DeepDistance: A multi-task deep regression model for cell detection in inverted microscopy images

Koyuncu, Can Fahrettin
Gunesli, Gozde Nur
Atalay, Rengül
This paper presents a new deep regression model, which we call DeepDistance, for cell detection in images acquired with inverted microscopy. This model considers cell detection as a task of finding most probable locations that suggest cell centers in an image. It represents this main task with a regression task of learning an inner distance metric. However, different than the previously reported regression based methods, the DeepDistance model proposes to approach its learning as a multi-task regression problem where multiple tasks are learned by using shared feature representations. To this end, it defines a secondary metric, normalized outer distance, to represent a different aspect of the problem and proposes to define its learning as complementary to the main cell detection task. In order to learn these two complementary tasks more effectively, the DeepDistance model designs a fully convolutional network (FCN) with a shared encoder path and end-to-end trains this FCN to concurrently learn the tasks in parallel. For further performance improvement on the main task, this paper also presents an extended version of the DeepDistance model that includes an auxiliary classification task and learns it in parallel to the two regression tasks by also sharing feature representations with them. DeepDistance uses the inner distances estimated by these FCNs in a detection algorithm to locate individual cells in a given image. In addition to this detection algorithm, this paper also suggests a cell segmentation algorithm that employs the estimated maps to find cell boundaries. Our experiments on three different human cell lines reveal that the proposed multi-task learning models, the DeepDistance model and its extended version, successfully identify the locations of cell as well as delineate their boundaries, even for the cell line that was not used in training, and improve the results of its counterparts.


Forward problem solution of electromagnetic source imaging using a new BEM formulation with high-order elements
Gençer, Nevzat Güneri (IOP Publishing, 1999-09-01)
Representations of the active cell populations on the cortical surface via electric and magnetic measurements are known as electromagnetic source images (EMSIs) of the human brain. Numerical solution of the potential and magnetic fields for a given electrical source distribution in the human brain is an essential part of electromagnetic source imaging. In this study, the performance of the boundary element method (BEM) is explored with different surface element types. A new BEM formulation is derived that m...
Direct Reconstruction of Pharmacokinetic-Rate Images of Optical Fluorophores From NIR Measurements
Alacam, Burak; Yazici, Birsen (Institute of Electrical and Electronics Engineers (IEEE), 2009-09-01)
In this paper, we present a new method to form pharmacokinetic-rate images of optical fluorophores directly from near infra-red (NIR) boundary measurements. We first derive a mapping from spatially resolved pharmacokinetic rates to NIR boundary measurements by combining compartmental modeling with a diffusion based NIR photon propagation model. We express this mapping as a state-space equation. Next, we introduce a spatio-temporal prior model for the pharmacokinetic-rate images and combine it with the state...
Continuous dimensionality characterization of image structures
Felsberg, Michael; Kalkan, Sinan; Kruger, Norbert (Elsevier BV, 2009-05-04)
Intrinsic dimensionality is a concept introduced by statistics and later used in image processing to measure the dimensionality of a data set. In this paper, we introduce a continuous representation of the intrinsic dimension of an image patch in terms of its local spectrum or, equivalently, its gradient field. By making use of a cone structure and barycentric co-ordinates, we can associate three confidences to the three different ideal cases of intrinsic dimensions corresponding to homogeneous image patche...
AKTIHANOGLU, M; OZGUC, B; AYKANAT, C (Springer Science and Business Media LLC, 1994-01-01)
This paper describes a system for modeling, animating, previewing and rendering articulated objects. The system has a modeler of objects that consists of joints and segments. The animator interactively positions the articulated object in its stick, control vertex, or rectangular prism representation and previews the motion in real time. Then the data representing the motion and the models is sent to a multicomputer [iPSC/2 Hypercube (Intel)]. The frames are rendered in parallel, exploiting the coherence bet...
Non-destructive recognition of dielectric coated conducting objects by using WD type time-frequency transformation and PCA-based fusion
Sayan, Gönül (Wiley, 2013-07-01)
This article demonstrates the applications of a non-destructive electromagnetic target recognition method, called Wigner distribution-principal component analysis (WD-PCA) method, to dielectric coated conducting spheres. These spheres are chosen to be highly similar having the same overall size but slightly different permittivity and thickness values in coating layers. Four different classifiers are simulated by using the WD-PCA method for varying sizes of object libraries under different noise conditions. ...
Citation Formats
C. F. Koyuncu, G. N. Gunesli, R. Atalay, and Ç. GÜNDÜZ DEMİR, “DeepDistance: A multi-task deep regression model for cell detection in inverted microscopy images,” MEDICAL IMAGE ANALYSIS, pp. 0–0, 2020, Accessed: 00, 2020. [Online]. Available: