Neil Tenenholtz's research while affiliated with Massachusetts General Hospital and other places

Publications (15)

Preprint
Full-text available
With the recent advances in A.I. methodologies and their application to medical imaging, there has been an explosion of related research programs utilizing these techniques to produce state-of-the-art classification performance. Ultimately, these research programs culminate in submission of their work for consideration in peer reviewed journals. To...
Chapter
We propose a 4D convolutional neural network (CNN) for the segmentation of retrospective ECG-gated cardiac CT, a series of single-channel volumetric data over time. While only a small subset of volumes in the temporal sequence is annotated, we define a sparse loss function on available labels to allow the network to leverage unlabeled images during...
Article
Full-text available
The growing interest in machine learning (ML) in healthcare is driven by the promise of improved patient care. However, how many ML algorithms are currently being used in clinical practice? While the technology is present, as demonstrated in a variety of commercial products, clinical integration is hampered by a lack of infrastructure, processes, a...
Chapter
We propose a deep learning-based technique for detection and quantification of abdominal aortic aneurysms (AAAs). The condition, which leads to more than 10,000 deaths per year in the United States, is asymptomatic, often detected incidentally, and often missed by radiologists. Our model architecture is a modified 3D U-Net combined with ellipse fit...
Preprint
We propose a deep learning-based technique for detection and quantification of abdominal aortic aneurysms (AAAs). The condition, which leads to more than 10,000 deaths per year in the United States, is asymptomatic, often detected incidentally, and often missed by radiologists. Our model architecture is a modified 3D U-Net combined with ellipse fit...
Preprint
Full-text available
We propose a 4D convolutional neural network (CNN) for the segmentation of retrospective ECG-gated cardiac CT, a series of single-channel volumetric data over time. While only a small subset of volumes in the temporal sequence are annotated, we define a sparse loss function on available labels to allow the network to leverage unlabeled images durin...
Article
Background: Diffusion-weighted imaging (DWI) is the gold standard for detection of acute ischemic stroke (AIS) and may guide patient selection for endovascular therapy. Machine learning algorithms can enhance clinical workflow in suspected AIS by providing early diagnosis and quantitative imaging biomarkers. We tested the hypothesis that our deep l...
Article
Background: Machine learning algorithms have proven accurate in the detection of intracranial hemorrhage (ICH) on head CT. Most reported algorithms, however, are limited to binary detection and global lesion volume estimation. We developed a pipeline to additionally perform subtype classification for clinical risk stratification, while also providi...
Chapter
The amounts of muscle and fat in a person’s body, known as body composition, are correlated with cancer risks, cancer survival, and cardiovascular risk. The current gold standard for measuring body composition requires time-consuming manual segmentation of CT images by an expert reader. In this work, we describe a two-step process to fully automate...
Chapter
Improved outcome in patients with ischemic stroke is achieved through acute diagnosis and early restoration of cerebral flow in appropriate patients. Diffusion-weighted MR imaging (DWI) plays a central role in these efforts by enabling rapid early localization and quantification of ischemic lesions. Automated detection and quantification can potent...
Chapter
Data diversity is critical to success when training deep learning models. Medical imaging data sets are often imbalanced as pathologic findings are generally rare, which introduces significant challenges when training deep learning models. In this work, we propose a method to generate synthetic abnormal MRI images with brain tumors by training a ge...
Preprint
Full-text available
The amounts of muscle and fat in a person's body, known as body composition, are correlated with cancer risks, cancer survival, and cardiovascular risk. The current gold standard for measuring body composition requires time-consuming manual segmentation of CT images by an expert reader. In this work, we describe a two-step process to fully automate...
Preprint
Data diversity is critical to success when training deep learning models. Medical imaging data sets are often imbalanced as pathologic findings are generally rare, which introduces significant challenges when training deep learning models. In this work, we propose a method to generate synthetic abnormal MRI images with brain tumors by training a ge...

Citations

... Deep convolutional neural networks have become popular research field of image classification [3,13,17,35,20,23,25]. It is used in not only simple processing of images, but also audio recognition [21,30], video recognition [12], and even text semantic processing [14,33]. ...
... The literature shows proof-of-concept identification of 5-8 basic brain MRI sequences using machine learning [1][2][3][4]. Standard machine learning approaches such as random forest classifiers (RFC) have demonstrated good accuracy, though these depend on consistency of the DICOM metadata, which is known to be variable [2,4]. ...
... Convolutional neural networks (CNN) have recently been used for analyzing medical images in CT, MRI and ultrasound (Cheng et al., 2016;Jackson et al., 2018;Litjens et al., 2017;Shen, Wu & Suk, 2017;Ronneberger, Fischer & Brox, 2015). However, there are yet only a few studies applying CNNs to AAA segmentation on computed tomographic angiography (CTA) (Zheng et al., 2018;Lu et al., 2019;López-Linares et al., 2019;Salvi, Finol & Menon, 2021;Dziubich et al., 2020). The previous studies addressed only segmentation for post-operative endovascular aneurysm repair (EVAR) of AAA (Freiman et al., 2010) with limited amounts of training data (Krizhevsky, Sutskever & Hinton, 2012;Long & Shelhamer, 2015). ...
... To this end, current and future generations of radiologists must be trained in AI and data governance competencies to be able to meet the demands of their evolving roles [36]. We recommend that this training begin as early as medical school or in early residency to allow for as much exposure and experience as possible [36]. ...
... The resulting segmentation masks for SAT and muscle are overlaid with highlighted cross-sectional slices (second row). The offsets between assessment results based on truncated slices and complete slices are presented in the bar plots (third row) For this reason, artificial intelligence (AI)-based approaches have been introduced for fully automatic BC assessment in several recent studies (Bridge et al., 2018;Lenchik et al., 2021;Magudia et al., 2021;Weston et al., 2019;Xu et al., 2022). ...
... A conventional method to alleviate this problem is using data augmentation techniques such as cropping, rotation, elastic deformations to obtain a larger data set [12]. However, these methods operate randomly and generate highly correlated images [13]. Furthermore, such techniques work on the whole image, which may lead to a missing of global topology information of the input. ...