• Corpus ID: 236957388

Contrastive Representation Learning for Rapid Intraoperative Diagnosis of Skull Base Tumors Imaged Using Stimulated Raman Histology

@article{Jiang2021ContrastiveRL,
  title={Contrastive Representation Learning for Rapid Intraoperative Diagnosis of Skull Base Tumors Imaged Using Stimulated Raman Histology},
  author={Cheng Jiang and Abhishek Bhattacharya and Joseph R Linzey and Rushikesh S. Joshi and Sung Jik Cha and Sudharsan Srinivasan and Daniel Alber and Akhil Kondepudi and Esteban Urias and Balaji Pandian and Wajd N. Al-Holou and Steven Sullivan and Benjamin Thompson and Jason Heth and Christian W. Freudiger and Siri Sahib S Khalsa and D. Pacione and John G. Golfinos and Sandra Camelo-Piragua and Daniel A. Orringer and Honglak Lee and Todd C. Hollon},
  journal={ArXiv},
  year={2021},
  volume={abs/2108.03555}
}
Background: Accurate diagnosis of skull base tumors is essential for providing personalized surgical treatment strategies. Intraoperative diagnosis can be challenging due to tumor diversity and lack of intraoperative pathology resources. Objective: To develop an independent and parallel intraoperative pathology workflow that can provide rapid and accurate skull base tumor diagnoses using label-free optical imaging and artificial intelligence (AI). Method: We used a fiber laser–based, label-free… 

Figures and Tables from this paper

OpenSRH: optimizing brain tumor surgery using intraoperative stimulated Raman histology
TLDR
OpenSRH is presented, the first public dataset of clinical SRH images from 300+ brain tumors patients and 1300+ unique whole slide optical images that will facilitate the clinical translation of rapid optical imaging and real-time ML-based surgical decision support in order to improve the access, safety, and efficacy of cancer surgery in the era of precision medicine.

References

SHOWING 1-10 OF 26 REFERENCES
Near Real-Time Intraoperative Brain Tumor Diagnosis Using Stimulated Raman Histology and Deep Neural Networks
TLDR
In a multicenter, prospective clinical trial, it is demonstrated that CNN-based diagnosis of SRH images was noninferior to pathologist-based interpretation of conventional histologic images (overall accuracy, 94.6% versus 93.9%).
Rapid, label-free detection of diffuse glioma recurrence using intraoperative stimulated Raman histology and deep neural networks.
TLDR
SRH with CNN-based diagnosis can be used to improve the intraoperative detection of glioma recurrence in near-real time and provide insight into how optical imaging and computer vision can be combined to augment conventional diagnostic methods and improve the quality of specimen sampling at gliomas recurrence.
AI-Assisted In Situ Detection of Human Glioma Infiltration Using a Novel Computational Method for Optical Coherence Tomography
TLDR
A novel artificial intelligence (AI)-assisted method for automated, real-time, in situ detection of glioma infiltration at high spatial resolution and excellent levels of sensitivity and specificity for detectingglioma-infiltrated brain tissue.
Rapid intraoperative histology of unprocessed surgical specimens via fibre-laser-based stimulated Raman scattering microscopy
TLDR
This work demonstrates the first application of SRS microscopy in the operating room by using a portable fibre-laser-based microscope and unprocessed specimens from 101 neurosurgical patients and builds and validated a multilayer perceptron based on quantified SRH image attributes that predicts brain-tumour subtype with 90% accuracy.
Dermatologist-level classification of skin cancer with deep neural networks
TLDR
This work demonstrates an artificial intelligence capable of classifying skin cancer with a level of competence comparable to dermatologists, trained end-to-end from images directly, using only pixels and disease labels as inputs.
Automated deep-neural-network surveillance of cranial images for acute neurologic events
TLDR
A deep-learning algorithm is developed to provide rapid and accurate diagnosis of clinical 3D head CT-scan images to triage and prioritize urgent neurological events, thus potentially accelerating time to diagnosis and care in clinical settings.
Intraoperative brain cancer detection with Raman spectroscopy in humans
TLDR
A handheld Raman spectroscopy probe enabled detection of invasive brain cancer intraoperatively in patients with grade 2 to 4 gliomas and may be able to classify cell populations in real time, making it an ideal guide for surgical resection and decision-making.
Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning
TLDR
A deep convolutional neural network model is trained on whole-slide images obtained from The Cancer Genome Atlas to accurately and automatically classify them into LUAD, LUSC or normal lung tissue and predicts the ten most commonly mutated genes in LUAD.
Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs.
TLDR
An algorithm based on deep machine learning had high sensitivity and specificity for detecting referable diabetic retinopathy and diabetic macular edema in retinal fundus photographs from adults with diabetes.
Intraoperative mass spectrometry mapping of an onco-metabolite to guide brain tumor surgery
TLDR
It is shown that a validated molecular marker—2-hydroxyglutarate generated from isocitrate dehydrogenase 1 mutant gliomas—can be rapidly detected from tumors using a form of ambient MS that does not require sample preparation, indicating that metabolite-imaging MS could transform many aspects of surgical care.
...
...