arXiv subjects

Mahdi S. Hosseini

Publications and source records attributed to Mahdi S. Hosseini.

46 records · Page 3Linked to original sources

arXiv2020

FocusLiteNN: High Efficiency Focus Quality Assessment for Digital Pathology

Out-of-focus microscopy lens in digital pathology is a critical bottleneck in high-throughput Whole Slide Image (WSI) scanning platforms, for which pixel-level automated Focus Quality Assessment (FQA) methods are highly desirable to help significantly accelerate the clinical workflows. Existing FQA methods include both knowledge-driven and data-driven approaches. While data-driven approaches such as Convolutional Neural Network (CNN) based methods have shown great promises, they are difficult to use in practice due to their high computational complexity and lack of transferability. Here, we propose a highly efficient CNN-based model that maintains fast computations similar to the knowledge-driven methods without excessive hardware requirements such as GPUs. We create a training dataset using FocusPath which encompasses diverse tissue slides across nine different stain colors, where the stain diversity greatly helps the model to learn diverse color spectrum and tissue structures. In our attempt to reduce the CNN complexity, we find with surprise that even trimming down the CNN to the minimal level, it still achieves a highly competitive performance. We introduce a novel comprehensive evaluation dataset, the largest of its kind, annotated and compiled from TCGA repository for model assessment and comparison, for which the proposed method exhibits superior precision-speed trade-off when compared with existing knowledge-driven and data-driven FQA approaches.

eess.IV↗

arXiv2020

AdaS: Adaptive Scheduling of Stochastic Gradients

The choice of step-size used in Stochastic Gradient Descent (SGD) optimization is empirically selected in most training procedures. Moreover, the use of scheduled learning techniques such as Step-Decaying, Cyclical-Learning, and Warmup to tune the step-size requires extensive practical experience--offering limited insight into how the parameters update--and is not consistent across applications. This work attempts to answer a question of interest to both researchers and practitioners, namely \textit{"how much knowledge is gained in iterative training of deep neural networks?"} Answering this question introduces two useful metrics derived from the singular values of the low-rank factorization of convolution layers in deep neural networks. We introduce the notions of \textit{"knowledge gain"} and \textit{"mapping condition"} and propose a new algorithm called Adaptive Scheduling (AdaS) that utilizes these derived metrics to adapt the SGD learning rate proportionally to the rate of change in knowledge gain over successive iterations. Experimentation reveals that, using the derived metrics, AdaS exhibits: (a) faster convergence and superior generalization over existing adaptive learning methods; and (b) lack of dependence on a validation set to determine when to stop training. Code is available at \url{https://github.com/mahdihosseini/AdaS}.

cs.LG↗

arXiv2019

On the Closed Form Expression of Elementary Symmetric Polynomials and the Inverse of Vandermonde Matrix

Inverse Vandermonde matrix calculation is a long-standing problem to solve nonsingular linear system $Vc=b$ where the rows of a square matrix $V$ are constructed by progression of the power polynomials. It has many applications in scientific computing including interpolation, super-resolution, and construction of special matrices applied in cryptography. Despite its numerous applications, the matrix is highly ill-conditioned where specialized treatments are considered for approximation such as conversion to Cauchy matrix, spectral decomposition, and algorithmic tailoring of the numerical solutions. In this paper, we propose a generalized algorithm that takes arbitrary pairwise (non-repetitive) sample nodes for solving inverse Vandermonde matrix. This is done in two steps: first, a highly balanced recursive algorithm is introduced with $\mathcal{O}(N)$ complexity to solve the combinatorics summation of the elementary symmetric polynomials; and second, a closed-form solution is tailored for inverse Vandermonde where the matrix' elements utilize this recursive summation for the inverse calculations. The numerical stability and accuracy of the proposed inverse method is analyzed through the spectral decomposition of the Frobenius companion matrix that associates with the corresponding Vandermonde matrix. The results show significant improvement over the state-of-the-art solutions using specific nodes such as $N$th roots of unity defined on the complex plane. A basic application in one dimensional interpolation problem is considered to demonstrate the utility of the proposed method for super-resolved signals.

math.NA↗

arXiv2019

Convolutional Deblurring for Natural Imaging

In this paper, we propose a novel design of image deblurring in the form of one-shot convolution filtering that can directly convolve with naturally blurred images for restoration. The problem of optical blurring is a common disadvantage to many imaging applications that suffer from optical imperfections. Despite numerous deconvolution methods that blindly estimate blurring in either inclusive or exclusive forms, they are practically challenging due to high computational cost and low image reconstruction quality. Both conditions of high accuracy and high speed are prerequisites for high-throughput imaging platforms in digital archiving. In such platforms, deblurring is required after image acquisition before being stored, previewed, or processed for high-level interpretation. Therefore, on-the-fly correction of such images is important to avoid possible time delays, mitigate computational expenses, and increase image perception quality. We bridge this gap by synthesizing a deconvolution kernel as a linear combination of Finite Impulse Response (FIR) even-derivative filters that can be directly convolved with blurry input images to boost the frequency fall-off of the Point Spread Function (PSF) associated with the optical blur. We employ a Gaussian low-pass filter to decouple the image denoising problem for image edge deblurring. Furthermore, we propose a blind approach to estimate the PSF statistics for two Gaussian and Laplacian models that are common in many imaging pipelines. Thorough experiments are designed to test and validate the efficiency of the proposed method using 2054 naturally blurred images across six imaging applications and seven state-of-the-art deconvolution methods.

eess.IV↗

arXiv2019

Encoding Visual Sensitivity by MaxPol Convolution Filters for Image Sharpness Assessment

In this paper, we propose a novel design of Human Visual System (HVS) response in a convolution filter form to decompose meaningful features that are closely tied with image sharpness level. No-reference (NR) Image sharpness assessment (ISA) techniques have emerged as the standard of image quality assessment in diverse imaging applications. Despite their high correlation with subjective scoring, they are challenging for practical considerations due to high computational cost and lack of scalability across different image blurs. We bridge this gap by synthesizing the HVS response as a linear combination of Finite Impulse Response (FIR) derivative filters to boost the falloff of high band frequency magnitudes in natural imaging paradigm. The numerical implementation of the HVS filter is carried out with MaxPol filter library that can be arbitrarily set for any differential orders and cutoff frequencies to balance out the estimation of informative features and noise sensitivities. We then design an innovative NR-ISA metric called `HVS-MaxPol' that (a) requires minimal computational cost, (b) produce high correlation accuracy with image blurriness, and (c) scales to assess synthetic and natural image blur. Specifically, the synthetic blur images are constructed by blurring the raw images using Gaussian filter, while natural blur is observed from real-life application such as motion, out-of-focus, etc. Furthermore, we create a natural benchmark database in digital pathology for validation of image focus quality in whole slide imaging systems called `FocusPath' consisting of 864 blurred images. Thorough experiments are designed to test and validate the efficiency of HVS-MaxPol across different blur databases and state-of-the-art NR-ISA metrics. The experiment result indicates that our metric has the best overall performance with respect to speed, accuracy and scalability.

eess.IV↗

arXiv2018

Focus Quality Assessment of High-Throughput Whole Slide Imaging in Digital Pathology

One of the challenges facing the adoption of digital pathology workflows for clinical use is the need for automated quality control. As the scanners sometimes determine focus inaccurately, the resultant image blur deteriorates the scanned slide to the point of being unusable. Also, the scanned slide images tend to be extremely large when scanned at greater or equal 20X image resolution. Hence, for digital pathology to be clinically useful, it is necessary to use computational tools to quickly and accurately quantify the image focus quality and determine whether an image needs to be re-scanned. We propose a no-reference focus quality assessment metric specifically for digital pathology images, that operates by using a sum of even-derivative filter bases to synthesize a human visual system-like kernel, which is modeled as the inverse of the lens' point spread function. This kernel is then applied to a digital pathology image to modify high-frequency image information deteriorated by the scanner's optics and quantify the focus quality at the patch level. We show in several experiments that our method correlates better with ground-truth $z$-level data than other methods, and is more computationally efficient. We also extend our method to generate a local slide-level focus quality heatmap, which can be used for automated slide quality control, and demonstrate the utility of our method for clinical scan quality control by comparison with subjective slide quality scores.

eess.IV↗

arXiv2017

Finite Differences in Forward and Inverse Imaging Problems--MaxPol Design

A systematic and comprehensive framework for finite impulse response (FIR) lowpass/fullband derivative kernels is introduced in this paper. Closed form solutions of a number of derivative filters are obtained using the maximally flat technique to regulate the Fourier response of undetermined coefficients. The framework includes arbitrary parameter control methods that afford solutions for numerous differential orders, variable polynomial accuracy, centralized/staggered schemes, and arbitrary side-shift nodes for boundary formulation. Using the proposed framework four different derivative matrix operators are introduced and their numerical stability is analyzed by studying their eigenvalues distribution in the complex plane. Their utility is studied by considering two important image processing problems, namely gradient surface reconstruction and image stitching. Experimentation indicates that the new derivative matrices not only outperform commonly used method but provide useful insights to the numerical issues in these two applications.

math.NA↗

arXiv2014

High-Accuracy Total Variation for Compressed Video Sensing

Numerous total variation (TV) regularizers, engaged in image restoration problem, encode the gradients by means of simple $[-1,1]$ FIR filter. Despite its low computational processing, this filter severely deviates signal's high frequency components pertinent to edge/discontinuous information and cause several deficiency issues known as texture and geometric loss. This paper addresses this problem by proposing an alternative model to the TV regularization problem via high order accuracy differential FIR filters to preserve rapid transitions in signal recovery. A numerical encoding scheme is designed to extend the TV model into multidimensional representation (tensorial decomposition). We adopt this design to regulate the spatial and temporal redundancy in compressed video sensing problem to jointly recover frames from under-sampled measurements. We then seek the solution via alternating direction methods of multipliers and find a unique solution to quadratic minimization step with capability of handling different boundary conditions. The resulting algorithm uses much lower sampling rate and highly outperforms alternative state-of-the-art methods. This is evaluated both in terms of restoration accuracy and visual quality of the recovered frames.

math.OC↗

arXiv2012

Compressed Sensing Recoverability In Imaging Modalities

The paper introduces a framework for the recoverability analysis in compressive sensing for imaging applications such as CI cameras, rapid MRI and coded apertures. This is done using the fact that the Spherical Section Property (SSP) of a sensing matrix provides a lower bound for unique sparse recovery condition. The lower bound is evaluated for different sampling paradigms adopted from the aforementioned imaging modalities. In particular, a platform is provided to analyze the well-posedness of sub-sampling patterns commonly used in practical scenarios. The effectiveness of the various designed patterns for sparse image recovery is studied through numerical experiments.

cs.IT↗

arXiv2009

Pigment Melanin: Pattern for Iris Recognition

Recognition of iris based on Visible Light (VL) imaging is a difficult problem because of the light reflection from the cornea. Nonetheless, pigment melanin provides a rich feature source in VL, unavailable in Near-Infrared (NIR) imaging. This is due to biological spectroscopy of eumelanin, a chemical not stimulated in NIR. In this case, a plausible solution to observe such patterns may be provided by an adaptive procedure using a variational technique on the image histogram. To describe the patterns, a shape analysis method is used to derive feature-code for each subject. An important question is how much the melanin patterns, extracted from VL, are independent of iris texture in NIR. With this question in mind, the present investigation proposes fusion of features extracted from NIR and VL to boost the recognition performance. We have collected our own database (UTIRIS) consisting of both NIR and VL images of 158 eyes of 79 individuals. This investigation demonstrates that the proposed algorithm is highly sensitive to the patterns of cromophores and improves the iris recognition rate.

cs.CV↗