SpineNet: Automatically Pinpointing Classification Evidence in Spinal MRIs

By Amir Jamaludin, Timor Kadir, Andrew Zisserman. 2016

67 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Neurology, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Neurology

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Visual Feature Attribution Using Wasserstein GANs (2017, methodology): “Pinpointing all evidence of a class is important for a variety of tasks such as weakly supervised localisation or segmentation of structures [41, 43, 65], and better understanding disease effects, and physiological or pathological processes in medical images [67, 18, 12, 19, 13, 27, 54, 30, 31, 63].”
A survey on deep learning in medical image analysis (2017, background): “A surprising number of complete applications with promising results are available; one that stands out is Jamaludin et al. (2016) who trained their system with 12K discs and claimed near-human performances across four di ﬀ erent radiological scoring tasks.”
ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases (2017, background): “Recent notable work includes (but do not limit to) an overview review on the future promise of deep learning [14] and a collection of important medical applications on lymph node and interstitial lung disease detection and classification [36, 42]; cerebral microbleed detection [11]; pulmonary nodule”
Deep Learning for Health Informatics (2017, background): “Multitasking refers to the idea of solving different classification problems simultaneously and it results in a drastic reduction of free parameters [133].”
3D deeply supervised network for automated segmentation of volumetric medical images (2017, background): “…performance on many challenging medical image analyis tasks, including classification ( Sirinukunwattana et al., 2016; Yu t al., 2017; Jamaludin et al., 2016 ), detection ( Setio et al., 2016; ou et al., 2016b; Shin et al., 2016 ) and segmentation ( Ciresan t al., 2012; Havaei et…”
Zoom-in-Net: Deep Mining Lesions for Diabetic Retinopathy Detection (2017, background): “Few previous works localize the lesions with image-level supervisions, such as visualizing the evidence hotspots of the spinal MRIs classification [10].”
Universal representations: The missing link between faces, text, planktons, and cat breeds (2017, background): “…to recognize faces [20, 42, 47, 51], classify [27, 17], detect [44, 35] or segment [9] high-level object categories, read text [15, 23], recognize bird, ﬂower, dog, or cat species [34], interpret a radiography, an echography, or a MRI image of different parts of the human anatomy [24], and so on.”
A guide to deep learning in healthcare (2019, background): “…tasks, including identifying moles from melanomas 9,10 , diabetic retinopathy, cardiovascular risk, and referrals from fundus 15,16 and optical coherence tomography (OCT) 17 images of the eye, breast lesion detection in mammograms 13 , and spinal analysis with magnetic resonance imaging 23 .”
Weakly-Supervised Evidence Pinpointing and Description (2017, methodology): “Moreover, our descriptor learning method differs from the recent CNN based evidence pinpointing techniques [12,13] in that we not only localise the evidence regions but at the same time give the description of these regions at optimal feature scales.”
Identifying pneumonia in chest X-rays: A deep learning approach (2019, methodology): “[16] applied CNN architecture to analyze the data obtained from spinal lumber magnetic resonance imaging (MRI).”