Carcinoid tumors in the small bowel are rare, making it challenging to collect a sufficiently large dataset of lesions with diverse sizes for training detection models using computed tomography (CT) scans. This scarcity particularly affects the detection performance on relatively small or large tumors. To address this limitation, we propose a novel image synthesis method that can selectively augment underrepresented tumor sizes to enhance detection performance. Our method enables size-controllable tumor generation by integrating a tumor segmentation model and a size-aware loss into the training process. Specifically, one dimension of the input noise vector is designated to control the size of the synthesized tumors. These tumors, generated at desired sizes, are implanted into CT scans to enrich the training data for a tumor detection network. Our method produces tumors with clearer size distinctions, while maintaining comparable visual realism compared to a baseline synthesis method. In a visual Turing test, human observers could not reliably distinguish synthetic tumors from real ones. Lesion-level evaluation using free-response receiver operating characteristic (FROC) curves demonstrated that detection performance improved when synthetic tumors were included during training (P=0.04). This method offers a promising direction for improving the detection of rare tumors such as small bowel carcinoid tumors.

The 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.

Carcinoid tumors in the small bowel are rare, making it challenging to collect a sufficiently large dataset of lesions with diverse sizes for training detection models using computed tomography (CT) scans. This scarcity particularly affects the detection performance on relatively small or large tumors. To address this limitation, we propose a novel image synthesis method that can selectively augment underrepresented tumor sizes to enhance detection performance. Our method enables size-controllable tumor generation by integrating a tumor segmentation model and a size-aware loss into the training process. Specifically, one dimension of the input noise vector is designated to control the size of the synthesized tumors. These tumors, generated at desired sizes, are implanted into CT scans to enrich the training data for a tumor detection network. Our method produces tumors with clearer size distinctions, while maintaining comparable visual realism compared to a baseline synthesis method. In a visual Turing test, human observers could not reliably distinguish synthetic tumors from real ones. Lesion-level evaluation using free-response receiver operating characteristic (FROC) curves demonstrated that detection performance improved when synthetic tumors were included during training (P=0.04). This method offers a promising direction for improving the detection of rare tumors such as small bowel carcinoid tumors.

The 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.

Ascites generally manifests in the advance stage of ovarian cancer, and often mimicked by abdominal fluids such as urine in bladder. Segmentation of ascites in the pelvic region becomes increasingly challenging when the bladder is filled with urine. Anatomical location is utilized in this work to distinguish ascites from bladder. The location information is computed from a body part regressor and concatenated with contrast-enhanced computed tomography (CT) data through an embedding layer. A 3D residual U-Net is trained on the concatenated data to segment ascites and identify bladder simultaneously. 112 CT scans were used in this study; 55 of them were used for training, 20 for validation, and the remaining 37 for testing. Dice coefficient score and Jacard index are two metrics to evaluate ascites and bladder segmentation. In comparison with 3D residual U-Net, the addition of anatomical location information and two-class segmentation improved the average dice scores of ascites and urine segmentation from 0.44±0.23 to 0.51±0.16 and 0.36±0.15 to 0.40±0.13 respectively. The average volume errors of ascites and urine were reduced from 1.81±3.09 to 0.93±1.85 liters and 0.6±0.81 to 0.56±0.76 liters, respectively. These results suggested that anatomical location information and two-class segmentation are the key features to improve ascites segmentation by differentiating bladder filled with urine regions.

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.

We present a new graph-based method for small bowel path tracking based on cylindrical constraints. A distinctive characteristic of the small bowel compared to other organs is the contact between parts of itself along its course, which makes the path tracking difficult together with the indistinct appearance of the wall. It causes the tracked path to easily cross over the walls when relying on low-level features like the wall detection. To circumvent this, a series of cylinders that are fitted along the course of the small bowel are used to guide the tracking to more reliable directions. It is implemented as soft constraints using a new cost function. The proposed method is evaluated against ground-truth paths that are all connected from start to end of the small bowel for 10 abdominal CT scans. The proposed method showed clear improvements compared to the baseline method in tracking the path without making an error. Improvements of 6.6% and 17.0%, in terms of the tracked length, were observed for two different settings related to the small bowel segmentation.

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% $\to$ 38.2%, 41.3% $\to$ 47.8%, 30.0% $\to$ 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.