We lifted 11 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| Masaaki-75/proct | pwc_unofficial | 1 of 11 |
| Function | Status | Where it lives |
|---|---|---|
| gaussian | Ran | Masaaki-75/proct/utilities/rec_loss.py code served (permissive licence) · get_code("0d209028c2dee969") |
| build_sincos2d_pos_embed | Not yet run | Masaaki-75/proct/modules/rope.py code served (permissive licence) · get_code("bb04d14701260c0f") |
| forward_channel_last | Not yet run | Masaaki-75/proct/modules/basic_layers.py code served (permissive licence) · get_code("0e211f4654d783be") |
| forward_channel_second | Not yet run | Masaaki-75/proct/modules/basic_layers.py code served (permissive licence) · get_code("799fe50f1f9e224c") |
| freq_bands | Not yet run | Masaaki-75/proct/modules/rope.py code served (permissive licence) · get_code("968a74d4e1310a55") |
| get_conv_block | Not yet run | Masaaki-75/proct/modules/basic_layers.py code served (permissive licence) · get_code("c6e8792591fbec4c") |
| get_metrics | Not yet run | Masaaki-75/proct/utilities/rec_loss.py code served (permissive licence) · get_code("8bf3319a7b1db318") |
| get_mse | Not yet run | Masaaki-75/proct/utilities/rec_loss.py code served (permissive licence) · get_code("363dfe1b7fa7f2ba") |
| pixel_freq_bands | Not yet run | Masaaki-75/proct/modules/rope.py code served (permissive licence) · get_code("025f4d123711b4e5") |
| poly_lr | Not yet run | Masaaki-75/proct/trainers/basic_trainer.py code served (permissive licence) · get_code("6de2f712f7f3e0a1") |
| vmap | Not yet run | Masaaki-75/proct/sources/proct.py code served (permissive licence) · get_code("413b87f93f023198") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Extracting, harvesting and building large-scale annotated radiological image datasets is a greatly important yet challenging problem. It is also the bottleneck to designing more effective data-hungry computing paradigms (e.g., deep learning) for medical image analysis. Yet, vast amounts of clinical annotations (usually associated with disease image findings and marked using arrows, lines, lesion diameters, segmentation, etc.) have been collected over several decades and stored in hospitals' Picture Archiving and Communication Systems. In this paper, we mine and harvest one major type of clinical annotation data - lesion diameters annotated on bookmarked images - to learn an effective multi-class lesion detector via unsupervised and supervised deep Convolutional Neural Networks (CNN). Our dataset is composed of 33,688 bookmarked radiology images from 10,825 studies of 4,477 unique patients. For every bookmarked image, a bounding box is created to cover the target lesion based on its measured diameters. We categorize the collection of lesions using an unsupervised deep mining scheme to generate clustered pseudo lesion labels. Next, we adopt a regional-CNN method to detect lesions of multiple categories, regardless of missing annotations (normally only one lesion is annotated, despite the presence of multiple co-existing findings). Our integrated mining, categorization and detection framework is validated with promising empirical results, as a scalable, universal or multi-purpose CAD paradigm built upon abundant retrospective medical data. Furthermore, we demonstrate that detection accuracy can be significantly improved by incorporating pseudo lesion labels (e.g., Liver lesion/tumor, Lung nodule/tumor, Abdomen lesions, Chest lymph node and others). This dataset will be made publicly available (under the open science initiative).
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1710.01766")
get_code_for_paper("1710.01766")
have("1710.01766")
Connect an agent — have() is free.