Papers › Improving RetinaNet for CT Lesion Detection with Dense Masks from Weak RECIST Labels

Improving RetinaNet for CT Lesion Detection with Dense Masks from Weak RECIST Labels

5 Jun 2019arXiv:1906.02283archive 2025-07-28

Martin Zlocha, Qi Dou, Ben Glocker

Accurate, automated lesion detection in Computed Tomography (CT) is an important yet challenging task due to the large variation of lesion types, sizes, locations and appearances. Recent work on CT lesion detection employs two-stage region proposal based methods trained with centroid or bounding-box annotations. We propose a highly accurate and efficient one-stage lesion detector, by re-designing a RetinaNet to meet the particular challenges in medical imaging. Specifically, we optimize the anchor configurations using a differential evolution search algorithm. For training, we leverage the response evaluation criteria in solid tumors (RECIST) annotation which are measured in clinical routine. We incorporate dense masks from weak RECIST labels, obtained automatically using GrabCut, into the training objective, which in combination with other advancements yields new state-of-the-art performance. We evaluate our method on the public DeepLesion benchmark, consisting of 32,735 lesions across the body. Our one-stage detector achieves a sensitivity of 90.77% at 4 false positives per image, significantly outperforming the best reported methods by over 5%.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1906.02283")

Code

Syntology Ran 0 of 13 code samples harvested from 1 repository linked to this paper; 13 have no recorded run.

By repository: community (archive-listed): 13 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

MarioNavarrete/anchor_optimization mentioned on GitHubGPL-3.0 report
fizyr/keras-retinanet mentioned on GitHubtfApache-2.0 report
martinzlocha/anchor-optimization mentioned on GitHubGPL-3.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested; 0 ran; 0 honoured the contract we drafted; 13 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

13unverified

Licence: 0 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from fizyr/keras-retinanet. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

bbox_transform_inv fizyr/keras-retinanet/keras_retinanet/backend/backend.py community (archive-listed) unverified Apache-2.0 (permissive) · 5b0e0c7a212d74ca · report
create_generator fizyr/keras-retinanet/keras_retinanet/bin/debug.py community (archive-listed) unverified Apache-2.0 (permissive) · f7a1ea7a29ff5fcb · report
create_generator fizyr/keras-retinanet/keras_retinanet/bin/evaluate.py community (archive-listed) unverified Apache-2.0 (permissive) · 28a0b71399edaa38 · report
densenet_retinanet fizyr/keras-retinanet/keras_retinanet/models/densenet.py community (archive-listed) unverified Apache-2.0 (permissive) · b24fdf51323ff27f · report
filter_detections fizyr/keras-retinanet/keras_retinanet/layers/filter_detections.py community (archive-listed) unverified Apache-2.0 (permissive) · 876bc5be4083b8e9 · report
focal fizyr/keras-retinanet/keras_retinanet/losses.py community (archive-listed) unverified Apache-2.0 (permissive) · 94708d13faf10d34 · report
parse_args fizyr/keras-retinanet/keras_retinanet/bin/convert_model.py community (archive-listed) unverified Apache-2.0 (permissive) · 2cc742d85463061d · report
parse_args fizyr/keras-retinanet/keras_retinanet/bin/debug.py community (archive-listed) unverified Apache-2.0 (permissive) · f3b605b2e9899c4d · report
parse_args fizyr/keras-retinanet/keras_retinanet/bin/evaluate.py community (archive-listed) unverified Apache-2.0 (permissive) · fb87a61525f75536 · report
resize_images fizyr/keras-retinanet/keras_retinanet/backend/backend.py community (archive-listed) unverified Apache-2.0 (permissive) · f72ab75d77478491 · report
run fizyr/keras-retinanet/keras_retinanet/bin/debug.py community (archive-listed) unverified Apache-2.0 (permissive) · 4f808cfce01205f8 · report
shift fizyr/keras-retinanet/keras_retinanet/backend/backend.py community (archive-listed) unverified Apache-2.0 (permissive) · 95689b7dfe9f464e · report
smooth_l1 fizyr/keras-retinanet/keras_retinanet/losses.py community (archive-listed) unverified Apache-2.0 (permissive) · 1b6055f42f4750b8 · report

Tasks

Computed Tomography (CT)Lesion DetectionMedical Object DetectionRegion ProposalSkin Lesion Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Medical Object Detection DeepLesion Improved RetinaNet Sensitivity 82.36 #9 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionConvolutionFPNFocal LossRetinaNet

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections