Deep Reinforcement Learning for Small Bowel Path Tracking Using Different Types of Annotations

Shin, Seung Yeon; Summers, Ronald M.

doi:10.1007/978-3-031-16443-9_53

Cited by 2 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this is very costly due to the difficulty of labeling the small bowel. [9][10][11][12][13] Instead, we use the intensity distribution of small bowel carcinoid tumors to compute a probability of being tumor for each voxel. This soft label is provided to our segmentation model as an auxiliary task so that it can inform the model about our region of interest, which could contain carcinoid tumors, based on the intensity.…”

Section: Introductionmentioning

confidence: 99%

Improving small lesion segmentation in CT scans using intensity distribution supervision: application to small bowel carcinoid tumor

Shin¹,

Shen²,

Wank³

et al. 2023

Medical Imaging 2023: Computer-Aided Diagnosis

View full text Add to dashboard Cite

Finding small lesions is very challenging due to lack of noticeable features, severe class imbalance, as well as the size itself. One approach to improve small lesion segmentation is to reduce the region of interest and inspect it at a higher sensitivity rather than performing it for the entire region. It is usually implemented as sequential or joint segmentation of organ and lesion, which requires additional supervision on organ segmentation. Instead, we propose to utilize an intensity distribution of a target lesion at no additional labeling cost to effectively separate regions where the lesions are possibly located from the background. It is incorporated into network training as an auxiliary task. We applied the proposed method to segmentation of small bowel carcinoid tumors in CT scans. We observed improvements for all metrics (33.5% → 38.2%, 41.3% → 47.8%, 30.0% → 35.9% for the global, per case, and per tumor Dice scores, respectively.) compared to the baseline method, which proves the validity of our idea. Our method can be one option for explicitly incorporating intensity distribution information of a target in network training.

show abstract

Section: Introductionmentioning

confidence: 99%

Improving small lesion segmentation in CT scans using intensity distribution supervision: application to small bowel carcinoid tumor

Shin¹,

Shen²,

Wank³

et al. 2023

Medical Imaging 2023: Computer-Aided Diagnosis

View full text Add to dashboard Cite

show abstract

“…Achieving a high accuracy for small bowel segmentation is relatively difficult due to: (1) its proximity to other organs in position and appearance, (2) locally variable appearance according to the bowel contents, and (3) variable configuration. [12][13][14] Besides, carcinoid tumors are typically small (often less than a centimeter). Putting together, detecting carcinoid tumors within the small bowel is more challenging than other lesions within an organ that has static and homogeneous appearance.…”

Section: Introductionmentioning

confidence: 99%

“…Detecting carcinoid tumors within the small bowel is challenging since it should identify the small bowel as well as carcinoid tumors themselves. Achieving a high accuracy for small bowel segmentation is relatively difficult due to: (1) its proximity to other organs in position and appearance, (2) locally variable appearance according to the bowel contents, and (3) variable configuration 12–14 . Besides, carcinoid tumors are typically small (often less than a centimeter).…”

Section: Introductionmentioning

confidence: 99%

Fully‐automated detection of small bowel carcinoid tumors in CT scans using deep learning

et al. 2023

Self Cite

View full text Add to dashboard Cite

BackgroundSmall bowel carcinoid tumor is a rare neoplasm and increasing in incidence. Patients with small bowel carcinoid tumors often experience long delays in diagnosis due to the vague symptoms, slow growth of tumors, and lack of clinician awareness. Computed tomography (CT) is the most common imaging study for diagnosis of small bowel carcinoid tumor. It is often used with positron emission tomography (PET) to capture anatomical and functional aspects of carcinoid tumors and thus to increase the sensitivity.PurposeWe compared three different kinds of methods for the automatic detection of small bowel carcinoid tumors on CT scans, which is the first to the best of our knowledge.MethodsThirty‐three preoperative CT scans of 33 unique patients with surgically‐proven carcinoid tumors within the small bowel were collected. Ground‐truth segmentation of tumors was drawn on CT scans by referring to available 18F‐DOPA PET scans and the corresponding radiology report. These scans were split into the trainval set (n = 24) and the test positive set (n= 9). Additionally, 22 CT scans of 22 unique patients who had no evidence of the tumor were collected to comprise the test negative set. We compared three different kinds of detection methods, which are detection network, patch‐based classification, and segmentation‐based methods. We also investigated the usefulness of small bowel segmentation for reduction of false positives (FPs) for each method. Free‐response receiver operating characteristic (FROC) curves and receiver operating characteristic (ROC) curves were used for lesion‐ and patient‐level evaluations, respectively. Statistical analyses comparing the FROC and ROC curves were also performed.ResultsThe detection network method performed the best among the compared methods. For lesion‐level detection, the detection network method, without the small bowel segmentation‐based filtering, achieved sensitivity values of (60.8%, 81.1%, 82.4%, 86.5%) at per‐scan FP rates of (1, 2, 4 ,8), respectively. The use of the small bowel segmentation did not improve the performance (). For patient‐level detection, again the detection network method, but with the small bowel segmentation‐based filtering, achieved the highest AUC of 0.86 with a sensitivity of 78% and specificity of 82% at the Youden point.ConclusionsThe carcinoid tumors in this patient population were very small and potentially difficult to diagnose. The presented method showed reasonable sensitivity at small numbers of FPs for lesion‐level detection. It also achieved a promising AUC for patient‐level detection. The method may have clinical application in patients with this rare and difficult to detect disease.

show abstract

Deep Reinforcement Learning for Small Bowel Path Tracking Using Different Types of Annotations

Cited by 2 publications

References 15 publications

Improving small lesion segmentation in CT scans using intensity distribution supervision: application to small bowel carcinoid tumor

Improving small lesion segmentation in CT scans using intensity distribution supervision: application to small bowel carcinoid tumor

Fully‐automated detection of small bowel carcinoid tumors in CT scans using deep learning

Contact Info

Product

Resources

About