Sailesh Conjeti

Sailesh Conjeti
Siemens Healthineers · Digital Health

Doctor of Philosophy
Leading a team of data scientists and machine learning engineers to build next-gen AI products for radioloy

About

84
Publications
20,366
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,056
Citations
Introduction
-- Helping upgrade medical diagnosis from an art to a digital data-driven science one image at a time. -- Highly motivated and passionate individual focused on bringing AI-based healthcare solutions that make a difference -- Currently Lead Data Scientist for the AI-Rad Companion portfolio of applications - covering over 100 algorithms productized within 7 cleared medical devices. -- Ex-Global Product Manager for AI-Rad Companion Chest X-ray - an AI-based Chest X-ray Diagnostic Aid - first of i
Additional affiliations
September 2013 - March 2014
Technische Universität München
Position
  • DAAD Exchange Student
August 2012 - August 2013
Indian Institute of Technology Kharagpur
Position
  • Research Assistant
Education
July 2014 - June 2017
Technische Universität München
Field of study
  • Medical Imaging Computing
July 2012 - May 2014
Indian Institute of Technology Kharagpur
Field of study
  • Medical Imaging and Informatics
August 2008 - May 2012
Birla Institute of Technology and Science Pilani
Field of study
  • Electrical and Electronics Engineering

Publications

Publications (84)
Article
Full-text available
Importance Most early lung cancers present as pulmonary nodules on imaging, but these can be easily missed on chest radiographs. Objective To assess if a novel artificial intelligence (AI) algorithm can help detect pulmonary nodules on radiographs at different levels of detection difficulty. Design, Setting, and Participants This diagnostic study...
Article
Full-text available
Traditional neuroimage analysis pipelines involve computationally intensive, time-consuming optimization steps, and thus, do not scale well to large cohort studies with thousands or tens of thousands of individuals. In this work we propose a fast and accurate deep learning based neuroimaging pipeline for the automated processing of structural human...
Chapter
The accurate quantification of visceral and subcutaneous adipose tissue (VAT and SAT) has become a mayor interest worldwide, given that these tissue types represent an important risk factor of metabolic disorders. Currently, the gold standard for measuring volumes of VAT and SAT is the manual segmentation of abdominal fat images from 3D Dixon magne...
Chapter
Traditional neuroimage analysis pipelines involve computationally intensive, time-consuming optimization steps, and thus, do not scale well to large cohort studies. With FastSurfer [1] we propose a fast deep-learning based alternative for the automated processing of structural human MRI brain scans, including surface reconstruction and cortical par...
Article
Full-text available
Histopathological Whole Slide Imaging (WSI) has become a standard in the detection of breast cancer. Automated image analysis methods attempt to reduce the workload from the clinicians and Convolutional Neural Networks (CNNs) are a popular choice for this purpose. However, size of a WSI image typically is approximately $40,000\times 40.000$ pixel...
Preprint
Traditional neuroimage analysis pipelines involve computationally intensive, time-consuming optimization steps, and thus, do not scale well to large cohort studies with thousands or tens of thousands of individuals. In this work we propose a fast and accurate deep learning based neuroimaging pipeline for the automated processing of structural human...
Article
Full-text available
Purpose: Introduce and validate a novel, fast, and fully automated deep learning pipeline (FatSegNet) to accurately identify, segment, and quantify visceral and subcutaneous adipose tissue (VAT and SAT) within a consistent, anatomically defined abdominal region on Dixon MRI scans. Methods: FatSegNet is composed of three stages: (a) Consistent lo...
Preprint
Full-text available
Purpose: Development of a fast and fully automated deep learning pipeline (FatSegNet) to accurately identify, segment, and quantify abdominal adipose tissue on Dixon MRI from the Rhineland Study - a large prospective population-based study. Method: FatSegNet is composed of three stages: (i) consistent localization of the abdominal region using two...
Article
Full-text available
We introduce Bayesian QuickNAT for the automated quality control of whole-brain segmentation on MRI T1 scans. Next to the Bayesian fully convolutional neural network, we also present inherent measures of segmentation uncertainty that allow for quality control per brain structure. For estimating model uncertainty, we follow a Bayesian approach, wher...
Preprint
Full-text available
We introduce Bayesian QuickNAT for the automated quality control of whole-brain segmentation on MRI T1 scans. Next to the Bayesian fully convolutional neural network, we also present inherent measures of segmentation uncertainty that allow for quality control per brain structure. For estimating model uncertainty, we follow a Bayesian approach, wher...
Article
Surgical tool detection is attracting increasing attention from the medical image analysis community. The goal generally is not to precisely locate tools in images, but rather to indicate which tools are being used by the surgeon at each instant. The main motivation for annotating tool usage is to design efficient solutions for surgical workflow an...
Article
Full-text available
Whole brain segmentation from structural magnetic resonance imaging (MRI) is a prerequisite for most morphological analyses, but is computationally intense and can therefore delay the availability of image markers after scan acquisition. We introduce QuickNAT, a fully convolutional, densely connected neural network that segments a MRI brain scan in...
Chapter
Several diseases of parkinsonian syndromes present similar symptoms at early stage and no objective widely used diagnostic methods have been approved until now. Positron emission tomography (PET) with \(^{18}\)F-FDG was shown to be able to assess early neuronal dysfunction of synucleinopathies and tauopathies. Tensor factorization (TF) based approa...
Poster
Full-text available
Undersampling the k-space data is widely adopted for acceleration of Magnetic Resonance Imaging (MRI). Current deep learning based approaches for supervised learning of MRI image reconstruction employ real-valued operations and representations by treating complex valued k-space/spatial-space as real values. In this paper, we propose complex dense f...
Chapter
Increased information sharing through short and long-range skip connections between layers in fully convolutional networks have demonstrated significant improvement in performance for semantic segmentation. In this paper, we propose Competitive Dense Fully Convolutional Networks (CDFNet) by introducing competitive maxout activations in place of naï...
Chapter
In this paper, we present a learning based, registration free, atlas ranking technique for selecting outperforming atlases prior to image registration and multi-atlas segmentation (MAS). To this end, we introduce ensemble hashing, where each data (image volume) is represented with ensemble of hash codes and a learnt distance metric is used to obvia...
Chapter
Undersampling the k-space data is widely adopted for acceleration of Magnetic Resonance Imaging (MRI). Current deep learning based approaches for supervised learning of MRI image reconstruction employ real-valued operations and representations by treating complex valued k-space/spatial-space as real values. In this paper, we propose complex dense f...
Chapter
Within medical imaging, manual curation of sufficient well-labeled samples is cost, time and scale-prohibitive. To improve the representativeness of the training dataset, for the first time, we present an approach to utilize large amounts of freely available web data through web-crawling. To handle noise and weak nature of web annotations, we propo...
Chapter
We introduce inherent measures for effective quality control of brain segmentation based on a Bayesian fully convolutional neural network, using model uncertainty. Monte Carlo samples from the posterior distribution are efficiently generated using dropout at test time. Based on these samples, we introduce next to a voxel-wise uncertainty map also t...
Chapter
In this paper, for the first time, we propose an evaluation method for deep learning models that assesses the performance of a model not only in an unseen test scenario, but also in extreme cases of noise, outliers and ambiguous input data. To this end, we utilize adversarial examples, images that fool machine learning models, while looking imperce...
Book
Full-text available
This book constitutes the refereed joint proceedings of the 4th International Workshop on Deep Learning in Medical Image Analysis, DLMIA 2018, and the 8th International Workshop on Multimodal Learning for Clinical Decision Support, ML-CDS 2018, held in conjunction with the 21st International Conference on Medical Imaging and Computer-Assisted Inter...
Article
In this paper, we present a learning based, registration free, atlas ranking technique for selecting outperforming atlases prior to image registration and multi-atlas segmentation (MAS). To this end, we introduce ensemble hashing, where each data (image volume) is represented with ensemble of hash codes and a learnt distance metric is used to obvia...
Preprint
Effectively measuring the similarity between two human motions is necessary for several computer vision tasks such as gait analysis, person identi- fication and action retrieval. Nevertheless, we believe that traditional approaches such as L2 distance or Dynamic Time Warping based on hand-crafted local pose metrics fail to appropriately capture the...
Preprint
Full-text available
Increased information sharing through short and long-range skip connections between layers in fully convolutional networks have demonstrated significant improvement in performance for semantic segmentation. In this paper, we propose Competitive Dense Fully Convolutional Networks (CDFNet) by introducing competitive maxout activations in place of nai...
Preprint
Full-text available
Undersampling the k-space data is widely adopted for acceleration of Magnetic Resonance Imaging (MRI). Current deep learning based approaches for supervised learning of MRI image reconstruction employ real-valued operations and representations by treating complex valued k-space/spatial-space as real values. In this paper, we propose complex dense f...
Preprint
Full-text available
Cross modal image syntheses is gaining significant interests for its ability to estimate target images of a different modality from a given set of source images,like estimating MR to MR, MR to CT, CT to PET etc, without the need for an actual acquisition.Though they show potential for applications in radiation therapy planning,image super resolutio...
Conference Paper
Full-text available
We introduce inherent measures for effective quality control of brain segmentation based on a Bayesian fully convolutional neural network, using model uncertainty. Monte Carlo samples from the posterior distribution are efficiently generated using dropout at test time. Based on these samples, we introduce next to a voxel-wise uncertainty map also t...
Conference Paper
Full-text available
We present a novel, parameter-efficient and practical fully convolutional neural network architecture, termed InfiNet, aimed at voxel-wise semantic segmentation of infant brain MRI images at iso-intense stage, which can be easily extended for other segmentation tasks involving multi-modalities. InfiNet consists of double encoder arms for T1 and T2...
Article
Within medical imaging, manual curation of sufficient well-labeled samples is cost, time and scale-prohibitive. To improve the representativeness of the training dataset, for the first time, we present an approach to utilize large amounts of freely available web data through web-crawling. To handle noise and weak nature of web annotations, we propo...
Article
Full-text available
In this paper, for the first time, we propose an evaluation method for deep learning models that assesses the performance of a model not only in an unseen test scenario, but also in extreme cases of noise, outliers and ambiguous input data. To this end, we utilize adversarial examples, images that fool machine learning models, while looking imperce...
Article
Full-text available
Whole brain segmentation from structural magnetic resonance imaging is a prerequisite for most morphological analyses, but requires hours of processing time and therefore delays the availability of image markers after scan acquisition. We introduce QuickNAT, a fully convolution neural network that segments a brain scan in 20 seconds. To enable trai...
Chapter
Intravascular ultrasound (IVUS) is a real-time cross-sectional imaging modality deployed in interventional cardiology for assessment of the extent of atherosclerosis. Visual reading of IVUS pull-backs is subject to inter- and intra-observer variability in reporting of vulnerable plaques causing myocardial infraction. In vivo IVUS tissue characteriz...
Article
Full-text available
Purpose: Docetaxel has a demonstrated survival benefit for patients with metastatic castration-resistant prostate cancer (mCRPC); however, 10% to 20% of patients discontinue docetaxel prematurely because of toxicity-induced adverse events, and the management of risk factors for toxicity remains a challenge. Patients and methods: The comparator a...
Conference Paper
We propose a novel deeply learnt convolutional neural network architecture for supervised hashing of medical images through residual learning, coined as Deep Residual Hashing (DRH). It offers maximal separability of classes in hashing space while preserving semantic similarities in local embedding neighborhoods. We also introduce a new optimization...
Conference Paper
In this paper, for the first time, we introduce a multiple instance (MI) deep hashing technique for learning discriminative hash codes with weak bag-level supervision suited for large-scale retrieval. We learn such hash codes by aggregating deeply learnt hierarchical representations across bag members through an MI pool layer. For better trainabili...
Conference Paper
Training deep fully convolutional neural networks (F-CNNs) for semantic image segmentation requires access to abundant labeled data. While large datasets of unlabeled image data are available in medical applications, access to manually labeled data is very limited. We propose to automatically create auxiliary labels on initially unlabeled data with...
Article
Full-text available
Ensemble methods have been successfully applied in a wide range of scenarios, including survival analysis. However, most ensemble models for survival analysis consist of models that all optimize the same loss function and do not fully utilize the diversity in available models. We propose heterogeneous survival ensembles that combine several surviva...
Article
Full-text available
Ensemble methods have been successfully applied in a wide range of scenarios, including survival analysis. However, most ensemble models for survival analysis consist of models that all optimize the same loss function and do not fully utilize the diversity in available models. We propose heterogeneous survival ensembles that combine several surviva...
Article
Full-text available
Training deep fully convolutional neural networks (F-CNNs) for semantic image segmentation requires access to abundant labeled data. While large datasets of unlabeled image data are available in medical applications, access to manually labeled data is very limited. We propose to automatically create auxiliary labels on initially unlabeled data with...
Article
Optical coherence tomography (OCT) is extensively used for diagnosis of diabetic macular edema due to its non-invasive imaging based assessment of the retinal layers. In this paper, we propose a new fully convolutional deep learning architecture, termed ReLayNet, for segmentation of retinal layers and fluid masses in eye OCT scans. ReLayNet uses a...
Article
Full-text available
In this paper, for the first time, we introduce a multiple instance (MI) deep hashing technique for learning discriminative hash codes with weak bag-level supervision suited for large-scale retrieval. We learn such hash codes by aggregating deeply learnt hierarchical representations across bag members through a dedicated MI pool layer. For better t...
Article
Background: Improvements to prognostic models in metastatic castration-resistant prostate cancer have the potential to augment clinical trial design and guide treatment strategies. In partnership with Project Data Sphere, a not-for-profit initiative allowing data from cancer clinical trials to be shared broadly with researchers, we designed an ope...
Article
Full-text available
This paper presents a new scalable algorithm for cross-modal similarity preserving retrieval in a learnt manifold space. Unlike existing approaches that compromise between preserving global and local geometries, the proposed technique respects both simultaneously during manifold alignment. The global topologies are maintained by recovering underlyi...
Article
Full-text available
Hashing aims at generating highly compact similarity preserving code words which are well suited for large-scale image retrieval tasks. Most existing hashing methods first encode the images as a vector of hand-crafted features followed by a separate binarization step to generate hash codes. This two-stage process may produce sub-optimal encoding. I...
Article
Full-text available
Ensemble methods have been successfully applied in a wide range of scenarios, including survival analysis. However, most ensemble models for survival analysis consist of models that all optimize the same loss function and do not fully utilize the diversity in available models. We propose heterogeneous survival ensembles that combine several surviva...
Article
Full-text available
The steadily growing amounts of digital neuroscientific data demands for a reliable, systematic, and computationally effective retrieval algorithm. In this paper, we present Neuron-Miner, which is a tool for fast and accurate reference-based retrieval within neuron image databases. The proposed algorithm is established upon hashing (search and retr...
Article
Background: In clinical research, the primary interest is often the time until occurrence of an adverse event, i.e., survival analysis. Its application to electronic health records is challenging for two main reasons: (1) patient records are comprised of high-dimensional feature vectors, and (2) feature vectors are a mix of categorical and real-va...
Article
In this paper, we propose metric Hashing Forests (mHF) which is a supervised variant of random forests tailored for the task of nearest neighbor retrieval through hashing. This is achieved by training independent hashing trees that parse and encode the feature space such that local class neighborhoods are preserved and encoded with similar compact...
Conference Paper
Deluge in the size and heterogeneity of medical image databases necessitates the need for content based retrieval systems for their efficient organization. In this paper, we propose such a system to retrieve prostate MR images which share similarities in appearance and content with a query image. We introduce deeply learnt hashing forests (DL-HF) f...
Article
In this paper, we propose a supervised domain adaptation (DA) framework for adapting decision forests in the presence of distribution shift between training (source) and testing (target) domains, given few labeled examples. We introduce a novel method for DA through an error-correcting hierarchical transfer relaxation scheme with domain alignment,...
Conference Paper
Full-text available
In this paper, for the first time, we propose a data-driven search and retrieval (hashing) technique for large neuron image databases. The presented method is established upon hashing forests, where multiple unsupervised random trees are used to encode neurons by parsing the neuromorphological feature space into balanced subspaces. We introduce an...
Conference Paper
Full-text available
Cryo-Electron Tomography is a leading imaging technique in structural biology, which is capable of acquiring two-dimensional projections of cellular structures at high resolution and close-to-native state. Due to the limited electron dose the resulting projections exhibit extremely low SNR and contrast. The 3D structure is then reconstructed and pa...