Radiology Objects in COntext (ROCO): A Multimodal Image Dataset
By Obioma Pelka, Sven Koitka, Johannes Rückert, Felix Nensa, Christoph M. Friedrich. CVII-STENT/LABELS@MICCAI, 2018
337 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Molecular Biology
View Paper: https://www.semanticscholar.org/paper/a564fabf130ff6e2742cfba90c7a4018937d764d
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Fahad Shahbaz Khan
- Salman Hameed Khan
- Munawar Hayat
- Matthew P. Lungren
- Gerard de Melo
- Christoph Meinel
- Hoifung Poon
- Robert Tinn
In Computer Vision and Pattern Recognition
- Fahad Shahbaz Khan
- Salman Hameed Khan
- Munawar Hayat
- Syed Waqas Zamir
- Ming-Hsuan Yang
- Luc Van Gool
- Huan Fu
- Ling Shao
In Molecular Biology
- Gerard de Melo
- Salman Hameed Khan
- Christoph Meinel
- Hoifung Poon
- Huan Fu
- Yanbo Xu
- Fahad Shahbaz Khan
- Tristan Naumann
Citations in the corpus
- PubMedCLIP: How Much Does CLIP Benefit Visual Question Answering in the Medical Domain? (2023, methodology): “In this work, the training and validation data splits from the original paper (Pelka et al., 2018) were used to train PubMedCLIP, with ViT-B/32 Vision Transformer (Dosovitskiy et al., 2021), ResNet RN-50 (He et al., 2016), and RN-50x4 visual encoder back-ends.”
- Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain? (2021, methodology): “To this end, we drew on the Radiology Objects in COntext (ROCO) dataset Pelka et al. [2018], which provides over 80 K samples.”
- BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs (2023, methodology): “PubMedCLIP [25] fine-tunes CLIP on the Radiology Objects in COn-text (ROCO) dataset [13], which consists of 80K radiology image-text pairs drawn from PubMed articles.”
- A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics (2023, neutral): “2 million papers Homepage U-Xray [296] Multimodel 3,955 reports and 7,470 images Homepage ROCO [297] Multimodel 81,000 radiology images and corresponding captions Homepage MedICaT [298] Multimodel 17,000 images includes captions Homepage PMC-OA [244] Multimodel 1.”
- Transformers in Medical Imaging: A Survey (2022, background): “Further, few medical datasets like ROCO [379], PEIR Gross [380], and ImageCLEF [381] are available that consist of multiple modalities, different body parts, and corresponding captions.”