIMIA Path24 and KIMIA Path960. For both of these datasets, FLIP and mFLIP descriptors show promising results in all experiments.Using KIMIA Path24 data, FLIP outperformed non-fine-tuned Inception-v3 and fine-tuned VGG16 and mFLIP outperformed fine-tuned Inception-v3 in feature extracting.

cs.CV↗

arXiv2020

Representation Learning of Histopathology Images using Graph Neural Networks

Representation learning for Whole Slide Images (WSIs) is pivotal in developing image-based systems to achieve higher precision in diagnostic pathology. We propose a two-stage framework for WSI representation learning. We sample relevant patches using a color-based method and use graph neural networks to learn relations among sampled patches to aggregate the image information into a single vector representation. We introduce attention via graph pooling to automatically infer patches with higher relevance. We demonstrate the performance of our approach for discriminating two sub-types of lung cancers, Lung Adenocarcinoma (LUAD) & Lung Squamous Cell Carcinoma (LUSC). We collected 1,026 lung cancer WSIs with the 40$\times$ magnification from The Cancer Genome Atlas (TCGA) dataset, the largest public repository of histopathology images and achieved state-of-the-art accuracy of 88.8% and AUC of 0.89 on lung cancer sub-type classification by extracting features from a pre-trained DenseNet

eess.IV↗

arXiv2020

Studying the Effect of Digital Stain Separation of Histopathology Images on Image Search Performance

Due to recent advances in technology, digitized histopathology images are now widely available for both clinical and research purposes. Accordingly, research into computerized image analysis algorithms for digital histopathology images has been progressing rapidly. In this work, we focus on image retrieval for digital histopathology images. Image retrieval algorithms can be used to find similar images and can assist pathologists in making quick and accurate diagnoses. Histopathology images are typically stained with dyes to highlight features of the tissue, and as such, an image analysis algorithm for histopathology should be able to process colour images and determine relevant information from the stain colours present. In this study, we are interested in the effect that stain separation into their individual stain components has on image search performance. To this end, we implement a basic k-nearest neighbours (kNN) search algorithm on histopathology images from two publicly available data sets (IDC and BreakHis) which are: a) converted to greyscale, b) digitally stain-separated and c) the original RGB colour images. The results of this study show that using H\&E separated images yields search accuracies within one or two percent of those obtained with original RGB images, and that superior performance is observed using the H\&E images in most scenarios we tested.

eess.IV↗

arXiv2019

Automatic Classification of Pathology Reports using TF-IDF Features

A Pathology report is arguably one of the most important documents in medicine containing interpretive information about the visual findings from the patient's biopsy sample. Each pathology report has a retention period of up to 20 years after the treatment of a patient. Cancer registries process and encode high volumes of free-text pathology reports for surveillance of cancer and tumor diseases all across the world. In spite of their extremely valuable information they hold, pathology reports are not used in any systematic way to facilitate computational pathology. Therefore, in this study, we investigate automated machine-learning techniques to identify/predict the primary diagnosis (based on ICD-O code) from pathology reports. We performed experiments by extracting the TF-IDF features from the reports and classifying them using three different methods---SVM, XGBoost, and Logistic Regression. We constructed a new dataset with 1,949 pathology reports arranged into 37 ICD-O categories, collected from four different primary sites, namely lung, kidney, thymus, and testis. The reports were manually transcribed into text format after collecting them as PDF files from NCI Genomic Data Commons public dataset. We subsequently pre-processed the reports by removing irrelevant textual artifacts produced by OCR software. The highest classification accuracy we achieved was 92\% using XGBoost classifier on TF-IDF feature vectors, the linear SVM scored 87\% accuracy. Furthermore, the study shows that TF-IDF vectors are suitable for highlighting the important keywords within a report which can be helpful for the cancer research and diagnostic workflow. The results are encouraging in demonstrating the potential of machine learning methods for classification and encoding of pathology reports.

cs.CL↗

arXiv2018

A Dataset and Preliminary Results for Umpire Pose Detection Using SVM Classification of Deep Features

In recent years, there has been increased interest in video summarization and automatic sports highlights generation. In this work, we introduce a new dataset, called SNOW, for umpire pose detection in the game of cricket. The proposed dataset is evaluated as a preliminary aid for developing systems to automatically generate cricket highlights. In cricket, the umpire has the authority to make important decisions about events on the field. The umpire signals important events using unique hand signals and gestures. We identify four such events for classification namely SIX, NO BALL, OUT and WIDE based on detecting the pose of the umpire from the frames of a cricket video. Pre-trained convolutional neural networks such as Inception V3 and VGG19 net-works are selected as primary candidates for feature extraction. The results are obtained using a linear SVM classifier. The highest classification performance was achieved for the SVM trained on features extracted from the VGG19 network. The preliminary results suggest that the proposed system is an effective solution for the application of cricket highlights generation.

cs.CV↗

arXiv2018

Comparing LBP, HOG and Deep Features for Classification of Histopathology Images

Medical image analysis has become a topic under the spotlight in recent years. There is a significant progress in medical image research concerning the usage of machine learning. However, there are still numerous questions and problems awaiting answers and solutions, respectively. In the present study, comparison of three classification models is conducted using features extracted using local binary patterns, the histogram of gradients, and a pre-trained deep network. Three common image classification methods, including support vector machines, decision trees, and artificial neural networks are used to classify feature vectors obtained by different feature extractors. We use KIMIA Path960, a publicly available dataset of $960$ histopathology images extracted from $20$ different tissue scans to test the accuracy of classification and feature extractions models used in the study, specifically for the histopathology images. SVM achieves the highest accuracy of $90.52\%$ using local binary patterns as features which surpasses the accuracy obtained by deep features, namely $81.14\%$.

eess.IV↗

arXiv2017

Opposition based Ensemble Micro Differential Evolution

Differential evolution (DE) algorithm with a small population size is called Micro-DE (MDE). A small population size decreases the computational complexity but also reduces the exploration ability of DE by limiting the population diversity. In this paper, we propose the idea of combining ensemble mutation scheme selection and opposition-based learning concepts to enhance the diversity of population in MDE at mutation and selection stages. The proposed algorithm enhances the diversity of population by generating a random mutation scale factor per individual and per dimension, randomly assigning a mutation scheme to each individual in each generation, and diversifying individuals selection using opposition-based learning. This approach is easy to implement and does not require the setting of mutation scheme selection and mutation scale factor. Experimental results are conducted for a variety of objective functions with low and high dimensionality on the CEC Black- Box Optimization Benchmarking 2015 (CEC-BBOB 2015). The results show superior performance of the proposed algorithm compared to the other micro-DE algorithms.

cs.NE↗

arXiv2017

Tumour Ellipsification in Ultrasound Images for Treatment Prediction in Breast Cancer

Recent advances in using quantitative ultrasound (QUS) methods have provided a promising framework to non-invasively and inexpensively monitor or predict the effectiveness of therapeutic cancer responses. One of the earliest steps in using QUS methods is contouring a region of interest (ROI) inside the tumour in ultrasound B-mode images. While manual segmentation is a very time-consuming and tedious task for human experts, auto-contouring is also an extremely difficult task for computers due to the poor quality of ultrasound B-mode images. However, for the purpose of cancer response prediction, a rough boundary of the tumour as an ROI is only needed. In this research, a semi-automated tumour localization approach is proposed for ROI estimation in ultrasound B-mode images acquired from patients with locally advanced breast cancer (LABC). The proposed approach comprised several modules, including 1) feature extraction using keypoint descriptors, 2) augmenting the feature descriptors with the distance of the keypoints to the user-input pixel as the centre of the tumour, 3) supervised learning using a support vector machine (SVM) to classify keypoints as "tumour" or "non-tumour", and 4) computation of an ellipse as an outline of the ROI representing the tumour. Experiments with 33 B-mode images from 10 LABC patients yielded promising results with an accuracy of 76.7% based on the Dice coefficient performance measure. The results demonstrated that the proposed method can potentially be used as the first stage in a computer-assisted cancer response prediction system for semi-automated contouring of breast tumours.

cs.CV↗

arXiv2016

Diversity Enhancement for Micro-Differential Evolution

The differential evolution (DE) algorithm suffers from high computational time due to slow nature of evaluation. In contrast, micro-DE (MDE) algorithms employ a very small population size, which can converge faster to a reasonable solution. However, these algorithms are vulnerable to a premature convergence as well as to high risk of stagnation. In this paper, MDE algorithm with vectorized random mutation factor (MDEVM) is proposed, which utilizes the small size population benefit while empowers the exploration ability of mutation factor through randomizing it in the decision variable level. The idea is supported by analyzing mutation factor using Monte-Carlo based simulations. To facilitate the usage of MDE algorithms with very-small population sizes, new mutation schemes for population sizes less than four are also proposed. Furthermore, comprehensive comparative simulations and analysis on performance of the MDE algorithms over various mutation schemes, population sizes, problem types (i.e. uni-modal, multi-modal, and composite), problem dimensionalities, and mutation factor ranges are conducted by considering population diversity analysis for stagnation and trapping in local optimum situations. The studies are conducted on 28 benchmark functions provided for the IEEE CEC-2013 competition. Experimental results demonstrate high performance and convergence speed of the proposed MDEVM algorithm.

cs.NE↗

arXiv2016

Barcodes for Medical Image Retrieval Using Autoencoded Radon Transform

Using content-based binary codes to tag digital images has emerged as a promising retrieval technology. Recently, Radon barcodes (RBCs) have been introduced as a new binary descriptor for image search. RBCs are generated by binarization of Radon projections and by assembling them into a vector, namely the barcode. A simple local thresholding has been suggested for binarization. In this paper, we put forward the idea of "autoencoded Radon barcodes". Using images in a training dataset, we autoencode Radon projections to perform binarization on outputs of hidden layers. We employed the mini-batch stochastic gradient descent approach for the training. Each hidden layer of the autoencoder can produce a barcode using a threshold determined based on the range of the logistic function used. The compressing capability of autoencoders apparently reduces the redundancies inherent in Radon projections leading to more accurate retrieval results. The IRMA dataset with 14,410 x-ray images is used to validate the performance of the proposed method. The experimental results, containing comparison with RBCs, SURF and BRISK, show that autoencoded Radon barcode (ARBC) has the capacity to capture important information and to learn richer representations resulting in lower retrieval errors for image retrieval measured with the accuracy of the first hit only.

cs.CV↗

arXiv2016

Automated Resolution Selection for Image Segmentation

It is well-known in image processing that computational cost increases rapidly with the number and dimensions of the images to be processed. Several fields, such as medical imaging, routinely use numerous very large images, which might also be 3D and/or captured at several frequency bands, all adding to the computational expense. Multiresolution analysis is a method of increasing the efficiency of the segmentation process. One multiresolution approach is the coarse-to-fine segmentation strategy, whereby the segmentation starts at a coarse resolution and is then fine-tuned during subsequent steps. The starting resolution for segmentation is generally selected arbitrarily with no clear selection criteria. The research reported in this paper showed that starting from different resolutions for image segmentation results in different accuracies and computational times, even for images of the same category (depicting similar scenes or objects). An automated method for resolution selection for an input image would thus be beneficial. This paper introduces a framework for the automated selection of the best resolution for image segmentation. We propose a measure for defining the best resolution based on user/system criteria, offering a trade-off between accuracy and computation time. A learning approach is then introduced for the selection of the resolution, whereby extracted image features are mapped to the previously determined best resolution. In the learning process, class (i.e., resolution) distribution is generally imbalanced, making effective learning from the data difficult. Experiments conducted with three datasets using two different segmentation algorithms show that the resolutions selected through learning enable much faster segmentation than the original ones, while retaining at least the original accuracy.

cs.CV↗

arXiv2016

Gabor Barcodes for Medical Image Retrieval

In recent years, advances in medical imaging have led to the emergence of massive databases, containing images from a diverse range of modalities. This has significantly heightened the need for automated annotation of the images on one side, and fast and memory-efficient content-based image retrieval systems on the other side. Binary descriptors have recently gained more attention as a potential vehicle to achieve these goals. One of the recently introduced binary descriptors for tagging of medical images are Radon barcodes (RBCs) that are driven from Radon transform via local thresholding. Gabor transform is also a powerful transform to extract texture-based information. Gabor features have exhibited robustness against rotation, scale, and also photometric disturbances, such as illumination changes and image noise in many applications. This paper introduces Gabor Barcodes (GBCs), as a novel framework for the image annotation. To find the most discriminative GBC for a given query image, the effects of employing Gabor filters with different parameters, i.e., different sets of scales and orientations, are investigated, resulting in different barcode lengths and retrieval performances. The proposed method has been evaluated on the IRMA dataset with 193 classes comprising of 12,677 x-ray images for indexing, and 1,733 x-rays images for testing. A total error score as low as $351$ ($\approx 80\%$ accuracy for the first hit) was achieved.

cs.CV↗

arXiv2016

Binary Codes for Tagging X-Ray Images via Deep De-Noising Autoencoders

A Content-Based Image Retrieval (CBIR) system which identifies similar medical images based on a query image can assist clinicians for more accurate diagnosis. The recent CBIR research trend favors the construction and use of binary codes to represent images. Deep architectures could learn the non-linear relationship among image pixels adaptively, allowing the automatic learning of high-level features from raw pixels. However, most of them require class labels, which are expensive to obtain, particularly for medical images. The methods which do not need class labels utilize a deep autoencoder for binary hashing, but the code construction involves a specific training algorithm and an ad-hoc regularization technique. In this study, we explored using a deep de-noising autoencoder (DDA), with a new unsupervised training scheme using only backpropagation and dropout, to hash images into binary codes. We conducted experiments on more than 14,000 x-ray images. By using class labels only for evaluating the retrieval results, we constructed a 16-bit DDA and a 512-bit DDA independently. Comparing to other unsupervised methods, we succeeded to obtain the lowest total error by using the 512-bit codes for retrieval via exhaustive search, and speed up 9.27 times with the use of the 16-bit codes while keeping a comparable total error. We found that our new training scheme could reduce the total retrieval error significantly by 21.9%. To further boost the image retrieval performance, we developed Radon Autoencoder Barcode (RABC) which are learned from the Radon projections of images using a de-noising autoencoder. Experimental results demonstrated its superior performance in retrieval when it was combined with DDA binary codes.

cs.CV↗