Automated measurement of bone scan index from a whole-body bone scintigram

Purpose We propose a deep learning-based image interpretation system for skeleton segmentation and extraction of hot spots of bone metastatic lesion from a whole-body bone scintigram followed by automated measurement of a bone scan index (BSI), which will be clinically useful. Methods The proposed system employs butterfly-type networks (BtrflyNets) for skeleton segmentation and extraction of hot spots of bone metastatic lesions, in which a pair of anterior and posterior images are processed simultaneously. BSI is then measured using the segmented bones and extracted hot spots. To further improve the networks, deep supervision (DSV) and residual learning technologies were introduced. Results We evaluated the performance of the proposed system using 246 bone scintigrams of prostate cancer in terms of accuracy of skeleton segmentation, hot spot extraction, and BSI measurement, as well as computational cost. In a threefold cross-validation experiment, the best performance was achieved by BtrflyNet with DSV for skeleton segmentation and BtrflyNet with residual blocks. The cross-correlation between the measured and true BSI was 0.9337, and the computational time for a case was 112.0 s. Conclusion We proposed a deep learning-based BSI measurement system for a whole-body bone scintigram and proved its effectiveness by threefold cross-validation study using 246 whole-body bone scintigrams. The automatically measured BSI and computational time for a case are deemed clinically acceptable and reliable.

MGUS bone

A 65-year-old man was referred to our hospital to undergo orthopedic surgery due to severe cervical ossification of the posterior longitudinal ligament. Computed tomography scanning showed a massive osteolytic lesion in his pelvis. Other screening examinations including detection of bone mineral density and osteoporosis biomarkers, bone scintigram and 18F-fluorodeoxyglucose-positron emission tomography were all normal. Bone marrow aspiration revealed slightly increased plasmacytes at 3.8%. These findings led to a diagnosis of monoclonal gammopathy with undetermined significance (MGUS). Architectural osteolytic bone associated with MGUS without apparent abnormality in bone mineral metabolism could be a common occurrence prior to onset or occurrence of multiple myeloma.

Letrozole Induced Hypercalcemia in a Patient with Breast Cancer

Hypersecretion of PTHrP is a relatively common cause of malignancy-related hypercalcemia. However, there is only one case report of letrozole induced hypercalcemia. A 52-year-old female patient was referred to our clinic because of the recent discovery of hypercalcemia (11.0 mg/dL). The patient had a history of left breast carcinoma. She had started a course of letrozole (aromatase inhibitor; 2.5 mg dose/day) ten months earlier. Patient’s parathyroid hormone-related protein levels were normal and a bone scintigram revealed no evidence of skeletal metastasis. Other potential causes of high calcium levels were ruled out. We recognized that, when letrozole was taken at one dose daily (2.5 mg), she had recurrent hypercalcemia. Our experience suggests that letrozole may precipitate hypercalcemia in a patient with breast cancer.