Background: PSMA PET/CT is the most sensitive molecular imaging modality for prostate cancer (PCa), yet much of the developing world has little or no access to PET/CT. [99mTc]Tc-PSMA scintigraphy (PS) is a cheaper and more accessible gamma camera-based alternative. However, many resource-constrained departments have only a single camera without tomographic or hybrid imaging functionality, and camera time is frequently in high demand. Simplifying imaging protocols by limiting the field of view (FOV) and omitting SPECT/CT or even SPECT may provide a partial solution. The aim was thus to determine the adequacy of PS planar-only and/or SPECT-only imaging protocols with a limited FOV.
Methods: The scans of 95 patients with histologically proven PCa who underwent PS with full-body planar and multi-FOV SPECT/CT were reviewed. The detection rates for uptake in the prostate gland/bed and in metastases were compared on planar, SPECT, and SPECT/CT. The agreement between modalities was calculated for the detection of metastases and for staging. The impact of imaging a limited FOV was determined.
Results: Pathological prostatic uptake was seen in all cases on SPECT/CT (excluding two post-prostatectomy patients), 90.3% of cases on SPECT, and 15.1% on planar images (p < 0.001). Eleven (11.7%) patients had seminal vesicle involvement on SPECT/CT, which was undetectable/indistinguishable on planar images and SPECT. The agreement between modalities was moderate to good (κ = 0.41 to 0.61) for the detection of nodal metastases, with detection rates that did not differ significantly (SPECT/CT = 11.6%, SPECT = 8.4%, planar = 5.3%). Detection rates for bone metastases were 14.7% (SPECT/CT) and 11.6% (SPECT and planar). Agreement between modalities for the detection of bone metastases was good (κ = 0.73 to 0.77). Three (3.1%) patients had visceral metastases on SPECT/CT, two of which were detected on SPECT and planar. There was good agreement between modalities for the TNM staging of patients (κ = 0.70 to 0.88). No metastatic lesions were missed on the limited FOV images.
Conclusion: When PS scintigraphy is performed, SPECT/CT is recommended. However, the lack of SPECT/CT capabilities should not preclude the use of PS in the presence of limited resources, as both planar and SPECT imaging are adequate and will correctly stage most PCa patients. Furthermore, time-based optimisations are achievable by limiting the FOV to exclude the distal lower limbs.
Background: Automatic segmentation of hepatocellular carcinoma (HCC) on computed tomography (CT) scans is in urgent need to assist diagnosis and radiomics analysis. The aim of this study is to develop a deep learning based network to detect HCC from dynamic CT images.
Methods: Dynamic CT images of 595 patients with HCC were used. Tumors in dynamic CT images were labeled by radiologists. Patients were randomly divided into training, validation and test sets in a ratio of 5:2:3, respectively. We developed a hierarchical fusion strategy of deep learning networks (HFS-Net). Global dice, sensitivity, precision and F1-score were used to measure performance of the HFS-Net model.
Results: The 2D DenseU-Net using dynamic CT images was more effective for segmenting small tumors, whereas the 2D U-Net using portal venous phase images was more effective for segmenting large tumors. The HFS-Net model performed better, compared with the single-strategy deep learning models in segmenting small and large tumors. In the test set, the HFS-Net model achieved good performance in identifying HCC on dynamic CT images with global dice of 82.8%. The overall sensitivity, precision and F1-score were 84.3%, 75.5% and 79.6% per slice, respectively, and 92.2%, 93.2% and 92.7% per patient, respectively. The sensitivity in tumors < 2 cm, 2-3, 3-5 cm and > 5 cm were 72.7%, 92.9%, 94.2% and 100% per patient, respectively.
Conclusions: The HFS-Net model achieved good performance in the detection and segmentation of HCC from dynamic CT images, which may support radiologic diagnosis and facilitate automatic radiomics analysis.
Purpose: To create radiomics signatures based on habitat to assess the instant response in lung metastases of colorectal cancer (CRC) after radiofrequency ablation (RFA).
Methods: Between August 2016 and June 2019, we retrospectively included 515 lung metastases in 233 CRC patients who received RFA (412 in the training group and 103 in the test group). Multivariable analysis was performed to identify independent risk factors for developing the clinical model. Tumor and ablation regions of interest (ROI) were split into three spatial habitats through K-means clustering and dilated with 5 mm and 10 mm thicknesses. Radiomics signatures of intratumor, peritumor, and habitat were developed using the features extracted from intraoperative CT data. The performance of these signatures was primarily evaluated using the area under the receiver operating characteristics curve (AUC) via the DeLong test, calibration curves through the Hosmer-Lemeshow test, and decision curve analysis.
Results: A total of 412 out of 515 metastases (80%) achieved complete response. Four clinical variables (cancer antigen 19-9, simultaneous systemic treatment, site of lung metastases, and electrode type) were utilized to construct the clinical model. The Habitat signature was combined with the Peri-5 signature, which achieved a higher AUC than the Peri-10 signature in the test set (0.825 vs. 0.816). The Habitat+Peri-5 signature notably surpassed the clinical and intratumor radiomics signatures (AUC: 0.870 in the test set; both, p < 0.05), displaying improved calibration and clinical practicality.
Conclusions: The habitat-based radiomics signature can offer precise predictions and valuable assistance to physicians in developing personalized treatment strategies.