Automated lesion segmentation is essential to provide fast, reproducible tumor load estimates. Though deep learning methods have achieved unprecedented results in this field, they are often difficult to interpret, hampering their potential integration in the clinic. An interpretable deep learning approach is proposed for segmenting melanoma lesions on whole-body fluorine-18 fluorodeoxyglucose ([18F]FDG) positron emission tomography (PET) / computed tomography (CT). This consists of an automated PET thresholding step to identify FDGavid regions, followed by a three-channel nnU-Net considering the binary mask in addition to the PET and CT images. This segmentation step differentiates healthy from malignant tissue and removes the restriction on lesion boundaries imposed by the thresholding. The proposed method, trained on 267 images and evaluated on two sets acquired at the same institute, achieved mean Dice similarity coefficients (DSC) of 0.779 and 0.638 with mean absolute volume differences of 15.2mL and 22.0 mL. The DSC proved significantly higher compared to a direct, two-channel nnU-Net considering only the PET and CT. The same was observed when retraining and testing on subsets of the public data of the autoPET challenge, containing melanoma, lung cancer and lymphoma patients. In addition, overall results proved superior to a previously proposed two-step approach, where a classification network categorized each component of increased tracer uptake as healthy or malignant. The proposed lesion segmentation method for whole-body [18F]FDG PET/CT incorporates prior thresholding information while allowing more flexibility in the lesion delineation than a pure thresholding approach and increased interpretability over a direct segmentation network.
The PHERGain study (NCT03161353) is assessing early metabolic responses to neoadjuvant treatment with trastuzumab-pertuzumab and chemotherapy de-escalation using a [
Background: Carrier-added [123I]-2-iodo-d-phenylalanine (CA [123I]-2-I-d-Phe) was previously found to have a preferential retention in tumors with a high tumor background contrast in animal models. A previous human dosimetry study demonstrated a favorable biodistribution and radiation burden in human subjects. Aim: The aim of this study was to investigate the potential of CA [131I]-2-I-d-Phe as an agent for radionuclide therapy. Methods: Sixty (60) nude athymic mice were inoculated subcutaneously with firefly luciferase-transduced R1M rhabdomyosarcoma cells. The mice in the therapy group were injected intravenously (i.v.) with 148 MBq [131I]-2-I-d-Phe (432 GBq/mmol) in kit solution. Controls were injected with kit solution without radioactivity, with physiological saline, or with 148 MBq [131I]− in physiological saline. Tumor growth was quantified using bioluminescent imaging and caliper measurements. Results: [131I]-2-I-d-Phe clearly reduced tumor growth in the treated mice compared with the control groups. A tumor growth-rate reduction of at least 33% was found for mice receiving a therapeutic dose. There were no serious adverse side-effects of the therapy. Conclusions: In conclusion, i.v. injection of CA 148 MBq [131I]-2-I-d-Phe specifically reduces tumor growth in athymic nude mice without relevant side-effects on the animals' health.
Supplementary Figure from Targeted Radionuclide Therapy with Low and High-Dose Lutetium-177–Labeled Single Domain Antibodies Induces Distinct Immune Signatures in a Mouse Melanoma Model
Erdheim-Chester disease (ECD) is a rare non-Langerhans’ cell histiocytosis. Mild but permanent juxta-articular bone pain in mainly knees and ankles is the most frequent associated symptom. Despite the pathognomonic radiographic findings, most cases are still diagnosed by the pathologist. The lesions consist of lipid-storing CD 68 +/ CD 1a – non- Langerhans’ cell histiocytes, most frequently localized in bone but also involving multiple organ systems in the body. We present a case report in which the diagnosis of ECD was established with 99mTc MDP bone SPECT/CT.
'%3e%3cg id='b'%3e%3cpath id='a' stroke='%23000' stroke-width='2' d='M-6-25H6m-12 3H6m-12 3H6'/%3e%3cuse xlink:href='%23a' y='44'/%3e%3c/g%3e%3cpath stroke='%23fff' d='M0 17v10'/%3e%3ccircle r='12' fill='%23cd2e3a'/%3e%3cpath fill='%230047a0' d='M0-12A6 6 0 0 0 0 0a6 6 0 0 1 0 12 12 12 0 0 1 0-24z'/%3e%3c/g%3e%3cg transform='rotate(-123.69)'%3e%3cuse xlink:href='%23b'/%3e%3cpath stroke='%23fff' d='M0-23.5v3M0 17v3.5m0 3v3'/%3e%3c/g%3e%3c/svg%3e)