Automatic detection of lytic and blastic thoracolumbar spine metastases on computed tomography

Abstract

ObjectiveTo evaluate a computer-aided detection (CADe) system for lytic and blastic spinal metastases on computed tomography (CT).MethodsWe retrospectively evaluated the CADe system on 20 consecutive patients with 42 lytic and on 30 consecutive patients with 172 blastic metastases. The CADe system was trained using CT images of 114 subjects with 102 lytic and 308 blastic spinal metastases. Lesions were annotated by experienced radiologists. Detected benign lesions were considered false-positive findings. Detector sensitivity and the number of false-positive findings were calculated as the criteria for detector performance, and free-response receiver operating characteristic (FROC) analysis was conducted. Detailed analysis of false-positive and false-negative findings was performed.ResultsAlgorithm runtime is 3 ± 0.5 min per patient. The system achieves a sensitivity of 83 % at 3.5 false positives per patient on average for blastic metastases and a sensitivity of 88 % at 3.7 false positives for lytic metastases. False positives appeared predominantly in the area of degenerative changes in the case of the blastic metastasis detector and in osteoporotic areas in the case of the lytic metastasis detector.ConclusionThe CADe system reliably detects thoracolumbar spine metastases in real time. An additional study is planned to evaluate how the bone lesion CADe system improves radiologists’ accuracy and efficiency in a clinical setting.Key Points• Computer-aided detection (CADe) of bone metastases has been developed for spinal CT.• The CADe system exhibits high sensitivity with a tolerable false-positive rate.• Analysis of false-positive detection may further improve the system.• CADe may reduce the number of missed spinal metastases at CT interpretation.

Mixed spine metastasis detection through positron emission tomography/computed tomography synthesis and multiclassifier

“…Additionally, compared to prior CT-based detection systems designed for sclerotic lesion detection, 9,13,14 lytic lesion detection, 6,7 and sclerotic/lytic but not mixed type detection, 15,16 this system uses a triple classifier process to detect all three lesion types: lytic, sclerotic, and mixed. Additionally, compared to Ref.…”

“…The technique was on two-dimensional (2-D) slices, and cortical shells were stripped before 11 texture features and 22 interslice texture difference features were extracted. Hammon et al 16 developed a system that detected lytic and sclerotic lesions separately using three cascade random forest-based discriminative models. Both low-level Haar-like features and higher level shape and texture features were extracted from sagittal images.…”

Pattern Recognition in Musculoskeletal Imaging Using Artificial Intelligence

“…Multiple computer-aided detection (CADe) software systems have been developed for the automated detection of spinal metastases. 8,[23][24][25][26][27][28][29][30] There are many systems for detecting a single type of lesion along the radiodensity spectrum, such as lytic [26][27][28] or sclerotic, [23][24][25] although some detect both types 8,29 as well as mixed lesions. 30 Among systems for the identification of osteolytic spinal lesions, the CADe algorithm developed by O'Connor et al identifies lytic lesions on CT of the chest, abdomen, and/or pelvis performed for other clinical indications.…”

“…2,6 Deep-learning algorithms solve some of these challenges, with the computer learning autonomously from images using a data set of labeled examples as the ground truth, without specified rules programmed by humans, resulting in a potentially superior performance to conventionally designed systems. 2,4 Many AI-based image interpretation tasks for musculoskeletal (MSK) pathologies have been studied including the diagnosis of bone tumors, 7 detection of osseous metastases, 8 assessment of bone age, 9 identification of fractures, 10 labeling of images, and detection and grading of osteoarthritis (OA). 11 In addition, AI applications for incidental MSK findings on non-MSK examinations have been developed, such as an automated system for the detection of shoulder dislocations on chest radiographs.…”

Progress in Fully Automated Abdominal CT Interpretation

“…In the setting of breast and prostate cancer, vertebral lesions may be the first sign of metastatic disease, preceding lymph node and organ involvement. Automated detection of both lytic and sclerotic vertebral metastases on body CT have been reported [145–147]. Sensitivities and false-positive rates for lytic and sclerotic metastases were 94% and 79% and 4.5 and 10.9 false-positives per patient, respectively [145, 146].…”